TY  - CONF
AU  - Jokić, Aleksandar
AU  - Khazraei, Amir
AU  - Petrović, Milica
AU  - Jakovljević, Živana
AU  - Pajić, Miroslav
PY  - 2023
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/7676
AB  - Visual servoing represents a control strategy
capable of driving dynamical systems from the current to the
desired pose, when the only available information is the images
generated at both poses. In this work, we analyze vulnerability
of such systems and introduce two types of attacks to deceive
visual servoing controller within a wheeled mobile robotic
system. The attack goal is to alter the visual servoing procedure
in such a way that mobile robot achieves the pose defined by an
attacker instead of the desired one. Specifically, the attacks
exploit image transformations developed using a methodology
based on simulated annealing. The main difference between the
attacks is the considered threat model – i.e., how the attacker
has infiltrated the system. The first attack assumes the realtime camera feed has been compromised and thus, the images
from the current pose are modified (e.g., during the acquisition
or communication); for the second, only the desired destination
image is potentially altered. Finally, in 3D simulations and realworld experiments, we show the effectiveness of cyber-attacks.
C3  - 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
T1  - Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control
EP  - 6348
SP  - 6342
DO  - 10.1109/IROS55552.2023.10341376
ER  - 

@conference{
author = "Jokić, Aleksandar and Khazraei, Amir and Petrović, Milica and Jakovljević, Živana and Pajić, Miroslav",
year = "2023",
abstract = "Visual servoing represents a control strategy
capable of driving dynamical systems from the current to the
desired pose, when the only available information is the images
generated at both poses. In this work, we analyze vulnerability
of such systems and introduce two types of attacks to deceive
visual servoing controller within a wheeled mobile robotic
system. The attack goal is to alter the visual servoing procedure
in such a way that mobile robot achieves the pose defined by an
attacker instead of the desired one. Specifically, the attacks
exploit image transformations developed using a methodology
based on simulated annealing. The main difference between the
attacks is the considered threat model – i.e., how the attacker
has infiltrated the system. The first attack assumes the realtime camera feed has been compromised and thus, the images
from the current pose are modified (e.g., during the acquisition
or communication); for the second, only the desired destination
image is potentially altered. Finally, in 3D simulations and realworld experiments, we show the effectiveness of cyber-attacks.",
journal = "2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)",
title = "Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control",
pages = "6348-6342",
doi = "10.1109/IROS55552.2023.10341376"
}

Jokić, A., Khazraei, A., Petrović, M., Jakovljević, Ž.,& Pajić, M.. (2023). Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control. in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 6342-6348.
https://doi.org/10.1109/IROS55552.2023.10341376

Jokić A, Khazraei A, Petrović M, Jakovljević Ž, Pajić M. Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control. in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). 2023;:6342-6348.
doi:10.1109/IROS55552.2023.10341376 .

Jokić, Aleksandar, Khazraei, Amir, Petrović, Milica, Jakovljević, Živana, Pajić, Miroslav, "Cyber-Attacks on Wheeled Mobile Robotic Systems with Visual Servoing Control" in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (2023):6342-6348,
https://doi.org/10.1109/IROS55552.2023.10341376 . .

TY  - CONF
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
PY  - 2023
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/7009
AB  - Industry 4.0 paradigm has brought about the changes in the way we manufacture. The integration of Cyber-Physical Systems into the Industrial Internet of Things represents the basis for the transition from traditionally centralized to distributed control systems where the overall control task is achieved through the cooperation of different devices which implies their mutual communication and constant information exchange. However, ubiquitous communication between devices with communication and computation capabilities opens up space for various cyber-attacks which can lead to catastrophic damage to equipment
and also can endanger the environment and human lives. Therefore, the development and implementation of cyber-attacks detection mechanisms are necessary to prevent negative effects. Deep learning (DL) techniques are successfully applied to generate models on which cyber-attacks detection algorithms are based. However, the size of the DL models is often unsuitable for implementation on industrial control devices that usually have significant computational constraints. The use of complex DL models may disrupt the operation of control systems and introduce unacceptable delays in real-time cyber-attacks detection algorithms. This paper explores the possibilities for application of knowledge distillation technique to generate lightweight DL models. These models are designed to align with the limitations of the devices on which they are deployed. The paper evaluates the performance of lightweight models in cyber-attacks detection algorithms, and compares them to algorithms based on DL models before distillation.
C3  - 39th International conference on production engineering of Serbia (ICPES 2023)
T1  - Generation of lightweight models for cyber-attacks detection algorithms using knowledge distillation
EP  - 31
SP  - 24
UR  - https://hdl.handle.net/21.15107/rcub_machinery_7009
ER  - 

@conference{
author = "Nedeljković, Dušan and Jakovljević, Živana",
year = "2023",
abstract = "Industry 4.0 paradigm has brought about the changes in the way we manufacture. The integration of Cyber-Physical Systems into the Industrial Internet of Things represents the basis for the transition from traditionally centralized to distributed control systems where the overall control task is achieved through the cooperation of different devices which implies their mutual communication and constant information exchange. However, ubiquitous communication between devices with communication and computation capabilities opens up space for various cyber-attacks which can lead to catastrophic damage to equipment
and also can endanger the environment and human lives. Therefore, the development and implementation of cyber-attacks detection mechanisms are necessary to prevent negative effects. Deep learning (DL) techniques are successfully applied to generate models on which cyber-attacks detection algorithms are based. However, the size of the DL models is often unsuitable for implementation on industrial control devices that usually have significant computational constraints. The use of complex DL models may disrupt the operation of control systems and introduce unacceptable delays in real-time cyber-attacks detection algorithms. This paper explores the possibilities for application of knowledge distillation technique to generate lightweight DL models. These models are designed to align with the limitations of the devices on which they are deployed. The paper evaluates the performance of lightweight models in cyber-attacks detection algorithms, and compares them to algorithms based on DL models before distillation.",
journal = "39th International conference on production engineering of Serbia (ICPES 2023)",
title = "Generation of lightweight models for cyber-attacks detection algorithms using knowledge distillation",
pages = "31-24",
url = "https://hdl.handle.net/21.15107/rcub_machinery_7009"
}

Nedeljković, D.,& Jakovljević, Ž.. (2023). Generation of lightweight models for cyber-attacks detection algorithms using knowledge distillation. in 39th International conference on production engineering of Serbia (ICPES 2023), 24-31.
https://hdl.handle.net/21.15107/rcub_machinery_7009

Nedeljković D, Jakovljević Ž. Generation of lightweight models for cyber-attacks detection algorithms using knowledge distillation. in 39th International conference on production engineering of Serbia (ICPES 2023). 2023;:24-31.
https://hdl.handle.net/21.15107/rcub_machinery_7009 .

Nedeljković, Dušan, Jakovljević, Živana, "Generation of lightweight models for cyber-attacks detection algorithms using knowledge distillation" in 39th International conference on production engineering of Serbia (ICPES 2023) (2023):24-31,
https://hdl.handle.net/21.15107/rcub_machinery_7009 .

TY  - CONF
AU  - Jakovljević, Živana
AU  - Nedeljković, Dušan
PY  - 2023
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/6883
AB  - The fourth industrial revolution known as Industry 4.0 brings digitalization of manufacturing processes to a new
level through ubiquitous interconnection and real-time information flow between information technologies (IT) and
operational technologies (OT) as parts of Industrial Control Systems (ICS). This information flow is not limited to but expands beyond factory walls enabling manufacturing systems to adapt quickly and efficiently to changing customer demands and diversified products. The adaptation is carried out through physical and/or functional reconfiguration of manufacturing systems where Industrial Internet of Things (IIoT) based on Cyber-Physical Systems (CPS) represents the key technical enabler. These changes result in a transition from centralized to distributed control systems architecture where the whole control task is achieved through intensive cooperation between smart devices (e.g., sensors and actuators) with integrated communication and computation capabilities. However, introducing IIoT in ICS brings about new cybersecurity issues due to increased communication between system elements and connection to the global network, making ICS vulnerable to different cyber-attacks with potentially catastrophic consequences. Recently, the research in ICS cybersecurity has intensified leading to significant results for continuous time and
discrete events-controlled systems. However, cybersecurity issues in motion control systems that are frequently employed in different manufacturing resources such as machine tools and industrial robots were not sufficiently explored. This work provides an overview of the cybersecurity related challenges in motion control tasks.
C3  - 10th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2023), Proceedings, Sarajevo, B&H, June 2023, ROI1.5, 2023
T1  - Cybersecurity issues in motion control – an overview of challenges
SP  - ROI1.5, 1-6
UR  - https://hdl.handle.net/21.15107/rcub_machinery_6883
ER  - 

@conference{
author = "Jakovljević, Živana and Nedeljković, Dušan",
year = "2023",
abstract = "The fourth industrial revolution known as Industry 4.0 brings digitalization of manufacturing processes to a new
level through ubiquitous interconnection and real-time information flow between information technologies (IT) and
operational technologies (OT) as parts of Industrial Control Systems (ICS). This information flow is not limited to but expands beyond factory walls enabling manufacturing systems to adapt quickly and efficiently to changing customer demands and diversified products. The adaptation is carried out through physical and/or functional reconfiguration of manufacturing systems where Industrial Internet of Things (IIoT) based on Cyber-Physical Systems (CPS) represents the key technical enabler. These changes result in a transition from centralized to distributed control systems architecture where the whole control task is achieved through intensive cooperation between smart devices (e.g., sensors and actuators) with integrated communication and computation capabilities. However, introducing IIoT in ICS brings about new cybersecurity issues due to increased communication between system elements and connection to the global network, making ICS vulnerable to different cyber-attacks with potentially catastrophic consequences. Recently, the research in ICS cybersecurity has intensified leading to significant results for continuous time and
discrete events-controlled systems. However, cybersecurity issues in motion control systems that are frequently employed in different manufacturing resources such as machine tools and industrial robots were not sufficiently explored. This work provides an overview of the cybersecurity related challenges in motion control tasks.",
journal = "10th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2023), Proceedings, Sarajevo, B&H, June 2023, ROI1.5, 2023",
title = "Cybersecurity issues in motion control – an overview of challenges",
pages = "ROI1.5, 1-6",
url = "https://hdl.handle.net/21.15107/rcub_machinery_6883"
}

Jakovljević, Ž.,& Nedeljković, D.. (2023). Cybersecurity issues in motion control – an overview of challenges. in 10th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2023), Proceedings, Sarajevo, B&H, June 2023, ROI1.5, 2023, ROI1.5, 1-6.
https://hdl.handle.net/21.15107/rcub_machinery_6883

Jakovljević Ž, Nedeljković D. Cybersecurity issues in motion control – an overview of challenges. in 10th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2023), Proceedings, Sarajevo, B&H, June 2023, ROI1.5, 2023. 2023;:ROI1.5, 1-6.
https://hdl.handle.net/21.15107/rcub_machinery_6883 .

Jakovljević, Živana, Nedeljković, Dušan, "Cybersecurity issues in motion control – an overview of challenges" in 10th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2023), Proceedings, Sarajevo, B&H, June 2023, ROI1.5, 2023 (2023):ROI1.5, 1-6,
https://hdl.handle.net/21.15107/rcub_machinery_6883 .

TY  - JOUR
AU  - Lesi, Vuk
AU  - Jakovljević, Živana
AU  - Pajić, Miroslav
PY  - 2023
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5616
AB  - Ever-increasing demands for highly-efficient customized manufacturing are driving the development of Industry 4.0. Reconfigurable manufacturing systems based on modular, convertible, and interoperable equipment present a key enabler of the fourth industrial revolution. Besides suitable mechanical design, control of these smart manufacturing resources should facilitate Internet of Things (IoT) integration and reconfigurability. Existing numerical control kernels (NCK)—the major control component for motion control—hinder rapid reconfiguration due to the complexity of their monolithic centralized structure. On the other hand, reconfigurability is naturally promoted by the distributed control paradigm, as proposed by the industrial IoT (IIoT) concept; hence, in this article, we investigate design challenges in distributing the conventional centralized NCK designs used for control of computerized numerical control systems. We introduce an architecture where each axis module is augmented with a networked, IIoT-enabled low-level controller (LLC) that performs local control and exposes a network interface for communication with other LLCs toward executing the desired process. These smart manufacturing resources communicate with an edge-based high-level controller (HLC) that provides the trajectory specification over the network and schedules manufacturing tasks. We investigate real-time and network bandwidth requirements of different mappings of the NCK layers to the LLCs and the HLC, providing design-time tradeoffs for implementing IoT-ready, distributed motion control. We demonstrate feasibility of our approach using industry-grade single-axis robots and low-cost IoT microcontrollers, and show that minimal accuracy impairment is introduced compared to the centralized setup based on ISO 230 and ISO 10791-7 standards.
T2  - IEEE Transactions on Industrial Informatics
T1  - IoT-Enabled Motion Control: Architectural Design Challenges and Solutions
EP  - 2294
IS  - 3
SP  - 2284
VL  - 19
DO  - 10.1109/TII.2022.3202175
ER  - 

@article{
author = "Lesi, Vuk and Jakovljević, Živana and Pajić, Miroslav",
year = "2023",
abstract = "Ever-increasing demands for highly-efficient customized manufacturing are driving the development of Industry 4.0. Reconfigurable manufacturing systems based on modular, convertible, and interoperable equipment present a key enabler of the fourth industrial revolution. Besides suitable mechanical design, control of these smart manufacturing resources should facilitate Internet of Things (IoT) integration and reconfigurability. Existing numerical control kernels (NCK)—the major control component for motion control—hinder rapid reconfiguration due to the complexity of their monolithic centralized structure. On the other hand, reconfigurability is naturally promoted by the distributed control paradigm, as proposed by the industrial IoT (IIoT) concept; hence, in this article, we investigate design challenges in distributing the conventional centralized NCK designs used for control of computerized numerical control systems. We introduce an architecture where each axis module is augmented with a networked, IIoT-enabled low-level controller (LLC) that performs local control and exposes a network interface for communication with other LLCs toward executing the desired process. These smart manufacturing resources communicate with an edge-based high-level controller (HLC) that provides the trajectory specification over the network and schedules manufacturing tasks. We investigate real-time and network bandwidth requirements of different mappings of the NCK layers to the LLCs and the HLC, providing design-time tradeoffs for implementing IoT-ready, distributed motion control. We demonstrate feasibility of our approach using industry-grade single-axis robots and low-cost IoT microcontrollers, and show that minimal accuracy impairment is introduced compared to the centralized setup based on ISO 230 and ISO 10791-7 standards.",
journal = "IEEE Transactions on Industrial Informatics",
title = "IoT-Enabled Motion Control: Architectural Design Challenges and Solutions",
pages = "2294-2284",
number = "3",
volume = "19",
doi = "10.1109/TII.2022.3202175"
}

Lesi, V., Jakovljević, Ž.,& Pajić, M.. (2023). IoT-Enabled Motion Control: Architectural Design Challenges and Solutions. in IEEE Transactions on Industrial Informatics, 19(3), 2284-2294.
https://doi.org/10.1109/TII.2022.3202175

Lesi V, Jakovljević Ž, Pajić M. IoT-Enabled Motion Control: Architectural Design Challenges and Solutions. in IEEE Transactions on Industrial Informatics. 2023;19(3):2284-2294.
doi:10.1109/TII.2022.3202175 .

Lesi, Vuk, Jakovljević, Živana, Pajić, Miroslav, "IoT-Enabled Motion Control: Architectural Design Challenges and Solutions" in IEEE Transactions on Industrial Informatics, 19, no. 3 (2023):2284-2294,
https://doi.org/10.1109/TII.2022.3202175 . .

TY  - JOUR
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3705
AB  - Extensive communication between smart devices in contemporary Industrial Control Systems (ICS) opens up a vast area for different cyber-attacks and malicious threats. The negative effects of these attacks can not only disrupt or completely disable the system functioning, but also they can have serious safety related consequences. Therefore, cybersecurity in ICS becomes one of the most important issues. In this paper we propose a method for the design of algorithms for the detection of cyber-attacks on communication links between smart devices. The method belongs to the class of semi-supervised data driven approaches and it is based on Convolutional Neural Networks (CNN). Starting from a predefined range of network hyperparameters and data obtained from system operation without attacks, the proposed method autonomously selects suitable CNN architecture and thresholds for online intrusion detection. Following the characteristics of ICS, the proposed intrusion detection is host based, and in our research we consider the structure of ICS and the feasibility of the attack detection algorithm implementation on control system devices. The method is experimentally verified using two case studies. In the first case study that refers to the publicly available dataset obtained from Secure Water Treatment (SWaT) testbed, we present a comparative analysis of the developed method with alternative approaches. The second case study considers a custom developed electro-pneumatic positioning system; in this system we carry out the real-world implementation and validation of the intrusion detection algorithm developed using the proposed method.
PB  - Elsevier Advanced Technology, Oxford
T2  - Computers & Security
T1  - CNN based method for the development of cyber-attacks detection algorithms in industrial control systems
VL  - 114
DO  - 10.1016/j.cose.2021.102585
ER  - 

@article{
author = "Nedeljković, Dušan and Jakovljević, Živana",
year = "2022",
abstract = "Extensive communication between smart devices in contemporary Industrial Control Systems (ICS) opens up a vast area for different cyber-attacks and malicious threats. The negative effects of these attacks can not only disrupt or completely disable the system functioning, but also they can have serious safety related consequences. Therefore, cybersecurity in ICS becomes one of the most important issues. In this paper we propose a method for the design of algorithms for the detection of cyber-attacks on communication links between smart devices. The method belongs to the class of semi-supervised data driven approaches and it is based on Convolutional Neural Networks (CNN). Starting from a predefined range of network hyperparameters and data obtained from system operation without attacks, the proposed method autonomously selects suitable CNN architecture and thresholds for online intrusion detection. Following the characteristics of ICS, the proposed intrusion detection is host based, and in our research we consider the structure of ICS and the feasibility of the attack detection algorithm implementation on control system devices. The method is experimentally verified using two case studies. In the first case study that refers to the publicly available dataset obtained from Secure Water Treatment (SWaT) testbed, we present a comparative analysis of the developed method with alternative approaches. The second case study considers a custom developed electro-pneumatic positioning system; in this system we carry out the real-world implementation and validation of the intrusion detection algorithm developed using the proposed method.",
publisher = "Elsevier Advanced Technology, Oxford",
journal = "Computers & Security",
title = "CNN based method for the development of cyber-attacks detection algorithms in industrial control systems",
volume = "114",
doi = "10.1016/j.cose.2021.102585"
}

Nedeljković, D.,& Jakovljević, Ž.. (2022). CNN based method for the development of cyber-attacks detection algorithms in industrial control systems. in Computers & Security
Elsevier Advanced Technology, Oxford., 114.
https://doi.org/10.1016/j.cose.2021.102585

Nedeljković D, Jakovljević Ž. CNN based method for the development of cyber-attacks detection algorithms in industrial control systems. in Computers & Security. 2022;114.
doi:10.1016/j.cose.2021.102585 .

Nedeljković, Dušan, Jakovljević, Živana, "CNN based method for the development of cyber-attacks detection algorithms in industrial control systems" in Computers & Security, 114 (2022),
https://doi.org/10.1016/j.cose.2021.102585 . .

TY  - JOUR
AU  - Lesi, Vuk
AU  - Jakovljević, Živana
AU  - Pajić, Miroslav
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/101
AB  - Internet of Things (IoT) technologies enable development of reconfigurable manufacturing systems--a new generation of modularized industrial equipment suitable for highly customized manufacturing. Sequential control in these systems is largely based on discrete events, whereas their formal execution semantics is specified as control interpreted Petri nets (CIPN). Despite industry-wide use of programming languages based on the CIPN formalism, formal verification of such control applications in the presence of adversarial activity is not supported. Consequently, in this article, we introduce security-aware modeling and verification techniques for CIPN-based sequential control applications. Specifically, we show how CIPN models of networked industrial IoT controllers can be transformed into time Petri net (TPN)-based models and composed with plant and security-aware channel models in order to enable system-level verification of safety properties in the presence of network-based attacks. Additionally, we introduce realistic channel-specific attack models that capture adversarial behavior using nondeterminism. Moreover, we show how verification results can be utilized to introduce security patches and facilitate design of attack detectors that improve system resiliency and enable satisfaction of critical safety properties. Finally, we evaluate our framework on an industrial case study.
PB  - IEEE - Inst Electrical Electronics Engineers Inc, Piscataway
T2  - IEEE Transactions on Automation Science and Engineering
T1  - Security Analysis for Distributed IoT-Based Industrial Automation
EP  - 3108
IS  - 4
SP  - 3093
VL  - 19
DO  - 10.1109/TASE.2021.3106335
ER  - 

@article{
author = "Lesi, Vuk and Jakovljević, Živana and Pajić, Miroslav",
year = "2022",
abstract = "Internet of Things (IoT) technologies enable development of reconfigurable manufacturing systems--a new generation of modularized industrial equipment suitable for highly customized manufacturing. Sequential control in these systems is largely based on discrete events, whereas their formal execution semantics is specified as control interpreted Petri nets (CIPN). Despite industry-wide use of programming languages based on the CIPN formalism, formal verification of such control applications in the presence of adversarial activity is not supported. Consequently, in this article, we introduce security-aware modeling and verification techniques for CIPN-based sequential control applications. Specifically, we show how CIPN models of networked industrial IoT controllers can be transformed into time Petri net (TPN)-based models and composed with plant and security-aware channel models in order to enable system-level verification of safety properties in the presence of network-based attacks. Additionally, we introduce realistic channel-specific attack models that capture adversarial behavior using nondeterminism. Moreover, we show how verification results can be utilized to introduce security patches and facilitate design of attack detectors that improve system resiliency and enable satisfaction of critical safety properties. Finally, we evaluate our framework on an industrial case study.",
publisher = "IEEE - Inst Electrical Electronics Engineers Inc, Piscataway",
journal = "IEEE Transactions on Automation Science and Engineering",
title = "Security Analysis for Distributed IoT-Based Industrial Automation",
pages = "3108-3093",
number = "4",
volume = "19",
doi = "10.1109/TASE.2021.3106335"
}

Lesi, V., Jakovljević, Ž.,& Pajić, M.. (2022). Security Analysis for Distributed IoT-Based Industrial Automation. in IEEE Transactions on Automation Science and Engineering
IEEE - Inst Electrical Electronics Engineers Inc, Piscataway., 19(4), 3093-3108.
https://doi.org/10.1109/TASE.2021.3106335

Lesi V, Jakovljević Ž, Pajić M. Security Analysis for Distributed IoT-Based Industrial Automation. in IEEE Transactions on Automation Science and Engineering. 2022;19(4):3093-3108.
doi:10.1109/TASE.2021.3106335 .

Lesi, Vuk, Jakovljević, Živana, Pajić, Miroslav, "Security Analysis for Distributed IoT-Based Industrial Automation" in IEEE Transactions on Automation Science and Engineering, 19, no. 4 (2022):3093-3108,
https://doi.org/10.1109/TASE.2021.3106335 . .

TY  - JOUR
AU  - Marković, Veljko
AU  - Jakovljević, Živana
AU  - Budak, Igor
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/91
AB  - 3D scanning devices are traditionally employed in reverse engineering tasks that can be carried out semi-automatically, with user assistance. However, their application in manufacturing process control requires automatic point cloud segmentation and extraction of geometric primitives. In this paper, we propose a method for automatic recognition of planes and cylinders (most frequently encountered geometric primitives in mechanical engineering) from unstructured point clouds. The method is based on the scatter of data during least squares fitting of second order surfaces. It consists of three phases and the first phase represents automatic point cloud segmentation. The second phase deals with merging of over-segmented regions and surfaces parameters estimation, whereas the final phase provides extraction of recognized geometric primitives. The method is experimentally verified using three real-world case studies, and its performances are compared with two state of the art recognition algorithms. The results have shown that the proposed method outperforms alternative approaches in terms of appropriately recognized planes and cylinders without surface type confusion, as well as when the recognition of non-existent primitives is considered. In addition, the method determines surfaces parameters with high accuracy.
PB  - Springer, New York
T2  - Visual Computer
T1  - Automatic recognition of cylinders and planes from unstructured point clouds
EP  - 4352
SP  - 4329
VL  - 38
DO  - 10.1007/s00371-021-02299-9
ER  - 

@article{
author = "Marković, Veljko and Jakovljević, Živana and Budak, Igor",
year = "2022",
abstract = "3D scanning devices are traditionally employed in reverse engineering tasks that can be carried out semi-automatically, with user assistance. However, their application in manufacturing process control requires automatic point cloud segmentation and extraction of geometric primitives. In this paper, we propose a method for automatic recognition of planes and cylinders (most frequently encountered geometric primitives in mechanical engineering) from unstructured point clouds. The method is based on the scatter of data during least squares fitting of second order surfaces. It consists of three phases and the first phase represents automatic point cloud segmentation. The second phase deals with merging of over-segmented regions and surfaces parameters estimation, whereas the final phase provides extraction of recognized geometric primitives. The method is experimentally verified using three real-world case studies, and its performances are compared with two state of the art recognition algorithms. The results have shown that the proposed method outperforms alternative approaches in terms of appropriately recognized planes and cylinders without surface type confusion, as well as when the recognition of non-existent primitives is considered. In addition, the method determines surfaces parameters with high accuracy.",
publisher = "Springer, New York",
journal = "Visual Computer",
title = "Automatic recognition of cylinders and planes from unstructured point clouds",
pages = "4352-4329",
volume = "38",
doi = "10.1007/s00371-021-02299-9"
}

Marković, V., Jakovljević, Ž.,& Budak, I.. (2022). Automatic recognition of cylinders and planes from unstructured point clouds. in Visual Computer
Springer, New York., 38, 4329-4352.
https://doi.org/10.1007/s00371-021-02299-9

Marković V, Jakovljević Ž, Budak I. Automatic recognition of cylinders and planes from unstructured point clouds. in Visual Computer. 2022;38:4329-4352.
doi:10.1007/s00371-021-02299-9 .

Marković, Veljko, Jakovljević, Živana, Budak, Igor, "Automatic recognition of cylinders and planes from unstructured point clouds" in Visual Computer, 38 (2022):4329-4352,
https://doi.org/10.1007/s00371-021-02299-9 . .

TY  - CONF
AU  - Jakovljević, Živana
AU  - Nedeljković, Dušan
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5278
AB  - U okviru ovog rada navode se rezultati istraživanja sprovedenih u okviru projekta MISSION4.0 pod nazivom Optimizacioni algoritmi za upravljanje i terminiranje kibernetsko fizičkih sistema u okviru Industrije 4.0 zasnovani na dubokom mašinskom učenju i inteligenciji roja, finansiranog od strane Fonda za nauku Republike Srbije u periodu od 2020-2022. godine. Prikazani rezultati odnose se na oblast sajber bezbednosti u kontinualnim sistemima upravljanja što predstavlja jedan od radnih paketa projekta MISSION4.0. U skladu sa tim, pravci istraživanja odnosili su se na razvoj algoritama za detekciju napada u industrijskim sistemima upravljanja sa centralizovanom i distribuiranom arhitekturom, kao i na primenu otvorene platforme za komunikaciju, u cilju bezbedne razmene podataka između uređaja različitih proizvođača. Pored toga, dobijeni rezultati i njihova integracija u predavanja i laboratorijske vežbe poslužili su kao osnova za edukaciju inženjera u oblastima kibernetsko fizičkih sistema, industrijskog interneta stvari i sajber bezbednosti.
PB  - University of Belgrade - Faculty of Mechanical Engineering
C3  - 43. JUPITER konferencija, 36. simpozijum „CIM u strategiji tehnološkog razvoja industrije prerade metala“, Zbornik radova / 43rd JUPITER Conference, Proceedings, Beograd, oktobar 2022
T1  - Sajber bezbednost u kontinualnim sistemima upravljanja – pregled rezultata u okviru projekta mission4.0
T1  - Cyber security in continuous-time controlled systems – overview of the results within the project of mission4.0
EP  - 1.16
SP  - 1.7
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5278
ER  - 

@conference{
author = "Jakovljević, Živana and Nedeljković, Dušan",
year = "2022",
abstract = "U okviru ovog rada navode se rezultati istraživanja sprovedenih u okviru projekta MISSION4.0 pod nazivom Optimizacioni algoritmi za upravljanje i terminiranje kibernetsko fizičkih sistema u okviru Industrije 4.0 zasnovani na dubokom mašinskom učenju i inteligenciji roja, finansiranog od strane Fonda za nauku Republike Srbije u periodu od 2020-2022. godine. Prikazani rezultati odnose se na oblast sajber bezbednosti u kontinualnim sistemima upravljanja što predstavlja jedan od radnih paketa projekta MISSION4.0. U skladu sa tim, pravci istraživanja odnosili su se na razvoj algoritama za detekciju napada u industrijskim sistemima upravljanja sa centralizovanom i distribuiranom arhitekturom, kao i na primenu otvorene platforme za komunikaciju, u cilju bezbedne razmene podataka između uređaja različitih proizvođača. Pored toga, dobijeni rezultati i njihova integracija u predavanja i laboratorijske vežbe poslužili su kao osnova za edukaciju inženjera u oblastima kibernetsko fizičkih sistema, industrijskog interneta stvari i sajber bezbednosti.",
publisher = "University of Belgrade - Faculty of Mechanical Engineering",
journal = "43. JUPITER konferencija, 36. simpozijum „CIM u strategiji tehnološkog razvoja industrije prerade metala“, Zbornik radova / 43rd JUPITER Conference, Proceedings, Beograd, oktobar 2022",
title = "Sajber bezbednost u kontinualnim sistemima upravljanja – pregled rezultata u okviru projekta mission4.0, Cyber security in continuous-time controlled systems – overview of the results within the project of mission4.0",
pages = "1.16-1.7",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5278"
}

Jakovljević, Ž.,& Nedeljković, D.. (2022). Sajber bezbednost u kontinualnim sistemima upravljanja – pregled rezultata u okviru projekta mission4.0. in 43. JUPITER konferencija, 36. simpozijum „CIM u strategiji tehnološkog razvoja industrije prerade metala“, Zbornik radova / 43rd JUPITER Conference, Proceedings, Beograd, oktobar 2022
University of Belgrade - Faculty of Mechanical Engineering., 1.7-1.16.
https://hdl.handle.net/21.15107/rcub_machinery_5278

Jakovljević Ž, Nedeljković D. Sajber bezbednost u kontinualnim sistemima upravljanja – pregled rezultata u okviru projekta mission4.0. in 43. JUPITER konferencija, 36. simpozijum „CIM u strategiji tehnološkog razvoja industrije prerade metala“, Zbornik radova / 43rd JUPITER Conference, Proceedings, Beograd, oktobar 2022. 2022;:1.7-1.16.
https://hdl.handle.net/21.15107/rcub_machinery_5278 .

Jakovljević, Živana, Nedeljković, Dušan, "Sajber bezbednost u kontinualnim sistemima upravljanja – pregled rezultata u okviru projekta mission4.0" in 43. JUPITER konferencija, 36. simpozijum „CIM u strategiji tehnološkog razvoja industrije prerade metala“, Zbornik radova / 43rd JUPITER Conference, Proceedings, Beograd, oktobar 2022 (2022):1.7-1.16,
https://hdl.handle.net/21.15107/rcub_machinery_5278 .

TY  - GEN
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5658
AB  - Tehničko rešenje (nova metoda - M85) pripada oblasti proizvodnog mašinstva i direktno se odnosi na jedan od domena istraživanja u okviru projekta „Deep Machine Learning and Swarm Intelligence-based Optimization Algorithms for Control and Scheduling of Cyber-Physical Systems in Industry 4.0“ (akronim - MISSION4.0, evidencioni broj 6523109), koji je finansiran od strane Fonda za nauku Republike Srbije – domen razvoja sistema za detekciju napada u cilju zaštite kibernetsko fizičkih sistema u okviru postrojenja Industrije 4.0. Shodno tome, metodom se rešava problem detekcije sajber napada na bazi signala dobijenih sa senzora raspoređenih unutar postrojenja. Sistem detekcije zasnovan je na modelu koji je dobijen dubokim mašinskim učenjem (DL - engl. Deep Learning). Konkretno, za modeliranje ponašanja sistema korišćeni su različiti tipovi rekurentnih neuronskih mreža (RNN - engl. Recurrent Neural Networks), kao i konvolucione neuronske mreže (CNN - engl. Convolutional Neural Networks). Predloženi algoritam je eksperimentalno verifikovan na dva javno dostupna skupa podataka: 1) SWaT (Secure Water Treatment) skup podataka i 2) skup podataka dobijen sa elektropneumatskog sistema za pozicioniranje koji je razvijen u okviru Laboratorije za automatizaciju proizvodnih procesa Mašinskog fakulteta Univerziteta u Beogradu.
T2  - Tehničko rešenje je prihvaćeno od strane Matičnog naučnog odbora za mašinstvo i industrijski softver, 2022.
T1  - Algoritam za detekciju sajber napada kod energetski ograničenih kibernetsko fizičkih sistema baziran na dubokom mašinskom učenju
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5658
ER  - 

@misc{
author = "Nedeljković, Dušan and Jakovljević, Živana",
year = "2022",
abstract = "Tehničko rešenje (nova metoda - M85) pripada oblasti proizvodnog mašinstva i direktno se odnosi na jedan od domena istraživanja u okviru projekta „Deep Machine Learning and Swarm Intelligence-based Optimization Algorithms for Control and Scheduling of Cyber-Physical Systems in Industry 4.0“ (akronim - MISSION4.0, evidencioni broj 6523109), koji je finansiran od strane Fonda za nauku Republike Srbije – domen razvoja sistema za detekciju napada u cilju zaštite kibernetsko fizičkih sistema u okviru postrojenja Industrije 4.0. Shodno tome, metodom se rešava problem detekcije sajber napada na bazi signala dobijenih sa senzora raspoređenih unutar postrojenja. Sistem detekcije zasnovan je na modelu koji je dobijen dubokim mašinskim učenjem (DL - engl. Deep Learning). Konkretno, za modeliranje ponašanja sistema korišćeni su različiti tipovi rekurentnih neuronskih mreža (RNN - engl. Recurrent Neural Networks), kao i konvolucione neuronske mreže (CNN - engl. Convolutional Neural Networks). Predloženi algoritam je eksperimentalno verifikovan na dva javno dostupna skupa podataka: 1) SWaT (Secure Water Treatment) skup podataka i 2) skup podataka dobijen sa elektropneumatskog sistema za pozicioniranje koji je razvijen u okviru Laboratorije za automatizaciju proizvodnih procesa Mašinskog fakulteta Univerziteta u Beogradu.",
journal = "Tehničko rešenje je prihvaćeno od strane Matičnog naučnog odbora za mašinstvo i industrijski softver, 2022.",
title = "Algoritam za detekciju sajber napada kod energetski ograničenih kibernetsko fizičkih sistema baziran na dubokom mašinskom učenju",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5658"
}

Nedeljković, D.,& Jakovljević, Ž.. (2022). Algoritam za detekciju sajber napada kod energetski ograničenih kibernetsko fizičkih sistema baziran na dubokom mašinskom učenju. in Tehničko rešenje je prihvaćeno od strane Matičnog naučnog odbora za mašinstvo i industrijski softver, 2022..
https://hdl.handle.net/21.15107/rcub_machinery_5658

Nedeljković D, Jakovljević Ž. Algoritam za detekciju sajber napada kod energetski ograničenih kibernetsko fizičkih sistema baziran na dubokom mašinskom učenju. in Tehničko rešenje je prihvaćeno od strane Matičnog naučnog odbora za mašinstvo i industrijski softver, 2022.. 2022;.
https://hdl.handle.net/21.15107/rcub_machinery_5658 .

Nedeljković, Dušan, Jakovljević, Živana, "Algoritam za detekciju sajber napada kod energetski ograničenih kibernetsko fizičkih sistema baziran na dubokom mašinskom učenju" in Tehničko rešenje je prihvaćeno od strane Matičnog naučnog odbora za mašinstvo i industrijski softver, 2022. (2022),
https://hdl.handle.net/21.15107/rcub_machinery_5658 .

TY  - CONF
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5277
AB  - The advent of the Industry 4.0 paradigm that relies on the concepts of Cyber-Physical Systems (CPS) and the Industrial Internet of Things (IIoT) leads to the transition from centralized to distributed control. In this approach, interconnected smart devices (sensors, actuators, etc.) as the key enablers achieve system control through coordinated work. Introduction of IIoT leads to ubiquitous communication between smart devices, thus opening up a vast area for potential malicious threats and attacks which can cause serious consequences, take to system dysfunction or even endanger human lives. Therefore, security mechanisms have to be developed to provide timely detection of different cyber-attacks and to keep the system safe and protected. Since industrial processes are often very complex and their analytical model is very difficult to determine, deep learning based methods for cyber-security mechanisms development are imposed as a technique of choice. Successful employment of data-driven solutions, particularly based on deep learning approaches usually requires a big amount of data. However, due to various limitations in the acquisition of data from the real process, its availability is still a major challenge. For instance, the Industry 4.0 factory implies frequent reconfiguration which reduces the time intervals available for experimental procedures such as data acquisition. One of the ways to deal with this issue is called data augmentation. In this paper, we apply data augmentation in the design of cyber-attack detection methods in Industrial Control Systems (ICS). In particular, we explore the possibilities for utilization of Generative Adversarial Networks (GAN) to generate the necessary amount of data for deep learning based modeling sing a relatively small number of available samples on input.
PB  - ETRAN Society, Belgrade, Academic Mind, Belgrade
C3  - 9th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2022), Proceedings, Novi Pazar, June 2022, ROI1.4
T1  - Gan-based data augmentation in the design of Cyber-attack detection methods
SP  - ROI1.4
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5277
ER  - 

@conference{
author = "Nedeljković, Dušan and Jakovljević, Živana",
year = "2022",
abstract = "The advent of the Industry 4.0 paradigm that relies on the concepts of Cyber-Physical Systems (CPS) and the Industrial Internet of Things (IIoT) leads to the transition from centralized to distributed control. In this approach, interconnected smart devices (sensors, actuators, etc.) as the key enablers achieve system control through coordinated work. Introduction of IIoT leads to ubiquitous communication between smart devices, thus opening up a vast area for potential malicious threats and attacks which can cause serious consequences, take to system dysfunction or even endanger human lives. Therefore, security mechanisms have to be developed to provide timely detection of different cyber-attacks and to keep the system safe and protected. Since industrial processes are often very complex and their analytical model is very difficult to determine, deep learning based methods for cyber-security mechanisms development are imposed as a technique of choice. Successful employment of data-driven solutions, particularly based on deep learning approaches usually requires a big amount of data. However, due to various limitations in the acquisition of data from the real process, its availability is still a major challenge. For instance, the Industry 4.0 factory implies frequent reconfiguration which reduces the time intervals available for experimental procedures such as data acquisition. One of the ways to deal with this issue is called data augmentation. In this paper, we apply data augmentation in the design of cyber-attack detection methods in Industrial Control Systems (ICS). In particular, we explore the possibilities for utilization of Generative Adversarial Networks (GAN) to generate the necessary amount of data for deep learning based modeling sing a relatively small number of available samples on input.",
publisher = "ETRAN Society, Belgrade, Academic Mind, Belgrade",
journal = "9th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2022), Proceedings, Novi Pazar, June 2022, ROI1.4",
title = "Gan-based data augmentation in the design of Cyber-attack detection methods",
pages = "ROI1.4",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5277"
}

Nedeljković, D.,& Jakovljević, Ž.. (2022). Gan-based data augmentation in the design of Cyber-attack detection methods. in 9th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2022), Proceedings, Novi Pazar, June 2022, ROI1.4
ETRAN Society, Belgrade, Academic Mind, Belgrade., ROI1.4.
https://hdl.handle.net/21.15107/rcub_machinery_5277

Nedeljković D, Jakovljević Ž. Gan-based data augmentation in the design of Cyber-attack detection methods. in 9th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2022), Proceedings, Novi Pazar, June 2022, ROI1.4. 2022;:ROI1.4.
https://hdl.handle.net/21.15107/rcub_machinery_5277 .

Nedeljković, Dušan, Jakovljević, Živana, "Gan-based data augmentation in the design of Cyber-attack detection methods" in 9th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2022), Proceedings, Novi Pazar, June 2022, ROI1.4 (2022):ROI1.4,
https://hdl.handle.net/21.15107/rcub_machinery_5277 .

TY  - CONF
AU  - Jakovljević, Živana
AU  - Nedeljković, Dušan
PY  - 2022
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3801
AB  - Implementation of Industry 4.0 concept in manufacturing environment requires the education of a new generation of engineers capable to address all the challenges that this industrial (r)evolution brings about. Cyber Physical Systems (CPS) represent technological basis of Industry 4.0 and the education of engineers in this highly interdisciplinary area is a paramount for successful implementation of Industry 4.0. In this paper we analyze expected levels of CPS implementation in manufacturing environment, opportunities that they offer with respect to manufacturing customization and high product variety, as well as the changes, challenges and threats that these systems introduce. Based on this analysis, the paper presents the most important topics that should be covered in manufacturing engineers’ education to provide them with necessary skills and competences, making them capable to effectively design and implement CPS based solutions and Industry 4.0 concept at factory shop-floor.
PB  - Springer Science and Business Media B.V.
C3  - Mechanisms and Machine Science
T1  - Cyber Physical Systems in Manufacturing Engineers Education
EP  - 743
SP  - 735
VL  - 109
DO  - 10.1007/978-3-030-88465-9_75
ER  - 

@conference{
author = "Jakovljević, Živana and Nedeljković, Dušan",
year = "2022",
abstract = "Implementation of Industry 4.0 concept in manufacturing environment requires the education of a new generation of engineers capable to address all the challenges that this industrial (r)evolution brings about. Cyber Physical Systems (CPS) represent technological basis of Industry 4.0 and the education of engineers in this highly interdisciplinary area is a paramount for successful implementation of Industry 4.0. In this paper we analyze expected levels of CPS implementation in manufacturing environment, opportunities that they offer with respect to manufacturing customization and high product variety, as well as the changes, challenges and threats that these systems introduce. Based on this analysis, the paper presents the most important topics that should be covered in manufacturing engineers’ education to provide them with necessary skills and competences, making them capable to effectively design and implement CPS based solutions and Industry 4.0 concept at factory shop-floor.",
publisher = "Springer Science and Business Media B.V.",
journal = "Mechanisms and Machine Science",
title = "Cyber Physical Systems in Manufacturing Engineers Education",
pages = "743-735",
volume = "109",
doi = "10.1007/978-3-030-88465-9_75"
}

Jakovljević, Ž.,& Nedeljković, D.. (2022). Cyber Physical Systems in Manufacturing Engineers Education. in Mechanisms and Machine Science
Springer Science and Business Media B.V.., 109, 735-743.
https://doi.org/10.1007/978-3-030-88465-9_75

Jakovljević Ž, Nedeljković D. Cyber Physical Systems in Manufacturing Engineers Education. in Mechanisms and Machine Science. 2022;109:735-743.
doi:10.1007/978-3-030-88465-9_75 .

Jakovljević, Živana, Nedeljković, Dušan, "Cyber Physical Systems in Manufacturing Engineers Education" in Mechanisms and Machine Science, 109 (2022):735-743,
https://doi.org/10.1007/978-3-030-88465-9_75 . .

TY  - CONF
AU  - Nedeljković, Dušan
AU  - Stanojević, Stefan
AU  - Puzović, Radovan
AU  - Jakovljević, Živana
PY  - 2021
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5274
AB  - Kompletna digitalizacija svih proizvodnih procesa u okviru Industrije 4.0 i povezivanje realnog sveta i njegove kibernetske (virtuelne) reprezentacije u realnom vremenu zahteva neometani protok informacija između i unutar svih nivoa piramide automatizacije. Jedan od ograničavajućih faktora u tom kontekstu predstavlja razmena podataka između uređaja i softverskih sistema različitih proizvođača koji po pravilu za komunikaciju koriste namenski kreirane protokole. Rešenje ovog problema se pronalazi u postizanju interoperabilnosti kroz primenu OPC-UA (engl. Open Platform Communication - Unified Architecture) standarda. U okviru ovog rada sprovedena je integracija resursa zasnovanih na servo motorima i sistema za izvršavanje proizvodnje korišćenjem OPC-UA.
PB  - University of Novi Sad, Faculty of Technical Sciences, Department of Production Engineering
C3  - Proceedings of the International Scientific Conference ETIKUM 2021, Novi Sad, 2021
T1  - Integracija proizvodnih resursa u sistem za izvršavanje proizvodnje korišćenjem opc-ua
EP  - 68
SP  - 65
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5274
ER  - 

@conference{
author = "Nedeljković, Dušan and Stanojević, Stefan and Puzović, Radovan and Jakovljević, Živana",
year = "2021",
abstract = "Kompletna digitalizacija svih proizvodnih procesa u okviru Industrije 4.0 i povezivanje realnog sveta i njegove kibernetske (virtuelne) reprezentacije u realnom vremenu zahteva neometani protok informacija između i unutar svih nivoa piramide automatizacije. Jedan od ograničavajućih faktora u tom kontekstu predstavlja razmena podataka između uređaja i softverskih sistema različitih proizvođača koji po pravilu za komunikaciju koriste namenski kreirane protokole. Rešenje ovog problema se pronalazi u postizanju interoperabilnosti kroz primenu OPC-UA (engl. Open Platform Communication - Unified Architecture) standarda. U okviru ovog rada sprovedena je integracija resursa zasnovanih na servo motorima i sistema za izvršavanje proizvodnje korišćenjem OPC-UA.",
publisher = "University of Novi Sad, Faculty of Technical Sciences, Department of Production Engineering",
journal = "Proceedings of the International Scientific Conference ETIKUM 2021, Novi Sad, 2021",
title = "Integracija proizvodnih resursa u sistem za izvršavanje proizvodnje korišćenjem opc-ua",
pages = "68-65",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5274"
}

Nedeljković, D., Stanojević, S., Puzović, R.,& Jakovljević, Ž.. (2021). Integracija proizvodnih resursa u sistem za izvršavanje proizvodnje korišćenjem opc-ua. in Proceedings of the International Scientific Conference ETIKUM 2021, Novi Sad, 2021
University of Novi Sad, Faculty of Technical Sciences, Department of Production Engineering., 65-68.
https://hdl.handle.net/21.15107/rcub_machinery_5274

Nedeljković D, Stanojević S, Puzović R, Jakovljević Ž. Integracija proizvodnih resursa u sistem za izvršavanje proizvodnje korišćenjem opc-ua. in Proceedings of the International Scientific Conference ETIKUM 2021, Novi Sad, 2021. 2021;:65-68.
https://hdl.handle.net/21.15107/rcub_machinery_5274 .

Nedeljković, Dušan, Stanojević, Stefan, Puzović, Radovan, Jakovljević, Živana, "Integracija proizvodnih resursa u sistem za izvršavanje proizvodnje korišćenjem opc-ua" in Proceedings of the International Scientific Conference ETIKUM 2021, Novi Sad, 2021 (2021):65-68,
https://hdl.handle.net/21.15107/rcub_machinery_5274 .

TY  - CONF
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
PY  - 2021
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5276
AB  - The emergence of the Industry 4.0 concept leads to crucial changes in manufacturing by building advanced industrial systems and applications based on Cyber-Physical Systems (CPS), as the core of this approach. Using CPS, manufacturing assets are designed in the form of systems of systems through interconnection of smart devices with integrated computation and communication capabilities. System control logic is distributed over a large number of resources, and its performance is achieved through their coordinated work and ubiquitous communication raising the issue of cyber-attacks by malicious adversaries. Since cybersecurity within industrial control systems is safety related, it is necessary to timely detect cyber-attacks on industrial assets; for these purposes a number of different approaches have been developed. As a technique of choice, deep learning (DL) based methods emerge, providing good online performances. In this work, we focus on the implementation of a DL based cyber-attack detection algorithm on an electro-pneumatic positioning system containing smart sensor and smart actuator. In particular, we employ cyber-attack detection procedure based on 1D Convolutional Neural Network (CNN) at the local controller of the smart actuator. The implemented algorithm can successfully detect cyber-attacks in real-time, as will be experimentally demonstrated.
PB  - Faculty of Technical Sciences, Department of Production Engineering, Novi Sad
C3  - Proceedings of the 14th International Scientific Conference MMA 2021 - Flexible Technologies, Novi Sad, september 2021
T1  - Implementation of cnn based algorithm for cyber-attacks detection on a real-world control system
EP  - 122
SP  - 119
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5276
ER  - 

@conference{
author = "Nedeljković, Dušan and Jakovljević, Živana",
year = "2021",
abstract = "The emergence of the Industry 4.0 concept leads to crucial changes in manufacturing by building advanced industrial systems and applications based on Cyber-Physical Systems (CPS), as the core of this approach. Using CPS, manufacturing assets are designed in the form of systems of systems through interconnection of smart devices with integrated computation and communication capabilities. System control logic is distributed over a large number of resources, and its performance is achieved through their coordinated work and ubiquitous communication raising the issue of cyber-attacks by malicious adversaries. Since cybersecurity within industrial control systems is safety related, it is necessary to timely detect cyber-attacks on industrial assets; for these purposes a number of different approaches have been developed. As a technique of choice, deep learning (DL) based methods emerge, providing good online performances. In this work, we focus on the implementation of a DL based cyber-attack detection algorithm on an electro-pneumatic positioning system containing smart sensor and smart actuator. In particular, we employ cyber-attack detection procedure based on 1D Convolutional Neural Network (CNN) at the local controller of the smart actuator. The implemented algorithm can successfully detect cyber-attacks in real-time, as will be experimentally demonstrated.",
publisher = "Faculty of Technical Sciences, Department of Production Engineering, Novi Sad",
journal = "Proceedings of the 14th International Scientific Conference MMA 2021 - Flexible Technologies, Novi Sad, september 2021",
title = "Implementation of cnn based algorithm for cyber-attacks detection on a real-world control system",
pages = "122-119",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5276"
}

Nedeljković, D.,& Jakovljević, Ž.. (2021). Implementation of cnn based algorithm for cyber-attacks detection on a real-world control system. in Proceedings of the 14th International Scientific Conference MMA 2021 - Flexible Technologies, Novi Sad, september 2021
Faculty of Technical Sciences, Department of Production Engineering, Novi Sad., 119-122.
https://hdl.handle.net/21.15107/rcub_machinery_5276

Nedeljković D, Jakovljević Ž. Implementation of cnn based algorithm for cyber-attacks detection on a real-world control system. in Proceedings of the 14th International Scientific Conference MMA 2021 - Flexible Technologies, Novi Sad, september 2021. 2021;:119-122.
https://hdl.handle.net/21.15107/rcub_machinery_5276 .

Nedeljković, Dušan, Jakovljević, Živana, "Implementation of cnn based algorithm for cyber-attacks detection on a real-world control system" in Proceedings of the 14th International Scientific Conference MMA 2021 - Flexible Technologies, Novi Sad, september 2021 (2021):119-122,
https://hdl.handle.net/21.15107/rcub_machinery_5276 .

TY  - CONF
AU  - Jakovljević, Živana
AU  - Nedeljković, Dušan
PY  - 2021
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5275
AB  - Cyber Physical Systems (CPS) and Internet of Things (IoT) open the way for new generation of Industrial Control Systems (ICS) characterized by high flexibility, modularity and reconfigurability necessary within Industry 4.0. Inevitable shift from centralized to distributed control systems is underway, but the changes are not as rapid as expected. One of the limiting factors is the lack of engineering techniques for distributed control systems design, simulation and verification. In this paper we analyze recently proposed techniques for distributed control systems development using an example of a simple transport system consisting of two CPS – smart conveyor belt and smart cylinder. In particular we consider the methods based on Control Interpreted Petri Nets (CIPN), Supervisory Control Theory (SCT) and IEC 61499 standard.
PB  - ETRAN Society, Belgrade, Academic Mind, Belgrade
C3  - 8th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2021), Proceedings, Republic of Srpska, Bosnia and Herzegovina, september 2021, ROI2.2
T1  - Distribution of control tasks to smart devices in industrial control systems: a case study
EP  - 590
SP  - 585
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5275
ER  - 

@conference{
author = "Jakovljević, Živana and Nedeljković, Dušan",
year = "2021",
abstract = "Cyber Physical Systems (CPS) and Internet of Things (IoT) open the way for new generation of Industrial Control Systems (ICS) characterized by high flexibility, modularity and reconfigurability necessary within Industry 4.0. Inevitable shift from centralized to distributed control systems is underway, but the changes are not as rapid as expected. One of the limiting factors is the lack of engineering techniques for distributed control systems design, simulation and verification. In this paper we analyze recently proposed techniques for distributed control systems development using an example of a simple transport system consisting of two CPS – smart conveyor belt and smart cylinder. In particular we consider the methods based on Control Interpreted Petri Nets (CIPN), Supervisory Control Theory (SCT) and IEC 61499 standard.",
publisher = "ETRAN Society, Belgrade, Academic Mind, Belgrade",
journal = "8th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2021), Proceedings, Republic of Srpska, Bosnia and Herzegovina, september 2021, ROI2.2",
title = "Distribution of control tasks to smart devices in industrial control systems: a case study",
pages = "590-585",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5275"
}

Jakovljević, Ž.,& Nedeljković, D.. (2021). Distribution of control tasks to smart devices in industrial control systems: a case study. in 8th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2021), Proceedings, Republic of Srpska, Bosnia and Herzegovina, september 2021, ROI2.2
ETRAN Society, Belgrade, Academic Mind, Belgrade., 585-590.
https://hdl.handle.net/21.15107/rcub_machinery_5275

Jakovljević Ž, Nedeljković D. Distribution of control tasks to smart devices in industrial control systems: a case study. in 8th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2021), Proceedings, Republic of Srpska, Bosnia and Herzegovina, september 2021, ROI2.2. 2021;:585-590.
https://hdl.handle.net/21.15107/rcub_machinery_5275 .

Jakovljević, Živana, Nedeljković, Dušan, "Distribution of control tasks to smart devices in industrial control systems: a case study" in 8th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2021), Proceedings, Republic of Srpska, Bosnia and Herzegovina, september 2021, ROI2.2 (2021):585-590,
https://hdl.handle.net/21.15107/rcub_machinery_5275 .

TY  - JOUR
AU  - Jakovljević, Živana
AU  - Lesi, Vuk
AU  - Pajić, Miroslav
PY  - 2021
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3622
AB  - Industrial Internet of Things (IIoT) represents a backbone of modern reconfigurable manufacturing systems (RMS), which enable manufacturing of a high product variety through rapid and easy reconfiguration of manufacturing equipment. In IIoT-enabled RMS, modular equipment is built from smart devices, each performing its own tasks, whereas the global functioning is achieved through their networking and intensive communication. Although device communication contributes to the system reconfigurability, it also opens up new security challenges due to potential vulnerability of communication links. In this article, we present security analysis for a major part of RMS in which manufacturing equipment is sequentially controlled and can be modeled as discrete event systems (DES). Control distribution within DES implies communication of certain events between smart modules. Specifically, in this work, we focus on attacks on communication of these events. In particular, we develop a method for modeling such attacks, including event insertion and removal attacks, in distributed sequential control; the method is based on the supervisory control theory framework. We show how the modeled attacks can be detected and provide a method for identification of communication links that require protection to avoid catastrophic damage of the system. Finally, we illustrate and experimentally validate applicability of our methodology on a real-world industrial case study with reconfigurable manufacturing equipment.
PB  - Ieee-Inst Electrical Electronics Engineers Inc, Piscataway
T2  - Ieee Transactions on Industrial Informatics
T1  - Attacks on Distributed Sequential Control in Manufacturing Automation
EP  - 786
IS  - 2
SP  - 775
VL  - 17
DO  - 10.1109/TII.2020.2987629
ER  - 

@article{
author = "Jakovljević, Živana and Lesi, Vuk and Pajić, Miroslav",
year = "2021",
abstract = "Industrial Internet of Things (IIoT) represents a backbone of modern reconfigurable manufacturing systems (RMS), which enable manufacturing of a high product variety through rapid and easy reconfiguration of manufacturing equipment. In IIoT-enabled RMS, modular equipment is built from smart devices, each performing its own tasks, whereas the global functioning is achieved through their networking and intensive communication. Although device communication contributes to the system reconfigurability, it also opens up new security challenges due to potential vulnerability of communication links. In this article, we present security analysis for a major part of RMS in which manufacturing equipment is sequentially controlled and can be modeled as discrete event systems (DES). Control distribution within DES implies communication of certain events between smart modules. Specifically, in this work, we focus on attacks on communication of these events. In particular, we develop a method for modeling such attacks, including event insertion and removal attacks, in distributed sequential control; the method is based on the supervisory control theory framework. We show how the modeled attacks can be detected and provide a method for identification of communication links that require protection to avoid catastrophic damage of the system. Finally, we illustrate and experimentally validate applicability of our methodology on a real-world industrial case study with reconfigurable manufacturing equipment.",
publisher = "Ieee-Inst Electrical Electronics Engineers Inc, Piscataway",
journal = "Ieee Transactions on Industrial Informatics",
title = "Attacks on Distributed Sequential Control in Manufacturing Automation",
pages = "786-775",
number = "2",
volume = "17",
doi = "10.1109/TII.2020.2987629"
}

Jakovljević, Ž., Lesi, V.,& Pajić, M.. (2021). Attacks on Distributed Sequential Control in Manufacturing Automation. in Ieee Transactions on Industrial Informatics
Ieee-Inst Electrical Electronics Engineers Inc, Piscataway., 17(2), 775-786.
https://doi.org/10.1109/TII.2020.2987629

Jakovljević Ž, Lesi V, Pajić M. Attacks on Distributed Sequential Control in Manufacturing Automation. in Ieee Transactions on Industrial Informatics. 2021;17(2):775-786.
doi:10.1109/TII.2020.2987629 .

Jakovljević, Živana, Lesi, Vuk, Pajić, Miroslav, "Attacks on Distributed Sequential Control in Manufacturing Automation" in Ieee Transactions on Industrial Informatics, 17, no. 2 (2021):775-786,
https://doi.org/10.1109/TII.2020.2987629 . .

TY  - JOUR
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
AU  - Miljković, Zoran
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3966
AB  - To improve productivity and efficiency in industrial manufacturing, the
fourth industrial revolution leads to the implementation of Cyber Physical
Systems (CPS) and Internet of Things (IoT) in the industrial environment.
Ubiquitous communication makes CPS susceptible to external influences,
which can have a negative intention; for instance, CPS are prone to
various attacks and malicious threats by different adversaries. The impact
of an attack on the system can lead to anomalies and serious consequences
for system parts or the system as a whole. Security mechanisms must be
developed in order to timely detect different attacks and to keep the system
safe and protected. In this paper, a method for sensor signal attacks
detection in a continuous time controlled systems has been proposed. The
method is based on Support Vector Machines (SVM) and tested on the data
obtained from the Secure Water Treatment (SWaT) testbed, a scaled-down
plant that produces purified water.
PB  - University of Belgrade - Faculty of Mechanical Engineering
T2  - FME Transactions, New Series
T1  - The Detection of Sensor Signal Attacks in Industrial Control Systems
EP  - 12
IS  - 1
SP  - 7
VL  - 48
DO  - 10.5937/fmet2001007N
ER  - 

@article{
author = "Nedeljković, Dušan and Jakovljević, Živana and Miljković, Zoran",
year = "2020",
abstract = "To improve productivity and efficiency in industrial manufacturing, the
fourth industrial revolution leads to the implementation of Cyber Physical
Systems (CPS) and Internet of Things (IoT) in the industrial environment.
Ubiquitous communication makes CPS susceptible to external influences,
which can have a negative intention; for instance, CPS are prone to
various attacks and malicious threats by different adversaries. The impact
of an attack on the system can lead to anomalies and serious consequences
for system parts or the system as a whole. Security mechanisms must be
developed in order to timely detect different attacks and to keep the system
safe and protected. In this paper, a method for sensor signal attacks
detection in a continuous time controlled systems has been proposed. The
method is based on Support Vector Machines (SVM) and tested on the data
obtained from the Secure Water Treatment (SWaT) testbed, a scaled-down
plant that produces purified water.",
publisher = "University of Belgrade - Faculty of Mechanical Engineering",
journal = "FME Transactions, New Series",
title = "The Detection of Sensor Signal Attacks in Industrial Control Systems",
pages = "12-7",
number = "1",
volume = "48",
doi = "10.5937/fmet2001007N"
}

Nedeljković, D., Jakovljević, Ž.,& Miljković, Z.. (2020). The Detection of Sensor Signal Attacks in Industrial Control Systems. in FME Transactions, New Series
University of Belgrade - Faculty of Mechanical Engineering., 48(1), 7-12.
https://doi.org/10.5937/fmet2001007N

Nedeljković D, Jakovljević Ž, Miljković Z. The Detection of Sensor Signal Attacks in Industrial Control Systems. in FME Transactions, New Series. 2020;48(1):7-12.
doi:10.5937/fmet2001007N .

Nedeljković, Dušan, Jakovljević, Živana, Miljković, Zoran, "The Detection of Sensor Signal Attacks in Industrial Control Systems" in FME Transactions, New Series, 48, no. 1 (2020):7-12,
https://doi.org/10.5937/fmet2001007N . .

TY  - JOUR
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
AU  - Miljković, Zoran
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3281
AB  - U cilju povećanja produktivnosti i efikasnosti proizvodnje, četvrta industrijska revolucija vodi ka implementaciji kibernetsko fizičkih sistema i interneta stvari u industrijskom okruženju. Sveobuhvatna komunikacija čini kibernetsko fizičke sisteme podložnim na spoljašnje uticaje, koji često mogu imati negativnu nameru, npr. napadi i smetnje proistekli od različitih uzročnika. Uticaj napada na sistem može dovesti do anomalija i ozbiljnih posledica po delove sistema ili sistem u celosti. Stoga, odbrambeni mehanizmi za pravovremenu detekciju napada moraju biti razvijeni, kako bi se sistem zaštitio i održala njegova funkcionalnost. U ovom radu, predložen je metod za detekciju napada na senzorske signale u kontinualno upravljanim sistemima. Metod je baziran na mašinama sa nosećim vektorima, a testiran na skupu podataka iz sistema za preradu vode.
AB  - To improve productivity and efficiency in industrial manufacturing, the fourth industrial revolution leads to the implementation of Cyber Physical Systems (CPS) and Internet of Things (IoT) in the industrial environment. Ubiquitous communication makes CPS susceptible to external influences, which can have a negative intention; for instance, CPS are prone to various attacks and malicious threats by different adversaries. The impact of an attack on the system can lead to anomalies and serious consequences for system parts or the system as a whole. Security mechanisms must be developed in order to timely detect different attacks and to keep the system safe and protected. In this paper, a method for sensor signal attacks detection in a continuous time controlled systems has been proposed. The method is based on Support Vector Machines (SVM) and tested on the data obtained from the Secure Water Treatment (SWaT) testbed, a scaled-down plant that produces purified water.
PB  - Univerzitet u Beogradu - Mašinski fakultet, Beograd
T2  - FME Transactions
T1  - Detekcija napada na senzorske signale u industrijskim kontrolnim sistemima
T1  - The detection of sensor signal attacks in industrial control systems
EP  - 12
IS  - 1
SP  - 7
VL  - 48
DO  - 10.5937/fmet2001007N
ER  - 

@article{
author = "Nedeljković, Dušan and Jakovljević, Živana and Miljković, Zoran",
year = "2020",
abstract = "U cilju povećanja produktivnosti i efikasnosti proizvodnje, četvrta industrijska revolucija vodi ka implementaciji kibernetsko fizičkih sistema i interneta stvari u industrijskom okruženju. Sveobuhvatna komunikacija čini kibernetsko fizičke sisteme podložnim na spoljašnje uticaje, koji često mogu imati negativnu nameru, npr. napadi i smetnje proistekli od različitih uzročnika. Uticaj napada na sistem može dovesti do anomalija i ozbiljnih posledica po delove sistema ili sistem u celosti. Stoga, odbrambeni mehanizmi za pravovremenu detekciju napada moraju biti razvijeni, kako bi se sistem zaštitio i održala njegova funkcionalnost. U ovom radu, predložen je metod za detekciju napada na senzorske signale u kontinualno upravljanim sistemima. Metod je baziran na mašinama sa nosećim vektorima, a testiran na skupu podataka iz sistema za preradu vode., To improve productivity and efficiency in industrial manufacturing, the fourth industrial revolution leads to the implementation of Cyber Physical Systems (CPS) and Internet of Things (IoT) in the industrial environment. Ubiquitous communication makes CPS susceptible to external influences, which can have a negative intention; for instance, CPS are prone to various attacks and malicious threats by different adversaries. The impact of an attack on the system can lead to anomalies and serious consequences for system parts or the system as a whole. Security mechanisms must be developed in order to timely detect different attacks and to keep the system safe and protected. In this paper, a method for sensor signal attacks detection in a continuous time controlled systems has been proposed. The method is based on Support Vector Machines (SVM) and tested on the data obtained from the Secure Water Treatment (SWaT) testbed, a scaled-down plant that produces purified water.",
publisher = "Univerzitet u Beogradu - Mašinski fakultet, Beograd",
journal = "FME Transactions",
title = "Detekcija napada na senzorske signale u industrijskim kontrolnim sistemima, The detection of sensor signal attacks in industrial control systems",
pages = "12-7",
number = "1",
volume = "48",
doi = "10.5937/fmet2001007N"
}

Nedeljković, D., Jakovljević, Ž.,& Miljković, Z.. (2020). Detekcija napada na senzorske signale u industrijskim kontrolnim sistemima. in FME Transactions
Univerzitet u Beogradu - Mašinski fakultet, Beograd., 48(1), 7-12.
https://doi.org/10.5937/fmet2001007N

Nedeljković D, Jakovljević Ž, Miljković Z. Detekcija napada na senzorske signale u industrijskim kontrolnim sistemima. in FME Transactions. 2020;48(1):7-12.
doi:10.5937/fmet2001007N .

Nedeljković, Dušan, Jakovljević, Živana, Miljković, Zoran, "Detekcija napada na senzorske signale u industrijskim kontrolnim sistemima" in FME Transactions, 48, no. 1 (2020):7-12,
https://doi.org/10.5937/fmet2001007N . .

TY  - CONF
AU  - Jakovljević, Živana
AU  - Nedeljković, Dušan
AU  - Ševarlić, Filip
AU  - Puzović, Radovan
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5273
AB  - Primena kibernetsko fizičkih sistema i industrijskog interneta stvari u proizvodnim pogonima otvara nove mogućnosti u oblasti automatizacije proizvodnje i dovodi do značajnih promena u industrijskoj proizvodnji nazvanih jednim imenom Industrija 4.0. Jedan od ključnih elemenata za efikasnu implementaciju rekonfigurabilnih tehnoloških sistema koji su u samoj osnovi Industrije 4.0 jeste introperabilnost između uređaja i softverskih sistema različitih proizvođača na svim nivoima piramide automatizacije. OPC-UA (engl. Open Platform Communication – Unified Architecture) je prepoznat kao najistaknutiji standard za ostvarivanje komunikacije između različitih sistema uz visok nivo interoperabilnosti. U okviru ovog rada izlažu se osnove OPC-UA i ukazuje se na mogućnosti njegove primene u proizvodnim pogonima. Pored toga, prikazuje se primer upotrebe OPC-UA u komunikaciji između automatskog sistema za montažu delova i sistema za izvršavanje proizvodnje uz automatski protok informacija u realnom vremenu.
PB  - University of Belgrade - Faculty of Mechanical Engineering
C3  - 42. JUPITER Konferencija, 44. simpozijum „Upravljanje proizvodnjom u industriji prerade metala“, Zbornik radova / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020, 4.1-4.12
T1  - Komunikacija između proizvodnih resursa korišćenjem opc-ua standarda
T1  - Communication between manufacturing resources using opc-ua standard
EP  - 4.12
SP  - 4.1
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5273
ER  - 

@conference{
author = "Jakovljević, Živana and Nedeljković, Dušan and Ševarlić, Filip and Puzović, Radovan",
year = "2020",
abstract = "Primena kibernetsko fizičkih sistema i industrijskog interneta stvari u proizvodnim pogonima otvara nove mogućnosti u oblasti automatizacije proizvodnje i dovodi do značajnih promena u industrijskoj proizvodnji nazvanih jednim imenom Industrija 4.0. Jedan od ključnih elemenata za efikasnu implementaciju rekonfigurabilnih tehnoloških sistema koji su u samoj osnovi Industrije 4.0 jeste introperabilnost između uređaja i softverskih sistema različitih proizvođača na svim nivoima piramide automatizacije. OPC-UA (engl. Open Platform Communication – Unified Architecture) je prepoznat kao najistaknutiji standard za ostvarivanje komunikacije između različitih sistema uz visok nivo interoperabilnosti. U okviru ovog rada izlažu se osnove OPC-UA i ukazuje se na mogućnosti njegove primene u proizvodnim pogonima. Pored toga, prikazuje se primer upotrebe OPC-UA u komunikaciji između automatskog sistema za montažu delova i sistema za izvršavanje proizvodnje uz automatski protok informacija u realnom vremenu.",
publisher = "University of Belgrade - Faculty of Mechanical Engineering",
journal = "42. JUPITER Konferencija, 44. simpozijum „Upravljanje proizvodnjom u industriji prerade metala“, Zbornik radova / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020, 4.1-4.12",
title = "Komunikacija između proizvodnih resursa korišćenjem opc-ua standarda, Communication between manufacturing resources using opc-ua standard",
pages = "4.12-4.1",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5273"
}

Jakovljević, Ž., Nedeljković, D., Ševarlić, F.,& Puzović, R.. (2020). Komunikacija između proizvodnih resursa korišćenjem opc-ua standarda. in 42. JUPITER Konferencija, 44. simpozijum „Upravljanje proizvodnjom u industriji prerade metala“, Zbornik radova / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020, 4.1-4.12
University of Belgrade - Faculty of Mechanical Engineering., 4.1-4.12.
https://hdl.handle.net/21.15107/rcub_machinery_5273

Jakovljević Ž, Nedeljković D, Ševarlić F, Puzović R. Komunikacija između proizvodnih resursa korišćenjem opc-ua standarda. in 42. JUPITER Konferencija, 44. simpozijum „Upravljanje proizvodnjom u industriji prerade metala“, Zbornik radova / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020, 4.1-4.12. 2020;:4.1-4.12.
https://hdl.handle.net/21.15107/rcub_machinery_5273 .

Jakovljević, Živana, Nedeljković, Dušan, Ševarlić, Filip, Puzović, Radovan, "Komunikacija između proizvodnih resursa korišćenjem opc-ua standarda" in 42. JUPITER Konferencija, 44. simpozijum „Upravljanje proizvodnjom u industriji prerade metala“, Zbornik radova / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020, 4.1-4.12 (2020):4.1-4.12,
https://hdl.handle.net/21.15107/rcub_machinery_5273 .

TY  - CONF
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5270
AB  - Current and forthcoming market requirements bring huge challenges to today manufacturing. Answer to the changing demands and high product variety is found in the integration of the Internet of Things (IoT) and Cyber-Physical Systems (CPS) into industrial plants. CPS as smart devices capable of data processing and information exchange enable fast adaptation of manufacturing resources to production of diversified products. Nevertheless, fully implemented internet communication at factory shop floor opens up a whole new area for potential cyber-attacks. The consequences of attacks can have a negative influence on the system or even endanger human lives. Therefore, defence techniques must be developed to ensure a high level of protection. Early detection of cyber-attacks is crucial to minimize or completely avoid the negative effects of the attack and keep the system safe and reliable. In this work, we propose an attack detection method based on deep learning approach. We explore the application of several deep learning architectures based on Simple Recurrent Neural Networks (Simple RNN) and Long Short-Term Memory (LSTM) based
RNN for generation of the detection mechanisms tailored to the concrete process. Our method was experimentally verified using
real world data and it proved to be effective, as it detected all considered attacks without false positives.
PB  - ETRAN Society, Belgrade, Academic Mind, Belgrade
C3  - 7th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2020), Proceedings, Belgrade, Čačak, Niš, Novi Sad, September 2020.
T1  - Cyber-attack detection method based on RNN
EP  - 731
SP  - 726
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5270
ER  - 

@conference{
author = "Nedeljković, Dušan and Jakovljević, Živana",
year = "2020",
abstract = "Current and forthcoming market requirements bring huge challenges to today manufacturing. Answer to the changing demands and high product variety is found in the integration of the Internet of Things (IoT) and Cyber-Physical Systems (CPS) into industrial plants. CPS as smart devices capable of data processing and information exchange enable fast adaptation of manufacturing resources to production of diversified products. Nevertheless, fully implemented internet communication at factory shop floor opens up a whole new area for potential cyber-attacks. The consequences of attacks can have a negative influence on the system or even endanger human lives. Therefore, defence techniques must be developed to ensure a high level of protection. Early detection of cyber-attacks is crucial to minimize or completely avoid the negative effects of the attack and keep the system safe and reliable. In this work, we propose an attack detection method based on deep learning approach. We explore the application of several deep learning architectures based on Simple Recurrent Neural Networks (Simple RNN) and Long Short-Term Memory (LSTM) based
RNN for generation of the detection mechanisms tailored to the concrete process. Our method was experimentally verified using
real world data and it proved to be effective, as it detected all considered attacks without false positives.",
publisher = "ETRAN Society, Belgrade, Academic Mind, Belgrade",
journal = "7th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2020), Proceedings, Belgrade, Čačak, Niš, Novi Sad, September 2020.",
title = "Cyber-attack detection method based on RNN",
pages = "731-726",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5270"
}

Nedeljković, D.,& Jakovljević, Ž.. (2020). Cyber-attack detection method based on RNN. in 7th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2020), Proceedings, Belgrade, Čačak, Niš, Novi Sad, September 2020.
ETRAN Society, Belgrade, Academic Mind, Belgrade., 726-731.
https://hdl.handle.net/21.15107/rcub_machinery_5270

Nedeljković D, Jakovljević Ž. Cyber-attack detection method based on RNN. in 7th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2020), Proceedings, Belgrade, Čačak, Niš, Novi Sad, September 2020.. 2020;:726-731.
https://hdl.handle.net/21.15107/rcub_machinery_5270 .

Nedeljković, Dušan, Jakovljević, Živana, "Cyber-attack detection method based on RNN" in 7th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN 2020), Proceedings, Belgrade, Čačak, Niš, Novi Sad, September 2020. (2020):726-731,
https://hdl.handle.net/21.15107/rcub_machinery_5270 .

TY  - CONF
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3448
AB  - High product variety imposed to manufacturing companies by contemporary market requires efficient adaptation of production, which leads to the application of Reconfigurable Manufacturing Systems (RMS). These systems are based on rapid and effective reconfiguration of manufacturing equipment that can be achieved only through high-level interoperability of the multi-vendor devices. OPC-UA (Open Platform Communication - Unified Architecture) as a platform-independent standard provides semantic interoperability and secure machine to machine communication and represents a basis for RMS development. In this paper, we illustrate how OPC-UA can be employed for integration of smart devices into legacy control system using an example of electropneumatic manipulation system and smart vision sensor. The smart vision sensor consists of a camera augmented by RaspberryPi platform that utilizes an image classification method based on convolutional neural networks (CNN).
PB  - Institute of Electrical and Electronics Engineers Inc.
C3  - 28th Telecommunications forum TELFOR 2020 - Proceedings, Serbia, Belgrade, November 24-25, 2020
T1  - Integration of Smart Vision Sensor into Manipulator Control System using OPC-UA
DO  - 10.1109/TELFOR51502.2020.9306524
ER  - 

@conference{
author = "Nedeljković, Dušan and Jakovljević, Živana",
year = "2020",
abstract = "High product variety imposed to manufacturing companies by contemporary market requires efficient adaptation of production, which leads to the application of Reconfigurable Manufacturing Systems (RMS). These systems are based on rapid and effective reconfiguration of manufacturing equipment that can be achieved only through high-level interoperability of the multi-vendor devices. OPC-UA (Open Platform Communication - Unified Architecture) as a platform-independent standard provides semantic interoperability and secure machine to machine communication and represents a basis for RMS development. In this paper, we illustrate how OPC-UA can be employed for integration of smart devices into legacy control system using an example of electropneumatic manipulation system and smart vision sensor. The smart vision sensor consists of a camera augmented by RaspberryPi platform that utilizes an image classification method based on convolutional neural networks (CNN).",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
journal = "28th Telecommunications forum TELFOR 2020 - Proceedings, Serbia, Belgrade, November 24-25, 2020",
title = "Integration of Smart Vision Sensor into Manipulator Control System using OPC-UA",
doi = "10.1109/TELFOR51502.2020.9306524"
}

Nedeljković, D.,& Jakovljević, Ž.. (2020). Integration of Smart Vision Sensor into Manipulator Control System using OPC-UA. in 28th Telecommunications forum TELFOR 2020 - Proceedings, Serbia, Belgrade, November 24-25, 2020
Institute of Electrical and Electronics Engineers Inc...
https://doi.org/10.1109/TELFOR51502.2020.9306524

Nedeljković D, Jakovljević Ž. Integration of Smart Vision Sensor into Manipulator Control System using OPC-UA. in 28th Telecommunications forum TELFOR 2020 - Proceedings, Serbia, Belgrade, November 24-25, 2020. 2020;.
doi:10.1109/TELFOR51502.2020.9306524 .

Nedeljković, Dušan, Jakovljević, Živana, "Integration of Smart Vision Sensor into Manipulator Control System using OPC-UA" in 28th Telecommunications forum TELFOR 2020 - Proceedings, Serbia, Belgrade, November 24-25, 2020 (2020),
https://doi.org/10.1109/TELFOR51502.2020.9306524 . .

TY  - CONF
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
AU  - Miljković, Zoran
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/4475
AB  - Razvoj tehnologija obrade slike otvara nove perspektive i doprinosi povećanju produktivnosti i kvaliteta širokog spektra industrijskih aplikacija. Klasifikacija slike spada u grupu najkompleksnijih procesa u oblasti digitalne obrade slike, a predstavlja dodeljivanje klase (iz prethodno definisanog skupa) slici koja se posmatra. U okviru ovog rada, klasifikacija slike koristi se u cilju određivanja orijentacije prizmatičnog dela. Predložena metoda klasifikacije zasnovana je na primeni konvolucionih neuronskih mreža (CNN - engl. Convolutional Neural Network). U zavisnosti od vrste ulaza koji se dovodi CNN-u, razmatrana su dva pristupa: prvi pristup podrazumeva preprocesiranje slike i izdvajanje obeležja baziranih na detekciji ivica; dok drugi pristup koristi sirove podatke (bez prethodno izdvojenih obeležja). Metod klasifikacije testiran je u realnom vremenu na eksperimentalnoj instalaciji baziranoj na Raspberry Pi platformi.
PB  - University of Belgrade - Faculty of Mechanical Engineering
C3  - 42. ЈУПИТЕР Конференција, 44. симпозијум „Управљање производњом у индустрији прераде метала“, Зборник радова  / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020
T1  - Класификација слике заснована на примени конволуционих неуронских мрежа
T1  - Image Clasiffication Based on Convolutional Neural Networks
EP  - 4.23
SP  - 4.13
UR  - https://hdl.handle.net/21.15107/rcub_machinery_4475
ER  - 

@conference{
author = "Nedeljković, Dušan and Jakovljević, Živana and Miljković, Zoran",
year = "2020",
abstract = "Razvoj tehnologija obrade slike otvara nove perspektive i doprinosi povećanju produktivnosti i kvaliteta širokog spektra industrijskih aplikacija. Klasifikacija slike spada u grupu najkompleksnijih procesa u oblasti digitalne obrade slike, a predstavlja dodeljivanje klase (iz prethodno definisanog skupa) slici koja se posmatra. U okviru ovog rada, klasifikacija slike koristi se u cilju određivanja orijentacije prizmatičnog dela. Predložena metoda klasifikacije zasnovana je na primeni konvolucionih neuronskih mreža (CNN - engl. Convolutional Neural Network). U zavisnosti od vrste ulaza koji se dovodi CNN-u, razmatrana su dva pristupa: prvi pristup podrazumeva preprocesiranje slike i izdvajanje obeležja baziranih na detekciji ivica; dok drugi pristup koristi sirove podatke (bez prethodno izdvojenih obeležja). Metod klasifikacije testiran je u realnom vremenu na eksperimentalnoj instalaciji baziranoj na Raspberry Pi platformi.",
publisher = "University of Belgrade - Faculty of Mechanical Engineering",
journal = "42. ЈУПИТЕР Конференција, 44. симпозијум „Управљање производњом у индустрији прераде метала“, Зборник радова  / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020",
title = "Класификација слике заснована на примени конволуционих неуронских мрежа, Image Clasiffication Based on Convolutional Neural Networks",
pages = "4.23-4.13",
url = "https://hdl.handle.net/21.15107/rcub_machinery_4475"
}

Nedeljković, D., Jakovljević, Ž.,& Miljković, Z.. (2020). Класификација слике заснована на примени конволуционих неуронских мрежа. in 42. ЈУПИТЕР Конференција, 44. симпозијум „Управљање производњом у индустрији прераде метала“, Зборник радова  / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020
University of Belgrade - Faculty of Mechanical Engineering., 4.13-4.23.
https://hdl.handle.net/21.15107/rcub_machinery_4475

Nedeljković D, Jakovljević Ž, Miljković Z. Класификација слике заснована на примени конволуционих неуронских мрежа. in 42. ЈУПИТЕР Конференција, 44. симпозијум „Управљање производњом у индустрији прераде метала“, Зборник радова  / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020. 2020;:4.13-4.23.
https://hdl.handle.net/21.15107/rcub_machinery_4475 .

Nedeljković, Dušan, Jakovljević, Živana, Miljković, Zoran, "Класификација слике заснована на примени конволуционих неуронских мрежа" in 42. ЈУПИТЕР Конференција, 44. симпозијум „Управљање производњом у индустрији прераде метала“, Зборник радова  / 42nd JUPITER Conference, Proceedings, Beograd, oktobar 2020 (2020):4.13-4.23,
https://hdl.handle.net/21.15107/rcub_machinery_4475 .

TY  - JOUR
AU  - Nedeljković, Dušan
AU  - Jakovljević, Živana
AU  - Miljković, Zoran
AU  - Pajić, Miroslav
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3442
AB  - Concept of Industry 4.0 and implementation of Cyber Physical Systems (CPS) and Internet of Things (IoT) in industrial plants are changing the way we manufacture. Introduction of industrial IoT leads to ubiquitous communication (usually wireless) between devices in industrial control systems, thus introducing numerous security concerns and opening up wide space for potential malicious threats and attacks. As a consequence of various cyber-attacks, fatal failures can occur on system parts or the system as a whole. Therefore, security mechanisms must be developed to provide sufficient resilience to cyber-attacks and keep the system safe and protected. In this paper we present a method for detection of attacks on sensor signals, based on e insensitive support vector regression (e-SVR). The method is implemented on publicly available data obtained from Secure Water Treatment (SWaT) testbed as well as on a real-world continuous time controlled electro-pneumatic positioning system. In both cases, the method successfully detected all considered attacks (without false positives).
PB  - Beograd : Društvo za telekomunikacije ; Akademska misao
T2  - Telfor Journal
T1  - Detection of cyber-attacks in systems with distributed control based on support vector regression
EP  - 109
IS  - 2
SP  - 104
VL  - 12
DO  - 10.5937/TELFOR2002104N
ER  - 

@article{
author = "Nedeljković, Dušan and Jakovljević, Živana and Miljković, Zoran and Pajić, Miroslav",
year = "2020",
abstract = "Concept of Industry 4.0 and implementation of Cyber Physical Systems (CPS) and Internet of Things (IoT) in industrial plants are changing the way we manufacture. Introduction of industrial IoT leads to ubiquitous communication (usually wireless) between devices in industrial control systems, thus introducing numerous security concerns and opening up wide space for potential malicious threats and attacks. As a consequence of various cyber-attacks, fatal failures can occur on system parts or the system as a whole. Therefore, security mechanisms must be developed to provide sufficient resilience to cyber-attacks and keep the system safe and protected. In this paper we present a method for detection of attacks on sensor signals, based on e insensitive support vector regression (e-SVR). The method is implemented on publicly available data obtained from Secure Water Treatment (SWaT) testbed as well as on a real-world continuous time controlled electro-pneumatic positioning system. In both cases, the method successfully detected all considered attacks (without false positives).",
publisher = "Beograd : Društvo za telekomunikacije ; Akademska misao",
journal = "Telfor Journal",
title = "Detection of cyber-attacks in systems with distributed control based on support vector regression",
pages = "109-104",
number = "2",
volume = "12",
doi = "10.5937/TELFOR2002104N"
}

Nedeljković, D., Jakovljević, Ž., Miljković, Z.,& Pajić, M.. (2020). Detection of cyber-attacks in systems with distributed control based on support vector regression. in Telfor Journal
Beograd : Društvo za telekomunikacije ; Akademska misao., 12(2), 104-109.
https://doi.org/10.5937/TELFOR2002104N

Nedeljković D, Jakovljević Ž, Miljković Z, Pajić M. Detection of cyber-attacks in systems with distributed control based on support vector regression. in Telfor Journal. 2020;12(2):104-109.
doi:10.5937/TELFOR2002104N .

Nedeljković, Dušan, Jakovljević, Živana, Miljković, Zoran, Pajić, Miroslav, "Detection of cyber-attacks in systems with distributed control based on support vector regression" in Telfor Journal, 12, no. 2 (2020):104-109,
https://doi.org/10.5937/TELFOR2002104N . .

TY  - JOUR
AU  - Jakovljević, Živana
AU  - Lesi, Vuk
AU  - Mitrović, Stefan M.
AU  - Pajić, Miroslav
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3412
AB  - Recent trends in manufacturing require the use of reconfigurable equipment that facilitates rapid and cost-effective change of functionality through modular design, which supports fast integration. Intelligent devices (e.g., sensors, actuators) with integrated computation and communication capabilities enable high-level modularity, not only with the respect to hardware components but also in terms of control functionality; this can be achieved by distributing control to different network-connected devices. Thus, to enable fast and reliable system reconfigurations, in this brief, we introduce a method for distribution of control tasks and generation of control code for the devices in the control network. Our approach is based on the control interpreted Petri nets (CIPNs) formalism. We start from a CIPN capturing the centralized (overall) control system, and the mapping of input and output signals to local controllers (LCs) (i.e., smart devices) that have direct physical access to system sensors and actuators. From these, our method automatically designs distributed control tasks for LCs in the network, as well as generates control code for each LC. The applicability of the proposed method is experimentally verified on two real-world case studies.
PB  - IEEE - Inst Electrical Electronics Engineers
T2  - IEEE Transactions on Control Systems Technology
T1  - Distributing Sequential Control for Manufacturing Automation Systems
EP  - 1594
IS  - 4
SP  - 1586
VL  - 28
DO  - 10.1109/TCST.2019.2912776
ER  - 

@article{
author = "Jakovljević, Živana and Lesi, Vuk and Mitrović, Stefan M. and Pajić, Miroslav",
year = "2020",
abstract = "Recent trends in manufacturing require the use of reconfigurable equipment that facilitates rapid and cost-effective change of functionality through modular design, which supports fast integration. Intelligent devices (e.g., sensors, actuators) with integrated computation and communication capabilities enable high-level modularity, not only with the respect to hardware components but also in terms of control functionality; this can be achieved by distributing control to different network-connected devices. Thus, to enable fast and reliable system reconfigurations, in this brief, we introduce a method for distribution of control tasks and generation of control code for the devices in the control network. Our approach is based on the control interpreted Petri nets (CIPNs) formalism. We start from a CIPN capturing the centralized (overall) control system, and the mapping of input and output signals to local controllers (LCs) (i.e., smart devices) that have direct physical access to system sensors and actuators. From these, our method automatically designs distributed control tasks for LCs in the network, as well as generates control code for each LC. The applicability of the proposed method is experimentally verified on two real-world case studies.",
publisher = "IEEE - Inst Electrical Electronics Engineers",
journal = "IEEE Transactions on Control Systems Technology",
title = "Distributing Sequential Control for Manufacturing Automation Systems",
pages = "1594-1586",
number = "4",
volume = "28",
doi = "10.1109/TCST.2019.2912776"
}

Jakovljević, Ž., Lesi, V., Mitrović, S. M.,& Pajić, M.. (2020). Distributing Sequential Control for Manufacturing Automation Systems. in IEEE Transactions on Control Systems Technology
IEEE - Inst Electrical Electronics Engineers., 28(4), 1586-1594.
https://doi.org/10.1109/TCST.2019.2912776

Jakovljević Ž, Lesi V, Mitrović SM, Pajić M. Distributing Sequential Control for Manufacturing Automation Systems. in IEEE Transactions on Control Systems Technology. 2020;28(4):1586-1594.
doi:10.1109/TCST.2019.2912776 .

Jakovljević, Živana, Lesi, Vuk, Mitrović, Stefan M., Pajić, Miroslav, "Distributing Sequential Control for Manufacturing Automation Systems" in IEEE Transactions on Control Systems Technology, 28, no. 4 (2020):1586-1594,
https://doi.org/10.1109/TCST.2019.2912776 . .

TY  - JOUR
AU  - Sokac, Mario
AU  - Budak, Igor
AU  - Katić, Marko
AU  - Jakovljević, Živana
AU  - Santosi, Željko
AU  - Vukelić, Đorđe
PY  - 2020
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/3368
AB  - The paper demonstrates a novel methodology for surface extraction of multi-material components (MMCs) on industrial X-ray computed tomography (CT) datasets. The methodology is based on a combination of fuzzy C-means clustering (FCM) and region growing (RG) methods. FCM, used as a preprocessing step, allows proper classification and improvement of different objects boundaries present on industrial X-ray CT datasets. Afterwards, application of RG method enables accurate segmentation of classified and improved X-ray CT datasets. The performance of presented approach has been tested on two CT datasets acquired on an industrial X-ray CT system NIKON XT H 225. It was also compared against two commercial industrial software VGStudio Max v3.1 and GOM Inspect v2018. Obtained results from application of the proposed approach show significant improvement in surface extraction of MMCs in CT datasets, especially in cases of low-density materials such as polymers. Verification has been conducted by obtaining reference measurements using contact coordinate measuring machine (CMM) Contura G2 by CARL ZEISS.
PB  - Elsevier Sci Ltd, Oxford
T2  - Measurement
T1  - Improved surface extraction of multi-material components for single-source industrial X-ray computed tomography
VL  - 153
DO  - 10.1016/j.measurement.2019.107438
ER  - 

@article{
author = "Sokac, Mario and Budak, Igor and Katić, Marko and Jakovljević, Živana and Santosi, Željko and Vukelić, Đorđe",
year = "2020",
abstract = "The paper demonstrates a novel methodology for surface extraction of multi-material components (MMCs) on industrial X-ray computed tomography (CT) datasets. The methodology is based on a combination of fuzzy C-means clustering (FCM) and region growing (RG) methods. FCM, used as a preprocessing step, allows proper classification and improvement of different objects boundaries present on industrial X-ray CT datasets. Afterwards, application of RG method enables accurate segmentation of classified and improved X-ray CT datasets. The performance of presented approach has been tested on two CT datasets acquired on an industrial X-ray CT system NIKON XT H 225. It was also compared against two commercial industrial software VGStudio Max v3.1 and GOM Inspect v2018. Obtained results from application of the proposed approach show significant improvement in surface extraction of MMCs in CT datasets, especially in cases of low-density materials such as polymers. Verification has been conducted by obtaining reference measurements using contact coordinate measuring machine (CMM) Contura G2 by CARL ZEISS.",
publisher = "Elsevier Sci Ltd, Oxford",
journal = "Measurement",
title = "Improved surface extraction of multi-material components for single-source industrial X-ray computed tomography",
volume = "153",
doi = "10.1016/j.measurement.2019.107438"
}

Sokac, M., Budak, I., Katić, M., Jakovljević, Ž., Santosi, Ž.,& Vukelić, Đ.. (2020). Improved surface extraction of multi-material components for single-source industrial X-ray computed tomography. in Measurement
Elsevier Sci Ltd, Oxford., 153.
https://doi.org/10.1016/j.measurement.2019.107438

Sokac M, Budak I, Katić M, Jakovljević Ž, Santosi Ž, Vukelić Đ. Improved surface extraction of multi-material components for single-source industrial X-ray computed tomography. in Measurement. 2020;153.
doi:10.1016/j.measurement.2019.107438 .

Sokac, Mario, Budak, Igor, Katić, Marko, Jakovljević, Živana, Santosi, Željko, Vukelić, Đorđe, "Improved surface extraction of multi-material components for single-source industrial X-ray computed tomography" in Measurement, 153 (2020),
https://doi.org/10.1016/j.measurement.2019.107438 . .

TY  - CONF
AU  - Nedeljković, Dušan
AU  - Kokotović, Branko
AU  - Jakovljević, Živana
PY  - 2019
UR  - https://machinery.mas.bg.ac.rs/handle/123456789/5266
AB  - Trend identification gives a general tendency of a signal and as such can represent the first step in
signal change detection. This is often a method for extracting useful features from the measured signal that can be transferred to meaningful conclusions, which can serve as a basis for process control or predicting the future behavior of the process. Fourier analysis, owing to its simplicity, is traditionally applied in time series processing; however, it has shortcomings in the analysis of signals that are not periodic. As a result, a number of techniques with better performance in non-stationary signal analysis have been proposed. In this paper, we carry out comparative analysis of two techniques for trend identification of non-stationary signals: Discrete Wavelet Transform (DWT) and Singular Spectrum Analysis (SSA). The analysis involves examining the applicability of these techniques both in offline and in real-time cases. Comparative analysis, as a result, gives support for the decision in selecting the technique of choice depending on the application.
PB  - World Association for Innovative Technologies
C3  - International Conference on Innovative Technologies (IN-TECH 2019), Proceedings, Belgrade, september 2019, 48-51.
T1  - Comparative analysis of discrete wavelet transform and singular spectrum analysis in signal trend identification
EP  - 51
SP  - 48
UR  - https://hdl.handle.net/21.15107/rcub_machinery_5266
ER  - 

@conference{
author = "Nedeljković, Dušan and Kokotović, Branko and Jakovljević, Živana",
year = "2019",
abstract = "Trend identification gives a general tendency of a signal and as such can represent the first step in
signal change detection. This is often a method for extracting useful features from the measured signal that can be transferred to meaningful conclusions, which can serve as a basis for process control or predicting the future behavior of the process. Fourier analysis, owing to its simplicity, is traditionally applied in time series processing; however, it has shortcomings in the analysis of signals that are not periodic. As a result, a number of techniques with better performance in non-stationary signal analysis have been proposed. In this paper, we carry out comparative analysis of two techniques for trend identification of non-stationary signals: Discrete Wavelet Transform (DWT) and Singular Spectrum Analysis (SSA). The analysis involves examining the applicability of these techniques both in offline and in real-time cases. Comparative analysis, as a result, gives support for the decision in selecting the technique of choice depending on the application.",
publisher = "World Association for Innovative Technologies",
journal = "International Conference on Innovative Technologies (IN-TECH 2019), Proceedings, Belgrade, september 2019, 48-51.",
title = "Comparative analysis of discrete wavelet transform and singular spectrum analysis in signal trend identification",
pages = "51-48",
url = "https://hdl.handle.net/21.15107/rcub_machinery_5266"
}

Nedeljković, D., Kokotović, B.,& Jakovljević, Ž.. (2019). Comparative analysis of discrete wavelet transform and singular spectrum analysis in signal trend identification. in International Conference on Innovative Technologies (IN-TECH 2019), Proceedings, Belgrade, september 2019, 48-51.
World Association for Innovative Technologies., 48-51.
https://hdl.handle.net/21.15107/rcub_machinery_5266

Nedeljković D, Kokotović B, Jakovljević Ž. Comparative analysis of discrete wavelet transform and singular spectrum analysis in signal trend identification. in International Conference on Innovative Technologies (IN-TECH 2019), Proceedings, Belgrade, september 2019, 48-51.. 2019;:48-51.
https://hdl.handle.net/21.15107/rcub_machinery_5266 .

Nedeljković, Dušan, Kokotović, Branko, Jakovljević, Živana, "Comparative analysis of discrete wavelet transform and singular spectrum analysis in signal trend identification" in International Conference on Innovative Technologies (IN-TECH 2019), Proceedings, Belgrade, september 2019, 48-51. (2019):48-51,
https://hdl.handle.net/21.15107/rcub_machinery_5266 .