Maša Milošević
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Maša Milošević has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Nikola Ivačko
University of Nis
5 shared publications - Ivan Ćirić
University of Niš, Faculty of Mechanical Engineering, Republic of Serbia
4 shared publications - Dušan Stojiljković
University of Nis
3 shared publications - Ana Kitić
University of Nis
2 shared publications Ana Momčilović
Academy of Technical Applied Sciences Belgrade, Serbia
1 shared publication- Danijela Ristić-Durrant
OHB Digital Services GmbH, 28359 Bremen, Germany
1 shared publication
Latest Publications
- 30 September 2024
- Published by Springer Nature
- p. 133-147
Robustness Evaluation of Pre-trained vs. Fine-Tuned Computer Vision Models for Score Detection in Dynamic Sports Environments
- 30 September 2024
- Published by Springer Nature
- p. 133-147
Robustness Evaluation of Pre-trained vs. Fine-Tuned Computer Vision Models for Score Detection in Dynamic Sports Environments
- 1 February 2024
- Published by Springer Nature
- p. 206-217
CNN - Based Object Detection for Robot Grasping in Cluttered Environment
- 1 February 2024
- Published by Springer Nature
- p. 206-217
CNN - Based Object Detection for Robot Grasping in Cluttered Environment
- 1 February 2024
- Published by Springer Nature
- p. 218-228
Performance Prediction of Bio-inspired Compliant Grippers Using Machine Learning Algorithms
- 1 February 2024
- Published by Springer Nature
- p. 218-228
Performance Prediction of Bio-inspired Compliant Grippers Using Machine Learning Algorithms
- Open Access
- 28 September 2023
- Published by Acadlore Publishing Services Limited in Journal of Engineering Management and Systems Engineering
- Vol. 2 (4) , 196-203
Isogeometric Finite Element Analysis with Machine Learning Integration for Piezoelectric Laminated Shells
Innovative lightweight smart structures incorporating piezoelectric material-based active elements, both as sensors and actuators, have been identified to present manifold advantages over traditional passive systems. Such structures have become intrinsically integrated into smart mechatronic systems, necessitating advanced design, testing, and control techniques. Real-time simulation of shell-type deformable objects, especially when employing the finite element method for non-linear analysis and control, has been challenging due to the extensive computational demand. Presented herein is an efficacious implementation leveraging machine learning with the isogeometric finite element formulation. This implementation focuses on shell-like smart mechatronic structures crafted from composite laminates comprising piezoelectric layers, which are characterised by electro-mechanical coupling. The foundation for the shell kinematics is derived from the Mindlin-Reissner assumptions, effectively incorporating transverse shear effects. While the inclusion of machine learning facilitates real-time efficient operations, the isogeometric finite element analysis (FEA) introduces pronounced advantages over conventional finite element method (FEM), also serving as a valuable source of offline data crucial for the training phases of machine learning algorithms. A piezo-laminated semicircular arch has been analysed to exemplify the effectiveness and performance of the presented methodology. Explorations into further machine learning techniques and intelligent control schemes are also contemplated.
- 28 September 2023
- Published by Acadlore Publishing Services Limited in Journal of Engineering Management and Systems Engineering
- Vol. 2 (4) , 196-203
Open AccessIsogeometric Finite Element Analysis with Machine Learning Integration for Piezoelectric Laminated Shells
Innovative lightweight smart structures incorporating piezoelectric material-based active elements, both as sensors and actuators, have been identified to present manifold advantages over traditional passive systems. Such structures have become intrinsically integrated into smart mechatronic systems, necessitating advanced design, testing, and control techniques. Real-time simulation of shell-type deformable objects, especially when employing the finite element method for non-linear analysis and control, has been challenging due to the extensive computational demand. Presented herein is an efficacious implementation leveraging machine learning with the isogeometric finite element formulation. This implementation focuses on shell-like smart mechatronic structures crafted from composite laminates comprising piezoelectric layers, which are characterised by electro-mechanical coupling. The foundation for the shell kinematics is derived from the Mindlin-Reissner assumptions, effectively incorporating transverse shear effects. While the inclusion of machine learning facilitates real-time efficient operations, the isogeometric finite element analysis (FEA) introduces pronounced advantages over conventional finite element method (FEM), also serving as a valuable source of offline data crucial for the training phases of machine learning algorithms. A piezo-laminated semicircular arch has been analysed to exemplify the effectiveness and performance of the presented methodology. Explorations into further machine learning techniques and intelligent control schemes are also contemplated.
- Open Access
- 20 July 2023
- Published by University of Nis in Facta Universitatis, Series: Working and Living Environmental Protection
- p. 045-054
MAPPING AGRICULTURAL WASTE FOR BIOGAS PRODUCTION USING A FULLY CONVOLUTIONAL NEURAL NETWORK AND REMOTE SENSING IMAGERY
The increasing generation of waste and depletion of natural resources has led to a growing need for innovative approaches for utilizing different types of waste as potential energy and material resources. Agricultural activities produce large amounts of Agricultural Waste (AW), which, if not adequately managed, can lead to environmental degradation. One potential solution for the effective utilization of AW is converting it into biogas. However, commercializing this process requires a comprehensive understanding of the types and quantities of AW generated. In this paper, the use of a Fully Convolutional Neural Network (FCN), which has rapidly advanced with the progress of Artificial Intelligence and become essential for tasks such as Semantic Segmentation, Object Detection, and Image Classification, is proposed to improve the prediction of AW for biogas production. Furthermore, this paper presents a Deep Learning-based image segmentation method to recognize vineyard fields, which are a significant source of AW, using remote satellite images. The proposed approach can significantly improve the identification of AW sources, and thus contribute to the efficient and sustainable utilization of AW for biogas production.
- 20 July 2023
- Published by University of Nis in Facta Universitatis, Series: Working and Living Environmental Protection
- p. 045-054
Open AccessMAPPING AGRICULTURAL WASTE FOR BIOGAS PRODUCTION USING A FULLY CONVOLUTIONAL NEURAL NETWORK AND REMOTE SENSING IMAGERY
The increasing generation of waste and depletion of natural resources has led to a growing need for innovative approaches for utilizing different types of waste as potential energy and material resources. Agricultural activities produce large amounts of Agricultural Waste (AW), which, if not adequately managed, can lead to environmental degradation. One potential solution for the effective utilization of AW is converting it into biogas. However, commercializing this process requires a comprehensive understanding of the types and quantities of AW generated. In this paper, the use of a Fully Convolutional Neural Network (FCN), which has rapidly advanced with the progress of Artificial Intelligence and become essential for tasks such as Semantic Segmentation, Object Detection, and Image Classification, is proposed to improve the prediction of AW for biogas production. Furthermore, this paper presents a Deep Learning-based image segmentation method to recognize vineyard fields, which are a significant source of AW, using remote satellite images. The proposed approach can significantly improve the identification of AW sources, and thus contribute to the efficient and sustainable utilization of AW for biogas production.
- Open Access
- 15 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2490
Simulation, Analysis, and Experimentation of the Compliant Finger as a Part of Hand-Compliant Mechanism Development
Compliant mechanisms are gaining popularity in many different fields, such as in microelectromechanical systems (MEMS), medical applications and health care, opto-mechatronic technology, aerospace engineering, and semiconductor equipment. One of the areas for utilizing compliant mechanisms is building models of human hand counterparts. These models are often used as grasping and rehabilitation devices. Because of their properties, creating a human hand counterpart with compliant mechanisms is a much better choice compared with the models with traditional mechanisms; it looks more realistic, and its movements are much more natural compared with models with a traditional mechanism. A method of modeling and designing such a bio-inspired mechanism, as well as its experimental analysis with various forces applied, is presented in this paper. Two prototypes of the compliant fingers were obtained by 3D printing, and the calculation of the bending angle values was achieved by applying image processing to camera images of the compliant fingers’ prototypes. Image processing was conducted on images taken for both loaded and unloaded 3D-printed compliant finger prototype positions. Finally, these bending angle results are compared with the results obtained by Finite Element Method (FEM) analysis and experimental results acquired by a digital protractor.
- 15 February 2023
- Published by MDPI AG in Applied Sciences
- Vol. 13 (4) , 2490
Open AccessSimulation, Analysis, and Experimentation of the Compliant Finger as a Part of Hand-Compliant Mechanism Development
Compliant mechanisms are gaining popularity in many different fields, such as in microelectromechanical systems (MEMS), medical applications and health care, opto-mechatronic technology, aerospace engineering, and semiconductor equipment. One of the areas for utilizing compliant mechanisms is building models of human hand counterparts. These models are often used as grasping and rehabilitation devices. Because of their properties, creating a human hand counterpart with compliant mechanisms is a much better choice compared with the models with traditional mechanisms; it looks more realistic, and its movements are much more natural compared with models with a traditional mechanism. A method of modeling and designing such a bio-inspired mechanism, as well as its experimental analysis with various forces applied, is presented in this paper. Two prototypes of the compliant fingers were obtained by 3D printing, and the calculation of the bending angle values was achieved by applying image processing to camera images of the compliant fingers’ prototypes. Image processing was conducted on images taken for both loaded and unloaded 3D-printed compliant finger prototype positions. Finally, these bending angle results are compared with the results obtained by Finite Element Method (FEM) analysis and experimental results acquired by a digital protractor.