A Self-Adaptive CPS-Based Object Recognition Framework for Smart Glasses Using Dist-YOLOv3-Xception with Attention

Aradea Aradea, Irfan Darmawan, Rianto Rianto, Husni Mubarok, Ghatan Fauzi Nugraha

Abstract


The Industrial Era 4.0 has emerged as a response to the changes occurring in the world in a dynamic, unexpected, and uncertain manner. This situation requires analytical, predictive, and adaptive capabilities in an intelligent environment. This affects real-world object recognition in vision systems, which are frequently limited to specific signals. Thereby, it creates an adaptive gap. One potential solution to this problem is the development of self-adaptive cyber-physical systems (hereafter, SACPS) to enhance adaptability in recognizing diverse real-world objects. This paper introduces the SACPS model through an extended machine learning/deep learning model applied to smart glasses, which can detect and calculate object distances adaptively. The components of the developed model comprise smart glasses, contextual knowledge, and adaptive requirements based on the SACPS concept. We developed a pre-trained model by combining the Dist-YOLOv3 algorithm with Xception and an attention layer to obtain more optimal results. This research compared the new pre-trained model with those from previous research. Based on the evaluation, the model demonstrates improved performance compared to the baseline when tested on the KITTI dataset, recording a mean Recall (mRec) of 45.21%, mean Precision (mPrec) of 14.73%, and mean Average Precision (mAP) of 30.04%. Additionally, the adaptive system's response to increasing light intensity below 50 revealed good stability, with average post-enhancement brightness reaching 100.0703 (pixel intensity scale). These results demonstrate the significant potential of our model in handling changing environments with strong adaptation in diverse real-world object recognition scenarios. In the case of smart glass, the employment of SACPS can provide good adaptability in predicting distance and increasing light intensity.

Full Text:

PDF

References


] Hikmawati, N. U. Maulidevi, and K. Surendro, “Adaptive rule: A novel framework for recommender system,” ICT Express, vol. 6, no. 3, pp. 214–219, 2020, doi: 10.1016/j.icte.2020.06.001.

] [2] P. O. Antonino, A. Morgenstern, B. Kallweit, M. Becker, and T. Kuhn, “Straightforward Specification of Adaptation-Architecture-Significant Requirements of IoT-enabled Cyber-Physical Systems,” Proc. - 2018 IEEE 15th Int. Conf. Softw. Archit. Companion, ICSA-C 2018, pp. 19–26, 2018, doi: 10.1109/ICSA-C.2018.00012.

] [3] S. Zeadally, T. Sanislav, and G. D. Mois, “Self-Adaptation Techniques in Cyber-Physical Systems (CPSs),” IEEE Access, vol. 7, pp. 171126–171139, 2019, doi: 10.1109/ACCESS.2019.2956124.

] [4] A. Petrovska and A. Pretschner, “Learning Approach for Smart Self-Adaptive Cyber-Physical Systems,” in 2019 IEEE 4th International Workshops on Foundations and Applications of Self* Systems (FAS*W), 2019, pp. 234–236. doi: 10.1109/FAS-W.2019.00061.

] [5] E. Zavala, X. Franch, J. Marco, A. Knauss, and D. Damian, “SACRE: Supporting contextual requirements’ adaptation in modern self-adaptive systems in the presence of uncertainty at runtime,” Expert Syst. Appl., vol. 98, pp. 166–188, 2018, doi: 10.1016/j.eswa.2018.01.009.

] [6] A. Petrovska, S. Quijano, I. Gerostathopoulos, and A. Pretschner, “Knowledge aggregation with subjective logic in multi-agent self-adaptive cyber-physical systems,” Proc. - 2020 IEEE/ACM 15th Int. Symp. Softw. Eng. Adapt. Self-Managing Syst. SEAMS 2020, no. June, pp. 149–155, 2020, doi: 10.1145/3387939.3391600.

] [7] D. Gürdür and F. Asplund, “A systematic review to merge discourses: Interoperability, integration and cyber-physical systems,” J. Ind. Inf. Integr., vol. 9, no. October, pp. 14–23, 2018, doi: 10.1016/j.jii.2017.12.001.

] [8] Y. Eslami, M. Lezoche, P. Kalitine, and S. Ashouri, “How the cooperative cyber physical enterprise information systems (CCPEIS) improve the semantic interoperability in the domain of industry 4.0 through the knowledge formalization,” IFAC-PapersOnLine, vol. 54, no. 1, pp. 924–929, 2021, doi: 10.1016/j.ifacol.2021.08.110.

] [9] H. Nakagawa, A. Ohsuga, and S. Honiden, “Towards dynamic evolution of self-Adaptive systems based on dynamic updating of control loops,” Int. Conf. Self-Adaptive Self-Organizing Syst. SASO, pp. 59–68, 2012, doi: 10.1109/SASO.2012.17.

] [10] M. Vajgl, P. Hurtik, and T. Nejezchleba, “Dist-YOLO: Fast Object Detection with Distance Estimation,” Appl. Sci., vol. 12, no. 3, pp. 1–13, 2022, doi: 10.3390/app12031354.

] [11] F. Chollet, “Xception: Deep learning with depthwise separable convolutions,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 1800–1807, 2017, doi: 10.1109/CVPR.2017.195.

] [12] H. Walle, C. De Runz, B. Serres, and G. Venturini, “A Survey on Recent Advances in AI and Vision-Based Methods for Helping and Guiding Visually Impaired People,” Appl. Sci., vol. 12, no. 5, 2022, doi: 10.3390/app12052308.

] [13] J. R. Jiang, “An improved cyber-physical systems architecture for Industry 4.0 smart factories,” Adv. Mech. Eng., vol. 10, no. 6, pp. 918–920, 2018, doi: 10.1177/1687814018784192.

] [14] M. K. Habib and C. Chimsom I, “CPS: Role, Characteristics, Architectures and Future Potentials,” Procedia Comput. Sci., vol. 200, pp. 1347–1358, 2022, doi: 10.1016/j.procs.2022.01.336.

] [15] J. Zhou, Y. Huang, and B. Yu, “Mapping Vegetation-Covered Urban Surfaces Using Seeded Region Growing in Visible-NIR Air Photos,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens., vol. 8, no. 5, pp. 2212–2221, 2015, doi: 10.1109/JSTARS.2014.2362308.

] [16] M. Búr, G. Szilágyi, A. Vörös, and D. Varró, “Distributed graph queries over models@run.time for runtime monitoring of cyber-physical systems,” Int. J. Softw. Tools Technol. Transf., vol. 22, no. 1, pp. 79–102, 2020, doi: 10.1007/s10009-019-00531-5.

] [17] D. Weyns et al., “Towards Better Adaptive Systems by Combining MAPE, Control Theory, and Machine Learning,” Proc. - 2021 Int. Symp. Softw. Eng. Adapt. Self-Managing Syst. SEAMS 2021, no. 1, pp. 217–223, 2021, doi: 10.1109/SEAMS51251.2021.00036.

] [18] S. H. Ahmed, G. Kim, and D. Kim, “Cyber Physical System: Architecture, applications and research challenges,” IFIP Wirel. Days, no. November, 2013, doi: 10.1109/WD.2013.6686528.

] [19] M. Sony, “Design of cyber physical system architecture for industry 4.0 through lean six sigma: conceptual foundations and research issues,” Prod. Manuf. Res., vol. 8, no. 1, pp. 158–181, 2020, doi: 10.1080/21693277.2020.1774814.

] [20] T. Kluge, “A role-based architecture for self-adaptive cyber-physical systems,” Proc. - 2020 IEEE/ACM 15th Int. Symp. Softw. Eng. Adapt. Self-Managing Syst. SEAMS 2020, pp. 120–124, 2020, doi: 10.1145/3387939.3391601.

] [21] G. Weichhart, J. Mangler, C. Mayr-Dorn, A. Egyed, and A. Hämmerle, “Production process interoperability for cyber-physical production systems,” IFAC-PapersOnLine, vol. 54, no. 1, pp. 906–911, 2021, doi: 10.1016/j.ifacol.2021.08.188.

] [22] R. Casadei, A. Placuzzi, M. Viroli, and D. Weyns, “Augmented Collective Digital Twins for Self-Organising Cyber-Physical Systems,” Proc. - 2021 IEEE Int. Conf. Auton. Comput. Self-Organizing Syst. Companion, ACSOS-C 2021, pp. 160–165, 2021, doi: 10.1109/ACSOS-C52956.2021.00051.

] [23] A. Aradea, R. Rianto, and H. Mubarok, “Inference Model for Self-Adaptive IoT Service Systems,” Int. J. Intell. Eng. Syst., vol. 14, no. 4, pp. 337–349, 2021, doi: 10.22266/ijies2021.0831.30.

] [24] Aradea, I. Supriana, and K. Surendro, “ARAS: adaptation requirements for adaptive systems,” Autom. Softw. Eng., vol. 30, no. 1, p. 2, 2022, doi: 10.1007/s10515-022-00369-3.

] [25] J. Redmon and A. Farhadi, “YOLOv3: An Incremental Improvement,” 2018, [Online]. Available: http://arxiv.org/abs/1804.02767

] [26] D. Bahdanau, K. H. Cho, and Y. Bengio, “Neural machine translation by jointly learning to align and translate,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., pp. 1–15, 2015.

] [27] C. Wohlin, P. Runeson, M. Höst, M. C. Ohlsson, B. Regnell, and A. Wesslén, Experimentation in Software Engineering. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012. doi: 10.1007/978-3-642-29044-2.

] [28] M. M. John, H. H. Olsson, and J. Bosch, “Developing ML/DL Models: A Design Framework,” in 2020 IEEE/ACM International Conference on Software and System Processes (ICSSP), 2020, pp. 1–10.

] [29] A. Geiger, P. Lenz, and R. Urtasun, “Are we ready for autonomous driving? The KITTI vision benchmark suite,” in 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 3354–3361. doi: 10.1109/CVPR.2012.6248074.

] [30] K. Lu, F. Zhao, X. Xu, and Y. Zhang, “An object detection algorithm combining self-attention and YOLOv4 in traffic scene,” PLoS One, vol. 18, no. 5 May, pp. 1–18, 2023, doi: 10.1371/journal.pone.0285654.

] [31] L. Chen, W. Shi, and D. Deng, “Improved yolov3 based on attention mechanism for fast and accurate ship detection in optical remote sensing images,” Remote Sens., vol. 13, no. 4, pp. 1–18, 2021, doi: 10.3390/rs13040660.

] [32] J. Sun, H. Ge, and Z. Zhang, “AS-YOLO: An Improved YOLOv4 based on Attention Mechanism and SqueezeNet for Person Detection,” 2021 IEEE 5th Adv. Inf. Technol. Electron. Autom. Control Conf., vol. 5, pp. 1451–1456, 2021, [Online]. Available: https://api.semanticscholar.org/CorpusID:233198337

] [33] J. Terven and D. Cordova-Esparza, “A Comprehensive Review of YOLO: From YOLOv1 and Beyond,” pp. 1–34, 2023, [Online]. Available: http://arxiv.org/abs/2304.00501




DOI: https://doi.org/10.31449/inf.v49i15.8853

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.