Methods of Automatic Interpretation of Signals Used in Control Systems

• Autorzy: Wójcik, Krzysztof
• Języki publikacji: EN

Abstrakty

EN

The article presents the concepts of control systems that use methods of automatic analysis and interpretation of signals. These issues are presented through the description of three control strategies: simple closed-loop control, control using a process of classification, and using a signal understanding technique. The systems based on the discussed concepts are illustrated with examples of controlling a milling machine and an autonomous vehicle. In addition, in more detail, a task of learning human motor activities is described. This task, due to the nature of the controlled object, which is a human being, is extremely difficult. The article shows that the advanced control process, in which the control algorithm is selected and its parameters are adapted to the current situation, may be implemented through the use of the classification process and machine learning methods in general. Changing the algorithm is also possible using signal understanding techniques. These techniques, utilizing models of the objects, allow to predict the long-term effects of the control process. The ability to build control systems that operate in the above manner is of huge practical importance. The aim of this article is to describe the methods of automatic signal interpretation used in control processes and identify the main problems related to their use. The key problems refer to the acquisition of expert knowledge by the system. In order for this knowledge to be effectively transferred, the methods used in the system should have a high level of explainability. Showing the essential nature of this feature is the main outcome of this work.

Słowa kluczowe

EN

pattern recognition; motor learning; automatic control; machine learning; image understanding; CNN network

• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2024
• Tom: Vol. 18, no 3
• Strony: 79--91
• Opis fizyczny: Bibliogr. 40 poz., fig.

Twórcy

autor

Wójcik, Krzysztof,

Bibliografia

• 1. Dorf R., Bishop R. Modern Control Systems. Pearson Education Inc. 2011.
• 2. Tadeusiewicz R., Flasiński M. Rozpoznawanie obrazów. PWN 1991.
• 3. Szeliski R. Computer Vision: Algorithms and Applications. 2nd ed, Springer Science 2021.
• 4. Wójcik K., Krzesiński J. Multi-task guiding system of the Mt. Suhora Observatory. Astronomy and Astrophysics 1993; 280.
• 5. Tadeusiewicz R. Automatic understanding of signals. intelligent information processing and web mining, Proceedings of the International IIS: IIP-WM’04, Zakopane, Poland 2004; 577–590.
• 6. Sonka M., Hlavac V., Boyle R. Image Processing, Analysis and Machine Vision. Springer 1992.
• 7. Schmidt R., Lee T. Motor Learning and Performance: From Principles to Application. Human Kinetics 2019.
• 8. Wójcik K., Piekarczyk M. Machine learning methodology in a system applying the adaptive strategy for teaching human motions. Sensors 2020; 20: 314.
• 9. Wójcik K. Pattern recognition methods as a tool to build an automatic system for learning coordinated human motions. IEEE Access 2020; 8: 41407–41421.
• 10. Bark K., Hyman E., Tan F., Cha E., Jax S. Effects of Vibrotactile feedback on human learning of arm motions. IEEE Transactions on Neural Systems and Rehabilitation Engineering 2015; 10: 51–63.
• 11. Sigrist R., Rauter G., Riener R., Wolf P. Aug mented visual auditory, haptic, and multimodal feedback in motor learning: A review. Psychonomic Bulletin & Review 2013; 20.
• 12. Wawrzyn D. Projekt i montaż aktuatorów urządzeń wspomagających czynności ruchowe człowieka. Master thesis, Cracow University of Technology 2018.
• 13. Taborri J., Palermo, E., Rossi S. Automatic detection of faults in race walking: A comparative analysis of machine-learning algorithms fed with inertial sensor data. Sensors 2019; 19, 1461.
• 14. Blasiak S., Rangwala H. A Hidden Markov Model Variant for Sequence Classification. IJCAI 2011, Proceedings of the 22nd International Joint Conference on Artificial Intelligence, Barcelona, Spain 2011; 1192–1197.
• 15. Guo G., Wang H., Bell D., Bi Y., Greer K. KNN model-based approach in classification. OTM Confederated International Conferences CoopIS, DOA, and ODBASE 2003, Catania, Italy 2003; 986–996.
• 16. Kulikowski J. Ontological models as tools for image content understanding. international conference on computer vision and graphics. ICCVG 2010, Lecture Notes in Computer Science, Warsaw, Poland 2011; 43–58.
• 17. Pałka D., Zachara M., Wójcik K. Evolutionary scanner of web application vulnerabilities. Computer Net- works CN2016, Brunów, Poland 2016; 410–420.
• 18. Bishop C. Networks for Pattern Recognition. Oxford University Press 1995.
• 19. Zhang A., Lipton Z., Li M., Smola A. Dive into deep learning. release 0.16.1. https://d2l.ai. accessed on 2023.05.06, 2021
• 20. Krizhevsky A., Sutskever I., Hinton, G. ImageNet Classification with Deep Convolutional Neural Networks. https://proceedings.neurips.cc/paper/2012/ file/c399862d3b9d6b76c8436e924a68c45b- Paper. pdf accessed on 2023.05.06, 2013.
• 21. Munoz-Organero M., Powell L., Heller B., Harpin V. Using recurrent neural networks to compare movement patterns in ADHD and normally developing children based on acceleration signals from the wrist and ankle. Sensors 2019; 19.
• 22. Jetson embedded systems. https://www.nvidia.com/ en-us/autonomous-machines/ embedded-systems/ accessed on 2023.05.06, 2023.
• 23. Wójcik K. Automatyczny System Nauki Czynności Motorycznych Człowieka. Monograph, Cracow University of Technology 2023.
• 24. Li P., Zhang D., Wulamu A., Liu X., Chen P. Semantic relation model and dataset for remote sensing scene understanding. ISPRS International Journal of Geo-Information 2021; 10.
• 25. Tadeusiewicz R. Automatic understanding of medical images (opening lecture). The 2nd International Conference Innovative Technologies in Biomedicine, PULMO-CAR, Cracow, Poland 2015; 10–11.
• 26. Wójcik K. Hierarchical knowledge structure applied to image analyzing system - possibilities of practical usage. International Conference on Availability, Reliability, and Security ARES 2011, Vienna, Austria 2011; 149–163.
• 27. Yaxin Y., Zhenhuan J., Xinhua L., Xutang Z. An intelligent approach for construction domain ontology. IEEE International Conference on Automation and Logistics, New Delhi, India 2009.
• 28. Ehrig M., Haase P., Hefke M., Stojanovic N. Similarity for ontologies. A comprehensive framework. Proceedings of Workshop on Ontology and Enterprise Modelling, Ingredients for Interoperability, in conjunction with 5th International Conference on Practical Aspects of Knowledge Management, Vienna, Austria 2004.
• 29. Wójcik K., Pałka D., Bar O. Micro-ontology buildingmain variants of OTO method. Technical transactions, Series: Electrical Engineering 2018; 115: 115–130.
• 30. Wójcik K. Observation as learning methods in Simple Visual System of Vehicle Control. Applied Mechanics and Materials 2014; 613: 144–150.
• 31. Wójcik K. Inductive learning methods in the simple image understanding system. International Conference on Computer Vision and Graphics. ICCVG 2010, Lecture Notes in Computer Science, Warsaw, Poland 2010; 97–104.
• 32. Wójcik K. OTO Model of Building of Structural Knowledge - Areas of Usage and Problems. Advances in Intelligent Systems and Computing, Image Processing and Communications Challenges 4 IP&C, Bydgoszcz, Poland 2012; 215–222.
• 33. de Souza F., Sarkar S., Cámara-Chávez G. Building semantic understanding beyond deep learning from sound and vision. 23rd International Conference on Pattern Recognition (ICPR) IEEE, Cancun, Mexico 2016; 2097–2102.
• 34. Tapaswi M., Kumar V., Laptev I. Long term spatiotemporal modeling for action detection. Computer Vision and Image Understanding 2021; 210.
• 35. Mayer C., Timofte R., Paul G. Towards closing the gap in weakly supervised semantic segmentation with DCNNs: Combining local and global models. Computer Vision and Image Understanding 2021; 208.
• 36. Corso J. Generalized Image Understanding with Probabilistic Ontologies and Dynamic Adaptive Graph Hierarchies. https://web.eecs.umich. edu/~jjcorso/r/career/index.html accessed on 2023.05.06 2020.
• 37. Hrechuk A., Bushlya V., M’Saoubi R., Ståhl J.E. Quantitative analysis of chip segmentation in machining using an automated image processing method. Procedia CIRP 2019; 82: 314–319.
• 38. Ku Ch.Ch., Lee Y. Diagonal recurrent neural networks for dynamic systems control. IEEE Transactions on Neural Networks 1995; 6: 144–156.
• 39. Guidotti R., Monreale A., Ruggieri S., Turini F. A survey of methods for explaining black box models. ACM Computing Surveys 2019; 51(5): 1–42.
• 40. CNN Explainer. https://poloclub.github.io/cnn- explainer/ accessed on 2023.05.06

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).

Identyfikatory

DOI

10.12913/22998624/185846