Self-Learning Model for Pattern Recognition in Vision System Based on Adaptive Kernel

Aradea Aradea, Rianto Rianto, Nina Herlina, Irani Hoeronis

Abstract


Recently, the solution for recognizing and understanding an object based on visuals is to integrate the adaptation function (continuous machine-driven process) into the system update function involving humans (continuous human-driven process). However, this has created a gap between the adaptation function and the system. This situation requires understanding the system viewed as a dynamic composition of the learning process. This research introduced a self-learning model in the form of an adaptive kernel equipped with the SpinalNet architecture, and the goal of this study is to increase the Convolutional Neural Network (CNN) accuracy. The model consisted of a domain model, contextual knowledge, and adaptive learner developed based on the CNN with SpinalNet. The combination of Adaptive Kernel and SpiralNet in this CNN has a significant impact, allowing the model to adjust the selection of subsequent kernels based on the optimal input from the previous kernel. Moreover, this combination results in lower memory usage during training. The evaluation results show that our proposed model provides better classification accuracy than the SpiralNet model without the Adaptive Kernel. Furthermore, in terms of inference speed, our model outperforms SpiralNet, as evidenced by the use of fewer parameters

Full Text:

PDF

References


] Aradea, A., Supriana, I., & Surendro, K. (2020). Self-adaptive model based on goal-oriented requirements engineering for handling service variability. Journal of Information and Communication Technology, 19(2), 225-250. doi.org/10.32890/jict2020.19.2.4

] Aradea, I. Supriana, and K. Surendro, (2023) “ARAS: Adaptation Requirements for Adaptive Systems,” Automated Software Engineering, vol. 30, no. 2, 2023, doi: 10.1007/s10515-022-00369-3.

] Danny Weyns, (2021) An Introduction to Self-Adaptive Systems - A Contemporary Software Engineering Perspective: Wave VII Learning from Experience, pp. 201-226, IEEE Press, John Wiley & Sons Ltd, 2021.

] Ali, Mollajan., AmirHossein, Shahdadi., Afshin, Ashofteh., Fatemeh, Hamedani-KarAzmoudehFar., Seyed, Hossein, Iranmanesh. (2023). System Adaptability Enhancement Based on Improving the System Reconfigurability by Modularization of the System Architecture. doi: 10.2139/ssrn.4519777.

] M. Bhadra, D. S. Lopera, R. Kunzelmann and W. Ecker, "A Model-Driven Architecture Approach to Accelerate Software Code Generation," 2024 7th International Conference on Software and System Engineering (ICoSSE), Paris, France, 2024, pp. 23-30, doi: 10.1109/ICoSSE62619.2024.00012.

] Mike Huisman, Jan N Van Rijn, and Aske Plaat(2021), A survey of deep meta-learning. Artificial Intelligence Review, 54(6):4483–4541.

] T. Gong, X. Zheng and X. Lu, "Meta Self-Supervised Learning for Distribution Shifted Few-Shot Scene Classification," in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 6510005, doi: 10.1109/LGRS.2022.3174277.

] P. Terhörst, M. Huber, N. Damer, F. Kirchbuchner, K. Raja and A. Kuijper, "Pixel-Level Face Image Quality Assessment for Explainable Face Recognition," in IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 5, no. 2, pp. 288-297, April 2023, doi: 10.1109/TBIOM.2023.3263186.

] S. Malakar, W. Chiracharit and K. Chamnongthai, "Masked Face Recognition With Generated Occluded Part Using Image Augmentation and CNN Maintaining Face Identity," in IEEE Access, vol. 12, pp. 126356-126375, 2024, doi: 10.1109/ACCESS.2024.3446652.

] H. -I. Kim, K. Yun and Y. M. Ro, "Face Shape-Guided Deep Feature Alignment for Face Recognition Robust to Face Misalignment," in IEEE Transactions on Biometrics, Behavior, and Identity Science, vol. 4, no. 4, pp. 556-569, Oct. 2022, doi: 10.1109/TBIOM.2022.3213845.

] D. Reis, J. Kupec, J. Hong, and A. Daoudi, “Real-Time Flying Object Detection with YOLOv8,” arXiv Prepr., 2023, doi: 10.48550/arXiv.2305.09972.

] Sarker, I.H. Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions. SN COMPUT. SCI. 2, 420 (2021). https://doi.org/10.1007/s42979-021-00815-1

] C. Xu, "Applying MLP and CNN on Handwriting Images for Image Classification Task," 2022 5th International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE), Wuhan, China, 2022, pp. 830-835, doi: 10.1109/AEMCSE55572.2022.00167.

] Kurniasari, L., Setyanto, A., 2020, Sentiment Analysis using Recurrent Neural Network, Journal of Physics: Conference Series, Vol. 1471, Bukit Tinggi, 18 Oktober, doi: 10.1088/1742-6596/1471/1/012018.

] G. Priyadharshini and D. R. Judie Dolly, "Comparative Investigations on Tomato Leaf Disease Detection and Classification Using CNN, R-CNN, Fast R-CNN and Faster R-CNN," 2023 9th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, 2023, pp. 1540-1545, doi: 10.1109/ICACCS57279.2023.10112860.

] Soydaner, D. (2020). A comparison of optimization algorithms for deep learning. International Journal of Pattern Recognition and Artificial Intelligence, 34(13), 2052013.

] G. L. Sree and R. Baskar, "Performance Analysis of CNN Algorithm in Comparison with LR algorithm for Face Recognition in Smart-Lock," 2024 International Conference on Trends in Quantum Computing and Emerging Business Technologies, Pune, India, 2024, pp. 1-5, doi: 10.1109/TQCEBT59414.2024.10545038.

] Kabir, H. M., Abdar, M., Jalali, S. M. J., Khosravi, A., Atiya, A. F., Nahavandi, S., & Srinivasan, D. (2020). Spinalnet: Deep neural network with gradual input. arXiv preprint arXiv:2007.03347.

] Aradea., Supriana, I., Surendro, K., & Darmawan, I. (2017). Integration of self-adaptation approach on requirements modeling. In T. Herawan, R. Ghazali, N. M. Nawi, & M. M. Deris (Eds.), Recent advances on soft computing and data mining (pp. 233–243). Springer International Publishing.

] Aradea, I. Supriana, K. Surendro, (2018) “Self-adaptive software modeling based on contextual requirements. Telecommunication, Computing, Electronics and Control 16(3): (2018) 1276-1288. http://dx.doi.org/10.12928/telkomnika.v16i0.7032.

] Aradea, Rianto, Husni Mubarok. (2021) "Inference Model for Self-Adaptive IoT Service Systems", International Journal of Intelligent Engineering and Systems, Vol.14, No.4, 2021, DOI: 10.22266/ijies2021.0831.30

] Aradea, Rianto and Husni Mubarok, (2022) "Cultivating Service Knowledge Models for IoT-Based Systems Adaptability", Informatica, Vol. 46, No.5, 2022, doi: https://doi.org/10.31449/inf.v46i5.3874

] M. Acheli, D. Grigori and M. Weidlich, "Discovering and Analyzing Contextual Behavioral Patterns From Event Logs," in IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 12, pp. 5708-5721, 1 Dec. 2022, doi: 10.1109/TKDE.2021.3077653.

] B. Yang, W. Wu, Y. Liu and H. Liu, "A Novel Sleep Stage Contextual Refinement Algorithm Leveraging Conditional Random Fields," in IEEE Transactions on Instrumentation and Measurement, vol. 71, pp. 1-13, 2022, Art no. 2505313, doi: 10.1109/TIM.2022.3154838.

] W. Zhao, S. Peng, J. Chen and R. Peng, "Contextual-Aware Land Cover Classification With U-Shaped Object Graph Neural Network," in IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1-5, 2022, Art no. 6510705, doi: 10.1109/LGRS.2022.3177778.




DOI: https://doi.org/10.31449/inf.v49i14.7272

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