single-au.php

IJAT Vol.17 No.3 pp. 206-216
doi: 10.20965/ijat.2023.p0206
(2023)

Research Paper:

Multi-Scale Batch-Learning Growing Neural Gas Efficiently for Dynamic Data Distributions

Fernando Ardilla, Azhar Aulia Saputra ORCID Icon, and Naoyuki Kubota ORCID Icon

Department of Mechanical Systems Engineering, Graduate School of Systems Design, Tokyo Metropolitan University
6-6 Asahigaoka, Hino, Tokyo 191-0065, Japan

Corresponding author

Received:
September 30, 2022
Accepted:
February 15, 2023
Published:
May 5, 2023
Keywords:
multi-scale batch-learning growing neural gas, topological structure, dynamic data
Abstract

Growing neural gas (GNG) has many applications, including topology preservation, feature extraction, dynamic adaptation, clustering, and dimensionality reduction. These methods have broad applicability in extracting the topological structure of 3D point clouds, enabling unsupervised motion estimation, and depicting objects within a scene. Furthermore, multi-scale batch-learning GNG (MS-BL-GNG) has improved learning convergence. However, it is only implemented on static or stationary datasets, and adapting to dynamic data remains difficult. Similarly, the learning rate cannot be increased if new nodes are added to the existing network after accumulating errors in the sampling data. Next, we propose a new growth approach that, when applied to MS-BL-GNG, significantly increases the learning speed and adaptability of dynamic data distribution input patterns. This method immediately adds data samples as new nodes to existing networks. The probability of adding a new node is determined by the distance between the first, second, and third closest nodes. We applied our method for monitoring a moving object at its pace to demonstrate the usefulness of the proposed model. In addition, optimization methods are used such that processing can be performed in real-time.

Cite this article as:
F. Ardilla, A. Saputra, and N. Kubota, “Multi-Scale Batch-Learning Growing Neural Gas Efficiently for Dynamic Data Distributions,” Int. J. Automation Technol., Vol.17 No.3, pp. 206-216, 2023.
Data files:
References
  1. [1] C. Greer, M. Burns, D. Wollman, and E. Griffor, “Cyber-Physical Systems and Internet of Things,” NIST Special Publication No.1900-202, 2019.
  2. [2] K. Oshio, K. Kaneko, and N. Kubota, “Multi-Scopic Simulation for Human-Robot Interactions Based on Multi-Objective Behavior Coordination,” Proc. of the 7th Int. Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII), 2021.
  3. [3] T. Fujita, T. Xi, R. Ikeda, S. Kehne, M. Fey, and C. Brecher, “Identification of a Practical Digital Twin for Simulation of Machine Tools,” Int. J. Automation Technol., Vol.16, No.3, pp. 261-268, 2022.
  4. [4] P. Wang, L. T. Yang, J. Li, J. Chen, and S. Hu, “Data Fusion in Cyber-Physical-Social Systems: State-of-the-Art and Perspectives,” Information Fusion, Vol.51, pp. 42-57, 2019.
  5. [5] H. Sawada, Y. Nakabo, Y. Furukawa, N. Ando, T. Okuma, H. Komoto, and K. Masui, “Digital Tools Integration and Human Resources Development for Smart Factories,” Int. J. Automation Technol., Vol.16, No.3, pp. 250-260, 2022.
  6. [6] H. Li, T. Yamada, P. Jolivet, K. Furuta, T. Kondoh, K. Izui, and S. Nishiwaki, “Full-Scale 3D Structural Topology Optimization Using Adaptive Mesh Refinement Based on the Level-Set Method,” Finite Elements in Analysis and Design, Vol.194, 103561, 2021.
  7. [7] A. A. Saputra, K. Wada, S. Masuda, and N. Kubota, “Multi-Scopic Neuro-Cognitive Adaptation for Legged Locomotion Robots,” Scientific Reports, Vol.12, 16222, 2022.
  8. [8] J. Su, R. Miyazaki, T. Tamaki, and K. Kaneda, “3D Modeling of Lane Marks Using a Combination of Images and Mobile Mapping Data,” Int. J. Automation Technol., Vol.12, No.3, pp. 386-394, 2018.
  9. [9] S. Chen, C. Duan, Y. Yang, D. Li, C. Feng, and D. Tian, “Deep Unsupervised Learning of 3D Point Clouds via Graph Topology Inference and Filtering,” IEEE Trans. on Image Processing, Vol.29, pp. 3183-3198, 2020.
  10. [10] J. Pang, D. Li, and D. Tian, “TearingNet: Point Cloud Autoencoder to Learn Topology-Friendly Representations,” 2021 IEEE/CVF Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 7449-7458, 2021.
  11. [11] F. Hensel, M. Moor, and B. Rieck, “A survey of topological machine learning methods,” Frontiers in Artificial Intelligence, Vol.4, 681108, 2021.
  12. [12] R. O. Duda, P. E. Hart, and D. G. Stork, ”Pattern classification,” 2nd Edition, John Wiley & Sons, 2012.
  13. [13] B. Fritzke, “Growing Cell Structures—A Self-Organizing Network for Unsupervised and Supervised Learning,” Neural Networks, Vol.7, No.9, pp. 1441-1460, 1994.
  14. [14] T. Kohonen, “The Self-Organizing Map,” Proc. of the IEEE, Vol.78, No.9, pp. 1464-1480, 1990.
  15. [15] T. M. Martinetz and K. J. Schulten, “A ‘Neural-Gas’ Network Learns Topologies,” T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas (Eds.), “Artificial Neural Networks,” pp. 397-402, North-Holland, 1991.
  16. [16] B. Fritzke, “Unsupervised Clustering with Growing Cell Structures,” IJCNN-91-Seattle Int. Joint Conf. on Neural Networks, Vol.2, pp. 531-536, 1991.
  17. [17] S. Orts-Escolano, J. Garcia-Rodriguez, V. Morell, M. Cazorla, M. Saval, and J. Azorin, “Processing Point Cloud Sequences with Growing Neural Gas,” 2015 Int. Joint Conf. on Neural Networks (IJCNN), 2015. https://doi.org/10.1109/IJCNN.2015.7280709
  18. [18] Y. Toda, A. Wada, H. Miyase, K. Ozasa, T. Matsuno, and M. Minami, “Growing Neural Gas with Different Topologies for 3D Space Perception,” Applied Sciences, Vol.12, No.3, 1705, 2022.
  19. [19] S. Orts-Escolano, J. Garcia-Rodriguez, V. Morell, M. Cazorla, J. A. S. Perez, and A. Garcia-Garcia, “3D Surface Reconstruction of Noisy Point Clouds Using Growing Neural Gas: 3D Object/scene Reconstruction,” Neural Processing Letters, Vol.43, No.2, pp. 401-423, 2016.
  20. [20] A. A. Saputra, C. W. Hong, and N. Kubota, “Real-Time Grasp Affordance Detection of Unknown Object for Robot-Human Interaction,” 2019 IEEE Int. Conf. on Systems, Man and Cybernetics (SMC), pp. 3093-3098, 2019.
  21. [21] W. H. Chin, C. K. Loo, and N. Kubota, “Multi-Channel Bayesian Adaptive Resonance Associative Memory for Environment Learning and Topological Map Building,” 2015 Int. Conf. on Informatics, Electronics & Vision (ICIEV), 2015. https://doi.org/10.1109/ICIEV.2015.7334064
  22. [22] A. A. Saputra, W. H. Chin, Y. Toda, N. Takesue, and N. Kubota, “Dynamic Density Topological Structure Generation for Real-Time Ladder Affordance Detection,” 2019 IEEE/RSJ Int. Conf. on Intelligent Robots and Systems (IROS), pp. 3439-3444, 2019.
  23. [23] M. Tscherepanow, “TopoART: A Topology Learning Hierarchical ART Network,” Proc. of the 20th Int. Conf. on Artificial Neural Networks (ICANN 2010), Part 3, pp. 157-167, 2010.
  24. [24] N. Masuyama, C. K. Loo, and S. Wermter, “A Kernel Bayesian Adaptive Resonance Theory with a Topological Structure,” Int. J. of Neural Systems, Vol.29, No.5, 1850052, 2019.
  25. [25] N. Mirehi, M. Tahmasbi, and A. T. Targhi, “Hand Gesture Recognition Using Topological Features,” Multimedia Tools and Applications, Vol.78, No.10, pp. 13361-13386, 2019.
  26. [26] P. M. Yanik, J. Manganelli, J. Merino, A. L. Threatt, J. O. Brooks, K. E. Green, and I. D. Walker, “Use of Kinect Depth Data and Growing Neural Gas for Gesture Based Robot Control,” 2012 6th Int. Conf. on Pervasive Computing Technologies for Healthcare (PervasiveHealth) and Workshops, pp. 283-290, 2012.
  27. [27] R. L. M. E. do Rego, A. F. R. Araujo, and F. B. de Lima Neto, “Growing Self-Organizing Maps for Surface Reconstruction from Unstructured Point Clouds,” 2007 Int. Joint Conf. on Neural Networks, pp. 1900-1905, 2007.
  28. [28] S. Marsland, J. Shapiro, and U. Nehmzow, “A Self-Organising Network that Grows When Required,” Neural Networks, Vol.15, Nos.8-9, pp. 1041-1058, 2002.
  29. [29] Y. Toda, W. Chin, and N. Kubota, “Unsupervised Neural Network Based Topological Learning from Point Clouds for Map Building,” 2017 Int. Symp. on Micro-NanoMechatronics and Human Science (MHS), 2017. https://doi.org/10.1109/MHS.2017.8305188
  30. [30] Y. Toda and N. Kubota, “Topological Structure Learning Based Enclosing Formation Behavior for Monitoring System,” 2018 IEEE Int. Conf. on Systems, Man, and Cybernetics (SMC), pp. 831-836, 2018.
  31. [31] Y. Toda, T. Matsuno, and M. Minami, “Multilayer Batch Learning Growing Neural Gas for Learning Multiscale Topologies,” J. Adv. Comput. Intell. Intell. Inform., Vol.25, No.6, pp. 1011-1023, 2021.
  32. [32] M. Iwasa, N. Kubota, and Y. Toda, “Multi-Scale Batch-Learning Growing Neural Gas for Topological Feature Extraction in Navigation of Mobility Support Robots,” 7th Int. Workshop on Advanced Computational Intelligence and Intelligent Informatics (IWACIII), 2021.
  33. [33] N. Doteguchi and N. Kubota, “Topological Tracking for Mobility Support Robots Based on Multi-Scale Batch Learning Growing Neural Gas,” Proc. of the 10th Int. Conf. on Mobile Wireless Middleware, Operating Systems and Applications (MOBILWARE 2021), pp. 17-31, 2022.
  34. [34] B. Fritzke, “A Self-Organizing Network that Can Follow Non-Stationary Distributions,” Proc. of the 7th Int. Conf. on Artificial Neural Networks, pp. 613-618, 1997.
  35. [35] H. Frezza-Buet, “Following Non-Stationary Distributions by Controlling the Vector Quantization Accuracy of a Growing Neural Gas Network,” Neurocomputing, Vol.71, Nos.7-9, pp. 1191-1202, 2008.
  36. [36] M. A. Molina-Cabello, E. López-Rubio, R. M. Luque-Baena, E. Domínguez, and K. Thurnhofer-Hemsi, “Neural Controller for PTZ Cameras Based on Nonpanoramic Foreground Detection,” 2017 Int. Joint Conf. on Neural Networks (IJCNN), pp. 404-411, 2017.
  37. [37] H. Frezza-Buet, “Online Computing of Non-Stationary Distributions Velocity Fields by an Accuracy Controlled Growing Neural Gas,” Neural Networks, Vol.60, pp. 203-221, 2014.
  38. [38] A. Angelopoulou, J. G. Rodriguez, S. Orts-Escolano, G. Gupta, and A. Psarrou, “Fast 2D/3D Object Representation with Growing Neural Gas,” Neural Computing and Applications, Vol.29, No.10, pp. 903-919, 2018.
  39. [39] J. Tünnermann, C. Born, and B. Mertsching, “Saliency from Growing Neural Gas: Learning Pre-Attentional Structures for a Flexible Attention System,” IEEE Trans. on Image Processing, Vol.28, No.11, pp. 5296-5307, 2019.
  40. [40] Y. Toda, X. Li, T. Matsuno, and M. Minami, “Region of Interest Growing Neural Gas for Real-Time Point Cloud Processing,” Proc. of the 12th Int. Conf. on Intelligent Robotics and Applications (ICIRA 2019), pp. 82-91, 2019.
  41. [41] A. A. Saputra, J. Botzheim, A. J. Ijspeert, and N. Kubota, “Combining Reflexes and External Sensory Information in a Neuromusculoskeletal Model to Control a Quadruped Robot,” IEEE Trans. on Cybernetics, Vol.52, No.8, pp. 7981-7994, 2022.
  42. [42] A. A. Saputra, N. Takesue, K. Wada, A. J. Ijspeert, and N. Kubota, “AQuRo: A Cat-Like Adaptive Quadruped Robot with Novel Bio-Inspired Capabilities,” Frontiers in Robotics and AI, Vol.8, 562524, 2021.
  43. [43] A. A. Saputra, C. W. Hong, M. Yani, F. Ardilla, A. R. A. Besari, Y. Toda, and N. Kubota, “Topological Based Environmental Reconstruction for Efficient Multi-Level Control of Robot Locomotion,” 2022 Int. Electronics Symp. (IES), pp. 491-496, 2022.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on May. 10, 2024