Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
144 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

An Active Learning Framework with a Class Balancing Strategy for Time Series Classification (2405.12122v1)

Published 20 May 2024 in cs.LG

Abstract: Training machine learning models for classification tasks often requires labeling numerous samples, which is costly and time-consuming, especially in time series analysis. This research investigates Active Learning (AL) strategies to reduce the amount of labeled data needed for effective time series classification. Traditional AL techniques cannot control the selection of instances per class for labeling, leading to potential bias in classification performance and instance selection, particularly in imbalanced time series datasets. To address this, we propose a novel class-balancing instance selection algorithm integrated with standard AL strategies. Our approach aims to select more instances from classes with fewer labeled examples, thereby addressing imbalance in time series datasets. We demonstrate the effectiveness of our AL framework in selecting informative data samples for two distinct domains of tactile texture recognition and industrial fault detection. In robotics, our method achieves high-performance texture categorization while significantly reducing labeled training data requirements to 70%. We also evaluate the impact of different sliding window time intervals on robotic texture classification using AL strategies. In synthetic fiber manufacturing, we adapt AL techniques to address the challenge of fault classification, aiming to minimize data annotation cost and time for industries. We also address real-life class imbalances in the multiclass industrial anomalous dataset using our class-balancing instance algorithm integrated with AL strategies. Overall, this thesis highlights the potential of our AL framework across these two distinct domains.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (113)
  1. Classification of textures using a tactile-enabled finger in dynamic exploration tasks. In 2021 IEEE Sensors, pages 1–4. IEEE, 2021.
  2. John Cristian Borges Gamboa. Deep learning for time-series analysis. arXiv preprint arXiv:1701.01887, 2017.
  3. Grasp-uts: an algorithm for unsupervised trajectory segmentation. International Journal of Geographical Information Science, 29(1):46–68, 2015.
  4. Vladimir Nasteski. An overview of the supervised machine learning methods. Horizons. b, 4:51–62, 2017.
  5. Comparison of machine learning approaches for time-series-based quality monitoring of resistance spot welding (rsw). Archives of Data Science, Series A (Online First), 5(1):13, 2018.
  6. Analytic: An active learning system for trajectory classification. IEEE computer graphics and applications, 37(5):28–39, 2017.
  7. A semi-supervised methodology for fishing activity detection using the geometry behind the trajectory of multiple vessels. Sensors, 22(16):6063, 2022.
  8. A semi-supervised approach for the semantic segmentation of trajectories. In 2018 19th IEEE International Conference on Mobile Data Management (MDM), pages 145–154. IEEE, 2018.
  9. Label-efficient time series representation learning: A review. arXiv preprint arXiv:2302.06433, 2023.
  10. Vista: A visual analytics platform for semantic annotation of trajectories. In Proceedings of the 22nd International Conference on Extending Database Technology (EDBT), 2019.
  11. A trajectory scoring tool for local anomaly detection in maritime traffic using visual analytics. ISPRS International Journal of Geo-Information, 10(6):412, 2021.
  12. Local anomaly detection in maritime traffic using visual analytics. In In EDBT/ICDT Workshops, 2021.
  13. Ptrail—a python package for parallel trajectory data preprocessing. SoftwareX, 19:101176, 2022.
  14. A dashboard tool for mobility data mining preprocessing tasks. In 2022 23rd IEEE International Conference on Mobile Data Management (MDM), pages 278–281. IEEE, 2022.
  15. Burr Settles. Active learning literature survey. Technical report, University of Wisconsin-Madison, 2009.
  16. Active learning strategies for robotic tactile texture recognition tasks. Frontiers in Robotics and AI, 11:1281060, 2024.
  17. Fast and accurate time series classification with weasel. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pages 637–646, 2017.
  18. Unfolding ais transmission behavior for vessel movement modeling on noisy data leveraging machine learning. IEEE Access, 11:18821–18837, 2022.
  19. Understanding evolution of maritime networks from automatic identification system data. GeoInformatica, pages 1–25, 2021.
  20. Tactile object recognition in early phases of grasping using underactuated robotic hands. Intelligent Service Robotics, 15(4):513–525, 2022.
  21. Evaluating data representations for object recognition during pick-and-place manipulation tasks. In 2022 IEEE International Systems Conference (SysCon), pages 1–6. IEEE, 2022.
  22. Comparing data representation techniques for tactile sensing in classification tasks. In 2023 IEEE SENSORS, pages 1–4. IEEE, 2023.
  23. Feature-based classification of time-series data. International Journal of Computer Research, 10(3):49–61, 2001.
  24. Rotation-invariant similarity in time series using bag-of-patterns representation. Journal of Intelligent Information Systems, 39:287–315, 2012.
  25. Time-series classification methods: Review and applications to power systems data. Big data application in power systems, pages 179–220, 2018.
  26. Extracting interpretable features for early classification on time series. In Proceedings of the 2011 SIAM international conference on data mining, pages 247–258. SIAM, 2011.
  27. Convolutional neural networks for time series classification. Journal of Systems Engineering and Electronics, 28(1):162–169, 2017.
  28. Deep learning for time series classification: a review. Data mining and knowledge discovery, 33(4):917–963, 2019.
  29. Optical remotely sensed time series data for land cover classification: A review. ISPRS Journal of photogrammetry and Remote Sensing, 116:55–72, 2016.
  30. A case driven study of the use of time series classification for flexibility in industry 4.0. Sensors, 20(24):7273, 2020.
  31. A window-based time series feature extraction method. Computers in biology and medicine, 89:466–486, 2017.
  32. Labelsens: enabling real-time sensor data labelling at the point of collection using an artificial intelligence-based approach. Personal and Ubiquitous Computing, 24:709–722, 2020.
  33. Visual interactive exploration and labeling of large volumes of industrial time series data. In International Conference on Enterprise Information Systems, pages 85–108. Springer, 2022.
  34. Automated label generation for time series classification with representation learning: Reduction of label cost for training. arXiv preprint arXiv:2107.05458, 2021.
  35. Acts: an active learning method for time series classification. In 2017 IEEE 33rd International Conference on Data Engineering (ICDE), pages 175–178. IEEE, 2017.
  36. A nearest neighbor-based active learning method and its application to time series classification. Pattern Recognition Letters, 146:230–236, 2021.
  37. A shapelet transform for time series classification. In Proceedings of the 18th ACM SIGKDD international conference on Knowledge discovery and data mining, pages 289–297, 2012.
  38. Cost-sensitive convolutional neural networks for imbalanced time series classification. Intelligent Data Analysis, 23(2):357–370, 2019.
  39. A systematic study of the class imbalance problem in convolutional neural networks. Neural networks, 106:249–259, 2018.
  40. Deepsmote: Fusing deep learning and smote for imbalanced data. IEEE Transactions on Neural Networks and Learning Systems, 2022.
  41. Lara Lusa et al. Evaluation of smote for high-dimensional class-imbalanced microarray data. In 2012 11th international conference on machine learning and applications, volume 2, pages 89–94. IEEE, 2012.
  42. Ib-gan: A unified approach for multivariate time series classification under class imbalance. In Proceedings of the 2022 SIAM International Conference on Data Mining (SDM), pages 217–225. SIAM, 2022.
  43. A gan-based anomaly detection approach for imbalanced industrial time series. IEEE Access, 7:143608–143619, 2019.
  44. Robotic tactile perception of object properties: A review. Mechatronics, 48:54–67, 2017.
  45. Texture discrimination with a soft biomimetic finger using a flexible neuromorphic tactile sensor array that provides sensory feedback. Soft Robotics, 8(5):577–587, 2021.
  46. A review of tactile information: Perception and action through touch. IEEE Transactions on Robotics, 36(6):1619–1634, 2020.
  47. Towards effective tactile identification of textures using a hybrid touch approach. In 2019 International Conference on Robotics and Automation (ICRA), pages 4269–4275. IEEE, 2019.
  48. Large-area and low-cost force/tactile capacitive sensor for soft robotic applications. Sensors, 22(11):4083, 2022.
  49. Tactile super-resolution model for soft magnetic skin. IEEE Robotics and Automation Letters, 7(2):2589–2596, 2022.
  50. Reskin: versatile, replaceable, lasting tactile skins. arXiv preprint arXiv:2111.00071, 2021.
  51. Touch sensing for humanoid robots. IEEE Instrumentation & Measurement Magazine, 18(5):13–19, 2015.
  52. Hand movements: A window into haptic object recognition. Cognitive psychology, 19(3):342–368, 1987.
  53. Data-driven analysis of kinaesthetic and tactile information for shape classification. In 2015 IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA), pages 1–5. IEEE, 2015.
  54. Dynamic tactile exploration for texture classification using a miniaturized multi-modal tactile sensor and machine learning. In 2020 IEEE International Systems Conference (SysCon), pages 1–7. IEEE, 2020.
  55. Vinicius Prado da Fonseca. Tactile sensor analysis during early stages of manipulation for single grasp identification of daily objects. Engineering Proceedings, 6(1):56, 2021.
  56. Computational intelligence and mechatronics solutions for robotic tactile object recognition. In 2015 IEEE 9th international symposium on intelligent signal processing (WISP) proceedings, pages 1–6. IEEE, 2015.
  57. Textile identification using fingertip motion and 3d force sensors in an open-source gripper. In 2017 IEEE International Conference on Robotics and Biomimetics (ROBIO), pages 424–429. IEEE, 2017.
  58. Texture recognition based on perception data from a bionic tactile sensor. Sensors, 21(15):5224, 2021.
  59. Supervised autoencoder joint learning on heterogeneous tactile sensory data: Improving material classification performance. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 10907–10913. IEEE, 2020.
  60. Tactile identification of objects using bayesian exploration. In 2013 IEEE international conference on robotics and automation, pages 3056–3061. IEEE, 2013.
  61. Trends and challenges in robot manipulation. Science, 364(6446):eaat8414, 2019.
  62. Iale: Imitating active learner ensembles. Journal of Machine Learning Research, 23(107):1–29, 2022.
  63. A sequential algorithm for training text classifiers. In SIGIR’94, pages 3–12. Springer, 1994.
  64. An analysis of active learning strategies for sequence labeling tasks. In proceedings of the 2008 conference on empirical methods in natural language processing, pages 1070–1079, 2008.
  65. Claude Elwood Shannon. A mathematical theory of communication. The Bell system technical journal, 27(3):379–423, 1948.
  66. Selecting influential examples: Active learning with expected model output changes. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part IV 13, pages 562–577. Springer, 2014.
  67. Samuel C Stanton. Situated experimental agents for scientific discovery. Science Robotics, 3(24):eaau4978, 2018.
  68. Active learning in robotics: A review of control principles. Mechatronics, 77:102576, 2021.
  69. Transparent active learning for robots. In 2010 5th ACM/IEEE International Conference on Human-Robot Interaction (HRI), pages 317–324. IEEE, 2010.
  70. Discriminative active learning for robotic grasping in cluttered scene. IEEE Robotics and Automation Letters, 8(3):1858–1865, 2023.
  71. ” what’s this?” comparing active learning strategies for concept acquisition in hri. In Companion of the 2021 ACM/IEEE International Conference on Human-Robot Interaction, pages 205–209, 2021.
  72. Gradient and log-based active learning for semantic segmentation of crop and weed for agricultural robots. In 2020 IEEE International Conference on Robotics and Automation (ICRA), pages 1350–1356. IEEE, 2020.
  73. Active image sampling on canonical views for novel object detection. In 2020 IEEE International Conference on Image Processing (ICIP), pages 2241–2245. IEEE, 2020.
  74. Toward next-generation learned robot manipulation. Science Robotics, 6(54):eabd9461, 2021.
  75. Recent advances in robot learning from demonstration. Annual review of control, robotics, and autonomous systems, 3:297–330, 2020.
  76. Rlad: Time series anomaly detection through reinforcement learning and active learning. arXiv preprint arXiv:2104.00543, 2021.
  77. Active learning for multivariate time series classification with positive unlabeled data. In 2015 IEEE 27th International Conference on Tools with Artificial Intelligence (ICTAI), pages 178–185. IEEE, 2015.
  78. Determination of temporal information granules to improve forecasting in fuzzy time series. Expert Systems with Applications, 41(6):3134–3142, 2014.
  79. Adaptive sliding window based activity recognition for assisted livings. Information Fusion, 53:55–65, 2020.
  80. Effects of sliding window variation in the performance of acceleration-based human activity recognition using deep learning models. PeerJ Computer Science, 8:e1052, 2022.
  81. Multimodal tactile texture dataset, 2023.
  82. A multimodal tactile dataset for dynamic texture classification. Data in Brief, page 109590, 2023.
  83. Multimodal bio-inspired tactile sensing module. IEEE Sensors Journal, 17(11):3231–3243, 2017.
  84. Thiago Eustaquio Alves de Oliveira and Vinicius Prado da Fonseca. Bioin-tacto: A compliant multi-modal tactile sensing module for robotic tasks. HardwareX, 16:e00478, 2023.
  85. Decision trees. Data mining and knowledge discovery handbook, pages 165–192, 2005.
  86. Extremely randomized trees. Machine learning, 63:3–42, 2006.
  87. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, pages 785–794, 2016.
  88. Leo Breiman. Random forests. Machine learning, 45:5–32, 2001.
  89. Scikit-learn: Machine learning in python. the Journal of machine Learning research, 12:2825–2830, 2011.
  90. A systematic analysis of performance measures for classification tasks. Information processing & management, 45(4):427–437, 2009.
  91. Review of image segmentation techniques for layup defect detection in the automated fiber placement process: A comprehensive study to improve afp inspection. Journal of Intelligent Manufacturing, 32(8):2099–2119, 2021.
  92. M Chan. New online fiber sensor technology unlocks value in fiber manufacturing. International Fiber Journal, 2000.
  93. A new convolutional neural network-based data-driven fault diagnosis method. IEEE Transactions on Industrial Electronics, 65(7):5990–5998, 2017.
  94. A global manufacturing big data ecosystem for fault detection in predictive maintenance. IEEE Transactions on Industrial Informatics, 16(1):183–192, 2019.
  95. Tackling faults in the industry 4.0 era—a survey of machine-learning solutions and key aspects. Sensors, 20(1):109, 2019.
  96. Dynamic tactile exploration for texture classification using a miniaturized multi-modal tactile sensor and machine learning. In 2020 IEEE International Systems Conference (SysCon), pages 1–7, 2020.
  97. Cost sensitive active learning using bidirectional gated recurrent neural networks for imbalanced fault diagnosis. Neurocomputing, 407:232–245, 2020.
  98. Towards zero defect manufacturing paradigm: A review of the state-of-the-art methods and open challenges. Computers in Industry, 134:103548, 2022.
  99. Machine learning applications in production lines: A systematic literature review. Computers & Industrial Engineering, 149:106773, 2020.
  100. Machine learning techniques applied to mechanical fault diagnosis and fault prognosis in the context of real industrial manufacturing use-cases: a systematic literature review. Applied Intelligence, 52(12):14246–14280, 2022.
  101. An industrial case study using vibration data and machine learning to predict asset health. In 2018 IEEE 20th Conference on Business Informatics (CBI), volume 1, pages 178–185. IEEE, 2018.
  102. Machine learning predictive maintenance on data in the wild. In 2019 IEEE 5th World Forum on Internet of Things (WF-IoT), pages 507–512. IEEE, 2019.
  103. Machine learning in composites manufacturing: A case study of automated fiber placement inspection. Composite Structures, 250:112514, 2020.
  104. Anomaly detection in automated fibre placement: Learning with data limitations. arXiv preprint arXiv:2307.07893, 2023.
  105. Manufacturing-induced imperfections in composite parts manufactured via automated fiber placement. Journal of Composites Science, 3(2):56, 2019.
  106. Quality detection and classification for ultrasonic welding of carbon fiber composites using time-series data and neural network methods. Journal of Manufacturing Systems, 61:562–575, 2021.
  107. Synthetic image data augmentation for fibre layup inspection processes: Techniques to enhance the data set. Journal of Intelligent Manufacturing, 32:1767–1789, 2021.
  108. Machine learning algorithms for labeling: Where and how they are used? In 2022 IEEE International Systems Conference (SysCon), pages 1–8. IEEE, 2022.
  109. A novel semi-supervised data-driven method for chiller fault diagnosis with unlabeled data. Applied Energy, 285:116459, 2021.
  110. A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery. Mechanical Systems and Signal Processing, 149:107327, 2021.
  111. A new semi-supervised fault diagnosis method via deep coral and transfer component analysis. IEEE Transactions on Emerging Topics in Computational Intelligence, 6(3):690–699, 2021.
  112. Active learning framework for time-series classification of vibration and industrial process data. In Annual Conference of the PHM Society, volume 13, 2021.
  113. Jerome H Friedman. Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189–1232, 2001.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now