Human Activity Recognition with Topological Data Analysis Using Machine Learning Algorithms

International Journal of Electrical and Electronics Engineering

© 2025 by SSRG - IJEEE Journal

Volume 12 Issue 11

Year of Publication : 2025

Authors : Sunil Chaudhari, Sanjay Kumar Singh, Sandeep Singh Senghar, Bhupesh Kumar Singh

10.14445/23488379/IJEEE-V12I11P115

How to Cite?

Sunil Chaudhari, Sanjay Kumar Singh, Sandeep Singh Senghar, Bhupesh Kumar Singh, "Human Activity Recognition with Topological Data Analysis Using Machine Learning Algorithms," SSRG International Journal of Electrical and Electronics Engineering, vol. 12,  no. 11, pp. 182-199, 2025. Crossref, https://doi.org/10.14445/23488379/IJEEE-V12I11P115

Abstract:

In the computer vision field, Human motion analysis is a significant research topic, as confirmed by an extensive range of applications like medical assistance, video surveillance, and virtual reality. Human motion analysis concerns the tracking, detection, and recognition of human behaviors and activities. Topology-based approaches have, in recent times, begun to come forward in the human action analysis field. These kinds of techniques are sometimes integrated with Machine Learning (ML) strategies, like Support Vector Machine (SVM) or a Convolutional Neural Network (CNN). In this work, a topology-aided Human Activity Recognition (HAR) method is developed using various ML methods, like Multilayer Perceptron (MLP), K Nearest Neighbor (KNN), Decision Tree, CNN, SVM, and Random Forest. From the time series data, topological features, like persistent landscape, Betti curve, Persistent images, Wasserstein amplitude, and Persistent Entropy, are extracted. Using the extracted features, the ML methods, Random Forest, SVM, CNN, Decision Tree, KNN, and MLP are used to recognize the human activities. Here, the overall analysis states that the CNN model attained better accuracy, recall, precision, and F1-score with the values of 98.3, 98.3, 96.9, and 98. Also, it is noted that the maximum accuracy of about 99% is attained for the watch_accel_score_personal label by the proposed method.

Keywords:

Human activity recognition, Human motion analysis, Topological data analysis, Machine learning.

References:

[1] Cheng Xu et al., “Innohar: A Deep Neural Network for Complex Human Activity Recognition,” IEEE Access, vol. 7, pp. 9893-9902, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Kun Xia, Jianguang Huang, and Hanyu Wang, “LSTM-CNN Architecture for Human Activity Recognition,” IEEE Access, vol. 8, pp. 56855-56866, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Shengqin Wang et al., “Skeleton-based Action Recognition via Temporal-Channel Aggregation,” arXiv Preprint, pp. 1-13, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Javier Lamar Leon et al., “Topological Features for Monitoring Human Activities at Distance,” International Workshop on Activity Monitoring by Multiple Distributed Sensing, Stockholm, Sweden, pp. 40-51, 2014.
[CrossRef] [Google Scholar] [Publisher Link]
[5] I-Cheng Chang, and Chung-Lin Huang, “The Model-based Human Body Motion Analysis System,” Image and Vision Computing, vol. 18, no. 14, pp. 1067-1083, 2000.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Umar Islambekov, Monisha Yuvaraj, and Yulia R. Gel, “Harnessing the Power of Topological Data Analysis to Detect Change Points,” Environmetrics, vol. 31, no. 1, pp. 1-26, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Marcin Żelawski, and Tomasz Hachaj, “The Application of Topological Data Analysis to Human Motion Recognition,” Technical Transactions, vol. 118, no. 1, pp. 1-10, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Adélie Garin, and Guillaume Tauzin, “A Topological “Reading” Lesson: Classification of MNIST using TDA,” 2019 18th IEEE International Conference on Machine Learning and Applications (ICMLA), Boca Raton, FL, USA, pp. 1551-1556, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Vraj Sheth, Urvashi Tripathi, and Ankit Sharma, “A Comparative Analysis of Machine Learning Algorithms for Classification Purpose,” Procedia Computer Science, vol. 215, pp. 422-431, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Abdulrahman Sumayli, and Saad M. Alshahrani, “Modeling and Prediction of Biodiesel Production by Using Different Artificial Intelligence Methods: Multi-Layer Perceptron (MLP), Gradient Boosting (GB), and Gaussian Process Regression (GPR),” Arabian Journal of Chemistry, vol. 16, no. 7, pp. 1-14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Mohammed Khalilia, Sounak Chakraborty, and Mihail Popescu, “Predicting Disease Risks from Highly Imbalanced Data Using Random Forest,” BMC Medical Informatics and Decision Making, vol. 11, no. 1, pp. 1-13, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Leila Mohammadpour et al., “A Survey of CNN-based Network Intrusion Detection,” Applied Sciences, vol. 12, no. 16, pp. 1-34, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Human Activity Recognition, Data and Web Science Group, 2025.
[Publisher Link]
[14] Frédéric Chazal, and Bertrand Michel, “An Introduction to Topological Data Analysis: Fundamental and Practical Aspects for Data Scientists,” Frontiers in Artificial Intelligence, vol. 4, pp. 1-28, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Milan Joshi, and Dhananjay Josh, “A survey of Topological Data Analysis Methods for Big Data in Healthcare Intelligence,” International Journal of Applied Engineering Research, vol. 14, no. 2, pp. 584-588, 2019.
[Google Scholar] [Publisher Link]
[16] Gregory D. Abowd et al., “Towards A Better Understanding of Context and Context-Awareness,” International Symposium on Handheld and Ubiquitous Computing, Karlsruhe, Germany, pp. 304-307, 1999.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Ling Bao, and Stephen S. Intille, “Activity Recognition from User-Annotated Acceleration Data,” International Conference on Pervasive Computing, Linz, and Vienna, Austria, pp. 1-17, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Diane Cook, Kyle D. Feuz, and Narayanan C. Krishnan, “Transfer Learning for Activity Recognition: A Survey,” Knowledge and Information Systems, vol. 36, no. 3, pp. 537-556, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Charissa Ann Ronao, and Sung-Bae Cho, “Human Activity Recognition with Smartphone Sensors Using Deep Learning Neural Networks,” Expert Systems with Applications, vol. 59, pp. 235-244, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Daniele Ravì et al., “A Deep Learning Approach to On-Node Sensor Data Analytics for Mobile or Wearable Devices,” IEEE Journal of Biomedical and Health Informatics, vol. 21, no. 1, pp. 56-64, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Charissa Ann Ronao, and Sung-Bae Cho, “Deep Convolutional Neural Networks for Human Activity Recognition with Smartphone Sensors,” International Conference on Neural Information Processing, Istanbul, Turkey, pp. 46-53, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Olympio Hacquard, “From Topological Features to Machine Learning Models: A Journey through Persistence Diagrams,” Doctoral Dissertation, Paris-Saclay University, 2023.
[Google Scholar] [Publisher Link]
[23] Sungjoon Park, Yoonseok Hwang, and Bohm-Jung Yang, “Unsupervised Learning of Topological Phase Diagram Using Topological Data Analysis,” Physical Review B, vol. 105, no. 19, pp. 1-12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Gunnar Carlsson et al., “Topological Data Analysis and Machine Learning Theory,” Proceeding Banff International Research Station Workshop, pp. 1-11, 2012.
[Google Scholar] [Publisher Link]
[25] Eric Cawi, Patricio S. La Rosa, and Arye Nehorai, “Designing Machine Learning Workflows with an Application to Topological Data Analysis,” PloS one, vol. 14, no. 12, pp. 1-26, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Angelo Trotta et al., “Edge Human Activity Recognition Using Federated Learning on Constrained Devices,” Pervasive and Mobile Computing, vol. 104, pp. 1-15, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Shiwen Lan et al., “Human Action Recognition based on MnasNet Optimized by Improved Version of Football Team Training Algorithm,” Biomedical Signal Processing and Control, vol. 110, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Lingyue Hu et al., “Improving Human Activity Recognition via Graph Attention Network with Linear Discriminant Analysis and Residual Learning,” Biomedical Signal Processing and Control, vol. 100, 2025.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Yan Yan et al., “Topological Nonlinear Analysis of Dynamical Systems in Wearable Sensor-Based Human Physical Activity Inference,” IEEE Transactions on Human-Machine Systems, vol. 53, no. 4, pp. 792-801, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Yuxuan Zhou et al., “BlockGCN: Redefine Topology Awareness for Skeleton-Based Action Recognition,” 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, pp. 2049-2058, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Walaa N. Ismail et al., “AUTO-HAR: An Adaptive Human Activity Recognition Framework Using an Automated CNN Architecture Design,” Heliyon, vol. 9, no. 2, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Hung-Cuong Nguyen et al., “Deep Learning for Human Activity Recognition on 3D Human Skeleton: Survey and Comparative Study,” Sensors, vol. 23, no. 11, pp. 1-33, 2023.
[CrossRef] [Google Scholar] [Publisher Link]