Signal Feature Extraction and Machine Learning Techniques for Human Activity Recognition

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2025 | Volume :12 | Issue : 01 | Page : –
By
vector

Aparna M. Bagde,

vector

Madhavi N. Jadhav,

vector

Suvarna A. Pathak,

  1. Assistant Professor, Department of Computer Engineering, JSPM Narhe Technical Campus, SPPU, Pune, Maharashtra, India
  2. Assistant Professor, Department of Computer Engineering, JSPM Narhe Technical Campus, SPPU, Pune, Maharashtra, India
  3. Assistant Professor, Department of Computer Engineering, JSPM Narhe Technical Campus, SPPU, Pune, Maharashtra, India

Abstract

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_abs_150307’);});Edit Abstract & Keyword

Human Activity Recognition (HAR) has emerged as a critical field of study with diverse applications in healthcare, fitness tracking, smart homes, and human-computer interaction. The aim of this research is to create an efficient HAR system through advanced techniques characterized by signal feature extraction and machine learning algorithms. The MEMS sensors are used appropriately during data mining to extract time-domain, frequency-domain, and statistical features, which are subsequently passed to the models for classification. Majority of the implementations of the experiments conducted in this study will be based on formulations of support vector machines (SVM), random forest, and neural networks to classify activities like walking, running, sitting, and lying down. Feature selection applications, such as PCA, were integrated into their methods to optimize the feature set, which further advanced the goal of efficiency and accuracy of the machine learning models. The experimental results prove the proposed approach as mostly accurate across the dataset in multiple activities conducted. Key performance indicators for the model include precision, recall, and F1-score, which help evaluate its effectiveness. These highlight the importance of combining optimized signal feature extraction with machine learning techniques to design real-time, reliable HAR systems. This study results in a contribution to scalable and adaptive HAR frameworks that lead to smart applications and intelligent systems monitoring them. Works will further delve into deep learning techniques and multimodal sensor data to enhance the performance of these systems.

Keywords: Human Activity Recognition, Signal Feature Extraction, Machine Learning Algorithms, Support Vector Machines, Random Forest, Neural Networks

[This article belongs to Journal of Mobile Computing, Communications & Mobile Networks (jomccmn)]

How to cite this article:
Aparna M. Bagde, Madhavi N. Jadhav, Suvarna A. Pathak. Signal Feature Extraction and Machine Learning Techniques for Human Activity Recognition. Journal of Mobile Computing, Communications & Mobile Networks. 2025; 12(01):-.
How to cite this URL:
Aparna M. Bagde, Madhavi N. Jadhav, Suvarna A. Pathak. Signal Feature Extraction and Machine Learning Techniques for Human Activity Recognition. Journal of Mobile Computing, Communications & Mobile Networks. 2025; 12(01):-. Available from: https://journals.stmjournals.com/jomccmn/article=2025/view=0

document.addEventListener(‘DOMContentLoaded’,function(){frmFrontForm.scrollToID(‘frm_container_ref_150307’);});Edit

References

1. Sensor HAR recognition App – File Exchange – MATLAB CentralFile Exchange – MATLAB Central. Mathworks.com. 2016. Available from: https://www.mathworks.com/matlabcentral/fileexchange/54138-sensor-har-recognition-app

2. Sensor Data Analytics (French Webinar Code) – File Exchange – MATLAB CentralFile Exchange – MATLAB Central. Mathworks.com. 2017. Available from: https://www.mathworks.com/matlabcentral/fileexchange/54139-sensor-data-analytics-french-webinar-code

3. Devarakonda PG, Bozic B. Particle swarm optimization of convolutional neural networks for human activity prediction. InOptimisation Algorithms and Swarm Intelligence 2022 Nov 2. IntechOpen. DOI: 10.5772/intechopen.97259

4. Anguita D, Ghio A, Oneto L, Parra X, Reyes-Ortiz JL. A public domain dataset for human activity recognition using smartphones. InEsann 2013 Apr 24 (Vol. 3, p. 3). 1-6. doi:10.1109/UbiquitousData.2013.6894664

5. Reyes-Ortiz, J. L., Samà, A., Parra, X., & Anguita, D. (2016). Transition-aware human activity recognition using smartphones. Proceedings of the International Joint Conference on Neural Networks, 2872-2879. doi:10.1109/IJCNN.2016.7727423

6. He, H., Wu, D., & Zhang, D. (2016). Transfer Learning for Brain-Computer Interfaces: A Euclidean Space Data Alignment Approach. IEEE Transactions on Biomedical Engineering, 63(4), 830-840. doi:10.1109/TBME.2015.2483832

7. Zhang S, Li Y, Zhang S, Shahabi F, Xia S, Deng Y, Alshurafa N. Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors. 2022 Feb 14;22(4):1476.

8. Ordonez, F. J., & Roggen, D. (2016). Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition. Proceedings of the European Symposium on Artificial Neural Networks, 223-228. doi:10.1016/j.neunet.2016.10.008

9. Zhang, X., Li, S., & Liu, W. (2018). Human Activity Recognition Using Smartphone Sensors Based on Feature Selection and Machine Learning. Sensors, 18(6), 1978-1992. doi:10.3390/s18061978

10. Attal F, Mohammed S, Dedabrishvili M, Chamroukhi F, Oukhellou L, Amirat Y. Physical human activity recognition using wearable sensors. Sensors. 2015 Dec;15(12):31314-38.

11. Souza VL, Oliveira AL, Cruz RM, Sabourin R. On dissimilarity representation and transfer learning for offline handwritten signature verification. In2019 International Joint Conference on Neural Networks (IJCNN) 2019 Jul 14 (pp. 1-9). IEEE.

12. Lara OD, Labrador MA. A survey on human activity recognition using wearable sensors. IEEE communications surveys & tutorials. 2012 Nov 29;15(3):1192-209.

13. Reiss A, Stricker D. Introducing a new benchmarked dataset for activity monitoring. In2012 16th international symposium on wearable computers 2012 Jun 18 (pp. 108-109). IEEE.

14. Zhang HB, Zhang YX, Zhong B, Lei Q, Yang L, Du JX, Chen DS. A comprehensive survey of vision-based human action recognition methods. Sensors. 2019 Feb 27;19(5):1005.

15. Lin X, Sánchez-Escobedo D, Casas JR, Pardàs M. Depth estimation and semantic segmentation from a single RGB image using a hybrid convolutional neural network. Sensors. 2019 Apr 15;19(8):1795.

16. Yazdansepas D, Saroha N, Ramaswamy L, Rasheed K. Towards Efficient and Real-Time Human Activity Recognition Using Wearable Sensors: A Shapelet-Based Pattern Matching Approach. In13th EAI International Conference on Body Area Networks 13 2020 (pp. 115-130). Springer International Publishing.

17. Rodrigues ES, Borges VR. Pore detection in fingerprints based on image subtraction and anisotropic diffusion filtering. In2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2018 Oct 7 (pp. 2061-2066). IEEE.

18. Kaur M, Singh D. Multi-modality medical image fusion technique using multi-objective differential evolution based deep neural networks. Journal of Ambient Intelligence and Humanized Computing. 2021 Feb;12(2):2483-93.

19. Yashraj Mishra, Ankita Jaiswal, Dr. Goldi Soni. A Comparative Study on Human Activity Recognition Using Smartphone Dataset through Machine Learning Approach. International Research Journal of Engineering and Technology. 2024;11(07):813-827.

20. Bruen D, Delaney C, Florea L, Diamond D. Glucose sensing for diabetes monitoring: recent developments. Sensors. 2017 Aug 12;17(8):1866.

21. Nguyen HD, Tran KP, Zeng X, Koehl L, Tartare G. An improved ensemble machine learning algorithm for wearable sensor data based human activity recognition. Reliability and Statistical Computing: Modeling, Methods and Applications. 2020:207-28.

22. Subasi A, Khateeb K, Brahimi T, Sarirete A. Human activity recognition using machine learning methods in a smart healthcare environment. InInnovation in health informatics 2020 Jan 1 (pp. 123-144). Academic Press.

23. Tian Y, Zhang J, Li L, Liu Z. A novel sensor-based human activity recognition method based on hybrid feature selection and combinational optimization. IEEE Access. 2021 Jul 27;9:107235-49.

24. Ronao CA, Cho SB. Human activity recognition with smartphone sensors using deep learning neural networks. Expert systems with applications. 2016 Oct 15;59:235-44.

25. Park J, Kim T. Learning doubly stochastic affinity matrix via Davis-Kahan theorem. In2017 IEEE International Conference on Data Mining (ICDM) 2017 Nov 18 (pp. 377-384). IEEE.

26. Chen Y, Xue Y. A deep learning approach to human activity recognition based on single accelerometer. In2015 IEEE international conference on systems, man, and cybernetics 2015 Oct 9 (pp. 1488-1492). IEEE.

27. Liu K, Wang Y, Chen R, Chu T, Bi J. A survey of human activity recognition using smartphones. Journal of Residuals Science & Technology. 2016;13(8):1-10.

28. Li X, You S, Chen W. Inducing embeddings for rare words through morphological decomposition, stemming and bidirectional translation. In2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA) 2019 Dec 16 (pp. 1039-1044). IEEE.

29. Wang H, Zhao J, Li J, Tian L, Tu P, Cao T, An Y, Wang K, Li S. Wearable Sensor‐Based Human Activity Recognition Using Hybrid Deep Learning Techniques. Security and communication Networks. 2020;2020(1):2132138.

30. Wang CC, Hou ZY, You JC. A high-precision CMOS temperature sensor with thermistor linear calibration in the (− 5 C, 120 C) temperature range. Sensors. 2018 Jul 5;18(7):2165.

31. Dhekane SG, Ploetz T. Transfer learning in human activity recognition: A survey. arXiv preprint arXiv:2401.10185. 2024 Jan 18.

32. Lauerman MH, Herrera AV, Albrecht JS, Chen HH, Bruns BR, Tesoriero RB, Scalea TM, Diaz JJ. Percentage of mortal encounters transferred in emergency general surgery. Journal of Surgical Research. 2019 Nov 1;243:391-8.

33. Ning L, Pittman R, Shen X. LCD: A fast contrastive divergence-based algorithm for restricted Boltzmann machine. Neural Networks. 2018 Dec 1;108:399-410.

Regular Issue Subscription Review Article
Volume 12
Issue 01
Received 07/01/2025
Accepted 09/01/2025
Published 24/01/2025
100