Skip to main content

Advertisement

Springer Nature Link
Log in

Human activity recognition by body-worn sensor data using bi-directional generative adversarial networks and frequency analysis techniques

  • Published:
The Journal of Supercomputing Aims and scope Submit manuscript

Abstract

Existing datasets used for human activity recognition (HAR) usually suffer from limitations in terms of size variation and distribution of activity classes, which can impair the generalizability and robustness of the trained model, especially in the case of activity classes with minority data. This paper proposes an architecture utilizing bi-directional generative adversarial networks (Bi-GANs) beside fast Fourier transform, which stacks the 1-D accelerometer signals as m frequency bins × frames × 3 orientations and produces an RGB-based features pattern. The extracted patterns allow the 2D-CNN-based Bi-GAN architecture to learn the accelerometer signals' cross-axis relationships, which served as input for training a deep learning model for activity recognition equipped with a fuzzy inference dense layer. Also, we have used Hidden Markov Models (HMMs) for post-processing the classifier's output, which integrates the window-level decision in more extended periods, obtaining a significant performance improvement. The proposed method examined and conducted on MobiAct, Up-Fall, Opportunity, and WISDM datasets with different rates of augmentation, reaching to the 99.7%, 99.96%, 86.8%, and 99.12% rate of accuracy, respectively.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

Data availability

No datasets were generated or analyzed during the current study.

References

  1. Tehrani A, Yadollahzadeh-Tabari M, Zehtab-Salmasi A, Enayatifar R (2023) Wearable sensor-based human activity recognition system employing Bi-LSTM algorithm. Comput J 67:961–975

    Article  Google Scholar 

  2. Bourjandi M, Yadollahzadeh-Tabari M, Golsorkhtabaramiri M (2022) Combined deep centralized coordinate learning and hybrid loss for human activity recognition. Concurr Comput Pract Exp 34(22):e6870

    Article  MATH  Google Scholar 

  3. Bourjandi M, Yadollahzadeh-Tabari M, GolsorkhtabariAmiri M (2022) Predicting user’s movement path in indoor environments using the stacked deep learning method and the fuzzy soft-max classifier. IET Signal Proc 16(5):546–561

    Article  MATH  Google Scholar 

  4. Shakerian R, Yadollahzadeh-Tabari M, Bozorgi Rad SY (2022) Proposing a Fuzzy Soft-max-based classifier in a hybrid deep learning architecture for human activity recognition. IET Biom 11(2):171–186

    Article  MATH  Google Scholar 

  5. Bourjandi M, Yadollahzadeh Tabari M, Golsorkhtabaramiri M (2022) Fuzzy centralized coordinate learning and hybrid loss for human activity recognition. Int J Eng 35(1):130–141

    Google Scholar 

  6. Keramati Hatkeposhti R, Yadollahzadeh-Tabari M, Golsorkhtabariamiri M (2023) Providing an approach for early prediction of fall in human activities based on wearable sensor data and the use of deep learning algorithms. Comput J 47:37

    MATH  Google Scholar 

  7. Keramati Hatkeposhti R, Yadollahzadeh Tabari M, GolsorkhtabariAmiri M (2022) Fall detection using deep learning algorithms and analysis of wearable sensor data by presenting a new sampling method. Int J Eng 35(10):1941–1958

    Article  MATH  Google Scholar 

  8. Nazarloo M, Yadollahzadeh-Tabari M, Motameni H (2022) Online multi-object tracking based on time and frequency domain features. IET Comput Digit Tech 16(1):19–28

    Article  MATH  Google Scholar 

  9. Gil-Martín M, San-Segundo R, Fernandez-Martinez F, Ferreiros-López J (2020) Improving physical activity recognition using a new deep learning architecture and post-processing techniques. Eng Appl Artif Intell 92:103679

    Article  Google Scholar 

  10. Sanabria AR, Zambonelli F, Ye J (2021) Unsupervised domain adaptation in activity recognition: a GAN-based approach. IEEE Access 9:19421–19438

    Article  MATH  Google Scholar 

  11. Ye J, Nakwijit P, Schiemer M, Jha S, Zambonelli F (2021) Continual activity recognition with generative adversarial networks. ACM Trans Internet Things 2(2):1–25

    Article  Google Scholar 

  12. Jimale AO, Noor MH (2022) Fully connected generative adversarial network for human activity recognition. IEEE Access 10:100257–100266

    Article  Google Scholar 

  13. Alharbi F, Ouarbya L, Ward JA (2020) Synthetic sensor data for human activity recognition. In: 2020 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1–9

  14. Li Z, Ma C, Shi X, Zhang D, Li W, Wu L (2021) Tsa-gan: a robust generative adversarial networks for time series augmentation. In: 2021 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1–8

  15. Soleimani, E, Nazerfard E (2021) Cross-subject transfer learning in human activity recognition systems using generative adversarial networks. Neurocomputing 426:26-34

  16. Xu W, Jang-Jaccard J, Liu T, Sabrina F (2022) Training a bidirectional gan-based one-class classifier for network intrusion detection. arXiv preprint arXiv:2202.01332

  17. Mutlu U, Alpaydın E (2020) Training bidirectional generative adversarial networks with hints. Pattern Recogn 103:107320

    Article  MATH  Google Scholar 

  18. Zhang W, Peng P, Zhang H (2021) Using bidirectional GAN with improved training architecture for imbalanced tasks. In: 2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD). IEEE, pp 714–719

  19. Zhang Z, Liu S, Li M, Zhou M, Chen E (2018) Bidirectional generative adversarial networks for neural machine translation. In: Proceedings of the 22nd Conference on Computational Natural Language Learning, pp 190–199

  20. Esmael B, Arnaout A, Fruhwirth RK, Thonhauser G (2012) Improving time series classification using Hidden Markov Models. In: 2012 12th International Conference on Hybrid Intelligent Systems (HIS). IEEE, pp 502–507

  21. Le HL, Nguyen DN, Nguyen TH, Nguyen HN (2022) A novel feature set extraction based on accelerometer sensor data for improving the fall detection system. Electronics 11(7):1030

    Article  MATH  Google Scholar 

  22. Sowmiya S, Menaka D (2022) Transformer model for human activity recognition using IoT wearables. In: International Conference on Computer Vision, High-Performance Computing, Smart Devices, and Networks. Springer, Singapore, pp 287–300

  23. Ordóñez FJ, Roggen D (2016) Deep convolutional and LSTM recurrent neural networks for multimodal wearable activity recognition. Sensors 16(1):115

    Article  MATH  Google Scholar 

  24. Ignatov A (2018) Real-time human activity recognition from accelerometer data using convolutional neural networks. Appl Soft Comput 62:915–922

    Article  MATH  Google Scholar 

  25. Wu X, Zheng Y, Chu CH, Cheng L, Kim J (2022) Applying deep learning technology for automatic fall detection using mobile sensors. Biomed Signal Process Control 72:103355

    Article  MATH  Google Scholar 

  26. Vavoulas G, Chatzaki C, Malliotakis T, Pediaditis M, Tsiknakis M (2016) The MobiAct dataset: recognition of activities of daily living using smartphones. In: International Conference on Information and Communication Technologies for Ageing Well and e-Health, vol 2. SciTePress, pp 143–151

  27. Nho YH, Ryu S, Kwon DS (2021) UI-GAN: generative adversarial network-based anomaly detection using user initial information for wearable devices. IEEE Sens J 21(8):9949–9958

    Article  MATH  Google Scholar 

  28. Ramirez H, Velastin SA, Cuellar S, Fabregas E, Farias G (2023) BERT for activity recognition using sequences of skeleton features and data augmentation with GAN. Sensors 23(3):1400

    Article  Google Scholar 

  29. Zebhi S (2022) Human activity recognition using wearable sensors based on image classification. IEEE Sens J 22(12):12117–12126

    Article  Google Scholar 

  30. Papaleonidas A, Psathas AP, Iliadis L (2022) High accuracy human activity recognition using machine learning and wearable devices’ raw signals. J Inf Telecommun 6(3):237–253

    MATH  Google Scholar 

  31. Shrestha A, Li H, Le Kernec J, Fioranelli F (2020) Continuous human activity classification from FMCW radar with Bi-LSTM networks. IEEE Sens J 20(22):13607–13619

    Article  Google Scholar 

  32. Iloga S, Bordat A, Le Kernec J, Romain O (2021) Human activity recognition based on acceleration data from smartphones using HMMs. IEEE Access 9:139336–139351

    Article  Google Scholar 

  33. Manouchehri N, Bouguila N (2023) Human activity recognition with an HMM-based generative model. Sensors 23(3):1390

    Article  MATH  Google Scholar 

  34. Luo J, Li X, Younes R (2021) Toward data augmentation and interpretation in sensor-based fine-grained hand activity recognition. In: Deep Learning for Human Activity Recognition: Second International Workshop, DL-HAR 2020, Held in Conjunction with IJCAI-PRICAI 2020, Kyoto, Japan, January 8, 2021, Proceedings 2. Springer, Singapore, pp 30–42

  35. Martínez-Villaseñor L, Ponce H, Brieva J, Moya-Albor E, Núñez-Martínez J, Peñafort-Asturiano C (2019) UP-fall detection dataset: a multimodal approach. Sensors 19(9):1988

    Article  Google Scholar 

  36. Chavarriaga R et al (2013) The Opportunity challenge: a benchmark database for on-body sensor-based activity recognition. Pattern Recogn Lett 34:2033–2042

    Article  MATH  Google Scholar 

  37. Kwapisz JR, Weiss GM, Moore SA (2011) Activity recognition using cell phone accelerometers. ACM SIGKDD Explor Newsl 12(2):74–82

    Article  Google Scholar 

  38. Ketkar N, Ketkar N (2017) Introduction to keras. In: Deep Learning with Python: A Hands-On Introduction, pp 97–111

  39. Al-qaness MA, Dahou A, Trouba NT, Abd Elaziz M, Helmi AM (2024) TCN-inception: temporal convolutional network and inception modules for sensor-based human activity recognition. Future Gener Comput Syst 160:375–388

    Article  MATH  Google Scholar 

  40. Saidani O, Alsafyani M, Alroobaea R, Alturki N, Jahangir R, Jamel L (2023) An efficient human activity recognition using hybrid features and transformer model. IEEE Access 11:101373–101386

    Article  Google Scholar 

  41. Peppas K, Tsolakis AC, Krinidis S, Tzovaras D (2020) Real-time physical activity recognition on smart mobile devices using convolutional neural networks. Appl Sci 10(23):8482

    Article  MATH  Google Scholar 

  42. Kumar P, Suresh S (2023) Deep learning models for recognizing the simple human activities using smartphone accelerometer sensor. IETE J Res 69(8):5148–5158

    Article  MATH  Google Scholar 

  43. Jalal A, Quaid MA, Tahir SB, Kim K (2020) A study of accelerometer and gyroscope measurements in physical life-log activities detection systems. Sensors 20(22):6670

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Computer Engineering, Babol Branch, Islamic Azad University, Babol, Iran

    Zohre Kia

  2. Department of Computer Engineering, Sari Branch, Islamic Azad University, Sari, Iran

    Meisam Yadollahzaeh-Tabari & Homayun Motameni

Authors
  1. Zohre Kia
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Meisam Yadollahzaeh-Tabari
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Homayun Motameni
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

Mrs. ZK repapered the draft paper and find the resources and wrote the codes. Dr. MY as project administration proposes the main continuation of this paper and performs the required investigations. Dr. HM revised the draft version and made the required formal analysis.

Corresponding author

Correspondence to Meisam Yadollahzaeh-Tabari.

Ethics declarations

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kia, Z., Yadollahzaeh-Tabari, M. & Motameni, H. Human activity recognition by body-worn sensor data using bi-directional generative adversarial networks and frequency analysis techniques. J Supercomput 81, 342 (2025). https://doi.org/10.1007/s11227-024-06743-0

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s11227-024-06743-0

Keywords