S. M. Mohidul Islam; Kamrul Hasan Talukder

Modeling Human Activity Recognition with Deep Convolutional Neural Networks and Wearable Sensor Data

PDF (1248KB), PP.97-115

Views: 0 Downloads: 0

Author(s)

S. M. Mohidul Islam ^1,* Kamrul Hasan Talukder ¹

1. Computer Science and Engineering Discipline, Khulna University, Khulna, Bangladesh

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2026.04.06

Received: 6 Jan. 2026 / Revised: 15 Mar. 2026 / Accepted: 21 Jun. 2026 / Published: 8 Aug. 2026

Index Terms

Human ACTIVITY, Time-series DATA, BODY-worn SENSOR, Subject-dependency, LOPO-CV, DCNN

Abstract

Automatic Human activity Recognition has many applications in smart environments such as in smart homes, smart cities, smart industries, smart healthcare centers, etc. While performing the activities by the participants, ambient or body-worn sensors can measure physical movements and those data can be used to develop machine learning models for recognizing those activities. In this study, we have proposed a deep convolutional neural network (DCNN) based method for recognizing human activities using body-worn sensors’ time-series data after an enormous data analysis on the data. The quality data is produced and balanced using a preprocessing chain for human activity recognition based on data analysis. The Preprocessed data is segmented using a constant-size sliding window. We developed several different DCNN models using random searches and based on validation accuracy we selected the best one for further training and testing. The outcomes of the selected model are carried out as the final predicted activities. We assessed our method on three popular and standard datasets: PAMAP2, WISDM_ar_v1.1, and UCI-HAR, and achieved 98.11%, 98.48%, and 93.25% accuracies for subject-dependent case and 90.27%, 94.51%, and 98.67% accuracies for subject-independent case. The performances of the experimental results are measured using several evaluation metrics and measures that institute the strength of the proposed model over the state-of-the-art.

Cite This Paper

S. M. Mohidul Islam, Kamrul Hasan Talukder, "Modeling Human Activity Recognition with Deep Convolutional Neural Networks and Wearable Sensor Data", International Journal of Intelligent Systems and Applications(IJISA), Vol.18, No.4, pp.97-115, 2026. DOI:10.5815/ijisa.2026.04.06

Reference

[1]K. Sidney. Assessing self-maintenance: activities of daily living, mobility, and instrumental activities of daily living. Journal of the American Geriatrics Society, 31(12):721-727, December 1983. https://doi.org/10.1111/j.1532-5415.1983.tb03391.x.
[2]K. Ranjit and V. Geetha. Human activity recognition in smart home using deep learning techniques. In 2021 13th International conference on information & communication technology and system (ICTS), pages 230-234, October 2021. https://doi.org/10.1109/ICTS52701.2021.9609044.
[3]A.K.M. Masum, S. Jannat, E.H. Bahadur, M.G.R. Alam, S.I. Khan, and M.R. Alam. Human Activity Recognition Using Smartphone Sensors: A Dense Neural Network Approach. ICASERT, May 2019. https://doi.org/10.1109/ICASERT.2019.8934657.
[4]Zhou, X., Liang, W., Kevin, I., Wang, K., Wang, H., Yang, L.T. and Jin, Q. Deep-learning-enhanced human activity recognition for Internet of healthcare things. IEEE Internet of Things Journal, 7(7):6429-6438, April 2020.
[5]B. Debarshi, D. Sharma, W. Kim, M.F. Ijaz, and P.K. Singh. Ensem-HAR: An ensemble deep learning model for smartphone sensor-based human activity recognition for measurement of elderly health monitoring. Biosensors, 12(6):393, June 2022. https://doi.org/10.3390/bios12060393.
[6]G. Walid, R. Elbasiony, and S. Ashry. ADL classification based on autocorrelation function of inertial signals. In2017 16th IEEE International Conference on Machine Learning and Applications (ICMLA), pages 833-837, December 2017. https://doi.org/10.1109/ICMLA.2017.00-53.
[7]M. Stikic, T. Huynh, K.V. Laerhoven, and B. Schiele. ADL recognition based on the combination of RFID and accelerometer sensing. In 2008 second international conference on pervasive computing technologies for healthcare, pages 258-263, January 2008. https://doi.org/10.1109/PCTHEALTH.2008.4571084.
[8]A. Baldominos, P. Isasi, and Y. Saez. Feature selection for physical activity recognition using genetic algorithms. In 2017 IEEE Congress on Evolutionary Computation (CEC), pages 2185-2192, June 2017. https://doi.org/10.1109/CEC.2017.7969569.
[9]B.A. Atalaa, A. Alenany, A. Helmi, and I. Ziedan. Effect of data segmentation on the quality of human activity recognition. East Afr. Scholars J. Eng. Comput. Sci., 4480(7):133-145, 2020. https://doi.org/10.36349/easjecs.2020.v03i07.001.
[10]C. Xu, D. Chai, J. He, X. Zhang, and S. Duan. InnoHAR: A deep neural network for complex human activity recognition. IEEE Access, 7:9893-9902, January 2019. https://doi.org/10.1109/ACCESS.2018.2890675.
[11]D. Mukherjee, R. Mondal, P.K. Singh, R. Sarkar, and D. Bhattacharjee. EnsemConvNet: a deep learning approach for human activity recognition using smartphone sensors for healthcare applications. Multimedia Tools and Applications, 79:31663-31690, November 2020. https://doi.org/10.1007/s11042-020-09537-7.
[12]Y. Zhao, R. Yang, G. Chevalier, X. Xu, and Z. Zhang. Deep residual bidir-LSTM for human activity recognition using wearable sensors. Mathematical problems in engineering, 2018(1):7316954, 2018. https://doi.org/10.1155/2018/7316954.
[13]G. Ennio, G. Temperini, R. Galassi, L. Senigagliesi, and A.D. Santis. ADL recognition through machine learning algorithms on IoT air quality sensor dataset. IEEE Sensors Journal, 20(22):13562-13570, June 2020. https://doi.org/10.1109/JSEN.2020.3005642.
[14]W. Hom. Human action recognition with still images and video [online]. Available at: https://github.com/wendell-hom/human_action_recognition (Accessed on 5 January 2024).
[15]S.A. Bux, X. Wang, P. Angelov, and Z. Habib. Human action recognition using transfer learning with deep representations. In2017 International joint conference on neural networks (IJCNN), pages 463-469, May 2017. https://doi.org/10.1109/IJCNN.2017.7965890.
[16]Abdulazeem, Y., Balaha, H.M., Bahgat, W.M. and Badawy, M. Human action recognition based on transfer learning approach. IEEE Access, 9:82058-82069, June 2021.
[17]N. Hao, D. Nguyen, K. Yonekawa, M. Kurokawa, S. Wada, and K. Yoshihara. Multi-source transfer learning for human activity recognition in smart homes. In 2020 IEEE international conference on smart computing (SMARTCOMP), pages 274-277, September 2020. https://doi.org/10.1109/SMARTCOMP50058.2020.00063.
[18]Z. Shibo, Y. Li, S. Zhang, F. Shahabi, S. Xia, Y. Deng, and N. Alshurafa. Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors, 22(4):1476, February 2022. https://doi.org/10.3390/s22041476.
[19]Yang J, Xu Y, Cao H, Zou H, and Xie L. Deep learning and transfer learning for device-free human activity recognition: A survey. Journal of Automation and Intelligence, 1(1):100007, December 2022.
[20]Sefen, B, Sebastian B, Andreas D, and Slim A. Human activity recognition-using sensor data of smartphones and smartwatches. International Conference on Agents and Artificial Intelligence, 2:488-493, SciTePress, February 2016.
[21]Zhou B, Wang C, Huan Z, Li Z, Chen Y, Gao G, Li H, Dong C, and Liang J. A novel segmentation scheme with multi-probability threshold for human activity recognition using wearable sensors. Sensors, 22(19):7446, September 2022.
[22]Kong W, He L, and Wang H. Exploratory data analysis of human activity recognition based on smartphone. IEEE Access, 9:73355-64, May 2021.
[23]Khan, A.M., Siddiqi, M.H. and Lee, S.W. Exploratory data analysis of acceleration signals to select light-weight and accurate features for real-time activity recognition on smartphones. Sensors, 13(10):13099-13122, September 2013.
[24]Hammerla NY, Halloran S, and Plötz T. Deep. Convolutional and recurrent models for human activity recognition using wearables. arXiv preprint arXiv:1604.08880, April 2016.
[25]Shi, Wenbing, Xianjin Fang, Gaoming Yang, and Ji Huang. Human activity recognition based on multichannel convolutional neural network with data augmentation. IEEE Access, 10:76596-76606, July 2022.
[26]Ihianle, I.K., Nwajana, A.O., Ebenuwa, S.H., Otuka, R.I., Owa, K. and Orisatoki, M.O. A deep learning approach for human activities recognition from multimodal sensing devices. IEEE Access, 8:179028-179038, September 2020.
[27]S. Gupta. Deep learning based human activity recognition (HAR) using wearable sensor data. International Journal of Information Management Data Insights, 1(2):100046, November 2021. https://doi.org/10.1016/j.jjimei.2021.100046.
[28]R.K. Athota, and D. Sumathi. Human activity recognition based on hybrid learning algorithm for wearable sensor data. Measurement: Sensors, 24:100512, December 2022. https://doi.org/10.1016/j.measen.2022.100512.
[29]Gumaei A, Hassan MM, Alelaiwi A, and Alsalman H. A hybrid deep learning model for human activity recognition using multimodal body sensing data. IEEE Access, 7:99152-60, August 2019.
[30]Compagnon, P, Grégoire L, Stefan D, and Christophe G. Learning personalized ADL recognition models from few raw data. Artificial Intelligence in Medicine, 107:101916, July 2020.
[31]Shi, Xiaoran, Yaxin Li, Feng Zhou, and Lei Liu. Human activity recognition based on deep learning method. In 2018 International Conference on Radar (RADAR), pages 1-5, August 2018.
[32]D.V. Kuppevelt, C. Meijer, F. Huber, A.V.D. Ploeg, S. Georgievska, and V.T.V. Hees. Mcfly: Automated deep learning on time series. SoftwareX, 12:100548, July 2020. https://doi.org/10.1016/j.softx.2020.100548.
[33]A. Reiss, and D. Stricker. Introducing a new benchmarked dataset for activity monitoring. In2012 16th international symposium on wearable computers (ISWC), pages 108-109, June 2012. https://doi.org/10.1109/ISWC.2012.13.
[34]J.R. Kwapisz, G.M. Weiss, and S.A. Moore. Activity Recognition using Cell Phone Accelerometers. ACM SigKDD Explorations Newsletter, 12(2):74-82, March 2011. https://doi.org/10.1145/1964897.1964918.
[35]D. Anguita, A. Ghio, L. Oneto, X. Parra, and J. L. Reyes-Ortiz. A public domain dataset for human activity recognition using smartphones. Esann. 3(1):3-4, April 2013.
[36]Glen, S. Data Analysis & Exploratory Data Analysis (EDA) [online]. Available at: https://www.statisticshowto.com/probability-and-statistics/data-analysis/ (Accessed on 1 September 2022).
[37]Islam, S.M. and Talukder, K.H. Ensem-DeepHAR: Identification of Human Activity in Smart Environments using Ensemble of Deep Learning Methods and Motion Sensor Data. Measurement: Sensors, 36:101398, December 2024.
[38]He, H. and Ma, Y. Imbalanced learning: foundations, algorithms, and applications. 47, eds. 2013.
[39]Laguna, J.O., Garc, A., and Borrajo, D. A Dynamic SlidingWindow Approach for Activity Recognition. In Proceedings of the 19th International Conference on User Modeling, Adaption, and Personalization (UMAP), Girona, Spain, 11–15 July 2011, pages 219–230, 2011.
[40]Preece, S.J., Goulermas, J.Y., Kenney, L.P. and Howard, D. A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Transactions on Biomedical Engineering, 56(3):871-879, October 2008.
[41]D. Mukherjee, R. Mondal, P.K. Singh, R. Sarkar, and D. Bhattacharjee. EnsemConvNet: a deep learning approach for human activity recognition using smartphone sensors for healthcare applications. Multimedia Tools and Applications, 79:31663-31690, November 2020. https://doi.org/10.1007/s11042-020-09537-7.
[42]Baldominos, A., Cervantes, A., Saez, Y. and Isasi, P. A comparison of machine learning and deep learning techniques for activity recognition using mobile devices. Sensors, 19(3):521, January 2019.
[43]Bock, Marius, Alexander Hölzemann, Michael Moeller, and Kristof Van Laerhoven. Improving deep learning for HAR with shallow LSTMs. In Proceedings of the 2021 ACM International Symposium on Wearable Computers, pages 7-12, September 2021.
[44]Scikit-learn [online]. Available at: https://scikit-learn.org/stable/modules/cross_validation.html (Accessed on 1 February 2024).
[45]Bergstra, J. and Bengio, Y. Random search for hyper-parameter optimization. The Journal of machine learning research, 13(1):281-305, February 2012.
[46]Comparing randomized search and grid search for hyperparameter estimation [online], Available at: https://scikit-learn.org/stable/auto_examples/model_selection/plot_randomized_search.html (Accessed on 10 January 2024).
[47]Mcfly [online], Available at: https://mcfly.readthedocs.io/en/latest/ (Accessed on 10 January 2024).
[48]S. Wan, L. Qi, X. Xu, C. Tong, and Z. Gu. Deep learning models for real-time human activity recognition with smartphones. mobile networks and applications, 25(2):743-755, April 2020. https://doi.org/10.1007/s11036-019-01445-x.
[49]S.K. Challa, A. Kumar, and V.B. Semwal. A multibranch CNN-BiLSTM model for human activity recognition using wearable sensor data. The Visual Computer, 38(12):4095-4109, December 2022. https://doi.org/10.1007/s00371-021-02283-3.
[50]N. Dua, S.N. Singh, and V.B. Semwal. Multi-input CNN-GRU based human activity recognition using wearable sensors. Computing, 103(7):1461-1478, July 2021. https://doi.org/10.1007/s00607-021-00928-8.
[51]Jin, L., Wang, X., Chu, J. and He, M. Human activity recognition machine with an anchor-based loss function. IEEE Sensors Journal, 22(1):741-756, November 2021.
[52]Cheng, X., Zhang, L., Tang, Y., Liu, Y., Wu, H. and He, J. Real-time human activity recognition using conditionally parametrized convolutions on mobile and wearable devices. IEEE Sensors Journal, 22(6):5889-5901, February 2022.
[53]Challa, S.K., Kumar, A., Semwal, V.B. and Dua, N. An optimized deep learning model for human activity recognition using inertial measurement units. Expert Systems, 40(10):e13457, December 2023.
[54]Mim, T.R., Amatullah, M., Afreen, S., Yousuf, M.A., Uddin, S., Alyami, S.A., Hasan, K.F. and Moni, M.A. GRU-INC: An inception-attention based approach using GRU for human activity recognition. Expert Systems with Applications, 216:119419, April 2023.
[55]Ige, A.O. and Noor, M.H.M. A deep local-temporal architecture with attention for lightweight human activity recognition. Applied Soft Computing, 149:110954, December 2023.
[56]Subasi, A., Fllatah, A., Alzobidi, K., Brahimi, T. and Sarirete, A. Smartphone-based human activity recognition using bagging and boosting. Procedia Computer Science, 163:54-61, January 2019.
[57]Zhang, Y. and Ramachandran, K.M. Human activity recognition with streaming smartphone data. In 2019 Global Conference for Advancement in Technology (GCAT), pages 1-6, October 2019.
[58]K. Xia, J. Huang, and H. Wang. LSTM-CNN architecture for human activity recognition. IEEE Access, 8:56855-56866, March 2020. https://doi.org/10.1109/ACCESS.2020.2982225.
[59]Zhang, Y. and Ramachandran, K.M. Offline machine learning for human activity recognition with smartphone. 2020.
[60]W. Shi, X. Fang, G. Yang, and J. Huang. Human activity recognition based on multichannel convolutional neural network with data augmentation. IEEE Access, 10:76596-76606, July 2022. https://doi.org/10.1109/ACCESS.2022.3192452.
[61]Sain, M.K., Singha, J., Saini, S. and Semwal, V.B. Human action recognition using ConvBiLSTM-GRU in indoor environment. In 2023 IEEE Global Conference on Artificial Intelligence and Internet of Things (GCAIoT), pages 179-186, December 2023.
[62]Wang, Y., Xu, H., Liu, Y., Wang, M., Wang, Y., Yang, Y., Zhou, S., Zeng, J., Xu, J., Li, S. and Li, J. A novel deep multifeature extraction framework based on attention mechanism using wearable sensor data for human activity recognition. IEEE Sensors Journal, 23(7):7188-7198, February 2023.
[63]Islam, S.M. and Talukder, K.H. Ensem-EnsemHAR: Human Activity Recognition using Ensemble of Ensemble Methods and Smartphone Sensor Data. In 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), pages 1-7, June 2024.
[64]Islam, S.M. and Talukder, K.H. Exploratory analysis of smartphone sensor data for human activity recognition. IEEE Access, 11:99481-99498, September 2023.
[65]Saha, Utsab, Sawradip Saha, Md Tahmid Kabir, Shaikh Anowarul Fattah, and Mohammad Saquib. Decoding human activities: Analyzing wearable accelerometer and gyroscope data for activity recognition. IEEE Sensors Letters, July 2024.

International Journal of Intelligent Systems and Applications (IJISA)