Smartphone Based Real-Time Detection of Postural and Leg Abnormalities using Deep Learning Techniques
DOI:
https://doi.org/10.59796/jcst.V15N3.2025.112Keywords:
deep learning, accelerometer, gyroscope, sensor, classification, CNN, LSTMAbstract
This research presents an innovative real-time method for detecting leg postural abnormalities using deep learning techniques and smartphone sensors. The objectives are to: (1) develop a smartphone-based system for real-time classification of leg postures using accelerometer and gyroscope data, (2) evaluate the effectiveness of three deep learning models DNN, CNN, and CNN-LSTM in identifying spatial and temporal features, and (3) offer a low-cost, objective alternative to traditional assessment methods by addressing issues such as observer inconsistency and computational complexity. Accelerometer and gyroscope data from smartphones were used to develop a system that classified four leg postures: Pronation, Supination, Normal, and Postural Sway. Participants from various age groups carried a smartphone in their left pocket while standing and walking for 10, 20, and 30 seconds. This process produced a dataset of 29,823 records, which were verified and labeled by medical professionals based on observed postural characteristics. The CNN-LSTM model achieved the highest accuracy (96.4%) with strong class differentiation, demonstrating its effectiveness in capturing temporal dependencies. All three models were employed for unknown instances, and a majority voting approach was used for final classification. This proposed smartphone-based assessment system addresses limitations of traditional methods, such as inconsistencies due to subjective visual evaluations. This approach supports applications where leg posture is critical, such as in military, sports assessments, and disability certification, by offering an objective and accessible solution. Unlike video-based methods, it leverages widely available mobile technology, offering a low-computation, tamper-proof, and nonintrusive real-time surveillance system. Designed for automated and transparent evaluation, it has the potential to enhance the integrity of physical disability certifications.
References
Ahmedt-Aristizabal, D., Armin, M. A., Hayder, Z., Garcia-Cairasco, N., Petersson, L., Fookes, C., ... & McGonigal, A. (2024). Deep learning approaches for seizure video analysis: A review. Epilepsy & Behavior, 154, Article 109735. https://doi.org/10.1016/j.yebeh.2024.109735
Amjad, A., Qaiser, S., Błaszczyszyn, M., & Szczęsna, A. (2024). The evolution of frailty assessment using inertial measurement sensor‐based gait parameter measurements: A detailed analysis. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 14, Article e1557. https://doi.org/10.1002/widm.1557
.Anikwe, C. V., Nweke, H. F., Ikegwu, A. C., Egwuonwu, C. A., Onu, F. U., Alo, U. R., & Teh, Y. W. (2022). Mobile and wearable sensors for data-driven health monitoring system: State-of-the-art and future prospect. Expert Systems with Applications, 202, Article 117362. https://doi.org/10.1016/j.eswa.2022.117362
Badidi, E., Moumane, K., & El Ghazi, F. (2023). Opportunities, applications, and challenges of edge-AI enabled video analytics in smart cities: a systematic review. IEEE Access, 11, 80543-80572. https://doi.org/10.1109/ACCESS.2023.3300658
Banyam, T., & Rakpongsiri, K. (2024). Designing a low-cost force plate for postural assessment. Journal of Current Science and Technology, 14(3), Article 60. https://doi.org/10.59796/jcst.V14N3.2024.60
Barrett, E. K., Fard, C. M., Katinas, H. N., Moens, C. V., Perry, L. E., Ruddy, B. E., & Boukhechba, M. (2020, April 24). Mobile sensing: Leveraging machine learning for efficient human behavior modeling. In 2020 Systems and Information Engineering Design Symposium (SIEDS) (pp. 1–6). IEEE. https://doi.org/10.1109/SIEDS49339.2020.9106648
Booth, B. M., Mundnich, K., Feng, T., Nadarajan, A., Falk, T. H., Villatte, J. L., ... & Narayanan, S. (2019). Multimodal human and environmental sensing for longitudinal behavioral studies in naturalistic settings: Framework for sensor selection, deployment, and management. Journal of Medical Internet Research, 21(8), Article e12832. https://www.jmir.org/2019/8/e12832
Calcaterra, V., Marin, L., Vandoni, M., Rossi, V., Pirazzi, A., Grazi, R., ... & Zuccotti, G. (2022). Childhood obesity and incorrect body posture: Impact on physical activity and the therapeutic role of exercise. International Journal of Environmental Research and Public Health, 19(24), Article 16728. https://doi.org/10.3390/ijerph192416728.
Casilari-Pérez, E., & García-Lagos, F. (2019). A comprehensive study on the use of artificial neural networks in wearable fall detection systems. Expert Systems with Applications, 138, Article 112811. https://doi.org/10.1016/j.eswa.2019.07.028
Chen, S., Lach, J., Lo, B., & Yang, G. Z. (2016). Toward pervasive gait analysis with wearable sensors: A systematic review. IEEE Journal of Biomedical and Health Informatics, 20(6), 1521-1537. https://doi.org/10.1109/JBHI.2016.2608720
Di Biase, L., Pecoraro, P. M., Pecoraro, G., Shah, S. A., & Di Lazzaro, V. (2024). Machine learning and wearable sensors for automated Parkinson’s disease diagnosis aid: A systematic review. Journal of Neurology, 271(10), 6452–6470. https://doi.org/10.1007/s00415-024-12611-x
Grouios, G., Ziagkas, E., Loukovitis, A., Chatzinikolaou, K., & Koidou, E. (2022). Accelerometers in our pocket: Does smartphone accelerometer technology provide accurate data?. Sensors, 23(1), Article 192. https://doi.org/10.3390/s23010192
Guo, L., Kou, J., & Wu, M. (2022). Ability of wearable accelerometers-based measures to assess the stability of working postures. International Journal of Environmental Research and Public Health, 19(8), Article 4695. https://doi.org/10.3390/ijerph19084695
Kristanto, A., Wati, E., Bariyah, C., & Ma’ruf, F. (2023). The correlation between smartphone use and musculoskeletal symptoms. Journal of Current Science and Technology, 13(2), 326–338. https://doi.org/10.59796/jcst.V13N2.2023.1747
Lalwani, P., & Ganeshan, R. (2024). A novel CNN-BiLSTM-GRU hybrid deep learning model for human activity recognition. International Journal of Computational Intelligence Systems, 17(1), 1–20. https://doi.org/10.1007/s44196-024-00689-0
Liu, B., Tan, X., Jin, Y., Yu, W., & Li, C. (2021). Application of RR-XGBoost combined model in data calibration of micro air quality detector. Scientific Reports, 11(1), Article 15662. https://doi.org/10.1038/s41598-021-95027-1
Minango, P., Flores, A., Minango, J., & Zambrano, M. (2023, October). A comprehensive survey and analysis of CNN-LSTM-based approaches for human activity recognition [Conference presentation]. In G. M. C. Azevedo et al. (Eds.), Proceedings of the Brazilian Technology Symposium (pp. 586–595). Cham, Switzerland: Springer Nature. https://doi.org/10.1007/978-3-031-66961-3_54
Pradeepa, P., & Jeyakumar, M. K. (2022). Data redundancy removal using K-MAD based self-tuning spectral clustering and CKD prediction using ML techniques. Journal of Current Science and Technology, 12(3), 517–537. https://doi.org/10.14456/jcst.2022.40
Prasanth, H., Caban, M., Keller, U., Courtine, G., Ijspeert, A., Vallery, H., & Von Zitzewitz, J. (2021). Wearable sensor-based real-time gait detection: A systematic review. Sensors, 21(8), Article 2727. https://doi.org/10.3390/s21082727
Rakpongsiri, K., Srisurak, K., & Rakpongsiri, P. (2023). Predicting elderly falls using the roll factor in the "Smart Walk Trainer" equipment for body weight-balance analysis. Journal of Current Science and Technology, 13(3), 609–618. https://doi.org/10.59796/jcst.V13N3.2023.978
Ren, L., & Peng, Y. (2019). Research of fall detection and fall prevention technologies: A systematic review. IEEE Access, 7, 77702-77722. https://doi.org/10.1109/ACCESS.2019.2922708
Renani, M. S. (2023). Patient movement monitoring based on IMU and deep learning (Publication No. 2215) [Doctoral dissertation, University of Denver]. Electronic Theses and Dissertations. https://digitalcommons.du.edu/etd/2215
Rezaee, K., Rezakhani, S. M., Khosravi, M. R., & Moghimi, M. K. (2024). A survey on deep learning-based real-time crowd anomaly detection for secure distributed video surveillance. Personal and Ubiquitous Computing, 28(1), 135-151. https://doi.org/10.1007/s00779-021-01586-5
Sabah, R., Lam, M. C., Qamar, F., & Zaidan, B. B. (2024). A BiLSTM-based feature fusion with CNN model: Integrating smartphone sensor data for pedestrian activity recognition. IEEE Access, 12, Article 3468470. https://doi.org/10.1109/ACCESS.2024.3468470
Salchow-Hömmen, C., Skrobot, M., Jochner, M. C., Schauer, T., Kühn, A. A., & Wenger, N. (2022). Emerging portable technologies for gait analysis in neurological disorders. Frontiers in Human Neuroscience, 16, Article 768575. https://doi.org/10.3389/fnhum.2022.768575
Sarmadi, H., Entezami, A., Yuen, K. V., & Behkamal, B. (2023). Review on smartphone sensing technology for structural health monitoring. Measurement, 223, Article 113716. https://doi.org/10.1016/j.measurement.2023.113716
Sharma, S., Sharma, K., & Grover, S. (2024). Real-time data analysis with smart sensors. In Application of artificial intelligence in wastewater treatment. Cham, Switzerland: Springer Nature.
Siaw, T. U., & Han, Y. C. (2024). Necessity of Gyroscopes and Accelerometers in Angle Estimation for Quantitative Physiotherapy Evaluation of Lower Limb Kinematics During Walking. IEEE Sensors Journal, 24(21). 35481-35489. https://doi.org/10.1109/JSEN.2024.3457757
Stenum, J., Hsu, M. M., Pantelyat, A. Y., & Roemmich, R. T. (2024). Clinical gait analysis using video-based pose estimation: multiple perspectives, clinical populations, and measuring change. PLOS Digital Health, 3(3), Article e0000467. https://doi.org/10.1371/journal.pdig.0000467
Sulistianingsih, N., & Martono, G. H. (2024). Comparative study on stock movement prediction using hybrid deep learning model. ECTI-CIT Transactions, 18(4), 531–542. https://doi.org/10.37936/ecti-cit.2024184.256303
Tambe, S. N., Potharaju, S., Amiripalli, S. S., Tirandasu, R. K., & Jaidhan, B. J. (2025). Interdisciplinary research for predictive maintenance of MRI machines using machine learning. Journal of Current Science and Technology, 15(1), Article 78. https://doi.org/10.59796/jcst.V15N1.2025.78
Tasjid, M. S., & Marouf, A. A. (2022). Leveraging smartphone sensors for detecting abnormal gait for smart wearable mobile technologies. International Journal of Interactive Mobile Technologies, 15(24), 167–175. https://doi.org/10.3991/ijim.v15i24.25891
Trautmann, J., Zhou, L., Brahms, C. M., Tunca, C., Ersoy, C., Granacher, U., & Arnrich, B. (2021). Tripod: A treadmill walking dataset with IMU, pressure-distribution and photoelectric data for gait analysis. Data, 6(9), 95. https://doi.org/10.3390/data6090095
Ward, K. (2024). Foundations for clinical assessment in sports and exercise therapy. In Routledge handbook of sports and exercise therapy. London, UK: Routledge. https://doi.org/10.4324/9781003152170
Xiao, X., Yin, J., Xu, J., Tat, T., & Chen, J. (2024). Advances in machine learning for wearable sensors. ACS nano, 18(34), 22734-22751. https://doi.org/10.1021/acsnano.4c05851
Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., & Alshurafa, N. (2022). Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors, 22(4), Article 1476. https://doi.org/10.3390/s22041476
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Journal of Current Science and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
