Enhanced Human Activity Recognition (HAR) with IMU Sensors in Smartphones: Insights from Machine Learning Models

Yara M. Tahir; Ibrahim I. Hamarash

doi:10.21271/ZJPAS.37.4.9

Authors

Yara M. Tahir Department of Electrical Engineering, College of Engineering, Salahaddin University-Erbil, Erbil, Kurdistan, Iraq. https://orcid.org/0009-0006-6130-3795
Ibrahim I. Hamarash Department of Electrical Engineering, College of Engineering, Salahaddin University-Erbil, Erbil, Kurdistan, Iraq.

DOI:

https://doi.org/10.21271/ZJPAS.37.4.9

Keywords:

Accelerometer, Gyroscope, IMU, Human Activity Recognition (HAR), Machine Learning (ML)

Abstract

Human Activity Recognition (HAR) is the main software component in healthcare, sports, and interactive mobile applications. The accuracy of HAR component is strongly tied with the sensor used for the motion detection and it dictates the overall performance of the application. This paper investigates the use of Inertial Measurement Unit (IMU) sensors embedded in smartphones to investigate the HAR accuracy through machine learning approach. The accelerometer and gyroscope outputs are utilized to classify six human activities: going downstairs, going upstairs, sitting, standing, walking, and running, using Recurrent Neural Network (RNN), Random Forest (RF), and Deep Learning (DL) algorithms. A time series dataset comprising XYZ-axis measurements from accelerometer and gyroscope sensors across four types of smartphones, involving 30 participants is used to train the machine learning (ML) models. To enrich the dataset, sensor filtering, and fusion techniques are employed to evaluate different scenarios. The findings of the study provide significant insights into the capabilities of smartphone-embedded IMUs for HAR in mobile applications.

References

Aminchoudhury, N. & Badalsoni 2024. Wild-SHARD: Smartphone Sensor-based Human Activity Recognition Dataset in Wild. IEEEDataPort.

Anowar, F., Sadaoui, S. & Selim, B. 2021. Conceptual and empirical comparison of dimensionality reduction algorithms (PCA, KPCA, LDA, MDS, SVD, LLE, ISOMAP, LE, ICA, t-SNE). Computer Science Review, 40.

Aziz, N. K., Champion, J. & Hamarash, I. I. 2021. Evaluation of Smartphone’s Embedded Sensors Through Applications: A Case Study of Gyroscope and Accelerometer. UKH Journal of Science and Engineering, 5.

Biagetti, G., Crippa, P., Falaschetti, L., Orcioni, S., Turchetti, C., Biagetti, G., Crippa, P., Falaschetti, L., Orcioni, S. & Turchetti, C. 2018. Human activity monitoring system based on wearable sEMG and accelerometer wireless sensor nodes. BioMedical Engineering OnLine 2018 17:1, 17.

Chenkaixuan, Zhangdalin, Yaolina, Guobin, Yuzhiwen & Liuyunhao 2021. Deep Learning for Sensor-based Human Activity Recognition. ACM Computing Surveys (CSUR), 54.

Dalya Abdullah Anwar. (2021). Real Time Pain Detection Using Facial Action Units in Telehealth System . Zanco Journal of Pure and Applied Sciences, 33(5), 31–42. https://doi.org/10.21271/ZJPAS.33.5.4

Dastan, K. T. 2023. Detecting Falls in a Wheelchair Using Wearable IMU Sensor and Machine Learning Techniques. University of Kurdistan Hewler.

Friedl De Groote, S. V., Florian Vanhevel, Jean-Jacques Orban De Xivry 2021. Validation of a smartphone embedded inertial measurement unit for measuring postural stability in older adults. Gait & Posture, 84.

Gomez-Arrunategui, J. P., Eng, J. J. & Hodgson, A. J. 2022. Monitoring Arm Movements Post-Stroke for Applications in Rehabilitation and Home Settings | IEEE Journals & Magazine | IEEE Xplore. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 30.

Goodfellow, I., Bengio, Y. & Courville, A. 2016. Deep Learning.

Gu, C., Lin, W., He, X., Zhang, L. & Zhang, M. 2023. IMU-based motion capture system for rehabilitation applications: A systematic review. Biomimetic Intelligence and Robotics, 3.

Gupta, S. 2021. Deep learning based human activity recognition (HAR) using wearable sensor data. International Journal of Information Management Data Insights, 1.

Haider, C., & Ali, A. (2022). Comprehensive Study for Breast Cancer Using Deep Learning and Traditional Machine Learning . Zanco Journal of Pure and Applied Sciences, 34(2), 22–36. https://doi.org/10.21271/ZJPAS.34.2.3

Haoran Duan , S. W., Varun Ojha, Shizheng Wang, Yawen Huang, Yang Long, Rajiv Ranjan, Yefeng Zheng 2024. Wearable-based behaviour interpolation for semi-supervised human activity recognition. Information Sciences, 665.

Hasan, D. S., Crane III, C., & Hamarash, I. I. (2019). Using Inertia Sensors for Orientation Estimation of Robot Manipulators. Zanco Journal of Pure and Applied Sciences, 33 (s3). https://doi.org/10.21271/ZJPAS.31.s3.44

Li, S., Zhu, T., Duan, F., Chen, L., Ning, H., Nugent, C., & Wan, Y. (2025). HARMamba: Efficient and Lightweight Wearable Sensor Human Activity Recognition Based on Bidirectional Mamba. IEEE Internet of Things Journal, 12(3), 2373–2384. https://doi.org/10.1109/JIOT.2024.3463405

Liu, X., Zhang, X., Zhang, B., Zhou, B., He, Z. & Liu, T. 2024. An IMU-Based Ground Reaction Force Estimation Method and Its Application in Walking Balance Assessment | IEEE Journals & Magazine | IEEE Xplore. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 32.

Mannini, A., Intille, S. S., Rosenberger, M., Sabatini, A. M. & Haskell, W. 2013. Activity recognition using a single accelerometer placed at the wrist or ankle. Medicine and science in sports and exercise, 45.

Moshood A. Hambali, T. O. O., Kayode S. Adewole, Arun Kumar Sangaiah & Wei Gao 2022. Feature selection and computational optimization in high-dimensional microarray cancer datasets via InfoGain-modified bat algorithm. Multimedia Tools and Applications, 81, 36505–36549.

Nasrabadi, A. M., Eslaminia, A. R., Bakhshayesh, P. R., Ejtehadi, M., Alibiglou, L. & Behzadipour, S. 2022. A new scheme for the development of IMU-based activity recognition systems for telerehabilitation. Medical Engineering & Physics, 108.

O’brien, M. K., Shin, S. Y., Khazanchi, R., Fanton, M., Lieber, R. L., Ghaffari, R., Rogers, J. A. & Jayaraman, A. 2022. Wearable Sensors Improve Prediction of Post-Stroke Walking Function Following Inpatient Rehabilitation | IEEE Journals & Magazine | IEEE Xplore. IEEE Journal of Translational Engineering in Health and Medicine, 10.

Oliveira, N., Park, J. & Barrance, P. 2023. Using Inertial Measurement Unit Sensor Single Axis Rotation Angles for Knee and Hip Flexion Angle Calculations During Gait | IEEE Journals & Magazine | IEEE Xplore. IEEE Journal of Translational Engineering in Health and Medicine, 11.

Pantelopoulos, A. & Bourbakis, N. 2008. A survey on wearable biosensor systems for health monitoring | IEEE Conference Publication | IEEE Xplore. 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

Safwan Mahmood Al-Selwi , M. F. H., Said Jadid Abdulkadir, Amgad Muneer, Ebrahim Hamid Sumiea, Alawi Alqushaibi, Mohammed Gamal Ragab 2024. RNN-LSTM: From applications to modeling techniques and beyond—Systematic review. Journal of King Saud University - Computer and Information Sciences, 36.

Salem, F. M. 2022. Recurrent Neural Networks: From Simple to Gated Architectures.

Saputra, N. A., Riza, L. S., Setiawan, A. & Hamidah, I. 2024. A Systematic Review for Classification and Selection of Deep Learning Methods. Decision Analytics Journal, 12.

Schneider, P. & Xhafa, F. 2022. Machine learning: ML for eHealth systems. Anomaly Detection and Complex Event Processing over IoT Data Streams.

Shkel, A. M. & Wang, Y. 2021. Inertial Sensors and Inertial Measurement Units | part of Pedestrian Inertial Navigation with Self-Contained Aiding | Wiley-IEEE Press books | IEEE Xplore.

Soangra, R., Wen, Y., Yang, H. & Grant-Beuttler, M. 2022. Classifying Toe Walking Gait Patterns Among Children Diagnosed With Idiopathic Toe Walking Using Wearable Sensors and Machine Learning Algorithms | IEEE Journals & Magazine | IEEE Xplore. IEEE Access, 10.

Varoquaux, G. & Colliot, O. 2023. Evaluating Machine Learning Models and Their Diagnostic Value. Machine Learning for Brain Disorders.

Vincenzo Dentamaro, V. G., Donato Impedovo , Fabio Manca 2024. Human activity recognition with smartphone-integrated sensors: A survey. Expert Systems with Applications, 246.

Zhang, L., Liu, Y.-A., Wang, Q., Chen, H., Xu, J., & Li, D. (2025). A Fall Detection Device Based on Single Sensor Combined with Joint Features. Tsinghua Science and Technology, 30(2), 695–707. https://doi.org/10.26599/TST.2023.9010129.