journal article·2022-07-19Open access

A Pilot Study of the Efficiency of LSTM-Based Motion Classification Algorithms Using a Single Accelerometer

Kyu-Young Kang, Seul-Gi Lee, Hyeon Kang, Jung-Gil Kim, Gye-Rae Tack, Jin-Seung Choi

Applied Sciences· Volume 12· Issue 14

Abstract

Inertial sensors are widely used for classifying the motions of daily activities. Although hierarchical classification algorithms were commonly used for defined motions, deep-learning models have been used recently to classify a greater diversity of motions. In addition, ongoing studies are actively investigating algorithm efficiency (e.g., training time and accuracy). Thus, a deep-learning model was constructed in this study for the classification of a given motion based on the raw data of inertial sensors. Furthermore, the number of epochs (150, 300, 500, 750, and 900) and hidden units (100, 150, and 200) were varied in the model to determine its efficiency based on training time and accuracy, and the optimum accuracy and training time was determined. Using a basic long short-term memory (LSTM), which is a neural network known to be suitable for sequential data, the data classification training was conducted on a common desktop PC with typical specifications. The results show that the accuracy was the highest (99.82%) with 150 hidden units and 300 epochs, while the training time was also relatively short (78.15 min). In addition, the model accuracy did not always increase even when the model complexity was increased (by increasing the number of epochs and hidden units) and the training time increased as a consequence. Hence, through suitable combinations of the two factors that constitute deep-learning models according to the data, the potential development and use of efficient models have been verified. From the perspective of training optimization, this study is significant in having determined the importance of the conditions for hidden units and epochs that are suitable for the given data and the adverse effects of overtraining.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Context-Aware Activity Recognition Systems · Non-Invasive Vital Sign Monitoring · Human Mobility and Location-Based Analysis

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Department of Biomedical Engineering, Konkuk University, Chungju 27478, Korea

Research Institute of Biomedical Engineering, Konkuk University, Chungju 27478, Korea

Funding

the National Research Foundation of Korea

References (30)

Show source-provided references
1. Ability of Thigh-Worn ActiGraph and activPAL Monitors to Classify Posture and Motion10.1249/MSS.0000000000000497 ↗
2. Li, L., Xieb, Z., Liangc, Y., Horreyd, W., and Xu, X. (2019, January 24–27). Recognition of manual driving distraction through deep-learning and wearable sensing. Proceedings of the 10th International Driving Symposium on Human Factors in Driver Assessment, Training and Vehicle Design, Santa Fe, NM, USA.10.17077/drivingassessment.1670 ↗
3. Recognition of Human Hand Activities Based on a Single Wrist IMU Using Recurrent Neural Networks
4. Kreuzer, D., and Munz, M. (2021). Deep Convolutional and LSTM Networks on Multi-Channel Time Series Data for Gait Phase Recognition. Sensors, 21.10.3390/s21030789 ↗
5. Human Activity Recognition with Smartphone and Wearable Sensors Using Deep Learning Techniques: A Review10.1109/JSEN.2021.3069927 ↗
6. Um, T.T., Babakeshizadeh, V., and Kulic, D. (2017, January 24–28). Exercise motion classification from large-scale wearable sensor data using convolutional neural networks. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada.10.1109/IROS.2017.8206051 ↗
7. Deep Learning Models for Real-time Human Activity Recognition with Smartphones10.1007/s11036-019-01445-x ↗
8. Human activity recognition with smartphone sensors using deep learning neural networks10.1016/j.eswa.2016.04.032 ↗
9. Brain wave classification using long short-term memory network based OPTICAL predictor
10. Rajagukguk, R.A., Ramadhan, R.A.A., and Lee, H.J. (2020). A Review on Deep Learning Models for Forecasting Time Series Data of Solar Irradiance and Photovoltaic Power. Energies, 13.10.3390/en13246623 ↗
11. A survey on deep learning for human activity recognition
12. Zhang, S., Li, Y., Zhang, S., Shahabi, F., Xia, S., Deng, Y., and Alshurafa, N. (2022). Deep learning in human activity recognition with wearable sensors: A review on advances. Sensors, 22.10.3390/s22041476 ↗
13. Lgorithm and modeling of stock prices forecasting based on long short-term memory (LSTM)
14. Multivariate Time-Series Classification Using the Hidden-Unit Logistic Model10.1109/TNNLS.2017.2651018 ↗
15. Long short-term memory-Fully connected (LSTM-FC) neural network for PM2.5 concentration prediction10.1016/j.chemosphere.2018.12.128 ↗
16. Deep Learning-Based Motion Activity Recognition Using Smartphone Sensors
17. Effective inertial sensor quantity and locations on a body for deep learning-based worker’s motion recognition10.1016/j.autcon.2020.103126 ↗
18. Bouktif, S., Fiaz, A., Ouni, A., and Serhani, M.A. (2018). Optimal Deep Learning LSTM Model for Electric Load Forecasting using Feature Selection and Genetic Algorithm: Comparison with Machine Learning Approaches. Energies, 11.10.3390/en11071636 ↗
19. Chung, S., Lim, J., Noh, K.J., Kim, G., and Jeong, H. (2019). Sensor data acquisition and multimodal sensor fusion for human activity recognition using deep learning. Sensors, 19.10.3390/s19071716 ↗
20. A lightweight deep learning model for human activity recognition on edge devices10.1016/j.procs.2020.03.289 ↗
21. Deep-learning-enhanced human activity recognition for Internet of healthcare things10.1109/JIOT.2020.2985082 ↗
22. Smartphone and smartwatch-based biometrics using activities of daily living10.1109/ACCESS.2019.2940729 ↗
23. Oluwalade, B., Neela, S., Wawira, J., Adejumo, T., and Purkayastha, S. (2021, January 11–13). Human Activity Recognition using Deep Learning Models on Smartphones and Smartwatches Sensor Data. Proceedings of the HEALTHINF 2021—14th International Conference on Health Informatics, Online.10.5220/0010325906450650 ↗
24. Deep learning based human activity recognition (HAR) using wearable sensor data
25. Pienaar, S.W., and Malekian, R. (2019, January 18–20). Human Activity Recognition using LSTM-RNN Deep Neural Network Architecture. Proceedings of the 2019 IEEE 2nd Wireless Africa Conference (WAC), Pretoria, South Africa.10.1109/AFRICA.2019.8843403 ↗
26. Deep learning for sensor-based activity recognition: A survey10.1016/j.patrec.2018.02.010 ↗
27. A systematic review of smartphone-based human activity recognition methods for health research10.1038/s41746-021-00514-4 ↗
28. Trends in human activity recognition using smartphones10.1007/s40860-021-00147-0 ↗
29. Examining the validity of the ActivPAL monitor in measuring posture and ambulatory movement in children10.1186/1479-5868-9-119 ↗
30. Using Activity Monitors to Measure Sit-to-Stand Transitions in Overweight/Obese Youth10.1249/MSS.0000000000001266 ↗