Real-Time Detection of At-Risk Movements Using Smartwatch IMU Sensors
Source abstract
Abstract
The issue of personal safety for crime prevention has become a significant societal concern. Existing software on smartwatches developed for personal protection might provide GPS location tracking and emergency reporting, but this is limited to proactively detecting and responding to actual at-risk situations. This paper presents a real-time motion detection algorithm for smartwatches that utilizes an accelerometer to identify at-risk movements when a wearer is under threat. Daily activities, including walking, running, desk work, and being threatened, are distinguished by a machine learning-based alarm application. A total of 5534 data points across four classes were collected from experiments. The proposed 1D-CNN model exhibited the highest performance in comparison with SVM, k-NN, random forest, SGD. Additionally, our comparative analysis of using time-domain versus frequency-domain data in machine learning revealed that frequency-domain features offer advantages in both accuracy and real-time performance. Finally, the proposed inference model was implemented as a smartwatch application that can detect at-risk situations in real time. The application was tested in real-world scenarios, showcasing the effectiveness of personal safety.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Context-Aware Activity Recognition Systems · Anomaly Detection Techniques and Applications · Energy Efficient Wireless Sensor Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of AI Convergence, Sungshin Women’s University, 34 da-gil 2, Bomun-ro, Seongbuk-gu, Seoul 02844, Republic of Korea
Funding
Korean National Police Agency (KNPA, Korea)
References (22)
Show source-provided references
1. A study on improvement direction for personal safety measures for crime victims
2. The Current Legal Problems and an Improvement of Personal Protection System of Police for Crime Victim and Witness
3. A Study on the Perception and Improvement of Police Personal Protection Service of Crime Victims10.24055/kaps.22.1.11 ↗
4. Maglogiannis, I.L., Papadopoulos, H., Sioutas, S., and Makris, C. (2014). Fall Detection Using Commodity Smart Watch and Smart Phone. Artificial Intelligence Applications and Innovations, Springer.10.1007/978-3-662-44654-6_7 ↗
5. 3D Indoor Relative Position Estimation Method Based on Multi-agent UWB-IMU Fusion10.5302/J.ICROS.2023.23.0110 ↗
6. Khojasteh, S.B., Villar, J.R., Chira, C., González, V.M., and De la Cal, E. (2018). Improving fall detection using an on-wrist wearable accelerometer. Sensors, 18.10.3390/s18051350 ↗
7. Sharma, S., Salunke, D., Haldar, E., Mandlik, R., and Salke, N. (2022, January 24–26). A comprehensive survey on IoT based smart safety devices for women. Proceedings of the 2022 International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), Trichy, India.10.1109/ICAISS55157.2022.10010784 ↗
8. The Role of IoT in Woman’s Safety: A Systematic Literature Review10.1109/ACCESS.2023.3252903 ↗
9. Detection of important features and comparison of datasets for fall detection based on wrist-wearable devices10.1016/j.eswa.2023.121034 ↗
10. Jatesiktat, P., and Ang, W.T. (2017, January 11–15). An elderly fall detection using a wrist-worn accelerometer and barometer. Proceedings of the 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Seogwipo, Republic of Korea.10.1109/EMBC.2017.8036778 ↗
11. Usmani, S., Saboor, A., Haris, M., Khan, M.A., and Park, H. (2021). Latest Research Trends in Fall Detection and Prevention Using Machine Learning: A Systematic Review. Sensors, 21.10.3390/s21155134 ↗
12. Sivakumar, P. (2021, January 30–31). Real time crime detection using deep learning algorithm. Proceedings of the 2021 International Conference on System, Computation, Automation and Networking (ICSCAN), Puducherry, India.10.1109/ICSCAN53069.2021.9526393 ↗
13. Detection of Dangerous Situations using Deep Learning Model with Relational Inference10.33851/JMIS.2020.7.3.205 ↗
14. Ito, C., Cao, X., Shuzo, M., and Maeda, E. (2018, January 8–12). Application of CNN for Human Activity Recognition with FFT Spectrogram of Acceleration and Gyro Sensors. Proceedings of the 2018 ACM International Joint Conference and 2018 International Symposium on Pervasive and Ubiquitous Computing and Wearable Computers, Singapore.10.1145/3267305.3267517 ↗
15. Lee, S., Yoon, S., and Cho, H. (2017, January 13–16). Human activity recognition from accelerometer data using convolutional neural network. Proceedings of the 2017 IEEE International Conference on Big Data and Smart Computing (BigComp), Jeju, Republic of Korea.
16. (2024, December 09). Post-Training Quantization. Available online: https://ai.google.dev/edge/litert/models/post_training_quantization.
17. (2024, December 09). SVC. Available online: https://scikit-learn.org/1.5/modules/generated/sklearn.svm.SVC.html#sklearn.svm.SVC.
18. (2024, December 09). KNeighborsClassifier. Available online: https://scikit-learn.org/1.5/modules/generated/sklearn.neighbors.KNeighborsClassifier.html.
19. (2024, December 09). RandomForestClassifier. Available online: https://scikit-learn.org/1.5/modules/generated/sklearn.ensemble.RandomForestClassifier.html.
20. (2024, December 09). SGDClassifier. Available online: https://scikit-learn.org/1.5/modules/generated/sklearn.linear_model.SGDClassifier.html.
21. A review of sparsity-based clustering methods10.1016/j.sigpro.2018.02.010 ↗
22. Yi, K., Zhang, Q., Cao, L., Wang, S., Long, G., Hu, L., He, H., Niu, Z., Fan, W., and Xiong, H. (2023). A Survey on Deep Learning based Time Series Analysis with Frequency Transformation. arXiv.