Physical Violence Detection with Movement Sensors
With the development of movement sensors, activity recognition becomes more and more popular. Compared with daily-life activity recognition, physical violence detection is more meaningful and valuable. This paper proposes a physical violence detecting method. Movement data of acceleration and gyro are gathered by role playing of physical violence and daily-life activities. Time domain features and frequency domain ones are extracted and filtered to discribe the differences between physical violence and daily-life activities. A specific BPNN trained with the L-M method works as the classifier. Altogether 9 kinds of activities are involved. For 9-class classification, the average recognition accuracy is 67.0%, whereas for 2-class classification, i.e. activities are classified as violence or daily-life activity, the average recognition accuracy reaches 83.7%.
KeywordsPhysical violence detection Activity recognition Movement sensor
This paper was supported by the National Natural Science Foundation of China (61602127), and partly supported by the Directorate General of Higher Education, Indonesia (2142/E4.4/K/2013), and the Finnish Cultural Foundation, North Ostrobothnia Regional Fund.
The authors would like to thank Tuija Huuki, Vappu Sunnari, Seppo Laukka and Antti Siipo from University of Oulu, Finland, teachers Taina Aalto and Pekka Kurttila and principal Maija Laukka from Oulunlahti School, Finland, pupils from 2nd and 6th grades of Oulunlahti School, Tian Han and Zhu Zhang from Harbin University of Science and Technology, China, Yubo Zhang, Jifu Shi and Zhi Xun from Harbin Institute of Technology, China for their assistance to this work.
- 1.Cheng, L., Yu, Y., Liu, X., Su, J., Guan, Y.: Recognition of human activities using fast and adaptive sparse representation based on wearable sensors. In: 2017 16th IEEE International Conference on Machine Learning and Applications, pp. 944–949 (2017)Google Scholar
- 2.Nakano, K., Chakraborty, B.: Effect of dynamic feature for human activity recognition using smartphone sensors. In: 2017 IEEE 8th International Conference on Awareness Science and Technology (ICAST), pp. 539–543 (2017)Google Scholar
- 3.Hegde, N., Bries, M., Swibas, T., et al.: Automatic recognition of activities of daily living utilizing insole based and wrist worn wearable sensors. IEEE J. Biomed. Health Inform. 99, 1–9 (2018)Google Scholar
- 6.Ye, L., Ferdinando, H., Seppänen, T., et al.: An instance-based physical violence detection algorithm for school bullying prevention. In: 2015 International Wireless Communications and Mobile Computing Conference (IWCMC), Dubrovnik, Croatia, pp. 1384–1388 (2015)Google Scholar
- 8.Ferdinando, H., Seppänen, T., Alasaarela, E.: Enhancing emotion recognition from ECG signals using supervised dimensionality reduction. In: Proceeding of 6th International Conference on Pattern Recognition Applications and Methods (ICPRAM), 24–26 February 2017, Porto, Portugal, pp. 112–118 (2017)Google Scholar
- 9.Ferdinando, H., Ye, L., Seppänen, T., et al.: Emotion recognition by heart rate variability. Aust. J. Basic Appl. Sci. 8(10), 50–55 (2014)Google Scholar
- 10.El Aboudi, N., Benhlima, L.: Review on wrapper feature selection approaches. In: 2016 International Conference on Engineering and MIS (ICEMIS), pp. 1–5 (2016)Google Scholar
- 11.Huang, Z., Wang, W.: Multi-sensor fusion based on BPNN in quadruped ground classification. In: 2017 IEEE International Conference on Mechatronics and Automation (ICMA), pp. 1620–1625 (2017)Google Scholar
- 12.Bengang, W., Xinye, W., Zhoufei, Y., et al.: A method of optimized neural network by L-M algorithm to transformer winding hot spot temperature forecasting. In: 2017 IEEE Electrical Insulation Conference (EIC), pp. 87–91 (2017)Google Scholar