A Fall Detection Technique using Features from Multiple Sliding Windows
4
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
In recent years, falls among elderly people have gained serious attention as a major cause of injuries. Falls often lead to fatal consequences due to lack of prompt response and rescue. Therefore, a moreaccurate fall detection system and an effective feature extraction technique are required to preventand reduce the risk of such incidents. In this paper, we proposed an efficient feature extractiontechnique based on multiple sliding windows and validated it through a series of experiments usingsupervised learning algorithms. The experiments were conducted using the public datasets obtainedfrom tri-axial accelerometers. The results depicted that extraction of the feature from adjacentsliding windows led to high accuracy in supervised machine learning-based fall detection. Also, theexperiments conducted in this study suggested that the best accuracy can be achieved by keepingthe window size as small as 2 seconds. With the kNN classifier and dataset from wearable sensors,the experiments achieved accuracy rates of 94%.
Abstract
In recent years, falls among elderly people have gained serious attention as a major cause of injuries. Falls often lead to fatal consequences due to lack of prompt response and rescue. Therefore, a moreaccurate fall detection system and an effective feature extraction technique are required to preventand reduce the risk of such incidents. In this paper, we proposed an efficient feature extractiontechnique based on multiple sliding windows and validated it through a series of experiments usingsupervised learning algorithms. The experiments were conducted using the public datasets obtainedfrom tri-axial accelerometers. The results depicted that extraction of the feature from adjacentsliding windows led to high accuracy in supervised machine learning-based fall detection. Also, theexperiments conducted in this study suggested that the best accuracy can be achieved by keepingthe window size as small as 2 seconds. With the kNN classifier and dataset from wearable sensors,the experiments achieved accuracy rates of 94%.
참고문헌 (19)
- "Falls" (2018)[URL]
- Mao A., "Highly portable, Sensor-Based System for Human Fall Monitoring, Sensors", Sensors (2017)
- He, J., "An unobtrusive fall detection and alerting system based on Kalman filter and Bayes network classifier", Sensors (2017)
- Putra, P., "An Event Triggered Machine Learning Approach for Accelerometer-Based Fall Detection", Sensors (2018)
- Diep, N., "A classifier based approach to real-time fall detection using low-cost wearable sensors", Proc. Of International Conference on Soft Computing and Pattern Recognition(SoCPaR), pp.105~110 (2013)
- Dinh, C., "A New Real-time Fall Detection Approach Using Fuzzy and neural network", Proc. Of International Conference on Wearable Micro and Nano Technologies for Personalized Health, pp.57~60 (2009)
- Putra, P., "Window-size impact on detection rate of wearable-sensor based fall detection using supervised machine learning", Proc. Of IEEE Life Sciences Conference, pp.21~26 (2017)
- Li, Q., "Accurate, Fast Fall Detection using Gyroscopes and Accelerometer Derived Posture Information", Body Sensor Network, International Workshop on Wearable and Implantable Body Sensor Networks, pp.138~143 (2009)
- Lindemann, U., "Evaluation of a Fall Detector Based on Accelerometers: A Pilot Study", Med. Biol. Eng. Coput., 43, pp.548~551 (2005)
- Bagala, F., "Evaluation of Accelerometer-based Fall Detection Algorithms on Real-world Falls", PLoS ONE (2012)
- Ojetola, O., "Fall Detection with Wearable Sensors-SAFE (SmArt Fall dEtection)", Proc. Of International Conference on Intelligent Environments(IE), pp.318~321 (2011)
- Tong L., "HMM-Based Human Fall Detection and Prediction Method Using Tri-Axial Accelerometer", IEEE Sens. J., 13(1), pp.1249~1256 (2013)
- Habib, M.A., "Smartphone-Based Solutions for Fall Detection and Prevention: Challenges and Open Issues", Sensors, 14, pp.7181~7208 (2014)
- 김태웅, "빅데이터 기반의 가속도 신호를 이용한 집단 행동패턴 및 활동성 분석 시스템", 스마트미디어저널, 6(3), pp.83~88 (2017), (사)한국스마트미디어학회
- 이영훈, "Mi Band와 MongoDB를 사용한 생체정보 빅데이터 시스템의 설계", 스마트미디어저널, 5(4), pp.124~130 (2016), (사)한국스마트미디어학회
- Kangas, M., "Sensitivity and Specificity of Fall Detection in People Aged 40 Years and Over", Gait Posture, 29(4), pp.571~574 (2009)
- Ojetola, O., "Data Set for Fall Events and Daily Activities from Inertial Sensors", Proc. Of ACM Multimedia Systems Conference, pp.243~248 (2015)
- Pedregosa, F., "Scikit-learn: Machine Learning in Python", Journal of Machine Learning Research, 12, pp.2825~2830 (2011)
- Gjoreski, M., "Accelerometer Placement for Posture Recognition and Fall Detection", Proc. Of International Conference on Intelligent Environment(IE), pp.47~54 (2011)