A fall detection algorithm based on pattern recognition and human posture analysis

• Published in: ICCTA 2011 : IET International Conference on Communication Technology and Application : 14-16 October 2011 pp. 853 - 857
• Main Authors: Huang, Cheng, Luo, Haiyong, Zhao, Fang
• Format: Conference Proceeding
• Language: English
• Published: Stevenage IET 2011; The Institution of Engineering & Technology
• Subjects: Computer vision and image processing techniques; Image recognition; Knowledge engineering techniques; Markov processes; Medical administration; Sensing devices and transducers; high false positive rate; support vector machines; high false negative rate; hidden Markov model; data mining; object detection; healthcare application; hidden Markov models; sensor network; feature extraction; fall detection algorithm; human posture analysis; one-class support vector machine; accelerometers; security monitoring; medical administrative data processing; data mining method; temporal feature; health care; image recognition; pattern recognition
• ISBN: 9781849194709; 184919470X
• DOI: 10.1049/cp.2011.0790

Detecting fall is a particular important task in security monitoring and healthcare applications of sensor networks. However traditional approaches suffer from either a high false positive rate or high false negative rate, especially when the collected sensor data are unbalanced. Therefore, there is a lack of tradeoff between false alarms and misses for many traditional data mining methods to be applied. To solve this problem a novel fall detection algorithm based on pattern recognition and human posture analysis is presented in this paper. It firstly extracts thirty temporal features from the original data traces for different length adaptation of samples, and then exploits Hidden Markov Model (HMM) to filter the noisy character data and reduce the dimension of feature vectors. After that, it performs a closer classification with one-class Support Vector Machine (OCSVM) to filter the high false positive samples, and finally applies posture analysis to counteract the effects of high false negative samples until a satisfying accuracy is achieved. Simulation with real data demonstrates that the proposed algorithm outperforms other existing approaches.