Fall Detector Using Discrete Wavelet Decomposition And SVM Classifier

• Autorzy: Wójtowicz B. , Dobrowolski A. , Tomczykiewicz K.

Identyfikatory

DOI

10.1515/mms-2015-0026

• Języki publikacji: EN

Abstrakty

EN

This paper presents the design process and the results of a novel fall detector designed and constructed at the Faculty of Electronics, Military University of Technology. High sensitivity and low false alarm rates were achieved by using four independent sensors of varying physical quantities and sophisticated methods of signal processing and data mining. The manuscript discusses the study background, hardware development, alternative algorithms used for the sensor data processing and fusion for identification of the most efficient solution and the final results from testing the Android application on smartphone. The test was performed in four 6-h sessions (two sessions with female participants at the age of 28 years, one session with male participants aged 28 years and one involving a man at the age of 49 years) and showed correct detection of all 40 simulated falls with only three false alarms. Our results confirmed the sensitivity of the proposed algorithm to be 100% with a nominal false alarm rate (one false alarm per 8 h).

Słowa kluczowe

EN

fall detection; discrete wavelet transform; data fusion; support vector machine (SVM)

• Wydawca: Komitet Metrologii i Aparatury Naukowej PAN
• Czasopismo: Metrology and Measurement Systems
• Rocznik: 2015
• Tom: Vol. 22, nr 2
• Strony: 303--314
• Opis fizyczny: Bibliogr. 21 poz., rys., tab., wykr.

Twórcy

autor

Wójtowicz B.

• Military University of Technology, Faculty of Electronics, Kaliskiego 2, 00-908 Warsaw, Poland

autor

Dobrowolski A.

• Military University of Technology, Faculty of Electronics, Kaliskiego 2, 00-908 Warsaw, Poland

autor

Tomczykiewicz K.

• Military Institute of Health Service, Department of Neurology, Szaserów 128, 04-141 Warsaw, Poland

Bibliografia

• [1] Nyan, M.N., Tay, F.E.H., Koh, T.H., Sitoh, Y.Y., Tan, K.L. (2004). Location and sensitivity comparison of MEMS accelerometers in signal identification for ambulatory monitoring. Electron. Components Technol., 1(1-4), 956-960.
• [2] Shi, G., Chan, C.S., Li, W.J., Leung, K., Zou, Y., Jin, Y. (2009). Mobile Human Airbag System for Fall Protection Using MEMS Sensors and Embedded SVM Classifier. The IEEE Sens. J., 9(5), 495-503.
• [3] Szpringer, M., Wybraniec-Lewicka, B., Czerwiak, G., Michalska, M., Krawczyńska, J.(2008). Falls and injuries in geriatric age, Medical Studies, 9, 77-81.
• [4] Edbom-Kolarz, A., Marcinkowski, J.T. (2011). Falls of elderly people - causes, consequences, prevention. Hygeia Public Health, 313-318.
• [5] Rubenstein, L.Z., Josephson, K.R. (2006). Falls and their prevention in elderly people: What does the evidence show? Medical Clinics of North America, 90(5), 807-824.
• [6] Bourke, A.K., Lyons, G.M. (2008). A threshold-based fall-detection algorithm using a biaxial gyroscope sensor. Medical Engineering and Physics, 30(1), 84-90.
• [7] Rigler, S.K. (1999). Preventing falls in older adults. Hospital Pract.
• [8] Simpson, J.M. (1993). Elderly people at risk of falling: the role of muscle weakness. Physiother.
• [9] Thornby, M.A. (1995) Balance and falls in the frail older person: a review of the literature. Topics in Geriatric Rehabilitation.
• [10] Kalache, A., Fu, D.(2007). WHO Global Report on Falls Prevention in Older Age. WHO.
• [11] Wójtowicz, B., Dobrowolski, A. (2013). Multisensor data integrator to detect uncontrolled falls. Bulletin of the Military University of Technology, Warsaw, 62(4), 229-240.
• [12] Wójtowicz, B., Dobrowolski, A. (2014). Wireless falls detector. Electronics - constructions, technologies, applications, 55(3), 72-75.
• [13] Wójtowicz, B., Dobrowolski, A. (2014). Falls detector based on discrete wavelet transform and independent SVM classifiers. Electronics - constructions, technologies, applications, 55(3), 22-26.
• [14] Rubenstein, L.Z., Josephson, K.R. (2005). Fall risk assessment: step-by-step. In J.M. Hausdorffa, N.B. Alexandra (editors). Gait disorders: evaluation and management. Taylor & Francis, 169-184.
• [15] Schwickert, L., Becker, C., Lindemann, U., Maréchal, C., Bourke, A.K., Chiari, L., Helbostad, J.L., Zijlstra, W., Aminian, K., Todd, C., Bandinelli, S., Klenk, J. (2013). Fall detection with body-worn sensors: A systematic review.Zeitschrift für Gerontologie und Geriatrie, 46(8), 706-719.
• [16] Dobrowolski, A., Wierzbowski, M., Tomczykiewicz, K. (2012). Multiresolution MUAPs decomposition and SVM-based analysis in the classification of neuromuscular disorders. Computer Methods and Programs in Biomedicine, 107(3), 393-403.
• [17] Kalinowski, P., Woźniak, L., Strzelczyk, A., Jasiński, P., Jasiński, G. (2013). Efficiency of linear and non-linear classifiers for gas identification from electrocatalytic gas sensor. Metrol. Meas. Syst., 20(3), 501-512.
• [18] Wójtowicz, B., Dobrowolski, A. (2014). Multisensory falls detector using discrete wavelet decomposition and SVM classifier. Measurement Automation and Monitoring, 60(9), 729-732.
• [19] Smith, S. (2002). Digital Signal Processing: A Practical Guide for Engineers and Scientists. Newnes.
• [20] Li, H., Jiang, T. (2005), A class of edit kernels for SVMs to predict translation initiation sites in eukaryotic mRNAs. Journal of Computational Biology, 12(6), 702-718.
• [21] Bakir, G.H., Bottou, L., Weston, J. (2005). Breaking svm complexity with cross-training. Saul, L.K., Weiss, Y., Bottou, L., (eds.). Advances in Neural Information Processing Systems 17. MIT Press, 81-88.