A Novel Monitoring System for Fall Detection in Older People

Each year, more than 30% of people over 65 years-old suffer some fall. Unfortunately, this can generate physical and psychological damage, especially if they live alone and they are unable to get help. In this field, several studies have been performed aiming to alert potential falls of the older people by using different types of sensors and algorithms. In this paper, we present a novel non-invasive monitoring system for fall detection in older people who live alone. Our proposal is using very-low-resolution thermal sensors for classifying a fall and then alerting to the care staff. Also, we analyze the performance of three recurrent neural networks for fall detections: long short-term memory (LSTM), gated recurrent unit, and Bi-LSTM. As many learning algorithms, we have performed a training phase using different test subjects. After several tests, we can observe that the Bi-LSTM approach overcome the others techniques reaching a 93% of accuracy in fall detection. We believe that the bidirectional way of the Bi-LSTM algorithm gives excellent results because the use of their data is influenced by prior and new information, which compares to LSTM and GRU. Information obtained using this system did not compromise the user’s privacy, which constitutes an additional advantage of this alternative.

[1]  Wei Zheng,et al.  Leveraging Biomedical Resources in Bi-LSTM for Drug-Drug Interaction Extraction , 2018, IEEE Access.

[2]  Jihoon Hong,et al.  A fall detection system using low resolution infrared array sensor , 2014, 2014 IEEE 25th Annual International Symposium on Personal, Indoor, and Mobile Radio Communication (PIMRC).

[3]  N. Ricci,et al.  Falls in the elderly of the Family Health Program. , 2010, Archives of gerontology and geriatrics.

[4]  Weidong Min,et al.  Detection of Human Falls on Furniture Using Scene Analysis Based on Deep Learning and Activity Characteristics , 2018, IEEE Access.

[5]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[6]  S. Iliffe,et al.  Frailty in elderly people , 2013, The Lancet.

[7]  Francesco Piazza,et al.  Acoustic cues from the floor: A new approach for fall classification , 2016, Expert Syst. Appl..

[8]  Michi Yukawa,et al.  Geriatric syndromes and geriatric assessment for the generalist. , 2015, The Medical clinics of North America.

[9]  JingLin Chen,et al.  An Ensemble of Convolutional Neural Networks for Image Classification Based on LSTM , 2017, 2017 International Conference on Green Informatics (ICGI).

[10]  Yuefei Zhu,et al.  A Deep Learning Approach for Intrusion Detection Using Recurrent Neural Networks , 2017, IEEE Access.

[11]  Zhiqi Shen,et al.  Robust unobtrusive fall detection using infrared array sensors , 2017, 2017 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI).

[12]  Fathi M. Salem,et al.  Gate-variants of Gated Recurrent Unit (GRU) neural networks , 2017, 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS).

[13]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[14]  Houshang Darabi,et al.  LSTM Fully Convolutional Networks for Time Series Classification , 2017, IEEE Access.

[15]  E. Peterson,et al.  Falls, aging, and disability. , 2010, Physical medicine and rehabilitation clinics of North America.

[16]  Nabil Zerrouki,et al.  Vision-based fall detection system for improving safety of elderly people , 2017, IEEE Instrumentation & Measurement Magazine.

[17]  W. Sanderson,et al.  The coming acceleration of global population ageing , 2008, Nature.

[18]  M. Tinetti.  Clinical practice. Preventing falls in elderly persons. , 2003, The New England journal of medicine.

[19]  John Angelopoulos,et al.  Assessment of Mortality in Older Trauma Patients Sustaining Injuries from Falls or Motor Vehicle Collisions Treated in Regional Level I Trauma Centers , 2009, Annals of Surgery.

[20]  Luca Maria Gambardella,et al.  Fast image scanning with deep max-pooling convolutional neural networks , 2013, 2013 IEEE International Conference on Image Processing.

[21]  Yu-Lin Jeng,et al.  Development of Home Intelligent Fall Detection IoT System Based on Feedback Optical Flow Convolutional Neural Network , 2018, IEEE Access.

[22]  S. Jackson,et al.  The physiology of ageing , 2013 .

[23]  Yutaka Hata,et al.  A falling detection system with plural thermal array sensors , 2014, 2014 Joint 7th International Conference on Soft Computing and Intelligent Systems (SCIS) and 15th International Symposium on Advanced Intelligent Systems (ISIS).

[24]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[25]  M. C. Ashe,et al.  International comparison of cost of falls in older adults living in the community: a systematic review , 2010, Osteoporosis International.

[26]  D. Oliver,et al.  Preventing falls and fall-related injuries in hospitals. , 2010, Clinics in geriatric medicine.

[27]  D. Canning,et al.  Implications of population ageing for economic growth , 2010 .

[28]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[29]  Jeffrey M. Hausdorff,et al.  Risk factors for falls among older adults: a review of the literature. , 2013, Maturitas.

[30]  Nigel H. Lovell,et al.  Low-Power Fall Detector Using Triaxial Accelerometry and Barometric Pressure Sensing , 2016, IEEE Transactions on Industrial Informatics.

[31]  Xinguo Yu.  Approaches and principles of fall detection for elderly and patient , 2008, HealthCom 2008 - 10th International Conference on e-health Networking, Applications and Services.

[32]  Neil Johnson,et al.  A smart sensor to detect the falls of the elderly , 2004, IEEE Pervasive Computing.

[33]  Jürgen Schmidhuber,et al.  Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition , 2005, ICANN.