Towards an Accelerometer-Based Elderly Fall Detection System Using Cross-Disciplinary Time Series Features

Fall causes trauma or critical injury among the geriatric population which is a second leading accidental cause of post-injury mortality around the world. It is crucial to keep elderly people under supervision by ensuring proper privacy and comfort. Thus the elderly fall detection and prediction using wearable/ non-wearable sensors become an active field of research. In this work, a novel pipeline for fall detection based on wearable accelerometer data has been proposed. Three publicly available datasets have been used to validate our proposed method, and more than 7700 cross-disciplinary time-series features were investigated for each of the datasets. After following a series of feature reduction techniques such as mutual information, removing highly correlated features using the Pearson correlation coefficient, Boruta algorithm, we have obtained the dominant features for each dataset. Different classical machine learning (ML) algorithms were utilized to detect falls based on the obtained features. For individual datasets, the simple ML classifiers achieved very good accuracy. We trained our pipeline with two of the three datasets and tested with the remaining one dataset until all three datasets were used as the test set to show the generalization capability of our proposed pipeline. A set of 39 high-performing features is selected, and the classifiers were trained with them. For all the cases, the proposed pipeline showed excellent efficiency in detecting falls. This architecture performed better than most of the existing works in all the used publicly available datasets, proving the supremacy of the proposed data analysis pipeline.

[1]  Anice Jahanjoo,et al.  Accurate fall detection using 3-axis accelerometer sensor and MLF algorithm , 2017, 2017 3rd International Conference on Pattern Recognition and Image Analysis (IPRIA).

[2]  Iván García-Magariño,et al.  Combining novelty detectors to improve accelerometer-based fall detection , 2017, Medical & Biological Engineering & Computing.

[3]  A K Bourke,et al.  Evaluation of a threshold-based tri-axial accelerometer fall detection algorithm. , 2007, Gait & posture.

[4]  Jonathan F. Bean,et al.  Revisit, Subsequent Hospitalization, Recurrent Fall, and Death Within 6 Months After a Fall Among Elderly Emergency Department Patients , 2017, Annals of emergency medicine.

[5]  Elena I. Gaura,et al.  Data set for fall events and daily activities from inertial sensors , 2015, MMSys.

[6]  C. Medrano,et al.  Detecting Falls as Novelties in Acceleration Patterns Acquired with Smartphones , 2014, PloS one.

[7]  Jesús Francisco Vargas-Bonilla,et al.  Real-Life/Real-Time Elderly Fall Detection with a Triaxial Accelerometer , 2018, Sensors.

[8]  T. Vetter,et al.  Correlation Analysis in Medical Research. , 2020, Anesthesia and analgesia.

[9]  Vera Nadales,et al.  Recognition of Human Motion Related Activities from Sensors , 2010 .

[10]  Jesús Francisco Vargas-Bonilla,et al.  SisFall: A Fall and Movement Dataset , 2017, Sensors.

[11]  María de Lourdes Martínez-Villaseñor,et al.  UP-Fall Detection Dataset: A Multimodal Approach , 2019, Sensors.

[12]  Fouzi Lezzar,et al.  Camera-Based Fall Detection System for the Elderly With Occlusion Recognition , 2020 .

[13]  Abbes Amira,et al.  Fall detection and human activity classification using wearable sensors and compressed sensing , 2019, Journal of Ambient Intelligence and Humanized Computing.

[14]  T. Kennedy The prevention of falls in later life. A report of the Kellogg International Work Group on the Prevention of Falls by the Elderly. , 1987, Danish medical bulletin.

[15]  Eduardo Casilari-Pérez,et al.  A Study on the Application of Convolutional Neural Networks to Fall Detection Evaluated with Multiple Public Datasets , 2020, Sensors.

[16]  Yogesh Angal,et al.  Fall detection system for older adults , 2016, 2016 IEEE International Conference on Advances in Electronics, Communication and Computer Technology (ICAECCT).

[17]  A. Campbell,et al.  Examination by logistic regression modelling of the variables which increase the relative risk of elderly women falling compared to elderly men. , 1990, Journal of clinical epidemiology.

[18]  Zhizeng Luo,et al.  Evaluation of Feature Extraction and Recognition for Activity Monitoring and Fall Detection Based on Wearable sEMG Sensors , 2017, Sensors.

[19]  André Eugenio Lazzaretti,et al.  A Movement Decomposition and Machine Learning-Based Fall Detection System Using Wrist Wearable Device , 2018, IEEE Sensors Journal.

[20]  L. Rubenstein,et al.  Predictors of falls among elderly people. Results of two population-based studies. , 1989, Archives of internal medicine.

[21]  Bogdan Kwolek,et al.  Human fall detection on embedded platform using depth maps and wireless accelerometer , 2014, Comput. Methods Programs Biomed..

[22]  Daniela Micucci,et al.  UniMiB SHAR: a new dataset for human activity recognition using acceleration data from smartphones , 2016, ArXiv.

[23]  Reza Malekian,et al.  Fall detection using machine learning algorithms , 2016, 2016 24th International Conference on Software, Telecommunications and Computer Networks (SoftCOM).

[24]  Laura Montanini,et al.  A Footwear-Based Methodology for Fall Detection , 2018, IEEE Sensors Journal.

[25]  Sebastián Ventura,et al.  Distributed multi-label feature selection using individual mutual information measures , 2020, Knowl. Based Syst..

[26]  D. Rodell,et al.  Rehabilitation of elderly fallers: pilot study of a low to moderate intensity exercise program. , 1996, Archives of physical medicine and rehabilitation.

[27]  Wen-Chang Cheng,et al.  Fall Detection with the Support Vector Machine during Scripted and Continuous Unscripted Activities , 2012, Sensors.

[28]  W. Leslie,et al.  Preventing falls in elderly persons. , 2003, The New England journal of medicine.

[29]  Max A. Little,et al.  Highly comparative time-series analysis: the empirical structure of time series and their methods , 2013, Journal of The Royal Society Interface.

[30]  Petros Daras,et al.  Human Fall Detection from Acceleration Measurements Using a Recurrent Neural Network , 2018 .

[31]  Sabrina Eberhart Falls In Older People Prevention And Management , 2016 .

[32]  Eduardo Casilari-Pérez,et al.  UMAFall: A Multisensor Dataset for the Research on Automatic Fall Detection , 2017, FNC/MobiSPC.

[33]  Muhammad Awais Azam,et al.  Activity-Aware Fall Detection and Recognition Based on Wearable Sensors , 2019, IEEE Sensors Journal.

[34]  Manolis Tsiknakis,et al.  The MobiFall dataset: An initial evaluation of fall detection algorithms using smartphones , 2013, 13th IEEE International Conference on BioInformatics and BioEngineering.

[35]  A. Mallinson,et al.  Community-based exercise program reduces risk factors for falls in 65- to 75-year-old women with osteoporosis: randomized controlled trial. , 2002, CMAJ : Canadian Medical Association journal = journal de l'Association medicale canadienne.

[36]  E. Binder,et al.  Falls in older adults: risk assessment, management and prevention. , 2007, The American journal of medicine.

[37]  Andrea Mannini,et al.  Wearable Inertial Sensing for ICT Management of Fall Detection, Fall Prevention, and Assessment in Elderly , 2018, Technologies.

[38]  Joshua Ellul,et al.  Elderly Fall Detection Systems: A Literature Survey , 2020, Frontiers in Robotics and AI.

[39]  Dong-Soo Kwon,et al.  Cluster-Analysis-Based User-Adaptive Fall Detection Using Fusion of Heart Rate Sensor and Accelerometer in a Wearable Device , 2020, IEEE Access.

[40]  Paulo Vitor de Campos Souza,et al.  Stochastic parallel extreme artificial hydrocarbon networks: An implementation for fast and robust supervised machine learning in high-dimensional data , 2020, Eng. Appl. Artif. Intell..

[41]  Majd Saleh,et al.  Elderly Fall Detection Using Wearable Sensors: A Low Cost Highly Accurate Algorithm , 2019, IEEE Sensors Journal.