Combining novelty detectors to improve accelerometer-based fall detection

Research on body-worn sensors has shown how they can be used for the detection of falls in the elderly, which is a relevant health problem. However, most systems are trained with simulated falls, which differ from those of the target population. In this paper, we tackle the problem of fall detection using a combination of novelty detectors. A novelty detector can be trained only with activities of daily life (ADL), which are true movements recorded in real life. In addition, they allow adapting the system to new users, by recording new movements and retraining the system. The combination of several detectors and features enhances performance. The proposed approach has been compared with a traditional supervised algorithm, a support vector machine, which is trained with both falls and ADL. The combination of novelty detectors shows better performance in a typical cross-validation test and in an experiment that mimics the effect of personalizing the classifiers. The results indicate that it is possible to build a reliable fall detector based only on ADL.

[1]  Shehroz S. Khan,et al.  X-Factor HMMs for Detecting Falls in the Absence of Fall-Specific Training Data , 2014, IWAAL.

[2]  Ling Shao,et al.  A survey on fall detection: Principles and approaches , 2013, Neurocomputing.

[3]  Inmaculada Plaza,et al.  A comparison of public datasets for acceleration-based fall detection. , 2015, Medical engineering & physics.

[4]  Eric Jones,et al.  SciPy: Open Source Scientific Tools for Python , 2001 .

[5]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

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

[7]  Habib Fardoun,et al.  Personalizable smartphone application for detecting falls , 2014, IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI).

[8]  Eduardo Casilari-Pérez,et al.  Comparison and Characterization of Android-Based Fall Detection Systems , 2014, Sensors.

[9]  Greg Mori,et al.  A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials , 2016, Medical & Biological Engineering & Computing.

[10]  Konrad Paul Kording,et al.  Fall Classification by Machine Learning Using Mobile Phones , 2012, PloS one.

[11]  Robert P. W. Duin,et al.  Combining One-Class Classifiers , 2001, Multiple Classifier Systems.

[12]  Jeffrey M. Hausdorff,et al.  Evaluation of Accelerometer-Based Fall Detection Algorithms on Real-World Falls , 2012, PloS one.

[13]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[14]  Ethem Alpaydin,et al.  Introduction to machine learning , 2004, Adaptive computation and machine learning.

[15]  K. Aminian,et al.  Fall detection with body-worn sensors , 2013, Zeitschrift für Gerontologie und Geriatrie.

[16]  Inmaculada Plaza,et al.  Challenges, issues and trends in fall detection systems , 2013, Biomedical engineering online.

[17]  Wen-Chang Cheng,et al.  Triaxial Accelerometer-Based Fall Detection Method Using a Self-Constructing Cascade-AdaBoost-SVM Classifier , 2013, IEEE Journal of Biomedical and Health Informatics.

[18]  Isabelle Guyon,et al.  An Introduction to Variable and Feature Selection , 2003, J. Mach. Learn. Res..

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

[20]  Gary M. Weiss,et al.  The Impact of Personalization on Smartphone-Based Activity Recognition , 2012, AAAI 2012.

[21]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[22]  Fatimah Ibrahim,et al.  Smartphone-Based Solutions for Fall Detection and Prevention: Challenges and Open Issues , 2014, Sensors.

[23]  VARUN CHANDOLA,et al.  Anomaly detection: A survey , 2009, CSUR.

[24]  Y. Istefanopulos,et al.  IEEE Engineering in Medicine and Biology Society , 2019, IEEE Transactions on Biomedical Engineering.

[25]  Luca Palmerini,et al.  A Wavelet-Based Approach to Fall Detection , 2015, Sensors.

[26]  Daniela Micucci,et al.  Falls as anomalies? An experimental evaluation using smartphone accelerometer data , 2015, J. Ambient Intell. Humaniz. Comput..

[27]  K. Samsudin,et al.  Evaluation of fall detection classification approaches , 2012, 2012 4th International Conference on Intelligent and Advanced Systems (ICIAS2012).

[28]  Sansanee Auephanwiriyakul,et al.  Fall detection algorithm using linear prediction model , 2013, 2013 IEEE International Symposium on Industrial Electronics.

[29]  Maarit Kangas,et al.  Comparison of low-complexity fall detection algorithms for body attached accelerometers. , 2008, Gait & posture.

[30]  Alan K. Bourke,et al.  Assessment of waist-worn tri-axial accelerometer based fall-detection algorithms using continuous unsupervised activities , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[31]  Eduardo Casilari-Pérez,et al.  Analysis of Android Device-Based Solutions for Fall Detection , 2015, Sensors.

[32]  Inmaculada Plaza,et al.  The Effect of Personalization on Smartphone-Based Fall Detectors , 2016, Sensors.

[33]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..