A supervised approach to automatically extract a set of rules to support fall detection in an mHealth system

A cheap and portable approach to detect fall detection in real time is proposed.Acceleration data are gathered by a wearable sensor and sent to a mobile device.A set of IF-THEN rules is automatically extracted from acceleration data.This set of rules can be used in our real-time mobile monitoring system.If occurrence of a fall is detected by a rule, an alarm is automatically produced. Automatic fall detection is a major issue in the health care of elderly people. In this task the ability to discriminate in real time between falls and normal daily activities is crucial. Several methods already exist to perform this task, but approaches able to provide explicit formalized knowledge and high classification accuracy have not yet been developed and would be highly desirable. To achieve this aim, this paper proposes an innovative and complete approach to fall detection based both on the automatic extraction of knowledge expressed as a set of IF-THEN rules from a database of fall recordings, and on its use in a mobile health monitoring system. Whenever a fall is detected by this latter, the system can take immediate actions, e.g. alerting medical personnel. Our method can easily overcome the limitations of other approaches to fall detection. In fact, thanks to the knowledge gathering, it overcomes both the difficulty faced by a human being dealing with many parameters and trying to find out which are the most suitable, and also the need to apply a laborious trial-and-error procedure to find the values of the related thresholds. In addition, in our approach the extracted knowledge is processed in real time by a reasoner embedded in a mobile device, without any need for connection to a remote server. This proposed approach has been compared against four other classifiers on a database of falls simulated by volunteers, and its discrimination ability has been shown to be higher with an average accuracy of 91.88%. We have also carried out a very preliminary experimental phase. The best set of rules found by using the previous database has allowed us to achieve satisfactory performance in these experiments as well. Namely, on these real-world falls the obtained results in terms of accuracy, sensitivity, and specificity are of about 92%, 86%, and 96%, respectively.

[1]  Turgay Tugay Bilgin,et al.  A data mining approach for fall detection by using k-nearest neighbour algorithm on wireless sensor network data , 2012, IET Commun..

[2]  Ying-Wen Bai,et al.  Design and implementation of a fall monitor system by using a 3-axis accelerometer in a smart phone , 2012, 2012 IEEE 16th International Symposium on Consumer Electronics.

[3]  Robert C. Holte,et al.  Very Simple Classification Rules Perform Well on Most Commonly Used Datasets , 1993, Machine Learning.

[4]  M. Gams,et al.  TOWARDS ROBUST FALL DETECTION , 2011 .

[5]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[6]  Kenneth Meijer,et al.  Activity identification using body-mounted sensors—a review of classification techniques , 2009, Physiological measurement.

[7]  Ivanoe De Falco,et al.  Discovering interesting classification rules with genetic programming , 2002, Appl. Soft Comput..

[8]  Sylvain Arlot,et al.  A survey of cross-validation procedures for model selection , 2009, 0907.4728.

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

[10]  Pat Langley,et al.  Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[11]  M.H. Hassoun,et al.  Fundamentals of Artificial Neural Networks , 1996, Proceedings of the IEEE.

[12]  Alessio Vecchio,et al.  Recognition of false alarms in fall detection systems , 2011, 2011 IEEE Consumer Communications and Networking Conference (CCNC).

[13]  Javier Reina-Tosina,et al.  Design and Implementation of a Distributed Fall Detection System—Personal Server , 2009, IEEE Transactions on Information Technology in Biomedicine.

[14]  Matjaz Gams,et al.  Accelerometer Placement for Posture Recognition and Fall Detection , 2011, 2011 Seventh International Conference on Intelligent Environments.

[15]  Ágoston Srp,et al.  Fall Detection System for Older People , 2011 .

[16]  Raveendra Hegde,et al.  Technical Advances in Fall Detection System – A Review , 2013 .

[17]  Ying-Wen Bai,et al.  Design and implementation of a fall monitor system by using a 3-axis accelerometer in a smart phone , 2012, 2012 IEEE 16th International Symposium on Consumer Electronics.

[18]  Chin-Feng Lai,et al.  Detection of Cognitive Injured Body Region Using Multiple Triaxial Accelerometers for Elderly Falling , 2011, IEEE Sensors Journal.

[19]  Guang-Zhong Yang,et al.  Sensor Placement for Activity Detection Using Wearable Accelerometers , 2010, 2010 International Conference on Body Sensor Networks.

[20]  Marjorie Skubic,et al.  In-home fall risk assessment and detection sensor system. , 2013, Journal of gerontological nursing.

[21]  Ya-Hsin Hsueh,et al.  Real-Time Fall Detecting System Using a Tri-axial Accelerometer for Home Care , 2012, 2012 International Conference on Biomedical Engineering and Biotechnology.

[22]  Ivanoe De Falco,et al.  Differential Evolution for automatic rule extraction from medical databases , 2013, Appl. Soft Comput..

[23]  helliwoodmedia.  Annual Conference 2012 , 2012 .

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

[25]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[26]  Bettina Schnor,et al.  Fall-detection simulator for accelerometers with in-hardware preprocessing , 2012, PETRA '12.

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

[28]  Giuseppe De Pietro,et al.  Detecting Obstructive Sleep Apnea events in a real-time mobile monitoring system through automatically extracted sets of rules , 2013, 2013 IEEE 15th International Conference on e-Health Networking, Applications and Services (Healthcom 2013).

[29]  Basel Kikhia,et al.  Optimal Placement of Accelerometers for the Detection of Everyday Activities , 2013, Sensors.

[30]  A. Singh.  Challenges " # , 2006 .

[31]  Nader Karimi,et al.  Automatic Monocular System for Human Fall Detection Based on Variations in Silhouette Area , 2013, IEEE Transactions on Biomedical Engineering.

[32]  A Värri,et al.  A simple format for exchange of digitized polygraphic recordings. , 1992, Electroencephalography and clinical neurophysiology.

[33]  Giuseppe De Pietro,et al.  A Mobile Reasoning System for Supporting the Monitoring of Chronic Diseases , 2011, MobiHealth.

[34]  J. Paterson.  Annual Conference 2011 , 2011, The practising midwife.

[35]  John Nelson,et al.  Embedded fall and activity monitoring for a wearable ambient assisted living solution for older adults , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[36]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[37]  AGEinG And LifE CoursE , fAmiLy And Community HEALtH WHo Global report on falls Prevention in older Age , .

[38]  H. Altay Güvenir,et al.  Classification by Voting Feature Intervals , 1997, ECML.

[39]  K. S. Park,et al.  Fall detection algorithm for the elderly using acceleration sensors on the shoes , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.