System (for) Tracking Equilibrium and Determining Incline (STEADI)

The goal of this project was to design and implement a smartphone-based wearable system to detect fall events in real time. It has the acronym STEADI. Rather than have expensive customised hardware STEADI was implemented in a cost effective manner using a generic mobile computing device. In order to detect the fall event, we propose a fall detector that uses the accelerometer available in a mobile phone. As for detecting a fall we mainly divide the system in two sections, the signal processing and classification. For the processing both a median filter and a high pass filter are used. A Median filter is used to amplify/enhance the signal by removing impulsive noise while preserving the signal shape while the High pass filter is used to emphasise transitions in the signal. Then, in order to recognize a fall event, our STEADI system implements two methods that are a simple threshold analysis to determine whether or not a fall has occurred (threshold-based) and a more sophisticated Naive-Bayes classification method to differentiate falling from other mobile activities. Our experimental results show that by applying the signal processing and Naive-Bayes classification together increases the accuracy by more than 20% compared with using the threshold-based method alone. The Naive-Bayes achieved a detection accuracy of 95% in overall. Furthermore, an external sensor is introduced in order to enhance its accuracy. In addition to the fall detection, the systems can also provide location information using Google Maps as to the whereabouts of the fall event using the available GPS on the smartphone and sends the message to the caretaker via an SMS.

[1]  Claes Wohlin,et al.  A comparison of issues and advantages in agile and incremental development between state of the art and an industrial case , 2009, J. Syst. Softw..

[2]  Xiuxin Yang,et al.  A wearable real-time system for physical activity recognition and fall detection , 2010 .

[3]  Xin Wang.  Two-dimensional Bayesian estimator for image filtering , 1999, IEEE Trans. Image Process..

[4]  Alex Mihailidis,et al.  An intelligent emergency response system: preliminary development and testing of automated fall detection , 2005, Journal of telemedicine and telecare.

[5]  Woubshet Nema Behutiye.  Android ECG Application Development , 2012 .

[6]  Rich Caruana,et al.  An empirical comparison of supervised learning algorithms , 2006, ICML.

[7]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[8]  M N Nyan,et al.  A wearable system for pre-impact fall detection. , 2008, Journal of biomechanics.

[9]  Michael J. McGrath,et al.  Falls Prevention in the Home: Challenges for New Technologies , 2011 .

[10]  Jean Meunier,et al.  Video Surveillance for Fall Detection , 2011 .

[11]  M. Yuwono,et al.  Fall detection using a Gaussian distribution of clustered knowledge, augmented radial basis neural-network, and multilayer perceptron , 2011, 7th International Conference on Broadband Communications and Biomedical Applications.

[12]  Harry Zhang,et al.  The Optimality of Naive Bayes , 2004, FLAIRS.

[13]  Vikram Kapila,et al.  Technological Developments in Education and Automation, proceedings of the 2008 International Conference on Engineering Education, Instructional Technology, Assessment, and E-learning (EIAE 08) and International Conference on Industrial Electronics, Technology & Automation (IETA 08), part of the Int , 2010, EIAT/IETA.

[14]  Victor R. Basili,et al.  Iterative and incremental developments. a brief history , 2003, Computer.

[15]  R. Bajcsy,et al.  Wearable Sensors for Reliable Fall Detection , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[16]  V. Vaidehi,et al.  Video based automatic fall detection in indoor environment , 2011, 2011 International Conference on Recent Trends in Information Technology (ICRTIT).

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

[18]  Junji Yamato,et al.  Recognizing human action in time-sequential images using hidden Markov model , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[19]  Hussein Zedan,et al.  The implementation of an intelligent and video-based fall detection system using a neural network , 2014, Appl. Soft Comput..

[20]  Richard G. Lyons,et al.  Understanding Digital Signal Processing , 1996 .

[21]  Mark Hasegawa-Johnson,et al.  Acoustic fall detection using Gaussian mixture models and GMM supervectors , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[22]  Gopalaswamy Ramesh,et al.  Software Testing: Principles and Practices , 2005 .

[23]  Sen M. Kuo,et al.  Real-time digital signal processing , 2001 .

[24]  Harry Zhang,et al.  Naive Bayes for optimal ranking , 2008, J. Exp. Theor. Artif. Intell..

[25]  Angel R. Martinez,et al.  Computational Statistics Handbook with MATLAB , 2001 .

[26]  Kent L. Norman,et al.  Development of an instrument measuring user satisfaction of the human-computer interface , 1988, CHI '88.

[27]  James Brusey,et al.  Fall Detection with Wearable Sensors--Safe (Smart Fall Detection) , 2011, 2011 Seventh International Conference on Intelligent Environments.

[28]  A. Enis Çetin,et al.  HMM Based Falling Person Detection Using Both Audio and Video , 2005, 2006 IEEE 14th Signal Processing and Communications Applications.

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

[30]  F. Martin,et al.  Falls exercise interventions and reduced falls rate: always in the patient's interest? , 2007, Age and ageing.

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

[32]  M. Morris,et al.  Concurrent related validity of the GAITRite walkway system for quantification of the spatial and temporal parameters of gait. , 2003, Gait & posture.

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

[34]  Dong Xuan,et al.  PerFallD: A pervasive fall detection system using mobile phones , 2010, 2010 8th IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops).