Neural network based daily activity recognition without feature extraction

In recent years, human-computer interaction systems are become one of the most exciting areas in technological development. These systems aim to obtain personal information of people and development of an automated systems managed by this information. In this study, we have been studied a faster and higher accurate system design without feature extraction for the recognition of daily human activities and falling situation. Motion data were collected under knee with a 3-axis accelerometer. After data re-arrangement, a 250 data size window was applied to collected data. 250 XYZ axis data belonged to each windowed sample were written in an array and converted to 1×750 sized array. Finally, applying data reduction with PCA, the data were simulated by MLP, SVM and Naive-Bayes classifiers. The best result without feature extraction achieved by Naive Bayes classifier.

[1]  Yu Zhang,et al.  A wireless real-time fall detecting system based on barometer and accelerometer , 2012, 2012 7th IEEE Conference on Industrial Electronics and Applications (ICIEA).

[2]  Jin Wang,et al.  Generative models for automatic recognition of human daily activities from a single triaxial accelerometer , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[3]  Cecilio Angulo,et al.  Online motion recognition using an accelerometer in a mobile device , 2012, Expert Syst. Appl..

[4]  A K Bourke,et al.  Evaluation of waist-mounted tri-axial accelerometer based fall-detection algorithms during scripted and continuous unscripted activities. , 2010, Journal of biomechanics.

[5]  Isil Yazar,et al.  Temel Bileşen Analizi Yönteminin Ve Bazı Klasik Ve Robust Uyarlamalarının Yüz Tanıma Uygulamaları , 2009 .

[6]  David Howard,et al.  A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data , 2009, IEEE Transactions on Biomedical Engineering.

[7]  Jeen-Shing Wang,et al.  Using acceleration measurements for activity recognition: An effective learning algorithm for constructing neural classifiers , 2008, Pattern Recognit. Lett..

[8]  L Quagliarella,et al.  An interactive fall and loss of consciousness detector system. , 2008, Gait & posture.

[9]  Tülay Yildirim,et al.  Recognition of Patterns Without Feature Extraction by GRNN , 2007, ICANNGA.

[10]  Nigel H. Lovell,et al.  Implementation of a real-time human movement classifier using a triaxial accelerometer for ambulatory monitoring , 2006, IEEE Transactions on Information Technology in Biomedicine.