Human action recognition using wearable sensors and neural networks

Accurate recognition of daily activities could be useful in many fields including health, sports, childcare, and homes for the elderly, etc. In this paper, we propose a human action recognition method using data acquired from wearable sensors and learned using a Neural Network. The data collected from the sensors is processed for features using the Akamatsu transform. The Akamatsu Transform is a signal processing technique that given point, P(i) in a signal, N data points before and after the selected point are used to derive the integral and differential transforms, The Akamatsu Integration is an average of the N data points while the differential is the difference between the integral and the original value. Recently, wearable sensors are emerging as an indispensable method to recognize human actions.

[1]  Bernt Schiele,et al.  Unsupervised Discovery of Structure in Activity Data Using Multiple Eigenspaces , 2006, LoCA.

[2]  Didier Stricker,et al.  Introducing a New Benchmarked Dataset for Activity Monitoring , 2012, 2012 16th International Symposium on Wearable Computers.

[3]  Takuya Maekawa,et al.  Unsupervised Activity Recognition with User's Physical Characteristics Data , 2011, 2011 15th Annual International Symposium on Wearable Computers.

[4]  Irfan A. Essa,et al.  Discovering Characteristic Actions from On-Body Sensor Data , 2006, 2006 10th IEEE International Symposium on Wearable Computers.

[5]  Ling Bao,et al.  Activity Recognition from User-Annotated Acceleration Data , 2004, Pervasive.

[6]  Robert X. Gao,et al.  Multisensor Data Fusion for Physical Activity Assessment , 2012, IEEE Transactions on Biomedical Engineering.

[7]  Ricardo Chavarriaga,et al.  The Opportunity challenge: A benchmark database for on-body sensor-based activity recognition , 2013, Pattern Recognit. Lett..

[8]  Gaetano Borriello,et al.  A Practical Approach to Recognizing Physical Activities , 2006, Pervasive.

[9]  Plamen P. Angelov,et al.  Real time recognition of human activities from wearable sensors by evolving classifiers , 2011, 2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011).

[10]  Kristof Van Laerhoven,et al.  Spine versus porcupine: a study in distributed wearable activity recognition , 2004, Eighth International Symposium on Wearable Computers.

[11]  Paul Lukowicz,et al.  Combining Motion Sensors and Ultrasonic Hands Tracking for Continuous Activity Recognition in a Maintenance Scenario , 2006, 2006 10th IEEE International Symposium on Wearable Computers.

[12]  Matthai Philipose,et al.  Unsupervised Activity Recognition Using Automatically Mined Common Sense , 2005, AAAI.

[13]  Matthai Philipose,et al.  Common Sense Based Joint Training of Human Activity Recognizers , 2007, IJCAI.

[14]  Bernt Schiele,et al.  Scalable Recognition of Daily Activities with Wearable Sensors , 2007, LoCA.

[15]  Edward Sazonov,et al.  Monitoring of Posture Allocations and Activities by a Shoe-Based Wearable Sensor , 2011, IEEE Transactions on Biomedical Engineering.

[16]  Farkas Ioana-Iuliana,et al.  Detection of daily movements from data collected with two tri-axial accelerometers , 2011, 2011 34th International Conference on Telecommunications and Signal Processing (TSP).