Classification of Physiological Sensor Signals Using Artificial Neural Networks

Physiological signals have certain prominent characteristics that distinguish them from other types of physiological signals which are familiar to experts and assessed by inspection. The aim of this paper is to develop a computational model that can distinguish electrocardiogram, galvanic skin response and blood pressure signals acquired from sensors as well as detect corrupted signals which can arise due to hardware problems including sensor malfunction. Our work also investigates the impact of the signal modeling for various time lengths and determines an optimal signal time length for classification. This provides a method for automatic detection of corrupted signals during signal data collection which can be incorporated as a support tool during real-time sensor data acquisition.

[1]  Sophie R. DelDonno,et al.  Insomnia-related complaints correlate with functional connectivity between sensory–motor regions , 2013, Neuroreport.

[2]  B. McEwen,et al.  Stress and cognitive function , 1995, Current Opinion in Neurobiology.

[3]  Tamás D. Gedeon,et al.  Objective measures, sensors and computational techniques for stress recognition and classification: A survey , 2012, Comput. Methods Programs Biomed..

[4]  Michael L. Jacobson.  Analysis and classification of physiological signals using wavelet transforms , 2003, 10th IEEE International Conference on Electronics, Circuits and Systems, 2003. ICECS 2003. Proceedings of the 2003.

[5]  F. B. Reguig,et al.  Emotion recognition from physiological signals , 2011, Journal of medical engineering & technology.

[6]  Brian McDonald,et al.  Intelligent Biofeedback using an Immersive Competitive Environment , 2001 .

[7]  Tamás D. Gedeon,et al.  Modeling stress recognition in typical virtual environments , 2013, 2013 7th International Conference on Pervasive Computing Technologies for Healthcare and Workshops.

[8]  L. H. Miller,et al.  Replicability of two GSR indices as a function of stress and cognitive activity. , 1965, Journal of personality and social psychology.

[9]  Jennifer Healey,et al.  Detecting stress during real-world driving tasks using physiological sensors , 2005, IEEE Transactions on Intelligent Transportation Systems.

[10]  Tao Lin,et al.  Do physiological data relate to traditional usability indexes? , 2005, OZCHI.

[11]  Kevin T Sweeney,et al.  Intelligent artifact classification for ambulatory physiological signals , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[12]  Johannes Wagner,et al.  From Physiological Signals to Emotions: Implementing and Comparing Selected Methods for Feature Extraction and Classification , 2005, 2005 IEEE International Conference on Multimedia and Expo.

[13]  Fang Chen,et al.  Galvanic skin response (GSR) as an index of cognitive load , 2007, CHI Extended Abstracts.