Exploiting the Data Sensitivity of Neurometric Fidelity for Optimizing EEG Sensing

With newly developed wireless neuroheadsets, electroencephalography (EEG) neurometrics can be incorporated into in situ and ubiquitous physiological monitoring for human mental health. As a resource constraint system providing critical health services, the EEG headset design must consider both high application fidelity and energy efficiency. However, through empirical studies with an off-the-shelf Emotiv EPOC Neuroheadset, we uncover a mismatch between lossy EEG sensor communication and high neurometric application fidelity requirements. To tackle this problem, we study how to learn the sensitivity of neurometric application fidelity to EEG data. The learned sensitivity is used to develop two algorithms: 1) an energy minimization algorithm minimizing the energy usage in EEG sampling and networking while meeting applications' fidelity requirements and 2) a fidelity maximization algorithm maximizing the sum of all applications' fidelities through the incorporation and optimal utilization of a limited data buffer. The effectiveness of our proposed solutions is validated through trace-driven experiments.

[1]  Mani B. Srivastava,et al.  Compressive Sensing of Neural Action Potentials Using a Learned Union of Supports , 2011, 2011 International Conference on Body Sensor Networks.

[2]  Matthew Stewart,et al.  IEEE Transactions on Cybernetics , 2015, IEEE Transactions on Cybernetics.

[3]  Thierry Pun,et al.  A channel selection method for EEG classification in emotion assessment based on synchronization likelihood , 2007, 2007 15th European Signal Processing Conference.

[4]  Ali H. Shoeb,et al.  Sensor selection for energy-efficient ambulatory medical monitoring , 2009, MobiSys '09.

[5]  K. J. Ray Liu,et al.  Time-Reversal Wireless Paradigm for Green Internet of Things: An Overview , 2014, IEEE Internet of Things Journal.

[6]  Gang Zhou,et al.  ACR: Active Collision Recovery in Dense Wireless Sensor Networks , 2010, 2010 Proceedings IEEE INFOCOM.

[7]  Stephen P. Boyd,et al.  Convex Optimization , 2004, Algorithms and Theory of Computation Handbook.

[8]  Manfred K. Warmuth,et al.  The weighted majority algorithm , 1989, 30th Annual Symposium on Foundations of Computer Science.

[9]  John Lach,et al.  Enabling data-centric energy-fidelity scalability in wireless body area sensor networks , 2009, BODYNETS.

[10]  Di Xiao,et al.  Energy modeling and optimization through joint packet size analysis of BSN and WiFi networks , 2011, 30th IEEE International Performance Computing and Communications Conference.

[11]  Hsiao-Hwa Chen,et al.  An Energy-Aware Trust Derivation Scheme With Game Theoretic Approach in Wireless Sensor Networks for IoT Applications , 2014, IEEE Internet of Things Journal.

[12]  Owen Thomas,et al.  ACM SIGMETRICS Performance Evaluation Review , 2011 .

[13]  John Guttag,et al.  Reducing energy consumption of multi-channel mobile medical monitoring algorithms , 2008, HealthNet '08.

[14]  Krste Asanovic,et al.  Energy Aware Lossless Data Compression , 2003, MobiSys.

[15]  Anantha P. Chandrakasan,et al.  A Micro-power EEG acquisition SoC with integrated seizure detection processor for continuous patient monitoring , 2009, 2009 Symposium on VLSI Circuits.

[16]  Jie Liu,et al.  SpeakerSense: Energy Efficient Unobtrusive Speaker Identification on Mobile Phones , 2011, Pervasive.

[17]  Ali H. Shoeb,et al.  Application of Machine Learning To Epileptic Seizure Detection , 2010, ICML.

[18]  John Lach,et al.  Online Data and Execution Profiling for Dynamic Energy-Fidelity Optimization in Body Sensor Networks , 2010, 2010 International Conference on Body Sensor Networks.

[19]  Gang Zhou,et al.  MMSN: Multi-Frequency Media Access Control for Wireless Sensor Networks , 2006, Proceedings IEEE INFOCOM 2006. 25TH IEEE International Conference on Computer Communications.

[20]  Matthew Keally,et al.  AdaSense: Adapting sampling rates for activity recognition in Body Sensor Networks , 2013, 2013 IEEE 19th Real-Time and Embedded Technology and Applications Symposium (RTAS).

[21]  Andreas Terzis,et al.  Surviving wi-fi interference in low power ZigBee networks , 2010, SenSys '10.

[22]  D. Cacuci,et al.  Applications to large-scale systems , 2005 .

[23]  John G. Proakis,et al.  Digital Signal Processing Using MATLAB , 1999 .

[24]  Ionel Michael Navon,et al.  Sensitivity and Uncertainty Analysis, Volume II: Applications to Large-Scale Systems , 2005 .

[25]  W.J. Kaiser,et al.  MicroLEAP: Energy-aware Wireless Sensor Platform for Biomedical Sensing Applications , 2007, 2007 IEEE Biomedical Circuits and Systems Conference.

[26]  Seth Kiser,et al.  Early detection of Alzheimer's disease using nonlinear analysis of EEG via Tsallis entropy , 2010, 2010 Biomedical Sciences and Engineering Conference.

[27]  Guoliang Xing,et al.  PBN: towards practical activity recognition using smartphone-based body sensor networks , 2011, SenSys.

[28]  Cecilia Mascolo,et al.  EmotionSense: a mobile phones based adaptive platform for experimental social psychology research , 2010, UbiComp.

[29]  Gang Zhou,et al.  RadioSense: Exploiting Wireless Communication Patterns for Body Sensor Network Activity Recognition , 2012, 2012 IEEE 33rd Real-Time Systems Symposium.

[30]  Jeffrey B. Henriques,et al.  Left frontal hypoactivation in depression. , 1991, Journal of abnormal psychology.

[31]  Cecilia Mascolo,et al.  SociableSense: exploring the trade-offs of adaptive sampling and computation offloading for social sensing , 2011, MobiCom.

[32]  Rana El Kaliouby,et al.  Emotion detection using noisy EEG data , 2010, AH.