A Reservoir Computing Approach for Balance Assessment

A relevant aspect in the field of health monitoring is represented by the evaluation of balance stability in the elderly. The Berg Balance Scale (BBS) represents a golden standard test for clinical assessment of balance stability. Recently, the Wii Balance Board has been successfully validated as an effective tool for the analysis of static balance-related features such as the duration or the speed of assessment of patient’s center of pressure. In this paper we propose an innovative unobtrusive approach for automatic evaluation of balance assessment, by analyzing the whole temporal information generated by the balance board. In particular, using Recurrent Neural Networks implemented according to the Reservoir Computing paradigm, we propose to estimate the BBS score of a patient from the temporal data gathered during the execution on the balance board of one simple BBS exercise. The experimental assessment of the proposed approach on real-world data shows promising results.

[1]  Cathy Craig,et al.  Assessing and training standing balance in older adults: a novel approach using the 'Nintendo Wii' Balance Board. , 2011, Gait & posture.

[2]  F. Horak,et al.  The relevance of clinical balance assessment tools to differentiate balance deficits. , 2010, European journal of physical and rehabilitation medicine.

[3]  Stefano Chessa,et al.  Robot Localization by Echo State Networks Using RSS , 2013, WIRN.

[4]  Peter Tiño,et al.  Markovian Bias of Neural-based Architectures With Feedback Connections , 2007, Perspectives of Neural-Symbolic Integration.

[5]  Davide Bacciu,et al.  A cognitive robotic ecology approach to self-configuring and evolving AAL systems , 2015, Eng. Appl. Artif. Intell..

[6]  F. Horak,et al.  The Balance Evaluation Systems Test (BESTest) to Differentiate Balance Deficits , 2009, Physical Therapy.

[7]  Ching-Tien Shih,et al.  Assisting people with multiple disabilities actively correct abnormal standing posture with a Nintendo Wii balance board through controlling environmental stimulation. , 2010, Research in developmental disabilities.

[8]  Stefano Chessa,et al.  Predicting User Movements in Heterogeneous Indoor Environments by Reservoir Computing , 2011, IJCAI 2011.

[9]  Miikka Ermes,et al.  Accelerometry-Based Berg Balance Scale Score Estimation , 2014, IEEE Journal of Biomedical and Health Informatics.

[10]  B. Bloem,et al.  The clinical utility of posturography , 2008, Clinical Neurophysiology.

[11]  Herbert Jaeger,et al.  Optimization and applications of echo state networks with leaky- integrator neurons , 2007, Neural Networks.

[12]  Alessio Micheli,et al.  Robotic UBIquitous COgnitive Network , 2012, ISAmI.

[13]  Davide Bacciu,et al.  An experimental characterization of reservoir computing in ambient assisted living applications , 2013, Neural Computing and Applications.

[14]  Stefano Chessa,et al.  An Experimental Evaluation of Reservoir Computation for Ambient Assisted Living , 2012, WIRN.

[15]  Stefano Chessa,et al.  A General Purpose Distributed Learning Model for Robotic Ecologies , 2012, SyRoCo.

[16]  Stefano Chessa,et al.  User Movements Forecasting by Reservoir Computing Using Signal Streams Produced by Mote-Class Sensors , 2011, MOBILIGHT.

[17]  Claudio Gallicchio,et al.  Tree Echo State Networks , 2013, Neurocomputing.

[18]  Benjamin Schrauwen,et al.  An experimental unification of reservoir computing methods , 2007, Neural Networks.

[19]  M. Tinetti.  Performance‐Oriented Assessment of Mobility Problems in Elderly Patients , 1986, Journal of the American Geriatrics Society.

[20]  Herbert Jaeger,et al.  Reservoir computing approaches to recurrent neural network training , 2009, Comput. Sci. Rev..

[21]  Paul McCrory,et al.  Validity and reliability of the Nintendo Wii Balance Board for assessment of standing balance. , 2010, Gait & posture.

[22]  Stefano Chessa,et al.  Forecast-Driven Enhancement of Received Signal Strength (RSS)-Based Localization Systems , 2013, ISPRS Int. J. Geo Inf..

[23]  A. Micheli,et al.  A Preliminary Application of Echo State Networks to Emotion Recognition , 2014 .

[24]  Claudio Gallicchio,et al.  Architectural and Markovian factors of echo state networks , 2011, Neural Networks.

[25]  Harald Haas,et al.  Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[26]  Alessandro Saffiotti,et al.  Self-sustaining Learning for Robotic Ecologies , 2012, SENSORNETS.

[27]  John F. Kolen,et al.  Field Guide to Dynamical Recurrent Networks , 2001 .

[28]  B. E. Maki,et al.  A prospective study of postural balance and risk of falling in an ambulatory and independent elderly population. , 1994, Journal of gerontology.

[29]  B. E. Maki,et al.  Measuring balance in the elderly: validation of an instrument. , 1992, Canadian journal of public health = Revue canadienne de sante publique.

[30]  Stefano Chessa,et al.  Robotic Ubiquitous Cognitive Ecology for Smart Homes , 2015, Journal of Intelligent & Robotic Systems.

[31]  Stefano Chessa,et al.  Smart Environments and Context-Awareness for Lifestyle Management in a Healthy Active Ageing Framework , 2015, EPIA.

[32]  Benjamin Schrauwen,et al.  Reservoir Computing Trends , 2012, KI - Künstliche Intelligenz.

[33]  Stefano Chessa,et al.  Multisensor Data Fusion for Activity Recognition Based on Reservoir Computing , 2013, EvAAL.