A learning system for automatic Berg Balance Scale score estimation. (November 2017)

• Record Type: Journal Article
• Authors: Bacciu, Davide; Chessa, Stefano; Gallicchio, Claudio; Micheli, Alessio; Pedrelli, Luca; Ferro, Erina; Fortunati, Luigi; La Rosa, Davide; Palumbo, Filippo; Vozzi, Federico; Parodi, Oberdan
• Is Part Of: Engineering applications of artificial intelligence. Volume 66(2017:Jun.)
• Page Start: 60
• Page End: 74
• Publication Date: 2017-11
• Subjects: Balance assessment -- Reservoir computing -- Echo State Network -- Learning with temporal data -- Berg Balance Scale; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2017.08.018
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: The objective of this work is the development of a learning system for the automatic assessment of balance abilities in elderly people. The system is based on estimating the Berg Balance Scale (BBS) score from the stream of sensor data gathered by a Wii Balance Board. The scientific challenge tackled by our investigation is to assess the feasibility of exploiting the richness of the temporal signals gathered by the balance board for inferring the complete BBS score based on data from a single BBS exercise. The relation between the data collected by the balance board and the BBS score is inferred by neural networks for temporal data, modeled in particular as Echo State Networks within the Reservoir Computing (RC) paradigm, as a result of a comprehensive comparison among different learning models. The proposed system results to be able to estimate the complete BBS score directly from temporal data on exercise #10 of the BBS test, with ≈ 10 s of duration. Experimental results on real-world data show an absolute error below 4 BBS score points (i.e. below the 7% of the whole BBS range), resulting in a favorable trade-off between predictive performance and user's required time with respect to previous works in literature. Results achieved by RC models compare well also with respect to different related learning models. Overall, the proposed system puts forward as an effective tool for an accurate automated assessment of balance abilities in the elderly and it is characterized by being unobtrusive, easy to use and suitable for autonomous usage.