Improving Human Activity Recognition and its Application in Early Stroke Diagnosis

Stroke diagnosis is pretty much a failure right now. Would anything here be better?  
Test out these 17 diagnosis possibilities to find out which one is the best?  Or maybe the Qualcomm Xprize for the tricorder? 

http://www.worldscientific.com/doi/abs/10.1142/S0129065714500361

José R. Villar

Corresponding author.

Computer Science Department, University of Oviedo, ETSIMO, Oviedo, Asturias 33005, Spain

Silvia González

Instituto Tecnológico de Castilla y León c/López Bravo 70 Burgos, Burgos 09001, Spain

Javier Sedano

Instituto Tecnológico de Castilla y León c/López Bravo 70 Burgos, Burgos 09001, Spain

Camelia Chira

Computer Science Department, Tech. University of Cluj-Napoca, 28 Gh. Baritiu Street, 400027 Cluj-Napoca, Romania

Jose M. Trejo-Gabriel-Galan

Neurology Department of the Burgos' Hospital, Burgos, Spain

Accepted: 4 November 2014

Published: 16 February 2015

The development of efficient stroke-detection methods is of significant importance in today's society due to the effects and impact of stroke on health and economy worldwide. This study focuses on Human Activity Recognition (HAR), which is a key component in developing an early stroke-diagnosis tool. An overview of the proposed global approach able to discriminate normal resting from stroke-related paralysis is detailed. The main contributions include an extension of the Genetic Fuzzy Finite State Machine (GFFSM) method and a new hybrid feature selection (FS) algorithm involving Principal Component Analysis (PCA) and a voting scheme putting the cross-validation results together. Experimental results show that the proposed approach is a well-performing HAR tool that can be successfully embedded in devices.