TY - JOUR
T1 - A gesture recognition system for detecting behavioral patterns of ADHD
AU - Bautista, Miguel Ángel
AU - Hernández-Vela, Antonio
AU - Escalera, Sergio
AU - Igual, Laura
AU - Pujol, Oriol
AU - Moya, Josep
AU - Violant, Verónica
AU - Anguera, María T.
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2016/1
Y1 - 2016/1
N2 - We present an application of gesture recognition using an extension of dynamic time warping (DTW) to recognize behavioral patterns of attention deficit hyperactivity disorder (ADHD). We propose an extension of DTW using one-class classifiers in order to be able to encode the variability of a gesture category, and thus, perform an alignment between a gesture sample and a gesture class. We model the set of gesture samples of a certain gesture category using either Gaussian mixture models or an approximation of convex hulls. Thus, we add a theoretical contribution to classical warping path in DTW by including local modeling of intraclass gesture variability. This methodology is applied in a clinical context, detecting a group of ADHD behavioral patterns defined by experts in psychology/psychiatry, to provide support to clinicians in the diagnose procedure. The proposed methodology is tested on a novel multimodal dataset (RGB plus depth) of ADHD children recordings with behavioral patterns. We obtain satisfying results when compared to standard state-of-the-art approaches in the DTW context.
AB - We present an application of gesture recognition using an extension of dynamic time warping (DTW) to recognize behavioral patterns of attention deficit hyperactivity disorder (ADHD). We propose an extension of DTW using one-class classifiers in order to be able to encode the variability of a gesture category, and thus, perform an alignment between a gesture sample and a gesture class. We model the set of gesture samples of a certain gesture category using either Gaussian mixture models or an approximation of convex hulls. Thus, we add a theoretical contribution to classical warping path in DTW by including local modeling of intraclass gesture variability. This methodology is applied in a clinical context, detecting a group of ADHD behavioral patterns defined by experts in psychology/psychiatry, to provide support to clinicians in the diagnose procedure. The proposed methodology is tested on a novel multimodal dataset (RGB plus depth) of ADHD children recordings with behavioral patterns. We obtain satisfying results when compared to standard state-of-the-art approaches in the DTW context.
KW - Attention deficit hyperactivity disorder (ADHD)
KW - Convex hulls
KW - Dynamic time warping (DTW)
KW - Gaussian mixture models (GMMs)
KW - Gesture recognition
KW - Multimodal RGB-depth data
UR - http://www.scopus.com/inward/record.url?scp=84960362148&partnerID=8YFLogxK
U2 - 10.1109/TCYB.2015.2396635
DO - 10.1109/TCYB.2015.2396635
M3 - Journal article
C2 - 26684256
AN - SCOPUS:84960362148
SN - 2168-2267
VL - 46
SP - 136
EP - 147
JO - IEEE Transactions on Cybernetics
JF - IEEE Transactions on Cybernetics
IS - 1
M1 - 7047782
ER -