eduzhai > Applied Sciences > Engineering >

Scoring and Assessment in Medical VR Training Simulators with Dynamic Time Series Classification

  • Save

... pages left unread,continue reading

Document pages: 21 pages

Abstract: This research proposes and evaluates scoring and assessment methods forVirtual Reality (VR) training simulators. VR simulators capture detailedn-dimensional human motion data which is useful for performance analysis.Custom made medical haptic VR training simulators were developed and used torecord data from 271 trainees of multiple clinical experience levels. DTWMultivariate Prototyping (DTW-MP) is proposed. VR data was classified asNovice, Intermediate or Expert. Accuracy of algorithms applied for time-seriesclassification were: dynamic time warping 1-nearest neighbor (DTW-1NN) 60 ,nearest centroid SoftDTW classification 77.5 , Deep Learning: ResNet 85 , FCN75 , CNN 72.5 and MCDCNN 28.5 . Expert VR data recordings can be used forguidance of novices. Assessment feedback can help trainees to improve skillsand consistency. Motion analysis can identify different techniques used byindividuals. Mistakes can be detected dynamically in real-time, raising alarmsto prevent injuries.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×