SPHERE seminar- Beyond Activity recognition: Automated Skill Assessment From Accelerometer Data
Aftab Khan, Research Engineer, Toshiba
0.3 Merchant Venturers Building
In this seminar Aftab Khan will be talking about the next generation of human activity recognition applications in ubiquitous computing scenarios focuses on assessing the quality of activities, which goes beyond mere identification of activities of interest. Objective quality assessments are often difficult to achieve, hard to quantify, and typically require domain specific background information that bias the overall judgement and limit generalisation.
In this seminar, Aftab will present a framework for skill assessment in activity recognition that enables automatic quality analysis of human activities. Toshiba's approach is based on a hierarchical rule induction technique that effectively abstracts from noise-prone activity data and assesses activity data at different temporal contexts. Toshiba's approach requires minimal domain specific knowledge about the activities of interest, which makes it largely generalisable. By means of an extensive case study they demonstrate the effectiveness of the proposed framework in the context of dexterity training of 15 medical students engaging in 50 attempts of surgical activities.
For further information please contact Emma Pritchard (email@example.com)