Emotion recognition provides valuable information for human-computerinteractions . The large number of input channels involved in emotion recognition are significantly expensive from a memory perspective . The required vector storage is seamlessly reduced by 98% and the frequency of vector requests by at least 1/5 . The proposed techniques achieve two-class multi-modal classification accuracies of >76% for valence and >73% for arousal . The results demonstratethe potential of efficient hyperdimensional computing for low-power,multi-channeled emotion recognition tasks, are almost always better than state of the art. The results demonstrate the potential of . efficient hyperdimdimdiminances of . low-powered computing for .

Author(s) : Alisha Menon, Anirudh Natarajan, Reva Agashe, Daniel Sun, Melvin Aristio, Harrison Liew, Yakun Sophia Shao, Jan M. Rabaey

Links : PDF - Abstract

Code :
Coursera

Keywords : emotion - recognition - computing - efficient - results -

Leave a Reply

Your email address will not be published. Required fields are marked *