2026-09-18T19:52:54Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/81285 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Huang, Thomas S. Pavlovic, Vladimir Ivan 2015-09-25T20:10:24Z 2015-09-25T20:10:24Z 10000-01-01 1999 1999 Recent advances in various display and virtual technologies coupled with an explosion in available computing power have given rise to a number of novel human-computer interaction (HCI) modalities---speech, vision-based gesture recognition, eye tracking, EEG, etc. However, despite the abundance of novel interaction devices, the naturalness and efficiency of HCI has remained low. This is due in particular to the lack of robust sensory data interpretation techniques. To deal with the task of interpreting single and multiple interaction modalities this dissertation establishes a novel probabilistic approach based on dynamic Bayesian networks (DBNs). As a generalization of the successful hidden Markov models, DBNs are a natural basis for the general temporal action interpretation task. The problem of interpretation of single or multiple interacting modalities can then be viewed as a Bayesian inference task. In this work three complex DBN models are introduced: mixtures of DBNs, mixed-state DBNs, and coupled HMMs. In-depth study of these models yields efficient approximate inference and parameter learning techniques applicable to a wide variety of problems. Experimental validation of the proposed approaches in the domains of gesture and speech recognition confirms the model's applicability to both unimodal and multimodal interpretation tasks. Made available in DSpace on 2015-09-25T20:10:24Z (GMT). No. of bitstreams: 2 license.txt: 4848 bytes, checksum: 96035ab3f5e1c23cc7138a224ce498bd (MD5) 9921722.pdf: 7976127 bytes, checksum: 7c5292fdbc098658c52844901b0e5ab3 (MD5) Previous issue date: 1999 Embargo set by: Seth Robbins for item 82566 Lift date: Forever Reason: Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs Restricted to the U of I community idenfinitely during batch ingest of legacy ETDs U of I Only 160 p. Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 1999. http://hdl.handle.net/2142/81285 (MiAaPQ)AAI9921722 eng Computer Science Dynamic Bayesian Networks for Information Fusion With Applications to Human-Computer Interfaces text Electrical Engineering Electrical Engineering University of Illinois at Urbana-Champaign Dissertation Ph.D.