The Intelligent Multimodal Computing and Sensing (IMICS) Lab is part of the Computer Science Department at Texas State University.
Director: Dr. Vangelis Metsis
Welcome to our Research Lab, a vibrant and collaborative space where innovation meets impact. Our team is composed of interdisciplinary scholars committed to advancing the frontiers of Machine Learning, Computer Vision, Smart Health, Affective Computing, and Pervasive Computing.
Our research interests span several critical areas, from the exploration of human needs and behavior through the analysis of large-scale sensor data to the development of advanced machine learning models that facilitate practical applications in smart health and pervasive computing. We’re passionate about creating solutions that improve quality of life, harnessing technology to make a meaningful difference.
Our lab has made significant strides in Behavior Modeling and Activity Recognition, contributing to smart health applications that enhance physical therapy, detect abnormal behavior, and more. We’ve developed cutting-edge sleep monitoring methodologies, leveraging machine learning techniques for at-home, non-invasive sleep tracking and disorder detection.
We’ve also made noteworthy advancements in the integration of Virtual Reality, Affective Computing, and Physiological Biosignal Analysis. Our work in this domain has paved the way for innovative therapeutic interventions, such as using VR environments to help war veterans overcome social anxiety symptoms.
At our lab, we are continuously pushing the boundaries of what’s achievable, inspired by the belief that our work can contribute to a future where technology truly serves humanity. We invite you to explore our work and join us in our exciting journey of discovery and innovation. For more information about our research, please visit our Research page.
March 22, 2024
Our paper titled “BioDiffusion - A Versatile Diffusion Model for Biomedical Signal Synthesis” has been accepted for publication at the MDPI Bioengineering Journal.
March 11, 2024
Our paper titled “Enhancing Time-Series Prediction with Temporal Context Modeling - A Bayesian and Deep Learning Synergy” has been accepted for publication at FLAIRS-37.
October 10, 2023
Alex Katrompas defends his Ph.D. dissertation. Congratulations!
Title: Recurrence and Temporal Attention Synergy for Optimal Time-Series Modeling And Interpretability
June 30, 2023
Our paper titled “Temporal Attention Signatures for Interpretable Time-Series Prediction” has been accepted for publication at ICANN 2023.
June 8, 2023
Xiaomin Li defends her Ph.D. dissertation. Congratulations!
Title: Mitigating Data Shortage in Biomedical Signal Analysis – An Investigation into Transfer Learning and Generative Models
May 29, 2023
Our paper titled “Conditional Diffusion with Label Smoothing for Data Synthesis from Examples with Noisy Labels” has been accepted for publication at EUSIPCO 2023.
April 5, 2023
Lee Hinkle defends his Ph.D. dissertation. Congratulations!
Title: Deep Neural Network Representations of Physiological Time-Series Sensor Data for Improved Recognition Performance
April 5, 2023
Gentry Atkinson defends his Ph.D. dissertation. Congratulations!
Title: Mitigating the Effects of Label Noise in Time-Series Sensor Data
March 16, 2022
Our paper titled “TTS-GAN - A Transformer-based Time-Series Generative Adversarial Network” has been accepted for publication at AIME 2022.
