Wiki Contents

Affective Computing Group (ACG)

Affective Computing and Human-Computer Intelligent Interaction (HCII)

The Kansas State University Affective Computing Group (KSU ACG) is an affiliated research group of the Laboratory for Knowledge Discovery in Databases (KSU KDD Lab) under the direction of Dr. Heath L. Yates. Its research focus is at the nexus of artificial intelligence, machine learning, data science, affective computing, and the Internet of Things (IoT), particularly wearable instruments for human and animal telemetry.

Keywords

affective computing, artificial intelligence, machine learning, data science, wearables, animal telemetry

Affective Intelligence in Built Environments

This research focuses on applications of affective intelligence in human-developed spaces where people live, work, and recreate daily, also known as built environments. Built environments have been known to influence and impact individual affective responses. The impact of built environments on human well-being and mental health point towards a need to develop new metrics to measure and detect how humans respond subjectively in built environments. An initial approach taken in this work uses detection and classification of affective responses in built environments, given biometric data and environmental characteristics imputed by pattern analysis, which in turn is based on machine learning from sensor data, urban planning and architectural data, and subjective assessments including annotation. New approaches incorporate experimental designs for multisensor integration and learning to continuously monitor dynamic effects. Contributions that have grown out of this work include the development of spatiotemporal corpora for affect detection in built environments, leading to continuing work on the development and application of deep learning architectures and algorithms to time series data; generative models for augmented reality; and semisupervised inductive learning methods for active learning and transfer learning across different types of built environments. Early results have shown a machine learning approach can not only be used to detect arousal in built environments but also for the construction of novel explanatory models of the data.

Animal Telemetry for Time Series Learning and Spatiotemporal Predictive Analytics

This work investigates the problem of monitoring wearable and implantable sensors for estimation tasks such as temperature monitoring in livestock, for detection of early warning signs of infectious diseases.

Methods

Methods include general linear mixed models, multisensor integration using mixtures of recurrent convolutional neural networks, and traditional inductive learning methods such as logistic regression, random forests, etc.

Current Team Members

  • William H. Hsu - Professor, Computer Science, Kansas State University
  • Alexis Archer - Master of Science Graduate Student, Computer Science, Kansas State University

Affiliates

  • Heath Yates - Adjunct Assistant Professor, Computer Science, Kansas State University
  • Natasha Jacques - Ph.D. candidate, MIT
  • Carlos A. Aguirre - Developing Scholars Program and Undergraduate Research Programmer, Computer Science, Kansas State University

Alumni

  • Heath Yates - Ph.D. 2018
  • Divya Vani Lakkireddy - Master of Science 2021

Data Sets

To be posted.

Source Code

*GitHub repository by Heath Yates: code for Affective Intelligence in Built Environments.*

References

  • Picard, R. (1997). Affective Computing. Cambridge, MA, USA: MIT Press.

KDD Lab Publications

  • Yates, H., Chamberlain, B., Healey, J., & Hsu, W. (2018). Binary Classification of Arousal in Built Environments using Machine Learning. Working Notes of the 2nd International Joint Conference on Artificial Intelligence (IJCAI) Workshop on Artificial Intelligence in Affective Computing, Stockholm, Sweden, July 15, 2018.
  • Yates, H. (2018). Affective Intelligence in Built Environments. Ph.D. dissertation, Kansas State University, 2018.
  • Yates, H., Chamberlain, B., & Hsu, W. (2017). A Spatially Explicit Classification Model for Affective Computing in Built Environments. Proceedings of the 7th AAAC International Conference on Affective Computing and Intelligent Interaction (ACII 2017) Workshops and Demos, San Antonio, TX, USA, October 23-26, 2017.
  • Yates, H., Hsu, W., Chamberlain, B., & Norman, G. (2017). Arousal Detection for Biometric Data in Built Environments using Machine Learning. Working Notes of the 1st International Joint Conference on Artificial Intelligence (IJCAI) Workshop on Artificial Intelligence in Affective Computing, Melbourne, Australia, August 20, 2017.

Last updated by pozegov on Jul 6, 2023