Multi-Modal, Multi-Resolution, Multi-Source State Classification and Prediction

The Army Research Laboratory Research Associateship Program (ARL-RAP) offers a research opportunity focused on developing computational methods to estimate and model a person's state (affective, psychological, physiological state, or their gestures and actions) from sensor data. The research aims to predict a person's next state given their current one and the set of sensor information about them. Research areas include modeling correlations between different output states, integration or fusion of sensor data from multiple sources, processing sensor data of the autonomic and central nervous system in non-stationary settings, real-time classification of streaming multimodal sensor data, state prediction from multimodal sensor data, biologically inspired methods for pattern recognition, and modeling cross modality interactions. This research combines machine classification, EEG/ERP processing, EKG/ICG processing, gesture recognition, neuromorphic computing, and signal processing. The ARL-RAP is designed to increase involvement of creative and highly trained scientists and engineers from academia and industry in scientific and technical areas of relevance to the Army. The Computational and Information Sciences Directorate (CISD) conducts research in communications, atmospheric modeling, battlefield visualization, and computing relevant to achieving the digital battlefield.