Intelligent Data Fusion for Multi-Modal or Multi-Sensory Systems
Developing intelligent data fusion for chemical detection using multiple sensors, pattern recognition, and Bayesian decision trees to improve accuracy and efficiency.
This grant is no longer accepting proposals
NRC Research Associateship Programs has archived this opportunity.
Funder: NRC Research Associateship Programs
Due Dates: May 1, 2025 (Application Deadline)
Funding Amounts: $99,200 stipend plus $3,000 travel allowance; typical tenure 2-3 years
Summary: Postdoctoral fellowship to develop intelligent data fusion techniques for multi-modal chemical detection using pattern recognition and Bayesian decision trees to improve accuracy and efficiency.
Key Information: Open to U.S. citizens and permanent residents; relocation and health insurance benefits included; requires contacting Research Adviser prior to applying.
Description
This postdoctoral research opportunity at the Naval Research Laboratory (NRL) focuses on developing and optimizing intelligent data fusion techniques for chemical detection using multiple sensors. The project aims to create a cohesive data management and decision-making framework that integrates outputs from various sensors through pattern recognition and expert knowledge. The data fusion algorithms will be tailored to the characteristics of the input data types, applying empirical and theoretical heuristics to select appropriate decision and combination rules.
A key feature of the research is the use of a Bayesian decision tree to assess the output of the data fusion algorithms, providing resilience against missing or corrupted data and accommodating imperfect classifications. The ultimate goal is to implement an optimized data fusion network that starts with signal processing algorithms and culminates in a statistically rigorous Bayesian decision tree, enhancing detection accuracy beyond what individual sensors can achieve.
Keywords associated with this opportunity include data processing, decision trees, feature selection, and multivariate analysis.
