Skip to main content
ARS Home » Southeast Area » Athens, Georgia » U.S. National Poultry Research Center » Egg and Poultry Production Safety Research Unit » Research » Publications at this Location » Publication #412269
Research Project: Reduction of Foodborne Pathogens and Antimicrobial Resistance in Poultry Production Environments

Location: Egg and Poultry Production Safety Research Unit

Title: Towards Interpreting Multi-Objective Feature Associations

Author
item PILLAI, NISHA - Mississippi State University
item GIREESAN, GANGA - Mississippi State University
item Rothrock Jr, Michael
item NANDURI, BINDU - Mississippi State University
item CHEN, ZHIQIAN - Mississippi State University
item RAMKUMAR, MAHALINGAM - Mississippi State University

Submitted to: Institute of Electrical and Electronics Engineers Proceedings Fuzzy Systems
Publication Type: Proceedings
Publication Acceptance Date: 2/28/2024
Publication Date: 4/15/2024
Citation: Pillai, N., Gireesan, G., Rothrock Jr, M.J., Nanduri, B., Chen, Z., Ramkumar, M. 2024. Towards Interpreting Multi-Objective Feature Associations. Institute of Electrical and Electronics Engineers Proceedings Fuzzy Systems. https://doi.org/10.1109/SysCon61195.2024.10553467.
DOI: https://doi.org/10.1109/SysCon61195.2024.10553467

Interpretive Summary: NA

Technical Abstract: Understanding how multiple features are associated and contribute to a specific objective is as important as understanding how each feature contributes to a particular outcome. Interpretability of a single feature in a prediction may be handled in multiple ways; however, in a multi-objective prediction, it is difficult to obtain interpretability of a combination of feature values. To address this issue, we propose an objective specific feature interaction design using multi-labels to find the optimal combination of features in agricultural settings. One of the novel aspects of this design is the identification of a method that integrates feature explanations with global sensitivity analysis in order to ensure combinatorial optimization in multi-objective settings. We have demonstrated in our preliminary experiments that an approximate combination of feature values can be found to achieve the desired outcome using two agricultural datasets: one with preharvest poultry farm practices for multi-drug resistance presence, and one with post-harvest poultry farm practices for food-borne pathogens. In our combinatorial optimization approach, all three pathogens are taken into consideration simultaneously to account for the interaction between conditions that favor different types of pathogen growth. These results indicate that explanation-based approaches are capable of identifying combinations of features that reduce pathogen presence in fewer iterations than a baseline.