Institution profile

Missouri State University

Academic institutionnorthamerica · us
Official website
Research library16linked papers
Opportunities0open roles
Selected work

Representative Papers

MOXIE: Discovering Alternative Explanations for Biomedical Image Classifiers

Oct 03, 2026

This study addresses the limitation of traditional segment-wise explanation methods, which return a single explanation while overlooking how multiple image regions support predictions and how segmentation strategies influence outcomes. We propose MOXIE, a multi-objective evolutionary framework that employs the NSGA-II algorithm combined with diverse segmentation techniques, including SLIC and Felzenszwalb, to search for minimal image subsets that preserve classifier confidence. This approach generates a Pareto front of alternative explanations ranging from compact to high-fidelity representations, transcending the single-explanation paradigm by revealing the minimal contextual regions required for model decisions. Evaluated on blood cell and skin cancer datasets, MOXIE significantly outperforms LIME in terms of the hypervolume indicator and further exposes a confidence collapse issue inherent in the latter method.

0 citationsRead paper

Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity

Aug 04, 2026

This study addresses the dual challenges of benign heterogeneity—arising from diverse operating conditions and failure modes—and adversarial heterogeneity caused by malicious poisoning attacks in federated learning for aircraft engine remaining useful life prediction. To enhance both accuracy and security while preserving the privacy of raw sensor data, the work integrates personalized federated learning with robust aggregation mechanisms. It innovatively introduces a physics-informed sensor backdoor attack and presents the first systematic evaluation of the synergy between shared representation personalization and robust aggregators such as Krum. Experimental results demonstrate that shared representation personalization reduces the performance gap between local and centralized models by 70%, while Krum suppresses attack success rates from 94.9% to 2.8%, achieving high predictive accuracy alongside significantly improved robustness.

0 citationsRead paper

Extreme Adaptive Transformer for Time Series Forecasting

Jul 02, 2026

This work addresses the challenge of inadequately modeling rare yet high-impact extreme events in time series forecasting, particularly in hydrological streamflow prediction characterized by highly skewed distributions. To this end, the authors propose Exformer, a novel framework that explicitly captures dependencies between normal and extreme events within a Transformer architecture. Central to Exformer is an extreme-adaptive attention mechanism comprising three sparse attention components—Local, Stride, and Extreme—which respectively model short-term dynamics, periodic patterns, and extreme-event-related dependencies. Experimental results on four real-world hydrological datasets demonstrate that Exformer significantly outperforms state-of-the-art models in 3-day-ahead forecasting tasks, effectively enhancing predictive accuracy for extreme events in imbalanced time series.

0 citationsRead paper

Explanation-Aware Learning for Enhanced Interpretability in Biomedical Imaging

May 11, 2026

This work addresses the unreliability of existing medical image diagnosis models that often rely on non-causal or clinically irrelevant visual cues. To enhance trustworthiness, the authors propose a systematic framework that integrates explanation-aware loss directly into the end-to-end training objective by incorporating saliency-based interpretability supervision. A custom explanation loss function jointly optimizes diagnostic accuracy and spatial fidelity of model explanations. The study introduces two quantitative metrics—annotation coverage and saliency precision—to evaluate explanation quality and uncover the trade-off between explanation loss strength and model performance. Experiments on a chest X-ray dataset demonstrate that the proposed method achieves diagnostic accuracy comparable to baseline models while significantly improving spatial alignment between model-generated explanations and clinical annotations.

0 citationsRead paper
Recent publications

Latest Papers

MOXIE: Discovering Alternative Explanations for Biomedical Image Classifiers

Oct 03, 2026

This study addresses the limitation of traditional segment-wise explanation methods, which return a single explanation while overlooking how multiple image regions support predictions and how segmentation strategies influence outcomes. We propose MOXIE, a multi-objective evolutionary framework that employs the NSGA-II algorithm combined with diverse segmentation techniques, including SLIC and Felzenszwalb, to search for minimal image subsets that preserve classifier confidence. This approach generates a Pareto front of alternative explanations ranging from compact to high-fidelity representations, transcending the single-explanation paradigm by revealing the minimal contextual regions required for model decisions. Evaluated on blood cell and skin cancer datasets, MOXIE significantly outperforms LIME in terms of the hypervolume indicator and further exposes a confidence collapse issue inherent in the latter method.

0 citationsRead paper

Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client Heterogeneity

Aug 04, 2026

This study addresses the dual challenges of benign heterogeneity—arising from diverse operating conditions and failure modes—and adversarial heterogeneity caused by malicious poisoning attacks in federated learning for aircraft engine remaining useful life prediction. To enhance both accuracy and security while preserving the privacy of raw sensor data, the work integrates personalized federated learning with robust aggregation mechanisms. It innovatively introduces a physics-informed sensor backdoor attack and presents the first systematic evaluation of the synergy between shared representation personalization and robust aggregators such as Krum. Experimental results demonstrate that shared representation personalization reduces the performance gap between local and centralized models by 70%, while Krum suppresses attack success rates from 94.9% to 2.8%, achieving high predictive accuracy alongside significantly improved robustness.

0 citationsRead paper

Extreme Adaptive Transformer for Time Series Forecasting

Jul 02, 2026

This work addresses the challenge of inadequately modeling rare yet high-impact extreme events in time series forecasting, particularly in hydrological streamflow prediction characterized by highly skewed distributions. To this end, the authors propose Exformer, a novel framework that explicitly captures dependencies between normal and extreme events within a Transformer architecture. Central to Exformer is an extreme-adaptive attention mechanism comprising three sparse attention components—Local, Stride, and Extreme—which respectively model short-term dynamics, periodic patterns, and extreme-event-related dependencies. Experimental results on four real-world hydrological datasets demonstrate that Exformer significantly outperforms state-of-the-art models in 3-day-ahead forecasting tasks, effectively enhancing predictive accuracy for extreme events in imbalanced time series.

0 citationsRead paper

Explanation-Aware Learning for Enhanced Interpretability in Biomedical Imaging

May 11, 2026

This work addresses the unreliability of existing medical image diagnosis models that often rely on non-causal or clinically irrelevant visual cues. To enhance trustworthiness, the authors propose a systematic framework that integrates explanation-aware loss directly into the end-to-end training objective by incorporating saliency-based interpretability supervision. A custom explanation loss function jointly optimizes diagnostic accuracy and spatial fidelity of model explanations. The study introduces two quantitative metrics—annotation coverage and saliency precision—to evaluate explanation quality and uncover the trade-off between explanation loss strength and model performance. Experiments on a chest X-ray dataset demonstrate that the proposed method achieves diagnostic accuracy comparable to baseline models while significantly improving spatial alignment between model-generated explanations and clinical annotations.

0 citationsRead paper