Selected work

Representative Papers

An approach with Visual and Tabular Mamba to multimodal medical data using Mixed Fusion

Jun 17, 2026

This study addresses the challenge of effectively fusing medical images with clinical and demographic tabular data by proposing a hybrid multimodal fusion approach based on the Mamba architecture. The method employs a Vision Mamba to extract lesion image features and a Tabular Mamba to integrate image-derived prediction probabilities with structured clinical data, enabling end-to-end training for cancer classification. Notably, this work is the first to introduce Mamba into multimodal medical analysis and designs a Mixed Fusion structure that supports SHAP-based interpretability. Evaluated on the NDB-UFES dataset, the proposed approach significantly outperforms Transformer-based baselines while maintaining strong interpretability, demonstrating particularly superior performance in sensitivity-oriented metrics such as recall—making it well-suited for high-stakes clinical diagnostic scenarios.

0 citationsRead paper

The NetMob26 Dataset: A High-Resolution Multi-Source View of Public Bus Mobility in Niterói

May 18, 2026

This study addresses the scarcity of high-quality public transit ridership and passenger demand data by integrating heterogeneous multi-source datasets—including bus GPS trajectories, 7.2 million fare transactions, route and stop information, weather records, urban infrastructure, and sociodemographic statistics—at the scale of a single city to construct a high-resolution, supply-and-demand-oriented public transit dataset. Rigorous data cleaning, anomaly detection, standardization, and differential privacy-based anonymization ensure both data quality and individual privacy. A controlled-access mechanism is implemented to balance open data sharing with privacy preservation. The resulting dataset enables research on transit efficiency evaluation, passenger flow forecasting, accessibility analysis, and weather impact assessment, thereby providing a robust foundation for intelligent urban transportation governance.

0 citationsRead paper

Exploring label correlations using decision templates for ensemble of classifier chains

Mar 13, 2026

This work addresses the common oversight of inter-label dependencies in multi-label classification, which often limits the performance of ensemble classifier chains. To overcome this limitation, the authors propose UDDTECC, a novel method that explicitly models unconditional label dependencies during the decision template fusion stage for the first time, enabling more intelligent prediction aggregation. By integrating label dependency information into both the ensemble classifier chain architecture and the decision template framework, UDDTECC significantly enhances multi-label classification performance. Experimental results demonstrate that the proposed approach consistently outperforms conventional fusion strategies and stacking-based methods across most evaluation metrics, thereby validating its effectiveness and innovation.

0 citationsRead paper

Certified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods

Dec 23, 2025

Existing minimum-accuracy heuristics for quantum kernel methods suffer from high computational cost, applicability only to balanced datasets, and lack of theoretical guarantees. Method: This work generalizes the notion of minimum accuracy to arbitrary binary classification datasets under approximate quantum hardware, rigorously proving it as a theoretical lower bound on the empirical accuracy of linear classifiers. We propose a Pauli-direction-based Monte Carlo estimation technique, providing probabilistic error bounds and formal convergence guarantees. Crucially, our method evaluates quantum feature map quality without training a quantum support vector machine (QSVM). Contribution/Results: The approach significantly reduces computational complexity while ensuring scalability, theoretical soundness, and hardware compatibility. It constitutes the first provably reliable, practical tool for pre-screening quantum feature maps—enabling efficient, theoretically grounded selection of promising quantum embeddings prior to full quantum kernel training.

0 citationsRead paper

Combining SHAP and Causal Analysis for Interpretable Fault Detection in Industrial Processes

Oct 27, 2025

Complex industrial process data hinder fault detection model performance and interpretability, impeding reliable decision-making. To address this, we propose the first interpretable fault detection framework integrating SHAP values with causal graph modeling: SHAP quantifies feature contributions, while multi-algorithm causal discovery constructs a directed acyclic graph (DAG) to explicitly encode fault propagation mechanisms. Evaluated on the Tennessee Eastman Process benchmark, our method significantly improves fault identification accuracy and precisely identifies key causal drivers—such as cooling and separation systems—enabling root-cause attribution. Crucially, the learned causal structure aligns closely with SHAP-based feature importance rankings. This work achieves synergistic enhancement of predictive performance and causal interpretability, establishing a novel diagnostic paradigm for industrial intelligent maintenance that balances accuracy with operational transparency.

0 citationsRead paper

Recent publications

Latest Papers

An approach with Visual and Tabular Mamba to multimodal medical data using Mixed Fusion

Jun 17, 2026

This study addresses the challenge of effectively fusing medical images with clinical and demographic tabular data by proposing a hybrid multimodal fusion approach based on the Mamba architecture. The method employs a Vision Mamba to extract lesion image features and a Tabular Mamba to integrate image-derived prediction probabilities with structured clinical data, enabling end-to-end training for cancer classification. Notably, this work is the first to introduce Mamba into multimodal medical analysis and designs a Mixed Fusion structure that supports SHAP-based interpretability. Evaluated on the NDB-UFES dataset, the proposed approach significantly outperforms Transformer-based baselines while maintaining strong interpretability, demonstrating particularly superior performance in sensitivity-oriented metrics such as recall—making it well-suited for high-stakes clinical diagnostic scenarios.

0 citationsRead paper

The NetMob26 Dataset: A High-Resolution Multi-Source View of Public Bus Mobility in Niterói

May 18, 2026

This study addresses the scarcity of high-quality public transit ridership and passenger demand data by integrating heterogeneous multi-source datasets—including bus GPS trajectories, 7.2 million fare transactions, route and stop information, weather records, urban infrastructure, and sociodemographic statistics—at the scale of a single city to construct a high-resolution, supply-and-demand-oriented public transit dataset. Rigorous data cleaning, anomaly detection, standardization, and differential privacy-based anonymization ensure both data quality and individual privacy. A controlled-access mechanism is implemented to balance open data sharing with privacy preservation. The resulting dataset enables research on transit efficiency evaluation, passenger flow forecasting, accessibility analysis, and weather impact assessment, thereby providing a robust foundation for intelligent urban transportation governance.

0 citationsRead paper

Exploring label correlations using decision templates for ensemble of classifier chains

Mar 13, 2026

This work addresses the common oversight of inter-label dependencies in multi-label classification, which often limits the performance of ensemble classifier chains. To overcome this limitation, the authors propose UDDTECC, a novel method that explicitly models unconditional label dependencies during the decision template fusion stage for the first time, enabling more intelligent prediction aggregation. By integrating label dependency information into both the ensemble classifier chain architecture and the decision template framework, UDDTECC significantly enhances multi-label classification performance. Experimental results demonstrate that the proposed approach consistently outperforms conventional fusion strategies and stacking-based methods across most evaluation metrics, thereby validating its effectiveness and innovation.

0 citationsRead paper

Certified Lower Bounds and Efficient Estimation of Minimum Accuracy in Quantum Kernel Methods

Dec 23, 2025

Existing minimum-accuracy heuristics for quantum kernel methods suffer from high computational cost, applicability only to balanced datasets, and lack of theoretical guarantees. Method: This work generalizes the notion of minimum accuracy to arbitrary binary classification datasets under approximate quantum hardware, rigorously proving it as a theoretical lower bound on the empirical accuracy of linear classifiers. We propose a Pauli-direction-based Monte Carlo estimation technique, providing probabilistic error bounds and formal convergence guarantees. Crucially, our method evaluates quantum feature map quality without training a quantum support vector machine (QSVM). Contribution/Results: The approach significantly reduces computational complexity while ensuring scalability, theoretical soundness, and hardware compatibility. It constitutes the first provably reliable, practical tool for pre-screening quantum feature maps—enabling efficient, theoretically grounded selection of promising quantum embeddings prior to full quantum kernel training.

0 citationsRead paper

Combining SHAP and Causal Analysis for Interpretable Fault Detection in Industrial Processes

Oct 27, 2025

Complex industrial process data hinder fault detection model performance and interpretability, impeding reliable decision-making. To address this, we propose the first interpretable fault detection framework integrating SHAP values with causal graph modeling: SHAP quantifies feature contributions, while multi-algorithm causal discovery constructs a directed acyclic graph (DAG) to explicitly encode fault propagation mechanisms. Evaluated on the Tennessee Eastman Process benchmark, our method significantly improves fault identification accuracy and precisely identifies key causal drivers—such as cooling and separation systems—enabling root-cause attribution. Crucially, the learned causal structure aligns closely with SHAP-based feature importance rankings. This work achieves synergistic enhancement of predictive performance and causal interpretability, establishing a novel diagnostic paradigm for industrial intelligent maintenance that balances accuracy with operational transparency.

0 citationsRead paper