Selected work

Representative Papers

Fruit-HSNet: A Machine Learning Approach for Hyperspectral Image-Based Fruit Ripeness Prediction

Aug 02, 2026

This study addresses the challenges of limited labeled data and poor generalization across cameras and fruit species in hyperspectral image-based fruit maturity prediction. To overcome these issues, the authors propose Fruit-HSNet, a novel architecture that integrates spatial features extracted via Fourier transform with spectral signatures from the central pixel, fusing them through a learnable mechanism and employing a tailored classifier. Evaluated on the DeepHS Fruit dataset under realistic multi-camera and multi-species conditions, the model achieves an overall accuracy of 70.73%, representing a 12% improvement over existing methods. This work establishes a new state-of-the-art performance for the task by demonstrating, for the first time, strong cross-domain generalization capabilities in fruit maturity assessment using hyperspectral imaging.

0 citationsRead paper

PriEval-Protect: A Unified Framework for Privacy Evaluation and Protection in Healthcare Systems

Jul 15, 2026

This work addresses the limitations of current healthcare data privacy compliance approaches, which rely heavily on manual processes and treat policy auditing and technical risk assessment in isolation, leading to inefficiency and error-proneness. To overcome these challenges, the authors propose PriEval-Protect, a two-stage framework that integrates legal large language models with data-level privacy metrics during the evaluation phase. By leveraging retrieval-augmented generation (RAG), cryptographic identification, and analytic hierarchy process (AHP) weighting, the framework produces an interpretable, composite risk score. In the protection phase, it dynamically recommends mitigation strategies—such as federated learning or differential privacy—based on this score. Validated on real-world hospital data, PriEval-Protect enables synergistic compliance with GDPR and HIPAA, delivers precise risk assessment, and offers explainable privacy safeguards, significantly enhancing the automation and consistency of privacy governance.

0 citationsRead paper

Decoherence as Defence and the Magnitude of Noise Regularisation: A Rigorous N -Qubit Theory of Stochastic Quantum Neural Networks for Adversarially Robust Network Intrusion Detection

Jun 23, 2026

This study addresses the vulnerability of network intrusion detection systems under white-box adversarial attacks and the unclear regularization mechanisms of noise in quantum neural networks. To this end, the authors propose a theoretical framework of N-qubit Stochastic Quantum Neural Networks (SQNN) that incorporates decoherence to enhance adversarial robustness. By establishing a decoherence contraction theorem, they quantify the contracting effect of depolarizing noise on readout operators and reveal that quantum gate-level dropout and depolarizing noise correspond to equivalent regularization mechanisms in weight and output spaces, respectively. Experiments on the NSL-KDD dataset and neutral-atom hardware demonstrate that noisy SQNN significantly outperforms its noise-free counterpart under strong ℓ∞/ℓ₂ adversarial attacks (p=0.04), preventing accuracy from plummeting from 95% to 47% and reducing robustness variance by approximately 50%. Thirty repeated trials further confirm the high predictive accuracy of the proposed regularization formula (p<10⁻⁴).

0 citationsRead paper

Recent publications

Latest Papers

Fruit-HSNet: A Machine Learning Approach for Hyperspectral Image-Based Fruit Ripeness Prediction

Aug 02, 2026

This study addresses the challenges of limited labeled data and poor generalization across cameras and fruit species in hyperspectral image-based fruit maturity prediction. To overcome these issues, the authors propose Fruit-HSNet, a novel architecture that integrates spatial features extracted via Fourier transform with spectral signatures from the central pixel, fusing them through a learnable mechanism and employing a tailored classifier. Evaluated on the DeepHS Fruit dataset under realistic multi-camera and multi-species conditions, the model achieves an overall accuracy of 70.73%, representing a 12% improvement over existing methods. This work establishes a new state-of-the-art performance for the task by demonstrating, for the first time, strong cross-domain generalization capabilities in fruit maturity assessment using hyperspectral imaging.

0 citationsRead paper

PriEval-Protect: A Unified Framework for Privacy Evaluation and Protection in Healthcare Systems

Jul 15, 2026

This work addresses the limitations of current healthcare data privacy compliance approaches, which rely heavily on manual processes and treat policy auditing and technical risk assessment in isolation, leading to inefficiency and error-proneness. To overcome these challenges, the authors propose PriEval-Protect, a two-stage framework that integrates legal large language models with data-level privacy metrics during the evaluation phase. By leveraging retrieval-augmented generation (RAG), cryptographic identification, and analytic hierarchy process (AHP) weighting, the framework produces an interpretable, composite risk score. In the protection phase, it dynamically recommends mitigation strategies—such as federated learning or differential privacy—based on this score. Validated on real-world hospital data, PriEval-Protect enables synergistic compliance with GDPR and HIPAA, delivers precise risk assessment, and offers explainable privacy safeguards, significantly enhancing the automation and consistency of privacy governance.

0 citationsRead paper

Decoherence as Defence and the Magnitude of Noise Regularisation: A Rigorous N -Qubit Theory of Stochastic Quantum Neural Networks for Adversarially Robust Network Intrusion Detection

Jun 23, 2026

This study addresses the vulnerability of network intrusion detection systems under white-box adversarial attacks and the unclear regularization mechanisms of noise in quantum neural networks. To this end, the authors propose a theoretical framework of N-qubit Stochastic Quantum Neural Networks (SQNN) that incorporates decoherence to enhance adversarial robustness. By establishing a decoherence contraction theorem, they quantify the contracting effect of depolarizing noise on readout operators and reveal that quantum gate-level dropout and depolarizing noise correspond to equivalent regularization mechanisms in weight and output spaces, respectively. Experiments on the NSL-KDD dataset and neutral-atom hardware demonstrate that noisy SQNN significantly outperforms its noise-free counterpart under strong ℓ∞/ℓ₂ adversarial attacks (p=0.04), preventing accuracy from plummeting from 95% to 47% and reducing robustness variance by approximately 50%. Thirty repeated trials further confirm the high predictive accuracy of the proposed regularization formula (p<10⁻⁴).

0 citationsRead paper