Results 241 to 250 of about 16,046 (295)

Developing Synthetic Orthopantomogram Datasets Through Generative Models. [PDF]

Int Dent J
Adnan N, Ahmed SMF, Umer F.
europepmc   +1 more source

Cross‐Method Explanation Stability Under Prediction‐Preserving Perturbations in Explainable AI

Applied AI Letters, Volume 7, Issue 2, June 2026.
The cross‐method analysis showed common vulnerability patterns across gradient‐based and perturbation‐based explainers, whereas Grad‐CAM demonstrated a specific ability to be resilient. Further discussion revealed that, before prediction changes with increasing ε, explanation divergence could already have commenced, indicating that further explanation ...
Muhammad Hasnain, Tooba Gul, Muhammad Fawad Ahmed, Israr Ghani, Imran Ghani   +4 more
wiley   +1 more source

A novel generative oversampling for software defect prediction. [PDF]

Sci Rep
Goyal SR.
europepmc   +1 more source

Application of Artificial Intelligence in Food Science and Nutrition: Challenges and Future Perspectives

eFood, Volume 7, Issue 3, June 2026.
AI application can be very helpful in addressing different issues and shaping novel techniques in food production, food safety and quality, and food intake. AI application in food science, such as the food industry and processing, food safety and packaging, and nutrition.
Yaseen Galali, Pary Hadi, Arkan Mohammed Hassan, Holem Hashm Balaky, Tavga Sulaiman Rashid, Bashdar Abuzed Sadee, Tanya Salam Salih, Hamed Hassanzadeh   +7 more
wiley   +1 more source

Keeping up with the regions: a hybrid machine learning framework for estimating regional input-output tables. [PDF]

Sci Rep
De Pretis F, Tortoli D, Caria S.
europepmc   +1 more source

Backpropagation Network‐Based Contrastive Learning for Unsupervised Domain Adaptation

Engineering Reports, Volume 8, Issue 6, June 2026.
Unsupervised domain adaptation for contractive learning. ABSTRACT This study introduces a new method for domain adaptation for image classification tasks that aims to improve the model's performance on a target domain after being trained on a source domain.
Yushui Xiao, Yong Huang, Yujie Li
wiley   +1 more source

On the generalization limits of quantum generative adversarial networks with pure state generators. [PDF]

Sci Rep
Frkatovic J, Malemath A, Kankeu I, Werner Y, Tschöpe M, Rey VF, Suh S, Lukowicz P, Palaiodimopoulos N, Kiefer-Emmanouilidis M.   +9 more
europepmc   +1 more source

Defense Algorithm Based on Reinforcement Learning and Digital Twin for Distribution Protection Devices Adversarial Samples

Engineering Reports, Volume 8, Issue 6, June 2026.
Power system protection devices are vulnerable to adversarial samples. We propose a digital twin and reinforcement learning framework. It trains a virtual model within safe operational boundaries, reducing the false operation rate to below 3.5%. The model's inference delay is under 10 ms, meeting real‐time protection requirements.
Wei Zhang, Shuai Zhang, Song Wang, Zheran Zheng   +3 more
wiley   +1 more source

A review of recent advances in generative artificial intelligence models for biomolecular sciences. [PDF]

Acta Pharm Sin B
Jiang J, Li D, Wang G, Hayes N, Shi Y, Qiu H, Zhang B, Zhou T, Wei GW.   +8 more
europepmc   +1 more source

Semantic Evolution and Consistency Learning for Robust Malicious Network Traffic Detection

Engineering Reports, Volume 8, Issue 6, June 2026.
This paper proposes a semantic evolution and consistency network (SECN) for malicious traffic detection, modeling attack behaviors as temporally evolving semantics. By integrating dual‐level temporal representation and semantic consistency constraints, SECN achieves robust detection and strong generalization under encrypted, cross‐dataset, and unknown ...
Jing Yang, Wei Tan
wiley   +1 more source