Results 231 to 240 of about 243,531 (318)

Application of GAN–CNN in Risk Assessment of Pipeline Failures in Multiphase Pipeline With Image Information Encoding Approach

Energy Science &Engineering, EarlyView.
Field data from multiphase pipelines are transformed into grayscale images via Image Information Encoding, preserving feature values and interparameter relationships. A GAN–CNN model generates synthetic images that are decoded to expand the original database.
Sihang Chen, Na Zhang, Biyuan Shui
wiley   +1 more source

CCIW: Cover-Concealed Image Watermarking for Dual Protection of Privacy and Copyright. [PDF]

Entropy (Basel)
Li R, Wang S, Li M, Ren H.
europepmc   +1 more source

A Review of Overcurrent Protection in Smart Grids Under Cyber‐Physical Threats With a Cyber‐Physical Evaluation Framework

Energy Science &Engineering, EarlyView.
By manipulating current and voltage measurements, an assailant can induce unwanted relay action while attempting to avoid detection. Detecting advanced cyber intrusions in power protection environments requires specialised data analysis and anomaly detection methods.
Feras Alasali, Anas AlMajali, Naser Naily, Hassen Loukil, Salah AbuGhalyon, William Holderbaum, Abdelaziz Salah Saidi   +6 more
wiley   +1 more source

Large reasoning models are autonomous jailbreak agents. [PDF]

Nat Commun
Hagendorff T, Derner E, Oliver N.
europepmc   +1 more source

Decentralized Federated Learning for Wind Turbine Bearing Prognostics Under Data Scarcity and Statistical Heterogeneity

Energy Science &Engineering, EarlyView.
This paper proposes a decentralized peer‐to‐peer federated learning framework for wind turbine bearing remaining useful life prediction, introducing a virtual client paradigm in which statistical health indicators serve as independent feature‐level clients—enabling privacy‐preserving collaborative prognostics from a single physical asset under ...
Jihene Sidhom, Lotfi Saidi, Eric Bechhoefer   +2 more
wiley   +1 more source

Dialectal substitution as an adversarial approach for evaluating Arabic NLP robustness. [PDF]

Sci Rep
Alshemali B.
europepmc   +1 more source

A Deep Learning Framework for Forecasting Medium‐Term Covariance in Multiasset Portfolios

Journal of Forecasting, EarlyView.
ABSTRACT Forecasting the covariance matrix of asset returns is central to portfolio construction, risk management, and asset pricing. However, most existing models struggle at medium‐term horizons, several weeks to months, where shifting market regimes and slower dynamics prevail.
Pedro Reis, Ana Paula Serra, João Gama
wiley   +1 more source

A Diffusion-Based Time-Frequency Dual-Stream Contrastive Learning Model for Multivariate Time Series Anomaly Detection. [PDF]

Entropy (Basel)
Wu K, Xu C, Zhang R, Lu W, Ma Y, Zhang E, Tan K.   +6 more
europepmc   +1 more source

From text to multimodal: a survey of adversarial example generation in question answering systems [PDF]

Gülsüm Yiğit, Mehmet Fatih Amasyalı
openalex   +1 more source

Artificial Intelligence in Ophthalmology: Current Status, Challenges, and Future Perspectives

Health Care Science, EarlyView.
Current research of artificial intelligence (AI) in ophthalmology. ABSTRACT Artificial intelligence (AI) is revolutionizing ophthalmology by providing innovative solutions for disease screening, diagnosis, personalized treatment, and the delivery of global healthcare services.
She Chongyang, Tao Yong
wiley   +1 more source