Results 61 to 70 of about 16,073 (260)

A Language‐Guided Multimodal Foundation Model for Zero‐Shot and Multi‐Task Brain Signal Analysis

Advanced Intelligent Systems, EarlyView.
METIS aligns brain signals with natural‐language instructions to enable zero‐shot and multi‐task brain signal analysis. Pretrained on over 70 000 h of EEG and iEEG recordings, it generalizes across sleep stage classification, epilepsy detection, and neurological disorder diagnosis, providing a scalable foundation model for clinically meaningful brain ...
Mingzhi Chen, Yiyu Gui, Guibo Luo, Yuchao Yang   +3 more
wiley   +1 more source

Research on Diaphragm Pump Fault Diagnosis Method Based on Res‐DCB‐Net

Asia-Pacific Journal of Chemical Engineering, EarlyView.
ABSTRACT Nonstationary pressure pulsation signals of diaphragm pumps contain strong background noise and coupled characteristics. This makes it challenging to extract incipient fault features and to decouple faults with similar physical mechanisms. To address these limitations, this paper proposes a spatiotemporal fault diagnosis model named Res‐DCB ...
Jiahui Wang, Kaili Zhang, Yongxing Song, Zhaoxin Ma, Sitong Guan, Rongwang Chai, Kexiang Ceng, Jingting Liu   +7 more
wiley   +1 more source

Leveraging Big Multitemporal Multisource Satellite Data and Artificial Intelligence for the Detection of Complex and Invisible Features: The Case of Extensive Irrigation Mapping

Archaeological Prospection, EarlyView.
ABSTRACT The detection of buried or obscured archaeological features remains a central challenge in landscape archaeology, particularly in the irrigated floodplains of Mesopotamia where levees and canals formed the basis of complex agrarian systems. This study presents a deep learning–based approach for the large‐scale, automated detection of ancient ...
Nazarij Buławka, Hector A. Orengo, Felipe Lumbreras Ruiz, Iban Berganzo‐Besga, Ekta Gupta   +4 more
wiley   +1 more source

CUDA-LLM: LLMs Can Write Efficient CUDA Kernels

CoRR
Large Language Models (LLMs) have demonstrated strong capabilities in general-purpose code generation. However, generating the code which is deeply hardware-specific, architecture-aware, and performance-critical, especially for massively parallel GPUs, remains a complex challenge.
Wentao Chen, Jiace Zhu, Qi Fan, Yehan Ma, An Zou   +4 more
openaire   +2 more sources

TAMNet: Temporal and adaptive‐frequency network with MixStyle for cross‐region oil and fluid production forecasting

Deep Underground Science and Engineering, EarlyView.
This paper presents temporal and adaptive‐frequency network with MixStyle (TAMNet), a deep time‐series modeling framework for accurate and robust multi‐well oil productivity forecasting. TAMNet integrates transformer and long short‐term memory architectures to capture both short‐ and long‐term temporal dependencies, enhanced by a temporal gate unit ...
Chunxi Yang, Leifeng Meng, Qinghu Fan, Ziang Guo, Ting Bao, Pingdong Zhong, Fulin Luo   +6 more
wiley   +1 more source

Tree‐Boost–Guided CNN–BiLSTM–Transformer for Solar Irradiance Forecasting: Cross‐Regional Evidence for Sustainable Energy Planning

Energy Science &Engineering, EarlyView.
This graphical abstract illustrates a reproducible pipeline that combines gradient‐boosting‐based feature selection with a CNN–BiLSTM–Transformer model to forecast solar irradiance across multi‐site satellite and ground datasets, delivering robust, high‐accuracy predictions that support sustainable grid planning and reliable PV integration.
Muhammad Farhan Hanif, Usama Hassan, Javid Hussain, Irfan Ali Khan, Yuldasheva Gulora, Syed Masood Arif Bukhari   +5 more
wiley   +1 more source

Анализ эффективности гибридного параллельного алгоритма численного решения задачи Коши для эредитарных моделей объемной активности радона в рамках программного комплекса FEVO

Vestnik KRAUNC: Fiziko-Matematičeskie Nauki
В статье представлено исследование вычислительной эффективности гибридного параллельного алгоритма, реализующего нелокальную неявную конечно-разностную схему (IFDS) для численного решения задачи динамики объемной активности радона (ОАР).
Твёрдый, Д.А.
doaj   +1 more source

Land Use and Land Cover Analysis for Solid Waste Management in NCT Delhi Using Fusion Aware Segformer

Land Degradation &Development, EarlyView.
ABSTRACT The use of Land Use Land Cover (LULC) analysis is a fundamental requirement for urban solid waste management (SWM); however, conventional LULC analysis methods are not well suited to the spatio‐temporal variability, multi‐sensor heterogeneity, and seasonal variations of highly dynamic urban environments.
Rubeena Vohra, Ashish Kumar
wiley   +1 more source

Development and Verification of 2D Kinetic MOC Code Based on GPU

Yuanzineng kexue jishu, 2022
Time-dependent, whole-core calculation with high-fidelity pin-resolved details serves an important role in multi-physics reactor applications. However, the limitation of the current CPU has become a sore point. In order to maintain the high accuracy and
ZOU Hang;LIANG Liang;ZHANG Qian;SONG Peitao;ZHAO Qiang
doaj  

Predicting Statistical Signatures of Collective Emission in Disordered Color Center Ensembles

Laser &Photonics Reviews, EarlyView.
We present an efficient simulation framework for modeling collective emission in disordered ensembles of quantum emitters. The low computational complexity enables large‐scale Monte Carlo simulations. Applied to SiV−${\rm SiV}^{-}$ clusters, it predicts thresholded superradiant bursts set by emitter number and quantum efficiency, as well as interaction‐
Qingyi Zhou, Wenxin Wu, Maryam Zahedian, Zongfu Yu, Jennifer T. Choy   +4 more
wiley   +1 more source