Results 41 to 50 of about 3,768 (183)

GRU-BERT for NILM: A Hybrid Deep Learning Architecture for Load Disaggregation

AI
Non-Intrusive Load Monitoring (NILM) aims to disaggregate a household’s total aggregated power consumption into appliance-level usage, enabling intelligent energy management without the need for intrusive metering.
Annysha Huzzat, Ahmed S. Khwaja, Ali A. Alnoman, Bhagawat Adhikari, Alagan Anpalagan, Isaac Woungang   +5 more
doaj   +1 more source

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

Bi-GRU Enhanced Cost-Effective Memory-Aware End-to-End Learning for Geometric Constellation Shaping in Optical Coherent Communications

IEEE Photonics Journal
We propose a cost-effective and memory-aware end-to-end learning scheme utilizing bi-directional gated recurrent unit (bi-GRU) for geometric constellation shaping (GCS) under the first-order regular perturbation (FRP) auxiliary channel.
Zhiyang Liu, Xiaoyu Liu, Shilin Xiao, Weiying Yang, Weisheng Hu   +4 more
doaj   +1 more source

Feasibility of Wind‐Powered Green Hydrogen Production via a Hybrid Graph Neural Network‐Transformer Forecasting Model

Energy Science &Engineering, EarlyView.
ABSTRACT Accurate long‐term wind speed forecasting is pivotal for the strategic planning of renewable energy infrastructure, particularly for assessing the techno‐economic feasibility of wind‐powered green hydrogen facilities. However, capturing the complex spatiotemporal dependencies in climate data remains a significant challenge. This study proposes
Iman Baghaei, Mojtaba Mirhosseini, Alireza Zahedi   +2 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

Attention-based Binary Question Answering Using Hybrid of Bi-LSTM and Bi-GRU

مجلة بغداد للعلوم
Question Answering (QA) is a crucial aspect of Natural Language Processing (NLP) and information retrieval systems. Users usually hope to help with everyday life by teaching the program how to answer questions like a real person.
Nada Fadhil Mohammed, Israa Hadi Ali
doaj   +1 more source

Advanced Hybrid Techniques for Cyberattack Detection and Defense in IoT Networks

SECURITY AND PRIVACY, Volume 8, Issue 2, March/April 2025.
ABSTRACT The Internet of Things (IoT) represents a vast network of devices connected to the Internet, making it easier for users to connect to modern technology. However, the complexity of these networks and the large volume of data pose significant challenges in protecting them from persistent cyberattacks, such as distributed denial‐of‐service (DDoS)
Zaed S. Mahdi, Rana M. Zaki, Laith Alzubaidi   +2 more
wiley   +1 more source

A Multi‐Agent Bidding Strategy in Day‐Ahead Joint Energy and Reserve Markets Considering Risk Preferences

IET Smart Energy Systems, EarlyView.
A PER‐MATD3‐based bidding model for generators in day‐ahead joint energy and reserve markets is proposed. An aggressiveness coefficient quantifies risk preference, KAN improves interpretability and simulation results demonstrate enhanced coordinated decision‐making and training stability.
Xinge Xu, Teng Yan, Xiuming Bao, Dong Liu, Guodong Guo, Yingyun Sun   +5 more
wiley   +1 more source

ISSA optimized spatiotemporal prediction model of dissolved oxygen for marine ranching integrating DAM and Bi-GRU

Frontiers in Marine Science
In marine ranching aquaculture, dissolved oxygen (DO) is a crucial parameter that directly impacts the survival, growth, and profitability of cultured organisms.
Wenjing Liu, Wenjing Liu, Ji Wang, Ji Wang, Zhenhua Li, Zhenhua Li, Qingjie Lu, Qingjie Lu   +7 more
doaj   +1 more source

Multi‐Modal AI Approach in Depression Detection and Treatment: A Systematic Review of Last Decade

WIREs Data Mining and Knowledge Discovery, Volume 16, Issue 3, September 2026.
Overview of multimodal approaches for depression detection and treatment. ABSTRACT Depression is a common and devastating mental health illness with serious personal and societal consequences. Despite advancing treatment techniques, there are still hurdles in the effective diagnosis and treatment of depression, such as prompt diagnosis, personalized ...
Smith K. Khare, Esmaeil S. Nadimi, U. Rajendra Acharya, Victoria Blanes‐Vidal   +3 more
wiley   +1 more source