Advancements in hydrogen production through the integration of renewable energy sources with AI techniques: A comprehensive literature review

Applied Energy, Journal Year: 2025, Volume and Issue: 383, P. 125354 - 125354

Published: Jan. 17, 2025

Language: Английский

---

Scour depth prediction around bridge abutments: A comprehensive review of artificial intelligence and hybrid models

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(2)

Published: Feb. 1, 2025

Scouring around the bridge structure is a major concern of globe. Therefore, precise estimation scour depth essential to minimize failure and provide preventive measures. This review paper aims analyze critical various artificial intelligence (AI) techniques utilized in literature estimate abutment including neural networks (ANN), adaptive neuro-fuzzy inference systems (ANFIS), gene expression programming (GEP), support vector machines (SVM), extreme learning (ELM). The predictive power each technique was assessed terms different performance indicators, such as correlation coefficient (R), mean square error (MSE), predicted values, Taylor's diagram, sensitivity analysis, violin plot. highlights that by comparing AI techniques, ELM GEP have superior performance, especially predicting dealing with complex large datasets. However, limitations proposed solutions been reported for ANN, ANFIS, SVM, group method data handling (GMDH). main challenges GMDH were overfitting hyperparameter tuning. Based on technique, current found satisfactory because its computation speed capability. Moreover, would be helpful researchers working field hydraulics engineering, particularly scouring abutment.

Language: Английский

---

Applications of generative artificial intelligence in the teaching of customs and international law

Región Científica, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 3, 2025

This academic work explores the use of generative AI through Chatbot GPT, Gemini, Copilot, and Meta in teaching customs international law. analysis was carried out with a particular focus on education free trade agreements primary laws Mexico. The study's main findings show that Copilot is valuable tool for searching specific information articles trade. purpose achieved by applying prompts to obtain content question. Likewise, favorable results were obtained cases GPT AI. On other hand, Gemini showed unfavorable because it only general topics requested even provided erroneous information. These types tools allow students make more efficient searches save time when However, they can present or force them delve deeper into subject.

Language: Английский

---

Hybrid BiGRU‐CNN Model for Load Forecasting in Smart Grids with High Renewable Energy Integration

IET Generation Transmission & Distribution, Journal Year: 2025, Volume and Issue: 19(1)

Published: Jan. 1, 2025

ABSTRACT Integrating renewable energy sources into smart grids increases supply and demand management because are intermittent variable. To overcome this type of challenge, short‐term load forecasting (STLF) is essential for managing energy, demand‐side flexibility, the stability with integration. This paper presents a new model called BiGRU‐CNN to improve operation STLF in grids. The integrates bidirectional gated recurrent units (BiGRUs) temporal dependencies convolutional neural networks (CNNs) extract spatial patterns from consumption data. newly developed BiGRU captures past future contexts through processing, CNN component extracts high‐level features enhance accuracy prediction. compared two other hybrid models, CNN‐LSTM CNN‐GRU, on real‐world data American electric power (AEP) ISONE datasets. Simulation results show that proposed outperforms single‐step yielding root mean square error (RMSE) 121.43 123.57 (ISONE), absolute (MAE) 90.95 62.97 percentage (MAPE) 0.61% 0.41% (ISONE). For multi‐step forecasting, yields RMSE 680.02 581.12 MAE 481.12 411.20 MAPE 3.27% 2.91% can generate accurate reliable STLF, which useful massive energy‐integrated

Language: Английский

---

Improving the Accuracy of Groundwater Level Forecasting by Coupling Ensemble Machine Learning Model and Coronavirus Herd Immunity Optimizer

Water Resources Management, Journal Year: 2025, Volume and Issue: unknown

Published: May 3, 2025

Language: Английский

---

A survey of explainable artificial intelligence in healthcare: Concepts, applications, and challenges

Informatics in Medicine Unlocked, Journal Year: 2024, Volume and Issue: unknown, P. 101587 - 101587

Published: Oct. 1, 2024

Language: Английский

---

Detection of cyber attacks in electric vehicle charging systems using a remaining useful life generative adversarial network

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 24, 2025

Abstract Cybersecurity attacks targeting electric vehicle supply equipment (EVSE) and the broader (EV) ecosystem have become an escalating concern with increasing adoption of EVs growing connectivity infrastructure supporting them. The present research aims to contribute continuing cybersecurity studies on charging stations. In line this objective, study proposes remaining useful life (RUL) approach demonstrate potential impact estimating time a cyber attack EVSE what revolutionary changes it can bring security strategies using generative adversarial network (GAN). By taking proactive stance, manuscript will increase reduce economic reputational losses associated incidents. Accurate RUL estimates valuable information about status infrastructure. Thus, informed decisions maintenance crew scheduling are taken. To test technique’s effectiveness, we assess scenarios, including host EV charger (Electric Vehicle Supply Equipment—EVSE) in idle states. Furthermore, prediction results different deep learning models, such as gated recurrent units (GRUs), long short-term memory (LSTM), neural networks (RNNs), convolution (CNNs), multi-layer perceptron (MLP), dense layer integrated (GANs), mean absolute error (MAE), root square (RMSE), squared (MSE), R-squared (R 2 ). Afterward, compare measurements hybrid GAN-LSTM, GAN-GRU, GAN-RNN, GAN-CNN, GAN-MLP, GAN-Dense Layer. GAN-GRU model exhibits highest accuracy lowest MAE (0.0281). On contrary, GAN-CNN displays best overall performance concerning consistency variance explained. According results, integrating GAN into these architectures improves predictive model’s ability identify advance decreases rates.

Language: Английский

---

Application of Artificial Intelligence Technology in the Quality Detection of the Equal Protection Evaluation Report

Artificial Intelligence and Robotics Research, Journal Year: 2025, Volume and Issue: 14(01), P. 104 - 113

Published: Jan. 1, 2025

Language: Английский

---

Self-beneficial transactional social dynamics for cooperation in Shwachman-Diamond syndrome: a mixed-subject analysis using computational pragmatics

Frontiers in Psychology, Journal Year: 2025, Volume and Issue: 15

Published: Jan. 22, 2025

Background Shwachman-Diamond Syndrome (SDS) is a rare genetic disorder with documented cognitive and behavioral challenges. However, its socio-pragmatic dynamics remain underexplored, particularly in cooperative interactions where social norms economic considerations intersect. Objective This study investigates the socio-behavioral of SDS, focusing on how children condition navigate interactions. Using computational pragmatics, we aimed to identify underlying principles guiding their behavior. Methods A cohort 10 (5 5 matched controls) participated ecological tasks, including WISC-V “Comprehension” subtest, NEPSY-II perception Trognon Ecological Side Task for Assessment Speech-Act Processing (TEST-ASAP). Dialogues were analyzed using Topological Kinetic (2TK) model Recurrent Neural Network (RNN), enabling fine-grained insights into interaction patterns. Results Children SDS exhibited behaviors shaped by perceived benefits, often at expense established norms. Unlike classically observed other pathologies such as autism spectrum disorders, responses are influenced directness communication, driven personal gain, regardless indirectness requests. Computational analyses revealed strong divergences dialogical alignment when tasks lacked direct even corrective prompts. Conclusion demonstrate transactional approach interactions, prioritizing benefits over our unique dialogic frameworks, show that gain strongly shapes cooperation These findings underscore need targeted interventions enhance pragmatic skills adaptive functioning given profiles.

Language: Английский

---

Optimization Strategies in Consumer Choice Behavior for Personalized Recommendation Systems Based on Deep Reinforcement Learning

Journal of Organizational and End User Computing, Journal Year: 2025, Volume and Issue: 37(1), P. 1 - 35

Published: Jan. 24, 2025

In domains such as e-commerce and media recommendations, personalized recommendation systems effectively alleviate the issue of information overload. However, existing still face challenges in multimodal data processing, sparsity, dynamic changes user preferences. This paper proposes a Hierarchical Generative Reinforcement Learning Recommendation Optimization framework (HG-RLRO) that addresses these issues by integrating data, Adversarial Networks (GAN), Inverse (IRL), Temporal Difference (HTD). HG-RLRO employs multi-agent architecture to handle textual image utilizes GAN generate simulated behavior mitigate sparsity. IRL dynamically infers preferences across multiple time scales.

Language: Английский

---