Search Results (3,737)

The rapid shift toward electric vehicles (EVs) has underscored the critical importance of battery pack crashworthiness, creating a demand for lightweight, energy-absorbing protective systems. This review systematically explores bio-inspired cellular structures as promising solutions for improving the impact resistance of EV battery packs. Inspired by natural geometries, these designs exhibit superior energy absorption, controlled deformation behavior, and high structural efficiency compared to conventional configurations. A comprehensive analysis of experimental, numerical, and theoretical studies published up to mid-2025 was conducted, with emphasis on design strategies, optimization techniques, and performance under diverse loading conditions. Findings show that auxetic, honeycomb, and hierarchical multi-cell architectures can markedly enhance specific energy absorption and deformation control, with improvements often exceeding 100% over traditional structures. Finite element analyses highlight their ability to achieve controlled deformation and efficient energy dissipation, while optimization strategies, including machine learning, genetic algorithms, and multi-objective approaches, enable effective trade-offs between energy absorption, weight reduction, and manufacturability. Persistent challenges remain in structural optimization, overreliance on numerical simulations with limited experimental validation, and narrow focus on a few bio-inspired geometries and thermo-electro-mechanical coupling, for which engineering solutions are proposed. The review concludes with future research directions focused on geometric optimization, multi-physics modeling, and industrial integration strategies. Collectively, this work provides a comprehensive framework for advancing next-generation crashworthy battery pack designs that integrate safety, performance, and sustainability in electric mobility. Full article

This paper presents an in-depth review of cybersecurity challenges and advanced solutions in modern power-generation systems, with particular emphasis on smart grids. It examines vulnerabilities in devices such as smart meters (SMs), Phasor Measurement Units (PMUs), and Remote Terminal Units (RTUs) to cyberattacks, including False Data Injection Attacks (FDIAs), Denial of Service (DoS), and Replay Attacks (RAs). The study evaluates cutting-edge detection and mitigation techniques, such as Cluster Partition, Fuzzy Broad Learning System (CP-BLS), multimodal deep learning, and autoencoder models, achieving detection accuracies of (up to 99.99%) for FDIA identification. It explores critical aspects of power generation, including resource assessment, environmental and climatic factors, policy and regulatory frameworks, grid and storage integration, and geopolitical and social dimensions. The paper also addresses the transmission and distribution (T&D) system, emphasizing the role of smart-grid technologies and advanced energy-routing strategies that leverage Artificial Neural Networks (ANNs), Generative Adversarial Networks (GANs), and game-theoretic approaches to optimize energy flows and enhance grid stability. Future research directions include high-resolution forecasting, adaptive optimization, and the integration of quantum–AI methods to improve scalability, reliability, and resilience. Full article

A learning management system (LMS) plays a crucial role in supporting students’ educational activities by centralized platforms for course delivery, communication, and student support. Recently, many universities have integrated chatbots into their LMS to assist students with various inquiries and tasks. However, existing chatbots often necessitate human interventions to manually respond to complex queries, resulting in limited scalability and efficiency. In this paper, we present a memory-augmented large language model (LLM) framework that enhances the reasoning and contextual continuity of LMS-based chatbots. The proposed framework first embeds user queries and retrieves semantically relevant entries from various LMS resources, including instructional documents and academic frequently asked questions. Retrieved entries are then filtered through a two-stage confidence filtering process that combines similarity thresholds and LLM-based semantic validation. Validated information, along with user queries, is processed by LLM for response generation. To maintain coherence in multi-turn interactions, the chatbot incorporates short-term, long-term, and temporal event memories, which track conversational flow and personalize responses based on user-specific information, such as recent activity history and individual preferences. To evaluate response quality, we employed a multi-layered evaluation strategy combining BERTScore-based quantitative measurement, an LLM-as-a-Judge approach for automated semantic assessment, and a user study under multi-turn scenarios. The evaluation results consistently confirm that the proposed framework improves the consistency, clarity, and usefulness of the responses. These findings highlight the potential of memory-augmented LLMs for scalable and intelligent learning support within university environments. Full article

Artificial Intelligence (AI) is increasingly integrated into ship design workflows, offering enhanced capabilities for hydrodynamic and structural optimization. This review focuses on AI-based methods applied to key design tasks such as hull resistance prediction, structural weight reduction, and performance-driven form optimization. Techniques examined include deep neural networks (DNNs), support vector machines (SVMs), tree-based ensemble models, genetic algorithms (GAs), and surrogate modeling approaches. Comparative analyses from the literature indicate that ensemble tree methods, such as XGBoost, have achieved predictive accuracies up to $R^2$ = 0.995 in speed–power modeling, marginally surpassing DNN performance, while GA-based structural optimization studies have reported weight reductions exceeding 10%. The findings confirm that no single method is universally superior; rather, effectiveness depends on the problem definition, data quality, and computational resources available. Hybrid strategies that combine physics-based modeling with data-driven learning have demonstrated improved generalization, reduced data requirements, and enhanced interpretability. Practical challenges remain, including limited access to open high-fidelity datasets, the computational demands of complex models, and balancing predictive accuracy with explainability. The review concludes that AI should be employed as a complementary toolkit to augment human expertise, with method selection guided by design objectives, constraints, and integration within the broader ship design process. Full article

Existing visual SLAM systems with neural representations excel in static scenes but fail in dynamic environments where moving objects degrade performance. To address this, we propose a robust dynamic SLAM framework combining classic geometric features for localization with learned photometric features for dense mapping. Our method first tracks objects using instance segmentation and a Kalman filter. We then introduce a cascaded, coarse-to-fine strategy for efficient motion analysis: a lightweight sparse optical flow method performs a coarse screening, while a fine-grained dense optical flow clustering is selectively invoked for ambiguous targets. By filtering features on dynamic regions, our system drastically improves camera pose estimation, reducing Absolute Trajectory Error by up to 95% on dynamic TUM RGB-D sequences compared to ORB-SLAM3, and generates clean dense maps. The 3D Gaussian Splatting backend, optimized with a Gaussian pyramid strategy, ensures high-quality reconstruction. Validations on diverse datasets confirm our system’s robustness, achieving accurate localization and high-fidelity mapping in dynamic scenarios while reducing motion analysis computation by 91.7% over a dense-only approach. Full article

To foster the performance of wireless communication while saving energy, the integration of Intelligent Reflecting Surfaces (IRS) into autonomous vehicle (AV) communication networks is considered a powerful technique. This paper proposes a novel IRS-assisted vehicular communication model that combines Lagrange optimization and Gradient-Based Phase Optimization to determine the optimal transmission power, optimal interference transmission power, and IRS phase shifts. Additionally, the proposed model help increase the Signal-to-Interference-plus-Noise Ratio (SINR) by utilizing IRS, which leads to maximizes energy efficiency and the achievable data rate under a variety of environmental conditions, while guaranteeing that resource limits are satisfied. In order to represent dense vehicular environments, practical constraints for the system model, such as IRS reflection efficiency and interference, have been incorporated from multiple sources, namely, Device-to-Device (D2D), Vehicle-to-Vehicle (V2V), Vehicle-to-Base Station (V2B), and Cellular User Equipment (CUE). A Lagrangian optimization approach has been implemented to determine the required transmission interference power and the best IRS phase designs in order to enhance the system performance. Consequently, a one-dimensional convolutional neural network has been implemented for the optimized data provided by this framework as training input. This deep learning algorithm learns to predict the required optimal IRS settings quickly, allowing for real-time adaptation in dynamic wireless environments. The obtained results from the simulation show that the combined optimization and prediction strategy considerably enhances the system reliability and energy efficiency over baseline techniques. This study lays a solid foundation for implementing IRS-assisted AV networks in real-world settings, hence facilitating the development of next-generation vehicular communication systems that are both performance-driven and energy-efficient. Full article

Gray mold is one of the major diseases affecting tomato production. Its early symptoms are often inconspicuous, yet the disease spreads rapidly, leading to severe economic losses. Therefore, the development of efficient and non-destructive early detection technologies is of critical importance. At present, multispectral imaging-based detection methods are constrained by two major bottlenecks: limited sample size and single modality, which hinder precise recognition at the early stage of infection. To address these challenges, this study explores a detection approach integrating multispectral fluorescence and reflectance imaging, combined with machine learning algorithms, to enhance early recognition of tomato gray mold. Particular emphasis is placed on evaluating the effectiveness of multimodal information fusion in extracting early disease features, and on elucidating the quantitative relationships between disease progression and key physiological indicators such as chlorophyll content, water content, malondialdehyde levels, and antioxidant enzyme activities. Furthermore, an improved WGAN-GP (Wasserstein Generative Adversarial Network with Gradient Penalty) is employed to alleviate data scarcity under small-sample conditions. The results demonstrate that multimodal data fusion significantly improves model sensitivity to early-stage disease detection, while WGAN-GP-based data augmentation effectively enhances learning performance with limited samples. The Random Forest model achieved an early recognition precision of 97.21% on augmented datasets, and transfer learning models attained an overall precision of 97.56% in classifying different disease stages. This study provides an effective approach for the early prediction of tomato gray mold, with potential application value in optimizing disease management strategies and reducing environmental impact. Full article

Analog and mixed-signal integrated circuit (AMS-IC) designs remain a critical yet challenging aspect within electronic design automation (EDA), primarily due to the inherent complexity, nonlinear behavior, and increasing variability associated with advanced semiconductor technologies. Traditional manual and intuition-driven methodologies for AMS-ICs design, which rely heavily on iterative simulation loops and extensive designer experience, face significant limitations concerning efficiency, scalability, and reproducibility. Recently, machine learning (ML) techniques have emerged as powerful tools to address these challenges, offering significant enhancements in modeling, abstraction, optimization, and automation capabilities for AMS-ICs. This review systematically examines recent advancements in ML-driven methodologies applied to analog circuit design, specifically focusing on modeling techniques such as Bayesian inference and neural network (NN)-based surrogate models, optimization and sizing strategies, specification-driven predictive design, and artificial intelligence (AI)-assisted design automation for layout generation. Through an extensive survey of the existing literature, we analyze the effectiveness, strengths, and limitations of various ML approaches, identifying key trends and gaps within the current research landscape. Finally, the paper outlines potential future research directions aimed at advancing ML integration in AMS-ICs design, emphasizing the need for improved explainability, data availability, methodological rigor, and end-to-end automation. Full article

Deep learning (DL) has revolutionized medical image analysis (MIA), enabling early anomaly detection, precise lesion segmentation, and automated disease classification. However, its clinical integration faces two major challenges: reliance on limited, narrowly annotated datasets that inadequately capture real-world patient diversity, and the inherent “black-box” nature of DL decision-making, which complicates physician scrutiny and accountability. Eye tracking (ET) technology offers a transformative solution by capturing radiologists’ gaze patterns to generate supervisory signals. These signals enhance DL models through two key mechanisms: providing weak supervision to improve feature recognition and diagnostic accuracy, particularly when labeled data are scarce, and enabling direct comparison between machine and human attention to bridge interpretability gaps and build clinician trust. This approach also extends effectively to multimodal learning models (MLMs) and vision–language models (VLMs), supporting the alignment of machine reasoning with clinical expertise by grounding visual observations in diagnostic context, refining attention mechanisms, and validating complex decision pathways. Conducted in accordance with the PRISMA statement and registered in PROSPERO (ID: CRD42024569630), this review synthesizes state-of-the-art strategies for ET-DL integration. We further propose a unified framework in which ET innovatively serves as a data efficiency optimizer, a model interpretability validator, and a multimodal alignment supervisor. This framework paves the way for clinician-centered AI systems that prioritize verifiable reasoning, seamless workflow integration, and intelligible performance, thereby addressing key implementation barriers and outlining a path for future clinical deployment. Full article

Retinal vessel segmentation is crucial for analyzing medical images, where symmetry in vascular structures plays a fundamental role in diagnostic accuracy. In recent years, the rapid advancements in deep learning have provided robust tools for predicting detailed images. However, within many scenarios of medical image analysis, the task of data annotation remains costly and challenging to acquire. By leveraging symmetry-aware semi-supervised learning frameworks, our approach requires only a small portion of annotated data to achieve remarkable segmentation outcomes, significantly diminishing the costs associated with data labeling. At present, most semi-supervised approaches rely on pseudo-label update strategies. Nonetheless, while these methods generate high-quality pseudo-label images, they inevitably contain minor prediction errors in a few pixels, which can accumulate during iterative training, ultimately impacting learner performance. To address these challenges, we propose an enhanced semi-supervised vessel semantic segmentation approach that employs a symmetry-preserving pixel-level filtering strategy. This method retains highly reliable pixels in pseudo labels while eliminating those with low reliability, ensuring spatial symmetry coherence without altering the intrinsic spatial information of the images. The filtering strategy integrates various techniques, including probability-based filtering, edge detection, image filtering, mathematical morphology methods, and adaptive thresholding strategies. Each technique plays a unique role in refining the pseudo labels. Extensive experimental results demonstrate the superiority of our proposed method, showing that each filtering strategy contributes to enhancing learner performance through symmetry-constrained optimization. Full article

Fuel Moisture Content (FMC) is a critical indicator for assessing forest fire risk and formulating early warning strategies, as its spatiotemporal dynamics directly influence the accuracy of fire danger rating. To improve the accuracy of forest FMC estimation, this study proposes an innovative deep learning method integrating multi-source remote sensing data. By combining the global feature extraction capability of the Transformer architecture with the local temporal modeling advantages of Gated Recurrent Units (GRU) (referred to as the Transformer-GRU model), a high-precision FMC estimation framework is established. The study focuses on forested areas in California, USA, utilizing ground-measured FMC data alongside multi-source remote sensing datasets from MODIS, Sentinel-1, and Sentinel-2. A systematic comparison was conducted among Transformer-GRU model, standalone Transformer models, single GRU models, and two classical machine learning models (Random Forest, RF, and Support Vector Regression, SVR). Additionally, forward feature selection was employed to evaluate the performance of different models and feature combinations. The results demonstrate that (1) All models effectively utilize the derived features from multi-source remote sensing data, confirming the significant enhancement of multi-source data fusion for forest FMC estimation; (2) The Transformer-GRU model outperforms other models in capturing the nonlinear relationship between FMC and remote sensing data, achieving superior estimation accuracy (R² = 0.79, MAE = 8.70%, RMSE = 11.44%, rRMSE = 12.60%); (3) The spatiotemporal distribution patterns of forest FMC in California generated by the Transformer-GRU model align well with regional geographic characteristics and climatic variability, while exhibiting a strong relationship with historical wildfire occurrences. The proposed Transformer-GRU model provides a novel approach for high-precision FMC estimation, offering reliable technical support for dynamic forest fire risk early warning and resource management. Full article

Current machine learning approaches focusing on motor symptoms in Parkinson’s disease are commonly trained on small datasets and often lack generalizability from developmental setups to clinical applications. Foundation models using large, unlabeled datasets of healthy participants through self-supervised learning appear attractive for such setups with limited samples, despite the potential impact of motoric symptoms. Acting as an exemplar, this study aims to evaluate the robustness of fine-tuned models in recognizing movements related to motor examinations across datasets and recording setups. Accelerometer data of 51 participants with Parkinson’s disease in three different training and fine-tuning setups were used to tailor the general model to the disease. Training the model on pre-trained weights, both partially (F₁ = 0.70) and fully (F₁ = 0.69), statistically significantly outperformed training the model from scratch (F₁ = 0.55) in a nested cross-validation. For evaluation, the model’s ability to process data recorded from 24 patients in clinic was tested. The models achieved lower mean F₁ scores of 0.33 (train from scratch), 0.43 for full, and 0.48 for partial fine-tuning, but demonstrated improved generalizability and robustness regarding the orientation of sensors compared to training from scratch. Utilizing foundation models for accelerometer data trained on healthy participants and fine-tuned for clinical applications in movement disorders appears as an effective strategy for optimized generalizability with small datasets. Full article

Effective thermal management is crucial for optimizing the performance, efficiency, and durability of fuel-cell technologies, including proton-exchange membrane fuel cells (PEMFCs) and solid-oxide fuel cells (SOFCs). The operation of fuel cells involves complex heat generation mechanisms, primarily driven by electrochemical reactions, which can lead to significant energy loss as heat. This review examines the specific heat generation sources and challenges associated with different fuel-cell types, highlighting the critical importance of effective thermal management strategies. Key techniques for thermal regulation, including active and passive cooling systems, are examined in detail. Active cooling methods like liquid cooling and air cooling are effective in dissipating excess heat, while passive methods leverage advanced materials and optimized designs to enhance natural heat dissipation. Furthermore, innovative heat recovery systems are explored, demonstrating their potential to enhance overall energy efficiency by capturing and repurposing waste heat. The integration of machine learning techniques has arisen as a promising avenue for advancing temperature control in fuel cells. Reinforcement learning, deep learning algorithms, and support vector machines, along with artificial neural networks, are discussed in the context of their application in managing temperature dynamics and optimizing thermal performance. The review also emphasizes the significance of real-time monitoring, as well as adaptive control strategies to respond effectively to the dynamic operating conditions of fuel cells. Understanding and applying these thermal management strategies is essential for the successful commercialization of fuel cells across various sectors, ranging from automotive to stationary power generation. With the growing demand for clean energy solutions, progress in thermal management techniques will be crucial in improving the dependability and practicality of fuel-cell systems. Full article

This study explores how the integration of generative artificial intelligence, multi-objective evolutionary optimization, and reinforcement learning can enable sustainable and cost-effective decision-making in supply chain strategy. Using real-world retail demand data enriched with synthetic sustainability attributes, we trained a Variational Autoencoder (VAE) to generate plausible future demand scenarios. These were used to seed a Non-Dominated Sorting Genetic Algorithm (NSGA-II) aimed at identifying Pareto-optimal sourcing strategies that balance delivery cost and CO₂ emissions. The resulting Pareto frontier revealed favorable trade-offs, enabling up to 50% emission reductions for only a 10–15% cost increase. We further deployed a deep Q-learning (DQN) agent to dynamically manage weekly shipments under a selected balanced strategy. The reinforcement learning policy achieved an additional 10% emission reduction by adaptively switching between green and conventional transport modes in response to demand and carbon pricing. Importantly, the agent also demonstrated resilience during simulated supply disruptions by rerouting decisions in real time. This research contributes a novel AI-based decision architecture that combines generative modeling, evolutionary search, and adaptive control to support sustainability in complex and uncertain supply chains. Full article

Wetlands are natural ecosystems of great ecological and economic value. They provide undeniable ecosystem services that contribute to promoting sustainable development. Exposed to different pressures, these limnic ecosystems are particularly vulnerable to climate change. Thus, assessing wetland vulnerability is of utmost importance. Based on a systematic selection of relevant peer-reviewed studies, this paper helps to develop a general vision of the methods used to assess wetland vulnerability in different contexts, emphasizing the use of advanced computational approaches. Hence, an overview of different cases of wetlands all across the five continents and of different types of habitats is presented. Whether the wetland is permanently or seasonally flooded, coastal, or tropical, this study enables the analysis of diverse, already established vulnerability evaluation index systems. Some of these indices were computed using geographic information systems (GISs), artificial intelligence (AI), machine learning (ML), spatial principal component analysis (SPCA) and driver–pressure–state–impact–response (DPSIR) as evaluation models. Indeed, given the adoption of different methods, diverse models, and analytical approaches under different scenarios, the vulnerability assessment process should be seen as an iterative rather than a definitive process. An accurate wetland vulnerability assessment is essential for ensuring the sustainability of wetland ecosystems and for informing effective conservation and management strategies. Full article