Search Results (429)

This paper reviews recent progress in fault detection, reliability analysis, and predictive maintenance methods for grid-connected solar photovoltaic (PV) systems. With the rising adoption of solar power globally, maintaining system reliability and performance is vital for a sustainable energy supply. Common faults discussed include panel degradation, electrical issues, inverter failures, and grid disturbances, all of which affect system efficiency and safety. While traditional diagnostics like thermal imaging and V-I curve analysis offer valuable insights, they mostly detect issues reactively. New approaches using Artificial Intelligence (AI), Machine Learning (ML), and Internet of Things (IoT) enable real-time monitoring and predictive diagnostics, significantly enhancing accuracy and reliability. This study represents the introduction of a consolidated decision framework and taxonomy that systematically integrates and evaluates the fault types, symptoms, signals, diagnostics, and field-readiness across both plant types and voltage levels. Moreover, this study provides quantitative benchmarks of performance metrics, energy losses, and diagnostic accuracies of 95% confidence intervals. Adopting these advanced techniques promotes proactive management, reducing operational risks and downtime, thus reinforcing the resilience and sustainability of solar power infrastructure. Full article

Type 2 diabetes mellitus (T2DM) is a growing global health challenge, expected to affect over 600 million people by 2045. The discovery of new antidiabetic agents remains resource-intensive, motivating the use of machine learning (ML) for virtual screening based on molecular structure. In this study, we developed a predictive pipeline integrating two distinct descriptor types: high-dimensional numerical features from the Mordred library (>1800 2D/3D descriptors) and categorical ontological annotations from the ClassyFire and ChEBI systems. These encode hierarchical chemical classifications and functional group labels. The dataset included 45 active compounds and thousands of inactive molecules, depending on the descriptor system. To address class imbalance, we applied SMOTE and created balanced training and test sets while preserving independent validation sets. Thirteen ML models—including regression, SVM, naive Bayes, decision trees, ensemble methods, and others—were trained using stratified 12-fold cross-validation and evaluated across training, test, and validation. Ridge Regression showed the best generalization (MCC = 0.814), with Gradient Boosting following (MCC = 0.570). Feature importance analysis highlighted the complementary nature of the descriptors: Ridge Regression emphasized ClassyFire taxonomies such as CHEMONTID:0000229 and CHEBI:35622, while Mordred-based models (e.g., Random Forest) prioritized structural and electronic features like MAXsssCH and ETA_dEpsilon_D. This study is the first to systematically integrate and compare structural and ontological descriptors for antidiabetic compound prediction. The framework offers a scalable and interpretable approach to virtual screening and can be extended to other therapeutic domains to accelerate early-stage drug discovery. Full article

Smart manufacturing applications increasingly rely on time-series data from Industrial IoT sensors, yet these data streams often contain data quality issues (DQIs) that affect analysis and disrupt production. While traditional Machine Learning methods are difficult to apply due to the small amount of data available, the knowledge-based approach of Case-Based Reasoning (CBR) offers a way to reuse previously gained experience. We introduce the first end-to-end Case-Based Reasoning (CBR) framework that both detects and remedies DQIs in near real time, even when only a handful of annotated fault instances are available. Our solution encodes expert experience in the four CBR knowledge containers: (i) a vocabulary that represents sensor streams and their context in the DataStream format; (ii) a case base populated with fault-annotated event logs; (iii) tailored similarity measures—including a weighted Dynamic Time Warping variant and structure-aware list mapping—that isolate the signatures of missing-value, missing-sensor, and time-shift errors; and (iv) lightweight adaptation rules that recommend concrete repair actions or, where appropriate, invoke automated imputation and alignment routines. A case study is used to examine and present the suitability of the approach for a specific application domain. Although the case study demonstrates only limited capabilities in identifying Data Quality Issues (DQIs), we aim to support transparent evaluation and future research by publishing (1) a prototype of the Case-Based Reasoning (CBR) system and (2) a publicly accessible, meticulously annotated sensor-log benchmark. Together, these resources provide a reproducible baseline and a modular foundation for advancing similarity metrics, expanding the DQI taxonomy, and enabling knowledge-intensive reasoning in IoT data quality management. Full article

Taxonomies provide essential hierarchical structures for classifying information, enabling effective retrieval and knowledge organization in diverse domains such as e-commerce, academic research, and web search. Traditional taxonomy construction, heavily reliant on manual curation by domain experts, faces significant challenges in scalability, cost, and consistency when dealing with the exponential growth of digital data. Recent advancements in Large Language Models (LLMs) and Natural Language Processing (NLP) present powerful opportunities for automating this complex process. This paper explores the potential of LLMs for automated taxonomy generation, focusing on methodologies incorporating semantic embedding generation, keyword extraction, and machine learning clustering algorithms. We specifically investigate and conduct a comparative analysis of two primary LLM-based approaches using a dataset of eBay product descriptions. The first approach involves fine-tuning a pre-trained LLM using structured hierarchical data derived from chain-of-layer clustering outputs. The second employs prompt-engineering techniques to guide LLMs in generating context-aware hierarchical taxonomies based on clustered keywords without explicit model retraining. Both methodologies are evaluated for their efficacy in constructing organized multi-level hierarchical taxonomies. Evaluation using semantic similarity metrics (BERTScore and Cosine Similarity) against a ground truth reveals that the fine-tuning approach yields higher overall accuracy and consistency (BERTScore F1: 70.91%; Cosine Similarity: 66.40%) compared to the prompt-engineering approach (BERTScore F1: 61.66%; Cosine Similarity: 60.34%). We delve into the inherent trade-offs between these methods concerning semantic fidelity, computational resource requirements, result stability, and scalability. Finally, we outline potential directions for future research aimed at refining LLM-based taxonomy construction systems to handle large dynamic datasets with enhanced accuracy, robustness, and granularity. Full article

Breast cancer is a leading cause of mortality among women, disproportionately affecting Hispanic populations in the U.S., particularly those with limited health literacy and language access. To address these disparities, we present a bilingual, web-based educational platform tailored to low-literacy Hispanic users. The platform supports full navigation in English and Spanish, with seamless language switching and both written and spoken input options. It incorporates automatic speech recognition (ASR) capable of handling code-switching, enhancing accessibility for bilingual users. Educational content is delivered through culturally sensitive videos organized into four categories: prevention, detection, diagnosis, and treatment. Each video includes embedded and post-video assessment questions aligned with Bloom’s Taxonomy to foster active learning. Users can monitor their progress and quiz performance via a personalized dashboard. An integrated chatbot, powered by large language models (LLMs), allows users to ask foundational breast cancer questions in natural language. The platform also recommends relevant resources, including nearby treatment centers, and support groups. LLMs are further used for ASR, question generation, and semantic response evaluation. Combining language technologies and LLMs reduces disparities in cancer education and supports informed decision-making among underserved populations, playing a pivotal role in reducing information gaps and promoting informed healthcare decisions. Full article

Traditional lectures in veterinary anatomy often limit student engagement and higher-order thinking. The flipped classroom (FC) model shifts foundational content to independent study using interactive tools such as H5P^® and Wooclap^®, reserving classroom time for collaborative problem-solving. Objective: To evaluate the impact of the FC model on student engagement, preparation habits, and cognitive performance in veterinary anatomy, focusing on the respiratory and cardiovascular systems. Methodology: The intervention was implemented over two academic years (2023/24 and 2024/25) and included continuous assessment, cognitive-level evaluations based on Marzano’s taxonomy, platform analytics, and anonymous student surveys. Results: Platform data showed high engagement, with completion rates exceeding 90%. Students who prepared 2–3 days in advance performed better on application and integration tasks. Survey responses indicated a shift from passive video viewing to active learning strategies, such as structured note-taking and strategic time management. By 2024/25, 85% of students dedicated 30+ min to preparation, compared to 48% the previous year. Conclusion: The FC model fostered autonomy, spatial reasoning, and clinical contextualization. Aligned with constructivist principles, it supported Intended Learning Outcomes through adaptive scaffolding. Despite institutional challenges, the model proved scalable and pedagogically coherent, warranting further longitudinal research and broader curricular integration. Full article

The emergence of Artificial Intelligence (AI) has impacted the world of higher education, and institutions are faced with challenges in integrating AI into curricula. Within the field of biology education, there has been little to no research on AI capabilities to explain collegiate-level biological concepts. In this study, we evaluated the ability of ChatGPT-4, ChatGPT-3.5, Google’s Bard, and Microsoft’s Bing to perform on introductory-level college assessments. All AIs were able to pass the biology course with varying degrees of success related to the usage of image-based assessments. With image-based questions, Bing and Bard received a D− and D, respectively; GPT-3.5 and 4 both received a C−, compared to the average student grade of a B. However, without image-based questions in the assessments, AI scores were a full letter grade higher. Additionally, AI performance was analyzed based on the cognitive complexity of the question, based on Bloom’s Taxonomy of learning. Performance by all four AIs dropped significantly with increasing complex questions, while student performance remained consistent. Overall, this study evaluated the ability of different AIs to perform on collegiate-level biology assessments. By understanding their capabilities at different levels of complexity, educators will be better able to adapt assessments based on AI ability, particularly through the utilization of image- and sequence-based questions, and integrate AI into higher education curricula. Full article

Machine learning and deep learning techniques integrated with advanced sensing technologies have revolutionized agricultural engineering, addressing complex challenges in food production, quality assessment, and environmental monitoring. This survey presents a systematic review and meta-analysis of recent developments by examining the peer-reviewed literature from 2015 to 2024. The analysis reveals computational approaches ranging from traditional algorithms like support vector machines and random forests to deep learning architectures, including convolutional and recurrent neural networks. Deep learning models often demonstrate superior performance, showing 5–10% accuracy improvements over traditional methods and achieving 93–99% accuracy in image-based applications. Three primary application domains are identified: agricultural product quality assessment using hyperspectral imaging, crop and field management through precision optimization, and agricultural automation with machine vision systems. Dataset taxonomy shows spectral data predominating at 42.1%, followed by image data at 26.2%, indicating preference for non-destructive approaches. Current challenges include data limitations, model interpretability issues, and computational complexity. Future trends emphasize lightweight model development, ensemble learning, and expanding applications. This analysis provides a comprehensive understanding of current capabilities and future directions for machine learning in agricultural engineering, supporting the development of efficient and sustainable agricultural systems for global food security. Full article

Network slicing (NS) plays a vital role in enabling flexible and efficient resource allocation, tailored to diverse use cases and network domains. This survey paper explores the synergy between NS and Artificial Intelligence (AI), emphasizing how Machine Learning (ML) techniques can address challenges across the slice life-cycle. A key contribution of this work is an in-depth analysis of AI and primarily ML applications in each phase of the slice life-cycle, delving into their specific tasks and discussing the techniques applied to these tasks. Furthermore, we present a taxonomy based on different slicing criteria, offering a structured perspective to enhance understanding and implementation. Full article

The analysis of dynamic remote sensing scenes from unmanned aerial vehicles (UAVs) is shifting from reactive processing to proactive, predictive intelligence. Central to this evolution is video prediction—forecasting future imagery from past observations—which enables critical remote sensing applications like persistent environmental monitoring, occlusion-robust object tracking, and infrastructure anomaly detection under challenging aerial conditions. Yet, a systematic review of video prediction models tailored for the unique constraints of aerial remote sensing has been lacking. Existing taxonomies often obscure key design choices, especially for emerging operators like state-space models (SSMs). We address this gap by proposing a unified, multi-dimensional taxonomy with three orthogonal axes: (i) operator architecture; (ii) generative nature; and (iii) training/inference regime. Through this lens, we analyze recent methods, clarifying their trade-offs for deployment on UAV platforms that demand processing of high-resolution, long-horizon video streams under tight resource constraints. Our review assesses the utility of these models for key applications like proactive infrastructure inspection and wildlife tracking. We then identify open problems—from the scarcity of annotated aerial video data to evaluation beyond pixel-level metrics—and chart future directions. We highlight a convergence toward scalable dynamic world models for geospatial intelligence, which leverage physics-informed learning, multimodal fusion, and action-conditioning, powered by efficient operators like SSMs. Full article

Hearing-impaired people face challenges in expressing and perceiving emotions, and traditional single-modal emotion recognition methods demonstrate limited effectiveness in complex environments. To enhance recognition performance, this paper proposes a multimodal fusion neural network based on a multimodal multi-head attention fusion neural network (MMHA-FNN). This method utilizes differential entropy (DE) and bilinear interpolation features as inputs, learning the spatial–temporal characteristics of brain regions through an MBConv-based module. By incorporating the Transformer-based multi-head self-attention mechanism, we dynamically model the dependencies between EEG and facial expression features, enabling adaptive weighting and deep interaction of cross-modal characteristics. The experiment conducted a four-classification task on the MED-HI dataset (15 subjects, 300 trials). The taxonomy included happy, sad, fear, and calmness, where ‘calmness’ corresponds to a low-arousal neutral state as defined in the MED-HI protocol. Results indicate that the proposed method achieved an average accuracy of 81.14%, significantly outperforming feature concatenation (71.02%) and decision layer fusion (69.45%). This study demonstrates the complementary nature of EEG and facial expressions in emotion recognition among hearing-impaired individuals and validates the effectiveness of feature layer interaction fusion based on attention mechanisms in enhancing emotion recognition performance. Full article

Smart crop technologies offer promising solutions for enhancing agricultural productivity and sustainability, particularly in the face of global challenges such as resource scarcity and climate variability. However, their deployment in infrastructure-limited regions, especially across Africa, faces persistent barriers, including unreliable power supply, intermittent internet connectivity, and limited access to technical expertise. This study presents a PRISMA-guided systematic review of literature published between 2015 and 2025, sourced from the Scopus database including indexed content from ScienceDirect and IEEE Xplore. It focuses on key technological components including multimodal sensing, data fusion, IoT resource management, edge-cloud integration, and adaptive network design. The analysis of these references reveals a clear trend of increasing research volume and a major shift in focus from foundational unimodal sensing and cloud computing to more complex solutions involving machine learning post-2019. This review identifies critical gaps in existing research, particularly the lack of integrated frameworks for effective multimodal sensing, data fusion, and real-time decision support in low-resource agricultural contexts. To address this, we categorize multimodal sensing approaches and then provide a structured taxonomy of multimodal data fusion approaches for real-time monitoring and decision support. The review also evaluates the role of IoT virtualization as a pathway to scalable, adaptive sensing systems, and analyzes strategies for overcoming infrastructure constraints. This study contributes a comprehensive overview of smart crop technologies suited to infrastructure-limited agricultural contexts and offers strategic recommendations for deploying resilient smart agriculture solutions under connectivity and power constraints. These findings provide actionable insights for researchers, technologists, and policymakers aiming to develop sustainable and context-aware agricultural innovations in underserved regions. Full article

Accurate aircraft trajectory prediction is fundamental to air traffic management, operational safety, and intelligent aerospace systems. With the growing availability of flight data, deep learning has emerged as a powerful tool for modeling the spatiotemporal complexity of 4D trajectories. This paper presents a comprehensive review of deep learning-based approaches for aircraft trajectory prediction, focusing on their evolution, taxonomy, performance, and future directions. We classify existing models into five groups—RNN-based, attention-based, generative, graph-based, and hybrid and integrated models—and evaluate them using standardized metrics such as the RMSE, MAE, ADE, and FDE. Common datasets, including ADS-B and OpenSky, are summarized, along with the prevailing evaluation metrics. Beyond model comparison, we discuss real-world applications in anomaly detection, decision support, and real-time air traffic management, and highlight ongoing challenges such as data standardization, multimodal integration, uncertainty quantification, and self-supervised learning. This review provides a structured taxonomy and forward-looking perspectives, offering valuable insights for researchers and practitioners working to advance next-generation trajectory prediction technologies. Full article

Large Language Models (LLMs) exhibit remarkable generative capabilities but remain vulnerable to hallucinations—outputs that are fluent yet inaccurate, ungrounded, or inconsistent with source material. To address the lack of methodologically grounded surveys, this paper introduces a novel method-oriented taxonomy of hallucination mitigation strategies in text-based LLMs. The taxonomy organizes over 300 studies into six principled categories: Training and Learning Approaches, Architectural Modifications, Input/Prompt Optimization, Post-Generation Quality Control, Interpretability and Diagnostic Methods, and Agent-Based Orchestration. Beyond mapping the field, we identify persistent challenges such as the absence of standardized evaluation benchmarks, attribution difficulties in multi-method systems, and the fragility of retrieval-based methods when sources are noisy or outdated. We also highlight emerging directions, including knowledge-grounded fine-tuning and hybrid retrieval–generation pipelines integrated with self-reflective reasoning agents. This taxonomy provides a methodological framework for advancing reliable, context-sensitive LLM deployment in high-stakes domains such as healthcare, law, and defense. Full article

Power systems are undergoing a transformative transition as consumers seek greater participation in managing electricity systems. This shift has given rise to the concept of “prosumers,” individuals who both consume and produce electricity, primarily through renewable energy sources. While renewables offer undeniable environmental benefits, they also introduce significant energy management challenges. One major concern is the variability in energy consumption patterns within households, which can lead to inefficiencies. Also, improper energy management can result in economic losses due to unbalanced energy control or inefficient systems. Home Energy Management Systems (HEMSs) have emerged as a promising solution to address these challenges. A well-designed HEMS enables users to achieve greater efficiency in managing their energy consumption, optimizing asset usage while ensuring cost savings and system reliability. This paper presents a comprehensive systematic review of optimization techniques applied to HEMS development between 2019 and 2024, focusing on key technical and computational factors influencing their advancement. The review categorizes optimization techniques into two main groups: conventional methods, emerging techniques, and machine learning methods. By analyzing recent developments, this study provides an integrated perspective on the evolving role of HEMSs in modern power systems, highlighting trends that enhance the efficiency and effectiveness of energy management in smart grids. Unifying taxonomy of HEMSs (2019–2024) and integrating mathematical, heuristic/metaheuristic, and ML/DRL approaches across horizons, controllability, and uncertainty, we assess algorithmic complexity versus tractability, benchmark comparative evidence (cost, PAR, runtime), and highlight deployment gaps (privacy, cybersecurity, AMI/HAN, and explainability), offering a novel synthesis for AI-enabled HEMS. Full article