Search Results (4,724)

This study develops and validates an artificial intelligence (AI)-assisted internship learning platform for automotive electronics based on the Llama 3 large language model, aiming to enhance pedagogical effectiveness within vocational training contexts. Addressing critical issues such as the persistent theory–practice gap and limited innovation capability prevalent in existing curricula, we leverage the natural language processing (NLP) capabilities of Llama 3 through fine-tuning based on transfer learning to establish a specialized knowledge base encompassing fundamental circuit principles and fault diagnosis protocols. The implementation employs the Hugging Face Transformers library with optimized hyperparameters, including a learning rate of 5 × 10⁻⁵ across five training epochs. Post-training evaluations revealed an accuracy of 89.7% on validation tasks (representing a 12.4% improvement over the baseline model), a semantic comprehension precision of 92.3% in technical question-and-answer assessments, a mathematical computation accuracy of 78.4% (highlighting this as a current limitation), and a latency of 6.3 s under peak operational workloads (indicating a system bottleneck). Although direct trials involving students were deliberately avoided, the platform’s technical feasibility was validated through multidimensional benchmarking against established models (BERT-base and GPT-2), confirming superior domain adaptability (F1 = 0.87) and enhanced error tolerance (σ² = 1.2). Notable limitations emerged in numerical reasoning tasks (Cohen’s d = 1.15 compared to human experts) and in real-time responsiveness deterioration when exceeding 50 concurrent users. The study concludes that Llama 3 demonstrates considerable promise for automotive electronics skills development. Proposed future enhancements include integrating symbolic AI modules to improve computational reliability, implementing Kubernetes-based load balancing to ensure latency below 2 s at scale, and conducting longitudinal pedagogical validation studies with trainees. This research provides a robust technical foundation for AI-driven vocational education, especially suited to mechatronics fields that require close integration between theoretical knowledge and practical troubleshooting skills. Full article

This work contextualizes the possibility of deriving a unifying artificial intelligence framework by walking in the footsteps of General, Explainable, and Verified Artificial Intelligence (GEVAI): by considering explainability not only at the level of the results produced by a specification but also considering the explicability of the inference process as well as the one related to the data processing step, we can not only ensure human explainability of the process leading to the ultimate results but also mitigate and minimize machine faults leading to incorrect results. This, on the other hand, requires the adoption of automated verification processes beyond system fine-tuning, which are essentially relevant in a more interconnected world. The challenges related to full automation of a data processing pipeline, mostly requiring human-in-the-loop approaches, forces us to tackle the framework from a different perspective: while proposing a preliminary implementation of GEVAI mainly used as an AI test-bed having different state-of-the-art AI algorithms interconnected, we propose two other data processing pipelines, LaSSI and EMeriTAte+DF, being a specific instantiation of GEVAI for solving specific problems (Natural Language Processing, and Multivariate Time Series Classifications). Preliminary results from our ongoing work strengthen the position of the proposed framework by showcasing it as a viable path to improve current state-of-the-art AI algorithms. Full article

Background: Electrocardiograms (EKGs) are essential tools in emergency medicine, often used to evaluate chest pain, dyspnea, and other symptoms suggestive of cardiac dysfunction. Yet, EKGs are not universally administered to all emergency department (ED) patients. Understanding and predicting which patients receive an EKG may offer insights into clinical decision making, resource allocation, and potential disparities in care. This study examines whether integrating structured clinical data with free-text patient narratives can improve prediction of EKG utilization in the ED. Methods: We conducted a retrospective observational study to predict electrocardiogram (EKG) utilization using data from 13,115 adult emergency department (ED) visits in the nationally representative 2021 National Hospital Ambulatory Medical Care Survey–Emergency Department (NHAMCS-ED), leveraging both structured features—demographics, vital signs, comorbidities, arrival mode, and triage acuity, with the most influential selected via Lasso regression—and unstructured patient narratives transformed into numerical embeddings using Clinical-BERT. Four supervised learning models—Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF) and Extreme Gradient Boosting (XGB)—were trained on three inputs (structured data only, text embeddings only, and a late-fusion combined model); hyperparameters were optimized by grid search with 5-fold cross-validation; performance was evaluated via AUROC, accuracy, sensitivity, specificity and precision; and interpretability was assessed using SHAP values and Permutation Feature Importance. Results: EKGs were administered in 30.6% of adult ED visits. Patients who received EKGs were more likely to be older, White, Medicare-insured, and to present with abnormal vital signs or higher triage severity. Across all models, the combined data approach yielded superior predictive performance. The SVM and LR achieved the highest area under the ROC curve (AUC = 0.860 and 0.861) when using both structured and unstructured data, compared to 0.772 with structured data alone and 0.823 and 0.822 with unstructured data alone. Similar improvements were observed in accuracy, sensitivity, and specificity. Conclusions: Integrating structured clinical data with patient narratives significantly enhances the ability to predict EKG utilization in the emergency department. These findings support a personalized medicine framework by demonstrating how multimodal data integration can enable individualized, real-time decision support in the ED. Full article

Existing approaches to social media sentiment analysis typically focus on static classification, offering limited foresight into how public opinion evolves. This study addresses that gap by introducing the Multi-Feature Sentiment-Driven Forecasting (MFSF) framework, a novel pipeline that enhances sentiment trend prediction by integrating rich contextual information from text. Using state-of-the-art transformer models on the Sentiment140 dataset, our framework extracts three concurrent signals from each tweet: sentiment polarity, aspect-based scores (e.g., ‘price’ and ‘service’), and topic embeddings. These features are aggregated into a daily multivariate time series. We then employ a SARIMAX model to forecast future sentiment, using the extracted aspect and topic data as predictive exogenous variables. Our results, validated on the historical Sentiment140 Twitter dataset, demonstrate the framework’s superior performance. The proposed multivariate model achieved a 26.6% improvement in forecasting accuracy (RMSE) over a traditional univariate ARIMA baseline. The analysis confirmed that conversational aspects like ‘service’ and ‘quality’ are statistically significant predictors of future sentiment. By leveraging the contextual drivers of conversation, the MFSF framework provides a more accurate and interpretable tool for businesses and policymakers to proactively monitor and anticipate shifts in public opinion. Full article

This study assesses the quality of financial reporting in ten Central and Eastern European countries using a methodology based on natural language processing (NLP) techniques. 570 annual reports of companies listed on the main index on the stock exchanges of 10 Central and Eastern European (CEE) countries, over the period 2019–2023, were evaluated to determine the degree of convergence of the following four measurable qualitative characteristics: relevance, exact representation, comparability and understandability. The main objective is to identify consistency in the quality of accounting information based on the application of an international financial reporting framework. The applied methodology eliminates subjective variability by implementing a standardized scoring system, aligned with the criteria developed by NiCE, using libraries such as spaCy and NLTK for term extraction, respective sentiment analysis and word frequency evaluation. The results reveal significant heterogeneity in all characteristics examined, with statistical tests confirming substantial differences between countries. The investigation of relevance revealed partial convergence, with three dimensions achieving complete uniformity, while the exact representation showed the highest variability. The assessment of comparability showed a significant difference between countries’ extreme values, and in terms of comprehensibility a formalistic approach was evident, with technical dimensions outweighing user-oriented aspects. The overall quality index varied significantly across countries, with a notable average deterioration in 2023, indicating structural vulnerabilities in financial reporting systems. These findings support initial hypotheses on the lack of homogeneity in the quality of financial reporting in the selected region, despite the implementation of international standards. Full article

This study examines non-standard comparative and superlative adjective forms in Ukrainian and English, emphasizing their evaluative meanings and grammatical deviations. While prescriptive grammar dictates conventional comparison patterns, modern discourse—particularly in advertising, informal communication, and literary texts—exhibits an increasing prevalence of innovative comparative structures. Using a corpus-based approach, this research identifies patterns of positive and negative evaluative meanings, revealing that positive evaluations dominate non-standard comparatives in both languages, particularly in advertising (English: 78.5%, Ukrainian: 80.2%). However, English exhibits a higher tolerance for grammatical flexibility, while Ukrainian maintains a more restricted use, primarily in commercial and expressive discourse. The findings highlight the pragmatic and evaluative functions of such constructions, including hyperbolic emphasis, rhetorical contrast, and branding strategies. These insights contribute to research on comparative grammar, sentiment analysis, and natural language processing, particularly in modeling evaluative structures in computational linguistics. Full article

Mars has been a primary focus of planetary science, with significant advancements over the past two decades across disciplines including geological evolution, surface environment, and atmospheric and space science. However, the rapid growth of the related literature has rendered traditional manual review methods increasingly inadequate. This inadequacy is particularly evident in interdisciplinary research, which is often characterized by dispersed topics and complex semantics. To address this challenge, this study proposes an automated analysis framework based on natural language processing (NLP) to systematically review the Martian research in Earth and space science over the past two decades. The research database contains 151,196 Mars-related sentences extracted from 10,655 publications spanning 2001 to 2024. Using machine learning techniques, the framework clusters Mars-related sentences into semantically coherent groups and applies topic modeling to extract core research themes. It then analyzes their temporal evolution across the Martian solid, surface, atmosphere, and space environments. Finally, through sentiment analysis and semantic matching, it highlights unresolved scientific questions and potential directions for future research. This approach offers a novel perspective on the knowledge structure underlying Mars exploration and demonstrates the potential of NLP for large-scale literature analysis in planetary science. The findings potentially provide a structured foundation for building an interdisciplinary, peer-reviewed Mars knowledge base, which may inform future scientific research and mission planning. Full article

Recent advancements in generative artificial intelligence have significantly progressed the field of text-to-music generation, enabling users to create music from natural language descriptions. Despite the success of various models, such as MusicLM, MusicGen, and AudioLDM, the current approaches struggle to capture fine-grained genre-specific characteristics, precisely control musical attributes, and handle underrepresented cultural data. This paper introduces a novel, lightweight fine-tuning method for the AudioLDM framework using low-rank adaptation (LoRA). By updating only selected attention and projection layers, the proposed method enables efficient adaptation to musical genres with limited data and computational cost. The proposed method enhances controllability over key musical parameters such as rhythm, emotion, and timbre. At the same time, it maintains the overall quality of music generation. This paper represents the first application of LoRA in AudioLDM, offering a scalable solution for fine-grained, genre-aware music generation and customization. The experimental results demonstrate that the proposed method improves the semantic alignment and statistical similarity compared with the baseline. The contrastive language–audio pretraining score increased by 0.0498, indicating enhanced text-music consistency. The kernel audio distance score decreased by 0.8349, reflecting improved similarity to real music distributions. The mean opinion score ranged from 3.5 to 3.8, confirming the perceptual quality of the generated music. Full article

Adverse drug events (ADEs) significantly impact patient safety and health outcomes. Manual ADE detection from clinical narratives is time-consuming, labor-intensive, and costly. Recent advancements in large language models (LLMs), including transformer-based architectures such as Bidirectional Encoder Representations from Transformers (BERT) and Generative Pretrained Transformer (GPT) series, offer promising methods for automating ADE extraction from clinical data. These models have been applied to various aspects of pharmacovigilance and clinical decision support, demonstrating potential in extracting ADE-related information from real-world clinical data. Additionally, chatbot-assisted systems have been explored as tools in clinical management, aiding in medication adherence, patient engagement, and symptom monitoring. This narrative review synthesizes the current state of LLMs in ADE detection from a clinical perspective, organizing studies into categories such as human-facing decision support tools, immune-related ADE detection, cancer-related and non-cancer-related ADE surveillance, and personalized decision support systems. In total, 39 articles were included in this review. Across domains, LLM-driven methods have demonstrated promising performances, often outperforming traditional approaches. However, critical limitations persist, such as domain-specific variability in model performance, interpretability challenges, data quality and privacy concerns, and infrastructure requirements. By addressing these challenges, LLM-based ADE detection could enhance pharmacovigilance practices, improve patient safety outcomes, and optimize clinical workflows. Full article

Artificial intelligence (AI)-generated content (AIGC) is an innovative technology that utilizes machine learning, AI models, reward modeling, and natural language processing (NLP) to create diverse digital content such as videos, images, and text. It has the potential to support various human activities with significant implications in teaching and learning, facilitating heuristic teaching for educators. By using AIGC, teachers can create extensive knowledge content and effectively design instructional strategies to guide students, aligning with heuristic teaching. However, incorporating AIGC into heuristic teaching has controversies and concerns, which potentially mislead outcomes. Nevertheless, leveraging AIGC greatly benefits teachers in enhancing heuristic teaching. When integrating AIGC to support heuristic teaching, challenges and risks must be acknowledged and addressed. These challenges include the need for users to possess sufficient knowledge reserves to identify incorrect information and content generated by AIGC, the importance of avoiding excessive reliance on AIGC, ensuring users maintain control over their actions rather than being driven by AIGC, and the necessity of scrutinizing and verifying the accuracy of information and knowledge generated by AIGC to preserve its effectiveness. Full article

Social media platforms have emerged as valuable sources for mental health research, enabling the detection of conditions such as depression through analyses of user-generated posts. This manuscript offers practical, step-by-step guidance for applying machine learning and deep learning methods to mental health detection on social media. Key topics include strategies for handling heterogeneous and imbalanced datasets, advanced text preprocessing, robust model evaluation, and the use of appropriate metrics beyond accuracy. Real-world examples illustrate each stage of the process, and an emphasis is placed on transparency, reproducibility, and ethical best practices. While the present work focuses on text-based analysis, we discuss the limitations of this approach—including label inconsistency and a lack of clinical validation—and highlight the need for future research to integrate multimodal signals and gold-standard psychometric assessments. By sharing these frameworks and lessons, this manuscript aims to support the development of more reliable, generalizable, and ethically responsible models for mental health detection and early intervention. Full article

The use of informal language on social media and the sheer volume of information make it difficult for a computer system to analyse it automatically. The aim of this work is to design a new group decision-making method that applies two new consensus methods based on sentiment analysis. This method is designed for application in the analysis of texts on social media. To test the method, we will use posts from the so called social network X. The proposed model differs from previous work in this field by defining a new degree of subjectivity and a new degree of reliability associated with user opinions. This work also presents two new consensus measures, one focused on measuring the number of words classified as positive and negative and the other on analysing the percentage of occurrence of those words. Our method allows us to automatically extract preferences from the transcription of the texts used in the debate, avoiding the need for users to explicitly indicate their preferences. The application to a real case of public investment demonstrates the effectiveness of the approach in collaborative contexts that used natural language. Full article

Adversarial attacks in Natural Language Processing (NLP) present a critical challenge, particularly in sentiment analysis, where subtle input modifications can significantly alter model predictions. In search of more robust defenses against adversarial attacks on sentimental analysis, this research work introduces two novel defense mechanisms: the Lexicon-Based Random Substitute Model (LRSM) and the Word-Variant Voting Model (WVVM). LRSM employs randomized substitutions from a dataset-specific lexicon to generate diverse input variations, disrupting adversarial strategies by introducing unpredictability. Unlike traditional defenses requiring synonym dictionaries or precomputed semantic relationships, LRSM directly substitutes words with random lexicon alternatives, reducing overhead while maintaining robustness. Notably, LRSM not only neutralizes adversarial perturbations but occasionally surpasses the original accuracy by correcting inherent model misclassifications. Building on LRSM, WVVM integrates LRSM, Frequency-Guided Word Substitution (FGWS), and Synonym Random Substitution and Voting (RS&V) in an ensemble framework that adaptively combines their outputs. Logistic Regression (LR) emerged as the optimal ensemble configuration, leveraging its regularization parameters to balance the contributions of individual defenses. WVVM consistently outperformed standalone defenses, demonstrating superior restored accuracy and F1 scores across adversarial scenarios. The proposed defenses were evaluated on two well-known sentiment analysis benchmarks: the IMDB Sentiment Dataset and the Yelp Polarity Dataset. The IMDB dataset, comprising 50,000 labeled movie reviews, and the Yelp Polarity dataset, containing labeled business reviews, provided diverse linguistic challenges for assessing adversarial robustness. Both datasets were tested using 4000 adversarial examples generated by established attacks, including Probability Weighted Word Saliency, TextFooler, and BERT-based Adversarial Examples. WVVM and LRSM demonstrated superior performance in restoring accuracy and F1 scores across both datasets, with WVVM excelling through its ensemble learning framework. LRSM improved restored accuracy from 75.66% to 83.7% when compared to the second-best individual model, RS&V, while the Support Vector Classifier WVVM variation further improved restored accuracy to 93.17%. Logistic Regression WVVM achieved an F1 score of 86.26% compared to 76.80% for RS&V. These findings establish LRSM and WVVM as robust frameworks for defending against adversarial text attacks in sentiment analysis. Full article

In distance learning environments, learner engagement directly impacts attention, motivation, and academic performance. Signs of fatigue, negative affect, or critical remarks can warn of growing disengagement and potential dropout. However, most existing approaches rely on a single modality, visual or text-based, without providing a general view of learners’ cognitive and affective states. We propose a multimodal system that integrates three complementary analyzes: (1) a CNN-LSTM model augmented with warning signs such as PERCLOS and yawning frequency for fatigue detection, (2) facial emotion recognition by EmoNet and an LSTM to handle temporal dynamics, and (3) sentiment analysis of feedback by a fine-tuned BERT model. It was evaluated on three public benchmarks: DAiSEE for fatigue, AffectNet for emotion, and MOOC Review (Coursera) for sentiment analysis. The results show a precision of 88.5% for fatigue detection, 70% for emotion detection, and 91.5% for sentiment analysis. Aggregating these cues enables an accurate identification of disengagement periods and triggers individualized pedagogical interventions. These results, although based on independently sourced datasets, demonstrate the feasibility of an integrated approach to detecting disengagement and open the door to emotionally intelligent learning systems with potential for future work in real-time content personalization and adaptive learning assistance. Full article

In order to increase the effectiveness of model training, data reduction is essential to data-centric Artificial Intelligence (AI). It achieves this by locating the most instructive examples in massive datasets. To increase data quality and training efficiency, the main difficulty is choosing the best examples rather than the complete datasets. In this paper, we propose an effective data reduction strategy based on Pointwise $\mathcal{V}$-Information (PVI). To enable a static method, we first use PVI to quantify instance difficulty and remove instances with low difficulty. Experiments show that classifier performance is maintained with only a 0.0001% to 0.76% decline in accuracy when 10–30% of the data is removed. Second, we train the classifiers using a progressive learning strategy on examples sorted by increasing PVI, accelerating convergence and achieving a 0.8% accuracy gain over conventional training. Our findings imply that training a classifier on the chosen optimal subset may improve model performance and increase training efficiency when combined with an efficient data reduction strategy. Furthermore, we have adapted the PVI framework, which was previously limited to English datasets, to a variety of Chinese Natural Language Processing (NLP) tasks and base models, yielding insightful results for faster training and cross-lingual data reduction. Full article