Mach. Learn. Knowl. Extr., Volume 7, Issue 4 (December 2025) – 61 articles

In this study, a structured and methodological evaluation approach for eXplainable Artificial Intelligence (XAI) methods in medical image classification is proposed and implemented using LIME and SHAP explanations for chest X-ray interpretations. The evaluation framework integrates two critical perspectives: predictive model-centered and human-centered evaluations. Predictive model-centered evaluations examine the explanations’ ability to reflect changes in input and output data and the internal model structure. Human-centered evaluations, conducted with 97 medical experts, assess trust, confidence, and agreements with AI’s indicative and contra-indicative reasoning as well as their changes before and after provision of explainability. Key findings of our study include explanation of sensitivity of LIME and SHAP to model changes, their effectiveness in identifying critical features, and SHAP’s significant impact on diagnosis changes. Our results show that both LIME and SHAP negatively affected contra-indicative agreement. Case-based analysis revealed AI explanations reinforce trust and agreement when participant’s initial diagnoses are correct. In these cases, SHAP effectively facilitated correct diagnostic changes. This study establishes a benchmark for future research in XAI for medical image analysis, providing a robust foundation for evaluating and comparing different XAI methods. Full article

A receipt information extraction task requires both textual and spatial analyses. Early receipt analysis systems primarily relied on template matching to extract data from spatially structured documents. However, these methods lack generalizability across various document layouts and require defining the specific spatial characteristics of unseen document sources. The advent of convolutional and recurrent neural networks has led to models that generalize better over unseen document layouts, and more recently, multi-modal transformer-based models, which consider a combination of text, visual, and layout inputs, have led to an even more significant boost in document-understanding capabilities. This work focuses on the joint use of a neural multi-modal transformer and a rule-based model and studies whether this combination achieves higher performance levels than the transformer on its own. A comprehensively annotated dataset, comprising real-world and synthetic receipts, was specifically developed for this study. The open source optical character recognition model DocTR was used to textually scan receipts and, together with an image, provided input to the classifier model. The open-source pre-trained LayoutLMv3 transformer-based model was augmented with a classifier model head, which was trained for classifying textual data into 12 predefined labels, such as date, price, and shop name. The methods implemented in the rule-based model were manually designed and consisted of four types: pattern-matching rules based on regular expressions and logic, database search-based methods for named entities, spatial pattern discovery guided by statistical metrics, and error correcting mechanisms based on confidence scores and local distance metrics. Following hyperparameter tuning of the classifier head and the integration of a rule-based model, the system achieved an overall F1 score of 0.98 in classifying textual data, including line items, from receipts. Full article

Vasovagal syncope (VVS) affects 17% of children, significantly impairing quality of life. Machine learning (ML) models achieve high predictive accuracy of VVS in adults using blood pressure (BP) monitoring, but pediatric implementation remains challenging. The aim of the study was to evaluate whether ML models incorporating anthropometric data and heart rate variability (HRV) can predict VVS without BP monitoring in children with prior syncope or suspected VVS. We analyzed 87 participants (7–18 years) with VVS history. HRV indices (time-domain, frequency-domain, and nonlinear) were extracted from 5 min supine and standing ECG recordings using NeuroKit2. Multiple algorithms were tested with 10-fold cross-validation; SHAP analysis identified feature importance. AdaBoost achieved the performance of 71.0% accuracy, 76.3% sensitivity, and 63.3% specificity—78% of adult BP-dependent algorithm sensitivity. Weight, multifractal detrended fluctuation analysis during standing, and normalized low-frequency power were most influential. Alterations in symbolic dynamics and multiscale entropy indicated compromised autonomic complexity. ML models with anthropometric and HRV data show potential as an adjunctive screening tool to identify children at higher risk for syncope recurrence, requiring clinical confirmation. Full article

Background: Automated pain assessment aims to enable objective measurement of patients’ individual pain experiences for improving health care and conserving medical staff. This is particularly important for patients with a disability to communicate caused by mental impairments, unconsciousness, or infantile restrictions. When operating in the critical domain of health care, where wrong decisions harbor the risk of reducing patients’ quality of life—or even result in life-threatening conditions—multimodal pain assessment systems are the preferred choice to facilitate robust decision-making and to maximize resilience against partial sensor outages. Methods: Hence, we propose the MultiModal Supervised Contrastive Adversarial AutoEncoder (MM-SCAAE) pretraining framework for multi-sensor information fusion. Specifically, we implement an application-specific model to accomplish the task of pain recognition using biopotentials from the publicly available heat pain database BioVid. Results: Our model reaches new state-of-the-art performance for multimodal classification regarding all pain recognition tasks of ‘no pain’ versus ‘pain intensity’. For the most relevant task of ‘no pain’ versus ‘highest pain’, we achieve $84.22\%$ accuracy ($F_1$-score: $83.72\%$), which can be boosted in practice to an accuracy of ≈$95\%$ through grouped-prediction estimates. Conclusions: The generic MM-SCAAE framework offers promising perspectives for multimodal representation learning. Full article

This work investigates how different language modeling techniques affect the performance of an end-to-end automatic speech recognition (ASR) system for the Amazigh language. A (CNN-BiLSTM-CTC) model enhanced with an attention mechanism was used as the baseline. During decoding, two external language models were integrated using shallow fusion: a trigram N-gram model built with KenLM and a recurrent neural network language model (RNN-LM) trained on the same Tifdigit corpus. Four decoding methods were compared: greedy decoding; beam search; beam search with an N-gram language model; and beam search with a compact recurrent neural network language model. Experimental results on the Tifdigit dataset reveal a clear trade-off: the N-gram language model produces the best results compared to RNN-LM, with a phonetic error rate (PER) of 0.0268, representing a relative improvement of 4.0% over the greedy baseline model, and translates into an accuracy of 97.32%. This suggests that N-gram models can outperform neural approaches when reliable, limited data and lexical resources are available. The improved N-gram approach notably outperformed both simple beam search and the RNN neural language model. This improvement is due to higher-order context modeling, its optimized interpolation weights, and its adaptive lexical weighting tailored to the phonotactic structure of the Amazigh language. Full article

Operation and maintenance (O&M) events resulting from environmental factors (e.g., precipitation, temperature, seasonality, and unexpected weather conditions) are among the primary sources of operating costs and downtime in run-of-river small hydropower plants (SHPs). This paper presents a data-driven methodology for predicting such long events using machine learning models trained on historical power production, weather radar, and forecast data. Case studies on two Slovenian SHPs with different structural designs and levels of automation demonstrate how environmental features—such as day of year, rain duration, cumulative amount of rain, and rolling precipitation sums—can be used to forecast long events or shutdowns. The proposed approach integrates probabilistic classification outputs with threshold-consistency smoothing to reduce noise and stabilize predictions. Several algorithms were tested—including Logistic Regression, Support Vector Machine (SVM), Random Forest, Gradient Boosting, and k-Nearest Neighbors (k-NN)—across varying feature combinations for O&M model development, with cross-validation ensuring robust evaluation. The models achieved an F1-score of up to 0.58 in SHP1 (k-NN), showing strong seasonality dependence, and up to 0.68 in SHP2 (Gradient Boosting). For SHP1, the best model (k-NN) correctly detected 36 long events, while 15 were misclassified as no events and 38 false alarms were produced. For SHP2, the best model (Gradient Boosting) correctly detected 69 long events, misclassified 23 as no events, and produced 42 false alarms. The findings highlight that probabilistic machine learning-based forecasting can effectively support predictive O&M planning, particularly for manually operated or service-operated SHPs. Full article

Topic modeling is a fundamental technique in natural language processing used to uncover latent themes in large text corpora, yet existing approaches struggle to jointly achieve interpretability, semantic coherence, and scalability. Classical probabilistic models such as LDA and NMF rely on bag-of-words assumptions that obscure contextual meaning, while embedding-based methods (e.g., BERTopic, Top2Vec) improve coherence at the expense of diversity and stability. Prompt-based frameworks (e.g., TopicGPT) enhance interpretability but remain sensitive to prompt design and are computationally costly on large datasets. This study introduces VISTA (Vector-Similarity Topic Analysis), a multi-view, hierarchical, and interpretable framework that integrates complementary document embeddings, mutual-nearest-neighbor hierarchical clustering with selective dimension analysis, and large language model (LLM)-based topic labeling enforcing hierarchical coherence. Experiments on three heterogeneous corpora—BBC News, BillSum, and a mixed U.S. Government agency news + Twitter dataset—show that VISTA consistently ranks among the top-performing models, achieving the highest C_UCI coherence and a strong balance between topic diversity and semantic consistency. Qualitative analyses confirm that VISTA identifies domain-relevant themes overlooked by probabilistic or prompt-based models. Overall, VISTA provides a scalable, semantically robust, and interpretable framework for topic discovery, bridging probabilistic, embedding-based, and LLM-driven paradigms in a unified and reproducible design. Full article

This study explores a learning knowledge representation, using an iteratively reevaluated lattice of equivalence-classified properties. The proposed methodology is based on the evaluation feedback between the maximal and minimal elements of the compatibility lattice. The simplified example shows how the expert evaluations of conventional and advanced Artificial Intelligence/Machine Learning (AI/ML) computational tools contribute to generating novel solutions for manufacturing industries. The knowledge base is initialized with heuristically established equivalence classes and pairwise compatibility relations between classified properties. The learning process begins with a heuristically determined, initially evaluated subset of maximal elements (complete combinations), followed by the implementation of a theoretically established iterative learning algorithm, driven by evaluation feedback. Utilizing the normalized real-valued assessments of the complete combinations, the knowledge base undergoes reevaluation, leading to uncertain assessments of the binary compatibility relations. This evolving knowledge base then facilitates the algorithmic generation of new, tendentiously more effective complete combinations. Findings indicate that through these iterative learning steps, the uncertainty due to ‘lack of knowledge’ significantly decreases, while the uncertainty associated with accumulated knowledge increases. The overall summarized uncertainty initially reaches a minimum before gradually rising again. Further analysis of the knowledge base after several learning iterations reveals the contribution of individual binary relations to the valuation of newly proposed combinations, as well as contains lessons for the optional refinement of the initial compatibility lattice. Full article

Improving financial time series forecasting presents challenges because models often struggle to identify diverse fault patterns in unseen data. This issue is critical in fintech, where accurate and reliable forecasting of financial data is essential for effective risk management and informed investment strategies. This work addresses these challenges by initializing the weights and biases of two proposed models, Gated Recurrent Units (GRUs) and the Echo State Network (ESN), with different chaotic sequences to enhance prediction accuracy and capabilities. We compare reservoir computing (RC) and recurrent neural network (RNN) models with and without the integration of chaotic systems, utilizing standard initialization. The models are validated on six different datasets, including the 500 largest publicly traded companies in the US (S&P500), the Irish Stock Exchange Quotient (ISEQ) dataset, the XAU and USD forex pair (XAU/USD), the USD and JPY forex pair with respect to the currency exchange rate (USD/JPY), Chinese daily stock prices, and the top 100 index of UK companies (FTSE 100). The ESN model, combined with the Lorenz system, achieves the lowest error among other models, reinforcing the effectiveness of chaos-trained models for prediction. The proposed ESN model, accelerated by the Kintex-Ultrascale KCU105 FPGA board, achieves a maximum frequency of $83.5$ MHz and a power consumption of $0.677$ W. The results of the hardware simulation align with MATLAB R2025b fixed-point analysis. Full article

Sleep is increasingly acknowledged as a cornerstone of public health, with chronic sleep loss implicated in preventable injury and deaths. Obstructive sleep apnea (OSA) affects over one billion people worldwide but remains widely under-diagnosed due to dependence on polysomnography (PSG), an overnight, hospital-based intrusive procedure. As an adjunct to the clinical diagnosis of OSA, this paper presents a low-cost, smartphone-based Generative AI agent framework for sleep apnea detection and sleep coaching at the bedside. Powered by an on=device Generative AI model, the four agents of this framework include a classifier, an analyser, a visualiser, and a sleep coach. The key agent activities performed are sleep apnea detection, sleep data management, data analysis, and natural language sleep coaching. The framework was empirically evaluated on a subject-independent hold-out set drawn from a dataset of 500 clinician annotated clips collected from 10 clinically diagnosed OSA patients. Sleep apnea detection achieved an accuracy of 0.89, precision of 0.91, and recall of 0.88, with nightly Apnea–Hypopnea Index (AHI) estimates strongly correlated with PSG-based clinical scores. The framework was further assessed on the performance metrics of computation, latency, memory, and energy usage. The results of these experiments confirm the feasibility of the proposed framework for large-scale, low-cost OSA screening, with pathways for future work in federated learning, noise robustness, and broad clinical validation. Full article

The growing trend of using artificial intelligence models in many areas increases the need for a proper understanding of their functioning and decision-making. Although these models achieve high predictive accuracy, their lack of transparency poses major obstacles to trust. Explainable artificial intelligence (XAI) has emerged as a key discipline that offers a wide range of methods to explain the decisions of models. Selecting the most appropriate XAI method for a given application is a non-trivial problem that requires careful consideration of the nature of the method and other aspects. This paper proposes a systematic approach to solving this problem using multi-criteria decision-making (MCDM) techniques: ARAS, CODAS, EDAS, MABAC, MARCOS, PROMETHEE II, TOPSIS, VIKOR, WASPAS, and WSM. The resulting score is an aggregation of the results of these methods using Borda Count. We present a framework that integrates objective and subjective criteria for selecting XAI methods. The proposed methodology includes two main phases. In the first phase, methods that meet the specified parameters are filtered, and in the second phase, the most suitable alternative is selected based on the weights using multi-criteria decision-making and sensitivity analysis. Metric weights can be entered directly, using pairwise comparisons, or calculated objectively using the CRITIC method. The framework is demonstrated on concrete use cases where we compare several popular XAI methods on tasks in different domains. The results show that the proposed approach provides a transparent and robust mechanism for objectively selecting the most appropriate XAI method, thereby helping researchers and practitioners make more informed decisions when deploying explainable AI systems. Sensitivity analysis confirmed the robustness of our XAI method selection: LIME dominated 98.5% of tests in the first use case, and Tree SHAP dominated 94.3% in the second. Full article

Lyme disease, caused by the Borrelia burgdorferi bacterium and transmitted through black-legged (deer) tick bites, is becoming increasingly prevalent globally. According to data from the Lyme Disease Association, the number of cases has surged by more than 357% over the past 15 years. According to the Infectious Disease Society of America, traditional diagnostic methods are often slow, potentially allowing bacterial proliferation and complicating early management. This study proposes a novel hybrid deep learning framework to classify Lyme disease rashes, addressing the global prevalence of the disease caused by the Borrelia burgdorferi bacterium, which is transmitted through black-legged (deer) tick bites. This study presents a novel hybrid deep learning framework for classifying Lyme disease rashes, utilizing pre-trained models (ResNet50 V2, VGG19, DenseNet201) for initial classification. By combining VGG19 and DenseNet201 architectures, we developed a hybrid model, SkinVisualNet, which achieved an impressive accuracy of 98.83%, precision of 98.45%, recall of 99.09%, and an F1 score of 98.76%. To ensure the robustness and generalizability of the model, 5-fold cross-validation (CV) was performed, generating an average validation accuracy between 98.20% and 98.92%. Incorporating image preprocessing techniques such as gamma correction, contrast stretching and data augmentation led to a 10–13% improvement in model accuracy, significantly enhancing its ability to generalize across various conditions and improving overall performance. To improve model interpretability, we applied Explainable AI methods like LIME, Grad-CAM, CAM++, Score CAM and Smooth Grad to visualize the rash image regions most influential in classification. These techniques enhance both diagnostic transparency and model reliability, helping clinicians better understand the diagnostic decisions. The proposed framework demonstrates a significant advancement in automated Lyme disease detection, providing a robust and explainable AI-based diagnostic tool that can aid clinicians in improving patient outcomes. Full article

Automatic anomaly detection is vital in domains such as healthcare, finance, and cybersecurity, where subtle deviations may signal fraud, failures, or impending risks. This paper proposes an unsupervised anomaly-detection method called Anomaly Detection Based on Markovian Geometric Diffusion (AD-MGD). The technique is applicable to uni- and multidimensional datasets, employing Markovian Geometric Diffusion to uncover nonlinear structures in the relationships among instances. For multidimensional data, the scale parameter, which is crucial to the performance of the method, is tuned using Shannon entropy. The approach includes a global search followed by local refinement of the scale parameter, promoting adaptability to the data context. Experimental evaluations on synthetic and real datasets show that AD-MGD consistently outperforms classical methods such as KNN, LOF, and IForest in terms of area under the ROC curve (AUC), particularly in heterogeneous data scenarios. The results highlight the potential of AD-MGD in critical anomaly-detection applications, advancing the use of diffusion techniques in data mining. Full article

In recent decades, data collection technologies have evolved to facilitate the monitoring and improvement of numerous activities and processes in everyday human life. Their evolution is propelled by the advancement of artificial intelligence (AI), which aims to emulate human intelligence in the execution of related tasks. The remarkable success of deep learning (DL) and computer vision (CV) on image data prompted researchers to consider its application to time series and multivariate data. In this context, time series imaging has been identified as the research field for the transformation of time series data (a one-dimensional data format) into images (a two-dimensional data format). These data can be the variables or features of a system or phenomenon under consideration. State-of-the-art techniques for time series imaging include recurrence plot (RP), Gramian angular field (GAF), and Markov transition field (MTF). This paper proposes a novel, robust, and simple technique of time series imaging using Grayscale Fingerprint Features Field Imaging (G3FI). This novel technique is distinguished by the low resolution of the resulting image and the simplicity of the transformation procedure. The efficacy of the novel and state-of-the-art techniques for enhancing the performance of CNN-based classification models on time series datasets is thoroughly examined and compared. Full article

Marine mammal vocalizations, such as those of the Northern Right Whale (NARW), are often masked by underwater acoustic noise. The acoustic vocalization signals are characterized by features such as their amplitude, timing, modulation, duration, and spectral content, which cannot be robustly captured by a single feature extraction method. These complex signals pose additional detection challenges beyond their low SNR. Consequently, this study proposes a novel low-SNR NARW classifier for passive acoustic monitoring (PAM). This approach employs an ideal binary mask with a bidirectional long short-term memory highway network (IBM-BHN) to effectively detect and classify NARW upcalls in challenging conditions. To enhance model performance, the reported literature limitations were addressed by employing a hybrid feature extraction method and leveraging the BiLSTM to capture and learn temporal dependencies. Furthermore, the integration of a highway network improves information flow, enabling near-real-time classification and superior model performance. Experimental results show the IBM-BHN method outperformed five considered state-of-the-art baseline models. Specifically, the IBM-BHN achieved an accuracy of 98%, surpassing ResNet (94%), CNN (85%), LSTM (83%), ANN (82%), and SVM (67%). These findings highlight the practical potential of IBM-BHN to support near-real-time monitoring and inform evidence-based, adaptive policy enforcement critical for NARW conservation. Full article

Despite the growing use of Explainable Artificial Intelligence (XAI) in energy time-series forecasting, a systematic evaluation of explanation quality remains limited. This systematic review analyzes 50 peer-reviewed studies (2020–2025) applying XAI to load, price, or renewable generation forecasting. Using a PRISMA-inspired protocol, we introduce a dual-axis taxonomy and a four-factor framework covering global transparency, local fidelity, user relevance, and operational viability to structure our qualitative synthesis. Our analysis reveals that XAI application is not uniform but follows three distinct, domain-specific paradigms: a user-centric approach in load forecasting, a risk management approach in price forecasting, and a physics-informed approach in generation forecasting. Post hoc methods, particularly SHAP, dominate the literature (62% of studies), while rigorous testing of explanation robustness and the reporting of computational overhead (23% of studies) remain critical gaps. We identify key research directions, including the need for standardized robustness testing and human-centered design, and provide actionable guidelines for practitioners. Full article

The rapid growth of the body of literature on heavy metal hyperaccumulation in plants has created a critical bottleneck in data synthesis. Manual curation is slow, labor-intensive, and not scalable. To address this issue, we developed an artificial intelligence pipeline that automatically transforms unstructured scientific papers, including text, tables, and figures, into a structured knowledge database. Our system recovers numerical data and extracts key experimental parameters, such as plant species, metal types, concentrations, and growing conditions. This enables on-demand dataset generation. We validated our pipeline by replicating a recently published, manually curated dataset that required seven months of expert effort. Our tool achieved comparable accuracy in minutes per article. We implemented a dual-validation strategy combining standard extraction metrics with a qualitative “LLM-as-a-Judge” fact-checking layer to assess contextual correctness. This revealed that high extraction performance does not guarantee factual reliability, underscoring the necessity of semantic validation in scientific knowledge extraction. The resulting open, reproducible framework accelerates evidence synthesis, supports trend analysis (e.g., metal–plant co-occurrence networks), and provides a scalable solution for data-driven environmental research. Full article

We demonstrate that the potential bias in the scores generated by individual classifiers negatively affects their fusion. Consequently, we present an algorithm to improve the effectiveness of score fusion in classification. The algorithm corrects the score class conditional bias before fusion. The interest of the procedure is demonstrated theoretically, first in general terms and then considering exponential models for the score class conditional distributions. The case of beta distributions is also addressed using Monte Carlo simulations. Finally, a real-life application of fusion of two modalities (EEG, ECG) and two classifiers (Gaussian Bayes and Logistic Regression) is included, showing significant improvement with respect to conventional fusion without bias correction. Full article

This article presents the development of a modular software suite for automated analysis of scientific publications in PDF format. The system integrates vectorization, clustering, topic modelling, dimensionality reduction, and fuzzy logic to combine both formal (vector-based) and semantic (topic-based) approaches. Interactive 3D visualization supports intuitive exploration of thematic clusters, allowing users to highlight relevant documents and adjust analytical parameters. Validation on a maritime safety case study confirmed the system’s ability to process large publication collections, identify relevant sources, and reveal underlying knowledge structures. Compared to established frameworks such as PRISMA or Scopus/WoS Analytics, the proposed tool operates directly on full-text content, provides deeper thematic classification, and does not require subscription-based databases. The study also addresses the limitations arising from data bias and reproducibility issues in the semantic interpretability of safety-critical decision-making systems. The approach offers practical value for organizations in safety-critical domains—including transportation, energy, cybersecurity, and human–machine interaction—where rapid access to thematically related research is essential. Full article

Common Weakness Enumerations (CWEs) and Common Vulnerabilities and Exposures (CVEs) are open knowledge bases that provide definitions, descriptions, and samples of code vulnerabilities. The combination of Large Language Models (LLMs) with vulnerability knowledge bases helps to enhance and automate code vulnerability repair. Several key factors come into play in this setting, including (1) the retrieval of the most relevant context to a specific vulnerable code snippet; (2) augmenting LLM prompts with the retrieved context; and (3) the generated artifact form, such as a code repair with natural language explanations or a code repair only. Artifacts produced by these factors often lack transparency and explainability regarding the rationale behind the repair. In this paper, we propose an LLM-enabled framework for explainable recommendation of vulnerable code repairs with techniques addressing each factor. Our method is data-driven, which means the data characteristics of the selected CWE and CVE datasets and the knowledge base determine the best retrieval strategies. Across 100 experiments, we observe the inadequacy of the SOTA metrics to differentiate between low-quality and irrelevant repairs. To address this limitation, we design the LLM-as-a-Judge framework to enhance the robustness of recommendation assessments. Compared to baselines from prior works, as well as using static code analysis and LLMs in zero-shot, our findings highlight that multifaceted LLMs guided by retrieval context produce explainable and reliable recommendations under a small to mild level of self-alignment bias. Our work is developed on open-source knowledge bases and models, which makes it reproducible and extensible to new datasets and retrieval strategies. Full article

The growing number of domain-specific machine learning benchmarks has driven methodological progress, yet real-world deployments require a different evaluation approach. Model-aware synthetic benchmarks, designed to emphasize failure modes of existing models, are proposed to address this need. However, evaluating already well-performing models presents a significant challenge, as the limited number of high-quality data points where they exhibit errors makes it difficult to obtain statistically reliable estimates. To address this gap, we proposed a two-step benchmark construction process: (i) using a genetic algorithm to augment the data points where data-driven models exhibit poor prediction quality; (ii) using a generative model to approximate the distribution of these points. We established a general formulation for such benchmark construction, which can be adapted to non-classical machine learning models. Our experimental study demonstrates that our approach enables the accurate evaluation of data-driven models for both regression and classification problems. Full article

Reliable bearing fault diagnosis across diverse operating conditions remains a fundamental challenge in intelligent maintenance. Traditional data-driven models often struggle to generalize due to the limited ability to represent complex and heterogeneous feature relationships. To address this issue, this paper presents an Adaptive Multi-view Hypergraph Learning (AMH) framework for cross-condition bearing fault diagnosis. The proposed approach first constructs multiple feature views from time-domain, frequency-domain, and time–frequency representations to capture complementary diagnostic information. Within each view, an adaptive hyperedge generation strategy is introduced to dynamically model high-order correlations by jointly considering feature similarity and operating condition relevance. The resulting hypergraph embeddings are then integrated through an attention-based fusion module that adaptively emphasizes the most informative views for fault classification. Extensive experiments on the Case Western Reserve University and Ottawa bearing datasets demonstrate that AMH consistently outperforms conventional graph-based and deep learning baselines in terms of classification precision, recall, and F1-score under cross-condition settings. The ablation studies further confirm the importance of adaptive hyperedge construction and attention-guided multi-view fusion in improving robustness and generalization. These results highlight the strong potential of the proposed framework for practical intelligent fault diagnosis in complex industrial environments. Full article

The development of systems for the identification of elasmobranchs, including sharks and rays, is crucial for biodiversity conservation and fisheries management, as they represent one of the most threatened marine taxa. This challenge is constrained by data scarcity and the high morphological similarity among species, which limits the applicability of traditional supervised models trained on specific datasets. In this work, we propose an informed zero-shot learning approach that integrates external expert knowledge into the inference process, leveraging the multimodal CLIP framework. The methodology incorporates three main sources of knowledge: detailed text descriptions provided by specialists, schematic illustrations highlighting distinctive morphological traits, and the taxonomic hierarchy that organizes species at different levels. Based on these resources, we design a pipeline for prompt extraction and validation, taxonomy-aware classification strategies, and enriched embeddings through a prototype-guided attention mechanism. The results show significant improvements in CLIP’s discriminative capacity in a complex problem characterized by high inter-class similarity and the absence of annotated examples, demonstrating the value of integrating domain knowledge into methodology development and providing a framework adaptable to other problems with similar constraints. Full article

The rapid growth of technology has introduced robots into daily life, necessitating navigation frameworks that enable safe, human-friendly movement while accounting for social aspects. Such methods must also scale to situations with multiple humans and robots moving simultaneously. Recent advances in Deep Reinforcement Learning (DRL) have enabled policies that incorporate these norms into navigation. This work presents a socially aware navigation framework for mobile robots operating in environments shared with humans and other robots. The approach, based on single-agent DRL, models all interaction types between the ego robot, humans, and other robots. Training uses a reward function balancing task completion, collision avoidance, and maintaining comfortable distances from humans. An attention mechanism enables the framework to extract knowledge about the relative importance of surrounding agents, guiding safer and more efficient navigation. Our approach is tested in both dynamic and static obstacle environments. To improve training efficiency and promote socially appropriate behaviors, Imitation Learning is employed. Comparative evaluations with state-of-the-art methods highlight the advantages of our approach, especially in enhancing safety by reducing collisions and preserving comfort distances. Results confirm the effectiveness of our learned policy and its ability to extract socially relevant knowledge in human–robot environments where social compliance is essential for deployment. Full article

We propose a hybrid framework that integrates instance clustering with Automatic Generation of Algorithms (AGA) to produce specialized algorithms for classes of Multidimensional Knapsack Problem (MKP) instances. This approach is highly relevant given the latest trends in AI, where Large Language Models (LLMs) are actively being used to automate and refine algorithm design through evolutionary frameworks. Our method utilizes a feature-based representation of 328 MKP instances and evaluates K-means, HDBSCAN, and random clustering to produce 11 clusters per method. For each cluster, a master optimization problem was solved using Genetic Programming, evolving algorithms encoded as syntax trees. Fitness was measured as relative error against known optima, a similar objective to those being tackled in LLM-driven optimization. Experimental and statistical analyses demonstrate that clustering-guided AGA significantly reduces average relative error and accelerates convergence compared with AGA trained on randomly grouped instances. K-means produced the most consistent cluster-specialization. Cross-cluster evaluation reveals a trade-off between specialization and generalization. The results demonstrate that clustering prior to AGA is a practical preprocessing step for designing automated algorithms in NP-hard combinatorial problems, paving the way for advanced methodologies that incorporate AI techniques. Full article

Unsupervised Hebbian learning is a biologically inspired algorithm designed to extract representations from input images, which can subsequently support supervised learning. It presents a promising alternative to traditional artificial neural networks (ANNs). Many attempts have focused on enhancing Hebbian learning by incorporating more biologically plausible components. Contrarily, we draw inspiration from recent advances in ANNs to rethink and further improve Hebbian learning in three interconnected aspects. First, we investigate the issue of overfitting in Hebbian learning and emphasize the importance of selecting an optimal number of training epochs, even in unsupervised settings. In addition, we discuss the risks and benefits of anti-Hebbian learning in model performance, and our visualizations reveal that synapses resembling the input images sometimes do not necessarily reflect effective learning. Then, we explore the impact of different activation functions on Hebbian representations, highlighting the benefits of properly utilizing negative values. Furthermore, motivated by the success of large pre-trained language models, we propose a novel approach for leveraging unlabeled data from other datasets. Unlike conventional pre-training in ANNs, experimental results demonstrate that merging trained synapses from different datasets leads to improved performance. Overall, our findings offer fresh perspectives on enhancing the future design of Hebbian learning algorithms. Full article

Amid ongoing efforts to develop extremely large, multimodal models, there is increasing interest in efficient Small Language Models (SLMs) that can operate without reliance on large data-centre infrastructure. However, recent SLMs (e.g., LLaMA or Phi) with up to three billion parameters are predominantly trained in high-resource languages, such as English, which limits their applicability to industries that require robust NLP solutions for less-represented languages and low-resource settings, particularly those requiring low latency and adaptability to evolving label spaces. This paper examines a retrieval-based approach to multi-label text classification (MLC) for a media monitoring dataset, with a particular focus on less-represented languages, such as Slovene. This dataset presents an extreme MLC challenge, with instances labelled using up to twelve thousand categories. The proposed method, which combines retrieval with computationally efficient prediction, effectively addresses challenges related to multilinguality, resource constraints, and frequent label changes. We adopt a model-agnostic approach that does not rely on a specific model architecture or language selection. Our results demonstrate that techniques from the extreme multi-label text classification (XMC) domain outperform traditional Transformer-based encoder models, particularly in handling dynamic label spaces without requiring continuous fine-tuning. Additionally, we highlight the effectiveness of this approach in scenarios involving rare labels, where baseline models struggle with generalisation. Full article

The growing use of machine learning (ML) and artificial intelligence across sectors has shown strong potential to improve decision-making processes. However, the adoption of ML by non-technical professionals remains limited due to the complexity of traditional development workflows, which often require software engineering and data science expertise. In recent years, low-code and no-code platforms have emerged as promising solutions to democratize ML by abstracting many of the technical tasks typically involved in software engineering pipelines. This paper investigates whether these platforms can offer a viable alternative for making ML accessible to non-expert users. Beyond predictive performance, this study also evaluates usability, setup complexity, the transparency of automated workflows, and cost management under realistic “out-of-the-box” conditions. This multidimensional perspective provides insights into the practical viability of LC/NC tools in real-world contexts. The comparative evaluation was conducted using three leading cloud-based tools: Amazon SageMaker Canvas, Google Cloud Vertex AI, and Azure Machine Learning Studio. These tools employ ensemble-based learning algorithms such as Gradient Boosted Trees, XGBoost, and Random Forests. Unlike traditional ML workflows that require extensive software engineering knowledge and manual optimization, these platforms enable domain experts to build predictive models through visual interfaces. The findings show that all platforms achieved high accuracy, with consistent identification of key features. Google Cloud Vertex AI was the most user-friendly, SageMaker Canvas offered a highly visual interface with some setup complexity, and Azure Machine Learning delivered the best model performance with a steeper learning curve. Cost transparency also varied considerably, with Google Cloud and Azure providing clearer safeguards against unexpected charges compared to Sagemaker Canvas. Full article

Both remote sensing and medical fields benefited a lot from the machine learning methods, originally developed for computer vision and multimedia. We investigate the applicability of the same data mining-based machine learning (ML) techniques for exploring the structure of both Earth observation (EO) and medical image data. Support Vector Machine (SVM) is an explainable active learning tool to discover the semantic relations between the EO image content classes, extending this technique further to medical images of various types. The EO image dataset was acquired by multispectral and radar sensors (WorldView-2, Sentinel-2, TerraSAR-X, Sentinel-1, RADARSAT-2, and Gaofen-3) from four different urban areas. In addition, medical images were acquired by camera, microscope, and computed tomography (CT). The methodology has been tested by several experts, and the semantic classification results were checked by either comparing them with reference data or through the feedback given by these experts in the field. The accuracy of the results amounts to 95% for the satellite images and 85% for the medical images. This study opens the pathway to correlate the information extracted from the EO images (e.g., quality-of-life-related environmental data) with that extracted from medical images (e.g., medical imaging disease phenotypes) to obtain geographically refined results in epidemiology. Full article

Spectral clustering has established itself as a powerful technique for data partitioning across various domains due to its ability to handle complex cluster structures. However, its computational efficiency remains a challenge, especially with large datasets. In this paper, we propose an enhancement of spectral clustering by integrating Cover tree data structure to optimize the nearest neighbor search, a crucial step in the construction of similarity graphs. Cover trees are a type of spatial tree that allow for efficient exact nearest neighbor queries in high-dimensional spaces. By embedding this technique into the spectral clustering framework, we achieve significant reductions in computational cost while maintaining clustering accuracy. Through extensive experiments on random, synthetic, and real-world datasets, we demonstrate that our approach outperforms traditional spectral clustering methods in terms of scalability and execution speed, without compromising the quality of the resultant clusters. This work provides a more efficient utilization of spectral clustering in big data applications. Full article