Mach. Learn. Knowl. Extr., Volume 8, Issue 8 (August 2026) – 34 articles

Adaptive decision-making has emerged as an important direction in audio classification. Reinforcement learning (RL) and multi-armed bandit (MAB) methods offer principled frameworks for sequential and localized decision-making. However, despite growing interest in these approaches and the availability of review studies on audio classification and audio-based learning, their role within the audio classification pipeline remains fragmented and has not been systematically synthesized. This study presents a systematic review of RL- and MAB-based approaches in audio classification, to characterize how adaptive decision-making is formulated, where it is applied within the pipeline, and what impact it has on system performance, robustness, and efficiency. The review followed PRISMA guidelines. A literature search across IEEE Xplore, Scopus, Nature, and Google Scholar identified 1896 records. Thirty-one studies met the predefined inclusion criteria and data were extracted for analysis. Reporting quality was assessed using the TRIPOD framework, and methodological reliability was evaluated using a domain-specific risk-of-bias tool. The findings show that adaptive decision-making in audio classification is evolving toward a control-centric paradigm. RL-based optimization and control approaches dominated the literature, whereas bandit-based approaches remained comparatively underused. A central finding of the review is a structural mismatch between problem type and method choice. Many adaptive tasks are inherently local and repeated decision problems, yet they are predominantly addressed using full RL frameworks rather than lighter bandit formulations. This review introduces a taxonomy of adaptive decision-making mechanisms and proposes a unified framework that reframes audio classification as a layered decision-making process under uncertainty. The evidence suggests that the future of audio classification lies not only in improved prediction, but in adaptive decision-making architectures capable of managing uncertainty, variability, and real-world deployment constraints. Full article

Background: Large language models (LLMs) are increasingly explored for automated educational assessment, while future educational platforms may combine grading, feedback, learner analytics, and personalization. The objective of this study was to determine whether student-history metadata can influence the numerical score assigned to the same answer. Methods: This study introduces GradeDrift-LLM, a controlled framework for measuring student-history-induced score drift in LLM-based automated grading. We evaluated 1000 Computer Science answers from 100 students across six student-history conditions and eight open-weight LLMs. For each grading instance, the submitted answer, question, reference answer, rubric-related information, scoring scale, and grading instruction were kept constant; only the student-history condition varied. Results: Across 39,997 valid paired comparisons, 83.92% showed no drift, 9.40% showed upward drift, and 6.68% showed downward drift. Mean absolute drift was 0.2137 points, and the 95th percentile absolute drift was 1 point. Positive-history frames tended to increase scores, whereas negative-history frames tended to decrease them. Drift was model-dependent, not uniformly explained by approximate scale, and present in both technical and argumentative answers; rare extreme deviations reached 10 points. Conclusions: Student-history metadata can influence LLM-generated grading scores despite explicit instructions to ignore it. Future LLM-based grading systems should separate answer-based scoring from learner-context-based personalization and validate score invariance under controlled learner-context variations. Full article

Autonomous vehicles increasingly require capabilities that extend beyond perception towards contextual understanding, semantic reasoning, and explainable decision-making. Knowledge graphs (KGs) have emerged as a promising solution by integrating heterogeneous sensor data, traffic regulations, domain knowledge, and contextual information into unified semantic frameworks. This review systematically examines knowledge graph-based intelligent reasoning in autonomous driving through a PRISMA 2020-guided analysis of 47 peer-reviewed studies identified from the literature published from 1 January 2018 to 31 January 2026. The findings reveal that semantic scene understanding and ontology-based representations currently dominate the field, with 66.0% of studies integrating knowledge graphs with deep learning approaches. Neuro-symbolic methods and explainable AI components were identified in 38.3% and 34.0% of publications, respectively, indicating increasing research interest in hybrid and transparent AI architectures. The analysis further demonstrates that 80.9% of studies remain limited to benchmark datasets and simulation environments, whereas only 19.1% provide real-world validation, suggesting relatively low technological maturity and limited industrial readiness. Although KG-enabled approaches substantially improve contextual awareness, hidden hazard anticipation, and explainability compared with conventional perception-centric architectures, major challenges remain regarding scalability, ontology interoperability, semantic error propagation, real-time reasoning, and certification requirements. The review identifies the convergence of knowledge graphs, large language models, and neuro-symbolic AI as a promising direction for next-generation autonomous driving systems. Future research should therefore focus on uncertainty-aware reasoning, adaptive explainability, standardised evaluation methodologies, and certification-oriented real-world deployment strategies. Full article

Machine learning (ML) models have achieved remarkable success in areas ranging from healthcare to autonomous systems. Yet, their inherent complexity frequently obscures the reasoning behind their decisions, undermining transparency, accountability, and user trust. Compounding this issue is the absence of a universal methodology for comparing and ranking interpretability across diverse ML models and interpretability techniques. This paper addresses this gap by introducing a configurable framework of quantitative metrics to evaluate and rank interpretability. Our approach offers a structured, heuristic basis for assessing model clarity, decision logic, and accessibility, enabling practitioners to systematically compare interpretability across a wide range of algorithms and techniques. The resulting scores are intended as a practical, domain-configurable heuristic guide for comparison rather than a universal notion of interpretability. Full article

Remaining useful life (RUL) estimation is a fundamental task in Prognostics and Health Management (PHM), supporting condition-based and predictive maintenance of engineering systems. Data-driven methods contribute to many effective strategies for RUL prediction. However, two problems need to be solved when they are used in industrial applications: (1) The amount of data under one working condition is limited, and data from different working conditions suffer from domain discrepancies. These methods are constrained by distribution differences in data under different working conditions. (2) There is an urgent need to quickly achieve prediction with much less computing resources. To address these issues, a lightweight RUL prediction method called a knowledge transfer-based heterogeneous distillation network is proposed by combining knowledge distillation and transfer learning. First, the adversarial training mechanism is introduced for the extraction of domain-invariant features. Subsequently, a heterogeneous knowledge distillation framework is further designed for remaining useful life prediction, in which a bi-directional long short-term memory model serves as the teacher network and a compact fully connected network acts as the student model. The teacher model is used to learn informative degradation patterns and guide the training of the lightweight student model through knowledge transfer. Results obtained on the N-CMAPSS dataset verify that the proposed method achieves promising effectiveness and strong generalizability, reducing the average RMSE and MAE by 44.83% and 41.30%, respectively. Full article

This study conducts a clinical evaluation of a secure, locally deployed, quantized large language model (LLM) for automating modified Rankin Scale (mRS) score extraction from unstructured neurosurgical notes. We retrospectively selected 103 authentic clinical letters (2007–2025) from aneurysm patients at a tertiary neurosurgical centre. To comply with data privacy constraints, an open-source reasoning LLM (Qwen3-32B) with 4-bit quantization was deployed entirely on-premises. The LLM extracted mRS scores using a zero-shot approach with custom logits processors to enforce strict JSON formatting. Performance was compared to a reference standard (attending neurosurgeons’ consensus) and parallel scoring by medical residents and students. The LLM achieved excellent agreement with the attending consensus (QWK 0.95), matching the reliability of medical students (QWK 0.95) and residents (QWK 0.93). Exact agreement was 75%, and agreement within ±1 mRS point was 96%. Bayesian analysis strongly supported statistical equivalence between the model and human raters. The computationally optimized LLM demonstrated human-level classification reliability without task-specific fine-tuning. This approach successfully addresses key patient data privacy barriers and the formatting inconsistencies typical of open-ended generative models. Securely deploying a general-purpose, quantized LLM provides a scalable pathway for extracting functional outcomes and supports FAIR-aligned data systems. Full article

Client selection is a critical mechanism for ensuring robust convergence in Federated Learning (FL) systems, yet it remains vulnerable to Non-IID data distributions and Byzantine attacks. Deep Reinforcement Learning (DRL) has shown promise for automated client selection, yet existing methods suffer from three structural deficiencies: observation ambiguity, where scalar states cannot distinguish malicious updates from benign heterogeneity; reward fragility, whereby attackers exploit unbounded feedback to hijack policy updates; and risk blindness, as risk-neutral agents overlook the inherent variance in client contributions. To address these deficiencies, we propose InfRA-FL, a robust adaptive framework. A mutual-information-based state construction extracts high-utility features, resolving observation ambiguity. A Saturation-Aware Robust Reward (SARR) mechanism applies soft-clipping to bound each client’s influence on the policy gradient, provably neutralizing reward poisoning. URA-PPO, an uncertainty-aware algorithm with a dual-head Critic, optimizes a risk-penalized objective that shifts the agent from risk-neutral to risk-averse decision-making. Experiments on MNIST and CIFAR-10 under 20% Byzantine adversaries show that InfRA-FL outperforms state-of-the-art baselines by 5–10% in accuracy while accelerating convergence, establishing that principled information-theoretic observation and robust reward design suffice to secure RL-driven federated learning against targeted poisoning. Full article

Target-speaker automatic speech recognition (TS-ASR) enables transcription of a specific speaker in multi-talker environments, yet remains largely unexplored for multilingual, low-resource languages. Existing TS-ASR systems predominantly target monolingual English using diarization-based or speaker-embedding approaches, leaving a critical gap for languages such as Kazakh, where code-switching with Russian and English is commonplace. We propose Persona-ASR, a modular two-stage architecture. The first stage is an explicit target-presence gate that verifies whether the enrolled speaker appears in the mixture and emits a <no_target> token to suppress transcription when the speaker is absent, directly addressing the acoustic-hallucination failure mode of prior systems. The second stage performs enrollment-conditioned recognition: a 192-dimensional ECAPA-TDNN speaker embedding modulates a WavLM-Base-Plus encoder through feature-wise linear modulation (FiLM), while language-specific CTC heads enable joint Kazakh and English decoding without forcing Latin and Cyrillic symbols to compete in a single output space. To evaluate the system, we introduce KazMix3, a Kazakh overlap dataset for TS-ASR training, and PersonaMix, a controlled bilingual benchmark spanning same- and cross-language enrollment across varying interferer counts (1–3) and signal-to-noise ratios ($-3$ to $+3$ dB). Persona-ASR outperforms a strong off-the-shelf cascade baseline by 13.3 WER points on English and 24.6 on Kazakh, and matches a published monolingual English baseline. On PersonaMix, speaker conditioning reduces relative word error rate by 40.7% on English and 59.3% on Kazakh mixtures over an unconditioned variant of the same model, and cross-language enrollment (unseen during training) remains effective, increasing average raw WER by only 4.1 points (English) and 2.2 points (Kazakh) relative to same-language enrollment. To our knowledge, Persona-ASR is the first TS-ASR system for the Kazakh language, establishing a foundation for multilingual personalized ASR in low-resource settings. Full article

Reliable digital twins of complex nonlinear systems require not only high predictive accuracy but also physical consistency, robustness under degraded operating conditions, and explicit uncertainty handling. Purely data-driven models often suffer from poor generalization, unphysical behaviors, and limited interpretability when facing noisy measurements and unseen operating conditions. This paper introduces a knowledge-guided physics-informed hybrid learning framework that integrates recurrent neural networks with Unscented Kalman Filter (UKF) state estimation and embedded thermodynamic constraints within a unified uncertainty-aware architecture. The proposed PI-LSTM-UKF framework achieves competitive predictive accuracy and improved physical consistency relative to the residual-learning hybrids by tightly integrating physics-informed recurrent learning, thermodynamic constraints, and sequential UKF state estimation. While the UKF provides robust recursive correction under noisy measurements during closed-loop operation, the physics-informed Long Short-Term Memory (PI-LSTM) learns nonlinear corrections and long-term dynamics that cannot be captured by the linear model alone. The proposed framework is systematically benchmarked against a hierarchy of seven modeling approaches, including Dynamic Mode Decomposition with control (DMDc), Sparse Identification of Nonlinear Dynamics (SINDy), and residual-learning variants based on Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM). High-fidelity Simscape simulations of a Rankine-cycle steam turbine system are used as a challenging simulation-based case study. Results show that the knowledge-guided hybrid approach achieves competitive predictive accuracy, improved physical consistency, and robust performance under an unseen load profile, severe thermodynamic degradation, valve hysteresis, and substantially elevated sensor noise. The framework provides a promising simulation-based foundation for uncertainty-aware digital twins of nonlinear thermal power systems. Validation using operational plant data remains necessary before its application to real-time monitoring and predictive maintenance. Full article

Tabular foundation models (TFMs) have moved tabular machine learning from per-dataset training towards amortised in-context inference, fitting a small-to-medium table in a single forward pass without a training run. The 2024–2026 release train, the TabPFN and TabICL lines and challengers such as Mitra, LimiX and Orion, has produced a generation whose architectures, capabilities and limits are documented mainly in preprints, while existing surveys treat these models as a subsection of tabular deep learning or of language-model table understanding. This review is, to our knowledge, the first organised around the current generation. From a corpus of 961 screened records and 98 retained studies, it taxonomises the architectures by pretraining regime, maps the capability space across five axes, isolates the language-model-on-tabular strand for prediction, feature engineering and generation, and summarises openness and deployment. A dedicated critical synthesis then reads the reported capabilities against independent evidence: on the studies reviewed here, tree-based and deep models retain the lead across 142 curated datasets that go beyond the standard independent and identically distributed setting; on 112 datasets, the models attain the highest accuracy but weaker conditional coverage than gradient-boosted trees; and robustness under feature shift, fairness and generation quality remain open. Amortised in-context prediction is thus a working paradigm whose independent evidence has yet to match its benchmark claims. Full article

This work investigates the safe exploration problem in reinforcement learning, where an agent must maximize cumulative performance while simultaneously satisfying safety constraints. This challenge becomes particularly difficult in long-horizon tasks because safe reinforcement learning methods often become overly conservative, restricting exploration and preventing agents from reaching distant goals, while estimation errors accumulate over extended horizons. We propose Imagine To Ensure Safety in Hierarchical Reinforcement Learning (ITES), which combines a learnable world model with high-level and low-level policies to promote safety at both hierarchical levels. The novelty of ITES lies in jointly ensuring safe subgoal generation and safe subgoal execution within a hierarchical framework. The high-level policy generates intermediate subgoals that guide exploration toward safe regions, while the low-level policy uses imagined rollouts in the learned world model to reduce unsafe behavior during subgoal execution. We evaluate ITES on the long-horizon SafeAntMaze C-shape, SafeAntMaze W-shape, and SafePusher benchmarks, as well as on short-horizon Safety Gym tasks, using task performance and episodic cost under prescribed safety budgets. The results show that ITES achieves substantially higher task success and constraint-compliant success rates on the long-horizon benchmarks while maintaining mean episodic costs below the prescribed budgets. Full article

Quantum machine learning (QML) has emerged as a promising approach for analyzing the complex, high-dimensional data encountered in oncology, yet research in this area remains fragmented. This systematic literature review synthesizes current applications of QML in cancer care. Following PRISMA guidelines, six databases were searched for peer-reviewed English-language studies published between 2020 and 2026. Of the 212 records identified, 49 studies met the inclusion criteria after screening and quality assessment. The findings show that QML research is dominated by classification and detection tasks, while segmentation is beginning to emerge. Breast cancer and brain tumors are the most frequently investigated domains. Hybrid quantum-classical models, particularly quantum kernel methods, quantum neural networks, and quantum convolutional neural networks, are the predominant approaches. The main barriers to adoption are hardware limitations, including quantum noise, limited qubit availability, and reliance on simulators. Overall, QML in oncology remains in its early stages of development, with limited clinical validation, insufficient model interpretability, and little evidence of a clear quantum advantage. Future research should prioritize evaluation on real quantum hardware, larger and more diverse clinical datasets, standardized benchmarking against classical methods, and closer collaboration between computer scientists and oncology experts to facilitate clinical translation. Full article

Dataset distillation has achieved strong results in computer vision, but is largely underexplored in the tabular domain. We introduce a tabular dataset distillation method that projects the data through many random embedders (views) to achieve invariance to transformation and to focus on the consistency between real and synthetic sets. The synthetic set is determined through a formulation of distribution matching between the many-view projection of the original and distilled dataset. Building on this approach, our proposal achieves three goals: (1) we formulate the Tabular Alignment via Moment Embeddings (TAME) method and, by extensive empirical evaluation, we show its efficiency; (2) we evaluate TAME on a benchmark of 18 tabular datasets, with strong baselines and evaluation metrics; and (3) we present a structured set of studies analyzing the impact of losses, dataset geometry, embedder architecture, instances per class (IPC) budget and downstream classifiers. We show that the proposed TAME method consistently surpasses baselines on neural classifiers, while remaining competitive with strong coreset baselines on tree-based classifiers (RF, XGBoost). Performance is further increased, especially for tree-based classifiers with a lightweight validation method. Extensive evaluation, including on additional large-scale sets and ablation experiments, allow a better understanding of the method. Full article

Autonomous agricultural robots require accurate trajectory tracking to perform precision field operations such as seeding, fertilization, and pruning. Classical kinematic models fail to capture the nonlinear dynamics inherent to real field conditions, limiting the performance of model-based control strategies. This work proposes an optimal hybrid methodology integrating Takagi–Sugeno (T–S) fuzzy model identification and Pure Pursuit (PP) control within a Particle Swarm Optimization (PSO) framework for a simulated pruning tractor. Data-driven T–S fuzzy models for incremental displacements ${\mathcal{M}}_{\Delta x}$ and ${\mathcal{M}}_{\Delta y}$ are identified using Fuzzy C-Means and parameterized via PSO. These fuzzy models are embedded in a PP feedback control scheme with discrete-time PI velocity and PD steering controllers, whose four gains are tuned by a second PSO instance. The fuzzy models achieve identification Root-Mean-Square Errors (RMSEs) of 10.598 × 10⁻³ m and 8.125 × 10⁻³ m. Integrated into the control loop, the system yields a lateral RMSE of 6.6 × 10⁻³ m on the training path and generalizes effectively across twelve complex agricultural coverage trajectories, maintaining a lateral RMSE below 12 × 10⁻³ m and heading RMSE under 1 degree. This interpretable, fuzzy rule-based approach provides an accurate and replicable simulation baseline for future experimental implementation on physical platforms. Full article

This research introduces a new spectral pruning approach using the Adjacency Edge Index (AEI), which is a centrality measure from the theory of spectral graphs and first-order matrix perturbation theory. The AEI score reflects the contribution of each neuron to the network’s dynamic synchronizability via the Fiedler vector. The AEI approach thus offers a mathematically motivated saliency score in the context of data-driven neuron co-activation graphs. The proposed approach has been tested on MNIST, Fashion MNIST, KMNIST, and a real-world social network dataset. The approach has been extended to convolutional filter pruning on the CIFAR-10 dataset using spatial global average pooling. The AEI approach has been compared to magnitude-based pruning methods like L1 and L2 norms and gradient-based pruning methods like SNIP and GraSP. The robustness of the proposed approach has been established by comparing the results over five random seeds. The AEI approach is proposed as a principled, interpretable, structure-aware pruning criterion rather than an accuracy-maximising method. Spectral analysis demonstrates that AEI is the only evaluated method that systematically targets structurally peripheral neurons, whereas magnitude-based methods prune broadly across the structural spectrum and GraSP actively removes structurally central neurons, an effect most pronounced on more complex datasets and deeper architectures (CIFAR-100, ResNet-20), where it causes substantial accuracy degradation at high sparsity. The AEI approach has been extended to the Hybrid approach by combining the AEI and L2 norms. The Hybrid approach has been seen to improve the accuracy gap at 40% sparsity from 5.46 to 2.26 percentage points over the state of the art. The robustness of the proposed approach has been established by conducting ablation studies on the robustness of the approach to the selection of the graph. The approach has been seen to be moderately robust to the selection of the graph with Spearman’s $\rho$ ≈ 0.70. The accuracy gap has been seen to be less than 0.2%. Full article

Luminescence thermometry has evolved through decades of research focused on optimising materials and on extracting temperature information from isolated spectral features such as luminescence intensity ratios, bandwidth, line shift and excited-state lifetime. Despite extensive material development, these conventional methods remain fundamentally limited by construction: only a small subset of pre-selected spectral features is exploited, while the bulk of the temperature-relevant information encoded in the full spectrum is systematically discarded. A paradigm shift is presented here: Luminescence Thermometry 2.0 (LT 2.0), implemented through the newly developed SpectraSensML platform, in which machine learning regression operates on the entire emission spectrum to deliver temperature readout. The approach is demonstrated on a Yb³⁺-doped phosphor emitting in the near-infrared biological transparency window across 100 to 700 K. Yb³⁺ is a particularly demanding case: only the single ²F_5/2 multiplet emits, and its weakly thermally coupled Stark sub-levels yield modest sensitivity under conventional intensity-ratio thermometry. A total of 27 regression algorithms drawn from four families, namely tree ensembles, physics-aware regression models, kernel and instance methods, and neural networks, are systematically benchmarked. A sensor-fusion estimator that combines the first three principal components reaches an average root-mean-square error of 0.36 K on an unseen-temperature test set, a seven-fold improvement over the best luminescence intensity ratio variant. Standard normal variate (SNV) normalisation is identified as the most effective preprocessing strategy because it isolates the band-shape deformations that encode temperature. Single-component approaches that rely on the first principal component alone are shown to be quantitatively sub-optimal: multi-component regressors that exploit the first three principal components reduce the temperature uncertainty by close to an order of magnitude. The structural reason behind the failure of decision-tree ensembles on unseen temperatures is explained: their piecewise-constant predictions cannot interpolate beyond training set-points. The open-source SpectraSensML application used to obtain the results is released alongside the manuscript to enable reproducible community benchmarks. Full article

The increasing digitization of healthcare records and growing reliance on interconnected systems have increased hospitals’ exposure to cyber threats, including ransomware, brute-force attacks, and Structured Query Language (SQL) injection. Traditional cybersecurity approaches alone are often insufficient to address these threats, prompting growing interest in artificial intelligence (AI)-based decision-support tools. This paper evaluates the potential of ChatGPT for hospital cybersecurity and incident response while introducing a structured qualitative framework for evaluating Large Language Model (LLM)-generated cybersecurity recommendations in healthcare. Through three progressively designed experiments and a ransomware case study, we evaluate ChatGPT’s role in developing a hospital cybersecurity plan, detecting brute-force login attempts, responding to an SQL injection attack, and managing a ransomware incident. Responses are assessed using five evaluation dimensions: specificity, completeness, technical correctness, feasibility, and alignment with the National Institute of Standards and Technology (NIST) Cybersecurity Framework (CSF), including both explicit mapping and function coverage. The results demonstrate that ChatGPT provides structured, context-aware guidance that aligns well with NIST CSF 2.0 and addresses governance and third-party risks. However, the recommendations also exhibit limitations, including limited operational depth, assumptions about technology and regulatory environments, lack of prioritization for resource-constrained settings, and limited consideration of implementation costs. Overall, the proposed evaluation framework provides a systematic approach for assessing LLM-generated cybersecurity guidance, while the findings indicate that ChatGPT can serve as a valuable decision-support tool that should complement, rather than replace, qualified cybersecurity professionals. Full article

This paper presents a novel method for pruning deep neural networks based on the concept of flow, derived from the continuous modeling of signal propagation across layers. We derive flow functions for fully connected, convolutional, and self-attention architectures, and we propose a new iterative pruning algorithm, Iterative Flow-Aware Pruning (IFAP), that leverages these measures to identify and eliminate non-essential parameters while preserving critical information pathways. Extensive experiments across ten prominent architectures (including CNNs, vision transformers, and efficient mobile networks) on ten benchmark datasets demonstrate consistent accuracy–compression trade-offs: $81\%$ of the evaluated configurations achieve a 60–$81\%$ reduction in computational cost relative to the corresponding baseline model. Furthermore, $97\%$ of the evaluated configurations retain more than $98\%$ of their baseline Top-1 accuracy. These results validate flow-based importance scoring as a robust and general-purpose foundation for model optimization. Full article

Temperature–time profiles obtained through thermistor-based monitoring provide a rich but noise-sensitive source of information for estimating kinetic and thermal parameters in exothermic batch reactions. Conventional workflows typically combine deterministic smoothing with numerical differentiation, an approach that can amplify measurement noise and fail to propagate preprocessing uncertainty into the resulting reaction-rate and parameter estimates. To address these limitations, this study presents an uncertainty-aware Bayesian machine-learning framework that integrates scalable random-Fourier-feature Gaussian-process (RFF–GP) smoothing, analytical differentiation, temperature-derived apparent conversion, Bayesian parameter inference, posterior validation, predictive calibration, model comparison, ablation, sensitivity analysis, probabilistic benchmarking, simulation of thermal nonideality, and endpoint diagnostics. The framework was applied to $379,631$ cleaned thermistor observations. The production RFF–GP achieved a validation root-mean-square error of $0.04805\mathrm{K}$, yielding a stable latent temperature trajectory and an uncertainty-aware estimate of $dT/dt$. On a smaller matched subset, exact Gaussian-process regression achieved the highest predictive accuracy and the best probabilistic scores, whereas the RFF–GP reduced central-processing-unit runtime by approximately $4.1$-fold and remained applicable to the larger production fit. A Monte Carlo dropout neural comparator produced larger prediction errors and substantially wider predictive intervals. Six apparent thermokinetic structures were evaluated using mean-field variational inference, after which the nth-order and autocatalytic structures were validated using the No-U-Turn Sampler (NUTS). Under mean-field variational inference, the apparent autocatalytic structure achieved the lowest point estimate of the widely applicable information criterion (WAIC), the lowest derivative-domain error, and the lowest full-profile temperature-reconstruction root-mean-square error of $0.2920\mathrm{K}$. Its posterior obtained using NUTS yielded $E_a=40.98\mathrm{kJ}{\mathrm{mol}}^{-1}$, $k_{\mathrm{ref}}=0.005815{\min }^{-1}$, $\Delta T_{\mathrm{ad}}=56.11\mathrm{K}$, $m=0.1694$, and $n=1.0784$. The sampling diagnostics indicated satisfactory convergence, large effective sample sizes, and no divergent transitions. Although the MFVI posterior means and NUTS posterior medians were similar, variational inference produced narrower uncertainty intervals for several correlated parameters. Moving-block bootstrap intervals did not establish a decisive separation in WAIC among the leading structures. Expanded sensitivity, ablation, imperfect-insulation simulation, and endpoint-holdout analyses further showed that the apparent parameter estimates were sensitive to optimization, thermal nonideality, sensor response, and Gaussian-process boundary behavior. The autocatalytic formulation should therefore be interpreted as the best-performing apparent structure among the candidates tested rather than as evidence of a unique chemical mechanism. Overall, the framework extracted physically plausible apparent thermokinetic information from noisy temperature-only measurements while explicitly quantifying uncertainty arising from prediction, parameter estimation, model form, computation, thermal nonideality, and boundary behavior. Full article

Selective algorithmic auditing requires deciding which process evidence should receive attention when exhaustive review is infeasible. This Review introduces a four-layer framework that connects process representation, learning, inspection allocation, and governance within a single budgeted sequential decision problem over event streams. Unlike prior reviews centered on predictive process monitoring, explainability, cost analysis, or bibliometric structure, the proposed framework examines how these functions interact when human review, computation, latency, and documentation capacity are constrained. A structured and targeted survey of 89 unique publication families is used to illustrate and critically examine event-log, Petri-net, graph, object-centric, neural, uncertainty-aware, sequential, bandit, reinforcement learning, and audit architecture approaches. The reviewed evidence indicates that substantial bodies of work address the individual layers, but cross-layer evaluation remains fragmented and uses heterogeneous datasets, objectives, and validation protocols. The synthesis identifies five priorities: audit-ready benchmarks, explicit inspection budget protocols, calibrated uncertainty, transfer across organizational contexts, and reproducible governance interfaces. The main contribution is a computational framework and a corpus-bounded research agenda that connects representation, learning, inspection allocation, and governance for selective algorithmic auditing. Full article

Detecting a few hundred fraudulent transactions among hundreds of thousands is an extreme class-imbalance problem where one miss can cost a full transaction value. Stacking heterogeneous classifiers is the standard recipe, yet under a leakage-free, precision–recall evaluation, its ranking gain over the best single model is inconsistent: sizable when the base learners are diverse, and negligible when they are redundant. The ensemble’s dependable value lies elsewhere: member disagreement is a usable, threshold-free estimate of epistemic uncertainty. We propose Daunt (Disagreement As UNcertainty for Triage), which turns this disagreement into three deployment layers over one ensemble: (i) routing the most uncertain transactions to human review by ranking them on base-learner disagreement, (ii) deciding alarms by an example-dependent rule that weighs the fraud score against the transaction amount, and (iii) attaching interpretations verified for faithfulness and stability. On two contrasting datasets, the anonymized ULB ($0.17\%$ fraud) and feature-rich IEEE-CIS ($3.5\%$ fraud), deferring the $5\%$ most uncertain transactions raises system recall from $0.76$ to $0.91$ (ULB) and $0.66$ to $0.75$ (IEEE-CIS) while removing every automated false alarm, and the example-dependent rule recovers more fraudulent money than any global threshold. Daunt reframes the heterogeneous ensemble as a source of actionable uncertainty rather than an end in itself. Full article

Background: Artificial intelligence (AI) and machine-learning (ML) prognostic models are increasingly developed for inflammatory bowel disease (IBD), yet their reported performance and clinical readiness remain inadequately appraised. Methods: Following PRISMA 2020 and a registered protocol, we searched PubMed, Web of Science, IEEE Xplore, and arXiv (January 2012–January 2026) for studies developing or validating prognostic models in Crohn’s disease or ulcerative colitis. Two reviewers independently screened the studies, extracted data, and assessed risk of bias using PROBAST + AI; discrimination was summarized by area under the curve (AUC) and stratified by validation type. Results: Of the 3050 records, 111 studies were included. Treatment response was the most common target; laboratory data and electronic health records were the most frequent modalities. Across 83 studies, the median AUC was 0.850; externally validated models reached 0.870 versus 0.845 for internal-only and 0.790 for cross-validation-only. External validation was reported in 29.7%, calibration in 14.4% and analysis code in 3.6%; the analysis domain was the leading source of bias. Conclusions: The evidence base maps reported discrimination rather than demonstrated clinical readiness. Until calibration, decision-curve utility, and transportability are reported alongside external validation, clinical deployment remains premature. Full article

Automated detection of epileptic seizures from electroencephalogram (EEG) recordings is essential for timely clinical intervention and long-term patient monitoring. Deep learning achieves high accuracy, but its limited interpretability and computational demands restrict deployment in resource-constrained, real-time clinical environments; furthermore, classical machine learning studies have concentrated on a narrow group of well-known temporal features. This study systematically introduces and evaluates 25 less-explored time-domain features, 13 of which have no documented precedent as classification features in scalp EEG seizure detection, against 25 classical features and their 50-feature combination. Raw, unfiltered recordings from the CHB-MIT database were segmented into 10-second windows, and seven classical classifiers were optimized with GridSearchCV under subject-wise StratifiedGroupKFold cross-validation, with the data partitioned at the patient level such that no patient appeared in both the training and test sets. The multilayer perceptron trained on the combined 50-feature set performed best (accuracy 86.59%, F1-score 86.35%), exceeding the classical features alone by 5.1 and 4.6 percentage points, respectively; the less-explored features alone remained competitive (84.63%, 84.67%). SHAP analysis identified the exponent of the detrended fluctuation analysis (DFA)—a long-range, nonlinear measure of temporal correlation—as the most influential predictor. The curated feature set, its rigorous subject-level validation, and its interpretability provide a reproducible and computationally efficient foundation for future clinical deployment. Full article

Pixel-level annotation remains a major bottleneck for semantic segmentation, motivating methods that synthesize image–label pairs directly from generative models. Prior synthetic dataset generators typically obtain pseudo-labels from cross-attention maps or learned decoders over generative features; however, recent text-to-image (T2I) models increasingly use multimodal diffusion transformers (MM-DiTs), where concept localization is no longer exposed through a single cross-attention pathway but instead distributed across many layers and attention heads. Existing MM-DiT localization methods address this by aggregating saliency across heads, but we observe that this averaging can dilute clean target localizers due to attention head heterogeneity. We introduce HEADHUNTER, a training-free segmentation framework that uses aggregate concept saliency as a self-guided proxy to select the single attention head that best localizes a queried textual concept, yielding cleaner segmentation masks. We then use HEADHUNTER to turn target classes into training data automatically: a large language model (LLM) diversifies prompts, an MM-DiT generates images, HEADHUNTER produces pseudo-labels, and a vision language model (VLM) verifies each image–mask pair before acceptance. HEADHUNTER achieves strong zero-shot segmentation performance (81.2 mIoU on PASCAL VOC2012 and 73.2 mIoU on ImageNet-Segmentation), outperforming head aggregation and other interpretability methods. Using only our generated image–label pairs, we train segmentation models which reach 64.9 mIoU on VOC2012 validation, matching or outperforming comparable synthetic dataset generators and showing that the proposed pipeline produces effective dense labels without human intervention. Full article

Extracting transferable design knowledge from Discrete Element Method (DEM) simulations remains challenging in granular material handling. We develop an explainable surrogate framework for two solar-panel-recycling subsystems: a silo discharge system (outlet width 42–111 mm; hopper half-angle 30–60°) and an inclined belt conveyor (fin height 20–50 mm; belt velocity 0.109–0.627 m/s). Five algorithms—Response Surface Methodology (RSM), Artificial Neural Network (ANN), Random Forest (RF), Gradient Boosting Machine (GBM), and Gaussian Process Regression (GPR)—were evaluated by leakage-free grouped five-fold cross-validation using 34 design points per system (2² factorial expanded by Latin Hypercube Sampling). The best surrogate is response-specific: ANN was most accurate for silo discharge (R² = 0.964, RMSE = 0.91 kg/s); GPR gave the highest raw belt-MFR accuracy (R² = 0.976 ± 0.023, RMSE = 0.43 kg/s), though the interpretable RSM was near-equivalent and was adopted for optimization; and RSM was near-perfect for belt discharge angle (R² = 0.999 ± 0.001, RMSE = 0.057°). GPR performed the worst for silo discharge (R² = 0.384), confirming the algorithm selection must match the response complexity. SHAP analysis identified outlet width (78.6%) and belt velocity (58.9–76.8%) as dominant predictors. The proposed SHAP Asymmetry Ratio (SAR) offers an exploratory diagnostic for algorithm pre-selection in expensive simulation-driven surrogate workflows. Full article

Background: Accurate histological grading of gliomas, distinguishing low-grade (LGG) from high-grade (HGG) lesions, remains a critical determinant of treatment planning and patient prognosis. This study systematically investigates the optimal combination of structural MRI sequences, pretrained convolutional neural network (CNN) architectures, and supervised classifiers for automated glioma grade classification. Methods: Deep features were extracted from four MRI sequences (T1, contrast-enhanced T1 (T1Gd), T2, and FLAIR) from the BraTS 2023 dataset using five pretrained CNNs: VGG16, ResNet50, DenseNet121, EfficientNetB0, and InceptionV3. Features were refined via LASSO selection and classified using Random Forest, Support Vector Machine, XGBoost, Gradient Boosting, k-Nearest Neighbors (KNNs), and a shallow deep neural network. A patient-level 80/20 training–test partition was employed, with five-fold cross-validation used within the training set for feature selection and hyperparameter optimization. A total of 120 modality–extractor–classifier configurations were benchmarked on the held-out test set. Results: InceptionV3-derived features paired with KNN classifiers consistently yielded superior performance. Based on a TOPSIS multi-criteria ranking integrating accuracy, precision, recall, F1-score, and AUC, the best-performing configuration combined T1Gd features with KNN (closeness coefficient = 0.971; accuracy = 0.975, precision = 0.997, recall = 0.948, F1-score = 0.969, AUC = 0.996). The second-ranked configuration, using T1 features with KNN (closeness coefficient = 0.962), achieved significantly higher accuracy, recall, and F1-score, despite its slightly lower composite ranking. Conclusion: Deep feature extraction using InceptionV3 from T1-weighted MRI, coupled with KNN classification, represents a promising and practical approach for slice-level glioma grading and merits further validation in prospective clinical cohorts. Full article

Multi-view learning has emerged as an effective paradigm for integrating heterogeneous data representations in complex classification problems, yet selecting suitable learners for Multi-View Stacking architectures remains computationally challenging and highly dependent on expert decisions. This work proposes 3MuViS, a three-phase methodology for automatic learner selection in Multi-View Stacking that optimizes both view-level learners and the meta-learner according to a target classification metric. The method evaluates candidate machine learning algorithms through cross-validation and constructs optimized stacking configurations. Experiments were conducted on six heterogeneous datasets spanning network intrusion detection, human activity recognition, handwritten digit classification, and transportation mode detection. Performance was evaluated over 25 iterations using the Matthews Correlation Coefficient (MCC), and statistical significance was assessed using Wilcoxon tests. The results show that 3MuViS consistently outperformed stochastic selection strategies and achieved superior or comparable performance to fixed models in five of the six evaluated datasets while frequently approaching the Brute Force upper-bound baseline at a substantially lower computational cost. The findings indicate that jointly optimizing view-level and meta-level learners improves both predictive performance and stability, demonstrating the potential of 3MuViS as a general and efficient framework for multi-view classification problems across diverse domains. Full article

A parking space system is a vital component of a smart transport management system, and it helps in managing parking spaces, reducing traffic congestion, and improving mobility. Deep learning helps in releasing smart parking systems. Despite their higher computational efficiency, lightweight convolutional neural networks (CNNs) may have limited feature representation capabilities and suffer from the vanishing gradient problem, which can reduce classification performance under challenging parking scenarios. To address this limitation, lightweight CNN models, such as MobileNetV2, EfficientNetB0, DenseNet, and ConvNeXt, are considered, with squeeze-and-excitation (SE) blocks incorporated to enhance channel-wise feature recalibration and stabilize gradients throughout the network. MobileNetV2 captures discriminative local features. EfficientNetB0 learns multi-scale semantic representations through compound scaling. DenseNet promotes hierarchical feature reuse. ConvNeXt extracts robust contextual features. The extracted deep features are subsequently reduced in dimensionality using Uniform Manifold Approximation and Projection (UMAP) while preserving the underlying manifold structure and removing redundant information. The reduced features are then classified by the ensembling of XGBoost, LightGBM, and support vector machine (SVM) classifiers, and their predictions are combined through a weighted stacking ensemble to exploit their complementary strengths and improve generalization. The proposed framework was experimentally evaluated on the PKLot, CNRPark and CNRPark + Ext datasets, achieving classification accuracies of 99.3%, 98.7% and 99.1%, respectively, demonstrating its effectiveness and robustness for real-world smart-city parking applications. Full article

Given the emergence of new applications with stringent networking requirements, traditional bit-level communication may reach theoretical Shannon capacity and struggle to support such applications. Therefore, the idea of semantic communication (SC) has been proposed in literature. SC involves the use of artificial intelligence and a shared knowledge base to send a representation of data and reconstruct it at the receiver. In this paper, a SC system for document transmission is proposed. The system uses a transformer and a context encoder module to preserve the document’s knowledge and context information by quantifying the relationship between a current sentence and the preceding sentences. The semantic information is sent over a noisy channel, and a mutual information maximization model is used to reduce the effect of noise on the transmitted signal. The proposed system is trained in two stages; the first stage involves training the sentence-level transformers while the second stage involves training the sentence-level and the context-level transformers. The performance of the system is evaluated using two publicly available datasets. The results show that the performance of the proposed system is better than a sentence-level SC model in terms of BLEU score and sentence similarity over a Rayleigh fading channel. Full article

Deep hypergraph learning is evaluated almost entirely through leaderboards that rank methods by mean accuracy over a few random seeds, usually without significance testing. Is there a best hypergraph neural network, or does the apparent ordering reflect seed noise? We independently recomputed the node-classification track of DHG-Bench on a single GPU with twenty random seeds (against five upstream) and a different software stack, and applied a four-layer statistical audit to the per-seed accuracies: a reproducibility check, per-dataset paired Wilcoxon tests with Holm correction, an across-datasets Friedman/Iman–Davenport omnibus with Nemenyi and Holm-corrected pairwise tests, and a variance decomposition. Within a single dataset, twenty seeds distinguish most method pairs (74–98%), so the protocol is not underpowered. Across the nine datasets where all 17 methods complete, the omnibus rejects global equality (Kendall’s $W=0.45$), yet no pair survives Holm correction, and the top methods fall within one critical-difference band. One dataset carries more seed noise than between-method signal and cannot rank methods. The recompute also documents a non-reproducible method, a label-range data fault, and missing per-dataset configurations in the public release. No single method is statistically best across these datasets, so single-leader claims are not supported; we release a reusable significance-aware evaluation protocol. Full article