Anomaly detection in multivariate time series is a central challenge in industrial monitoring, as failures frequently arise from complex temporal dynamics and cross-sensor interactions. While recent deep learning models, including graph neural networks and Transformers, have demonstrated strong empirical performance, most approaches remain primarily correlational and offer limited support for causal interpretation and root-cause localization. This study introduces a causally-constrained probabilistic forecasting framework which is a Causally Guided Transformer (CGT) model for multivariate time-series anomaly detection, integrating an explicit time-lagged causal graph prior with deep sequence modeling. For each target variable, a dedicated forecasting block employs a hard parent mask derived from causal discovery to restrict the main prediction pathway to graph-supported causes, while a latent Gaussian head captures predictive uncertainty. To leverage residual correlational information without compromising the causal representation, a shadow auxiliary path with stop-gradient isolation and a safety-gated blending mechanism is incorporated to suppress non-causal contributions when reliability is low. Anomalies are identified using negative log-likelihood scores with adaptive streaming thresholding, and root-cause variables are determined through per-dimension probabilistic attribution and counterfactual clamping. Experiments on the ASD and SMD benchmarks indicate that the proposed method achieves state-of-the-art detection performance, with F1-scores of 96.19

While automation has transformed many areas inside clinical laboratories, microbiology still relies heavily on manual tasks, particularly the culture of samples on agar plates and their subsequent manual review for microorganism identification and antibiotic susceptibility profiling. Bacterial colony detection and classification require trained professionals, making the process time-consuming and prone to human error. Developing deep learning models to automate these tasks could improve microbiology workflows and accelerate clinical decision-making. In this study we trained and evaluated five object detection architectures (Faster R-CNN and RetinaNet with ResNet-50 and ResNet-101 backbones, and YOLOv8) on the Annotated Germs for Automated Recognition (AGAR) dataset for bacterial colony classification. Transfer learning, cross-subset generalization, and Weighted Box Fusion (WBF) ensemble methods were applied to enhance and characterize performance. Additionally, we created and publicly released a curated dataset of 165 agar plate images containing colonies of S. aureus, P. aeruginosa, and E. coli cultured across four distinct culture media. YOLOv8m achieved a mean Average Precision (mAP) of 69.0% on the AGAR dataset, outperforming the best Detectron2 model (Faster R-CNN ResNet-101, 63.1%) by 5.9 percentage points. A four-model WBF ensemble combining both architectures reached 70.5% mAP (95% CI: 68.4-71.7). Cross-subset evaluation showed that a single model trained on the full dataset generalizes well to individual imaging conditions, making subset-specific fine-tuning largely unnecessary. On the curated dataset, a mixed ensemble reached 58.7% mAP (95% CI: 57.1-63.7). These results demonstrate that architecture choice and training data diversity are the primary drivers of performance for colony detection on agar plates.

Multi-label data stream classification has emerged as a critical learning paradigm for real-world applications in which data arrive continuously, labels are not mutually exclusive, and the underlying data distribution evolves over time.However, this task faces problems inherent to dynamic environments, such as the continuous arrival of data at high speed and volume, changes in data distribution (concept drift), the emergence of new labels (concept evolution), and the latency in the arrival of ground-truth labels.This systematic literature review presents an in-depth analysis of proposals for multi-label data stream classification.We characterize the latest methods published between 2016 and 2025, provide a comprehensive overview, construct a thorough hierarchy, and discuss how each proposal addresses each problem.Furthermore, we discuss the adopted evaluation strategies and analyze the asymptotic complexity and resource consumption of the methods.Finally, we identify the main gaps and offer recommendations for future research directions in the field.The review reveals a strong methodological focus on concept drift adaptation, often at the expense of other critical challenges.In particular, label latency and evolving label spaces are rarely addressed in a principled or scalable manner, despite their relevance in real-world deployments.Overall, the field shows methodological maturity in drift-aware learning but lacks integrated solutions that jointly address delayed supervision, evolving labels, and efficiency constraints.

Forecasting the covariance matrix of asset returns is central to portfolio construction, risk management, and asset pricing. However, most existing models struggle at medium-term horizons, several weeks to months, where shifting market regimes and slower dynamics prevail. We propose a novel deep learning framework that integrates three-dimensional convolutional neural networks, bidirectional long short-term memory, and multihead attention to capture complex spatiotemporal patterns in asset return dynamics. Using daily data on 14 exchange-traded funds from 2017 to 2023, we demonstrate that our model improves out-of-sample covariance forecasts by reducing Euclidean and Frobenius distance metrics by up to 20% compared with classical benchmarks such as shrinkage estimators and GARCH-type models. These gains persist across distinct market regimes, including bull and bear periods, and remain robust across various forecast horizons and under both raw and excess return specifications. Portfolio simulations based on global minimum variance strategies reveal that the proposed model consistently delivers lower volatility and moderate turnover, even under no-short-selling constraints. This balance between risk reduction and trading efficiency underscores the economic relevance of the forecasts, particularly for institutional investors managing portfolios at medium-term horizons.

Data streams with varying feature spaces have received extensive attention recently, while the common concept drift in them remains underexplored. Unsupervised concept drift detectors can report potential drifts without class labels, making them suitable for practical scenarios where labeling is usually costly and difficult. However, existing unsupervised detectors usually operate under fixed feature spaces. To address this limitation, a Matching Degree Histogram-based unsupervised detector for data streams with Varying Feature Spaces (MDH-VFS) is proposed. Changes in input features are refined into four scenarios, specifying the sources of concept drifts in such data streams. Based on this, MDH-VFS monitors the distribution of each feature independently using the fix-slide windows model. A matching degree-based histogram (MD-Histogram) supporting online updating is proposed to model data distribution. MD-Histogram requires no prior distributions and captures data change more sensitively than traditional histograms. The dissimilarity between two MD-Histograms is measured by the Hellinger distance, and drift is detected using an adaptive thresholding strategy. Both the drift positions and drift features can be reported. Experimental results show that MDH-VFS can not only effectively detect drifts in data streams with varying feature spaces (achieving average F1-score/MCC above 77% and outperforming nine existing detectors with improvements of at least 43%), but also improve the classification performance of downstream learning algorithms (reaching a maximum average accuracy of 88% and yielding up to 7.23% improvement).

The classic literature conveys innovation strategy the leading and starting role to generate business growth due to technology development and more effective managerial practices. However, the advent of Artificial Intelligence (AI) reverts this paradigm in the context of Industry 5.0. The focus is moving from “how innovation fosters AI” to “how AI fosters innovation”. Therefore, our research question can be stated as follows: What factors influence the effect of AI on Innovation Capacity in the context of Industry 5.0? To address this question, we conducted a quantitative study using a survey sample of 174 industrial AI use cases. With this data, we assess 3 hypotheses and critically discuss the influence of 4 factors extracted from the literature: organization age, AI maturity, manufacturing strategy, and innovation capacity. Further, we evaluate a conceptual model to predict AI's effect on innovation capacity in the context of Industry 5.0. A Bayesian Network is trained on the dataset that supports diagnosis and prediction of innovation capacity types with an overall path-level accuracy of 95%. This study provides researchers with a new understanding of the interplay between artificial intelligence and human intelligence in innovation management. It provides practitioners with a quantitative decision framework to guide their transition towards Industry 5.0.

In the evolving field of machine learning, ensuring group fairness has become a critical concern, prompting the development of algorithms designed to mitigate bias in decision-making processes. Group fairness refers to the principle that a model’s decisions should be equitable across different groups defined by sensitive attributes such as gender or race, ensuring that individuals from privileged groups and unprivileged groups are treated fairly and receive similar outcomes. However, achieving fairness in the presence of group-specific concept drift remains an unexplored frontier, and our research represents pioneering efforts in this regard. Group-specific concept drift refers to situations where one group experiences concept drift over time, while another does not, leading to a decrease in fairness even if accuracy (ACC) remains fairly stable. Within the framework of federated learning (FL), where clients collaboratively train models, its distributed nature further amplifies these challenges since each client can experience group-specific concept drift independently while still sharing the same underlying concept, creating a complex and dynamic environment for maintaining fairness. The most significant contribution of our research is the formalization and introduction of the problem of group-specific concept drift and its distributed counterpart, shedding light on its critical importance in the field of fairness. In addition, leveraging insights from prior research, we adapt an existing distributed concept drift adaptation algorithm to tackle group-specific distributed concept drift, which uses a multimodel approach, a local group-specific drift detection mechanism, and continuous clustering of models over time. The findings from our experiments highlight the importance of addressing group-specific concept drift and its distributed counterpart to advance fairness in machine learning.

Efficient public transportation management is essential for the development of large urban centers, providing several benefits such as comprehensive coverage of population mobility, reduction of transport costs, better control of traffic congestion, and significant reduction of environmental impact limiting gas emissions and pollution. Realizing these benefits requires a deeply understanding the population and transit patterns and the adoption of approaches to model multiple relations and characteristics efficiently. This work addresses these challenges by providing a novel dataset that includes various public transportation components from three different systems: regular buses, subway, and BRT (Bus Rapid Transit). Our dataset comprises daily information from about 700,000 passengers in Salvador, one of Brazil’s largest cities, and local public transportation data with approximately 2,000 vehicles operating across nearly 400 lines, connecting almost 3,000 stops and stations. With data collected from March 2024 to March 2025 at a frequency lower than one minute, SUNT stands as one of the largest, most comprehensive, and openly available urban datasets in the literature.

State-of-the-art data stream mining has long drawn from ensembles of the Very Fast Decision Tree, a seminal algorithm honored with the 2015 KDD Test-of-Time Award. However, the emergence of large tabular models, i.e., transformers designed for structured numerical data, marks a significant paradigm shift. These models move beyond traditional weight updates, instead employing in-context learning through prompt tuning. By using on-the-fly sketches to summarize unbounded streaming data, one can feed this information into a pre-trained model for efficient processing. This work bridges advancements from both areas, highlighting how transformers' implicit meta-learning abilities, pre-training on drifting natural data, and reliance on context optimization directly address the core challenges of adaptive learning in dynamic environments. Exploring real-time model adaptation, this research demonstrates that TabPFN, coupled with a simple sliding memory strategy, consistently outperforms ensembles of Hoeffding trees, such as Adaptive Random Forest, and Streaming Random Patches, across all non-stationary benchmarks.

Real time location data derived from mobile applications is a powerful tool for addressing various urban challenges, including tourism planning, parking management, bus route optimization, and resource allocation. Besides, it offers invaluable insights for shaping strategic decisions in commercial domains such as location based services, market share analysis, and behavioral profiling. In this expansive study, we aim to address all of the aforementioned challenges by investigating the behaviors and patterns of smartphone users within urban environments, particularly in the domains of tourism, transportation, and retail. Our approach encompasses the development of a sophisticated data platform from inception to implementation, which includes the formulation of use cases, architectural design, and implementation of modules. We employ state of the art techniques and technologies, including data anonymization, ETL pipelines, and utilizing Google BigQuery and Vertex AI for data processing and machine learning model development. A modular architecture based on reusable analytical building blocks was developed to generate data products that support multiple stakeholder driven use cases. Additionally, we apply interactive data visualization techniques via Power BI to facilitate the effective interpretation of analytical findings by stakeholders. The developed models address a wide range of mobility analytics tasks, including mobility profiling, frequent trajectory mining, area of influence analysis, traffic anomaly detection, and origin destination pattern analysis. The results demonstrate the framework's ability to capture user mobility dynamics at fine spatial and temporal resolutions, providing actionable insights for urban planning and strategic business decision making.

Training machine learning models with more than one data modality has enhanced predictive performance in most contexts. Thus, many recent applications of machine learning use data from different sources and forms. Multimodal data augmentation (MMDA) addresses critical challenges in multimodal learning, such as data scarcity, modality imbalance, and cross-modal alignment. This survey systematically reviews 68 state-of-the-art MMDA approaches, and, as result, proposes a taxonomy for the area. For each revised paper, this survey analyzes its methodology, applications, and predictive performance gains, while highlighting key challenges, such as scalability and evaluation metrics. The proposed taxonomy provides a unified framework for understanding MMDA methods, their strengths, and limitations. This survey also identifies emerging trends, including the integration of large language models and diffusion processes, and outlines future research directions to advance multimodal learning.

Early fault detection remains a critical challenge in predictive maintenance (PdM), particularly within critical infrastructure, where undetected failures or delayed interventions can compromise safety and disrupt operations. Traditional anomaly detection methods are typically reactive, relying on real-time sensor data to identify deviations as they occur. This reactive nature often provides insufficient lead time for effective maintenance planning. To address this limitation, we propose a novel two-stage early detection framework that integrates time series forecasting with anomaly detection to anticipate equipment failures several hours in advance. In the first stage, future sensor signal values are predicted using forecasting models; in the second, conventional anomaly detection algorithms are applied directly to the forecasted data. By shifting from real-time to anticipatory detection, the framework aims to deliver actionable early warnings, enabling timely and preventive maintenance.We validate this approach through a case study focused on metro train systems, an environment where early fault detection is crucial for minimizing service disruptions, optimizing maintenance schedules, and ensuring passenger safety. The framework is evaluated across three forecast horizons (1, 3, and 6 hours ahead) using twelve state-of-the-art anomaly detection algorithms from diverse methodological families. Detection performance is assessed using five performance metrics. Results show that anomaly detection remains highly effective at short to medium horizons, with performance at 1-hour and 3-hour forecasts comparable to that of real-time data. Ensemble and deep learning models exhibit strong robustness to forecast uncertainty, maintaining consistent results with real-time data even at 6-hour forecasts. In contrast, distance and density based models suffer substantial degradation at longer horizons (6-hours), reflecting their sensitivity to distributional shifts in predicted signals.Overall, the proposed framework offers a practical and extensible solution for enhancing traditional PdM systems with proactive capabilities. By enabling early anomaly detection on forecasted data, it supports improved decision-making, operational resilience, and maintenance planning in industrial environments.

Predictive maintenance applications have increasingly been approached with deep learning techniques in recent years due to their high predictive performance. However, as in other real-world application scenarios, the need for explainability is often stated but not sufficiently addressed, which can limit adoption in practice. In this study, we will focus on predicting failures of trains operating in Porto, Portugal. While recent works have found high-performing deep neural network architectures that feature a parallel explainability pipeline, we find that the generated explanations can be hard to comprehend in practice due to their low support over the failure range. In this work, we propose a novel online rule-learning approach that is able to generate simple rules that cover the entirety of the detected failures. We evaluate our method against AMRules, a state-of-the-art online rule-learning approach, on two datasets gathered from trains operated by Metro do Porto. Our experiments show that our approach consistently generates rules with very high support that are simultaneously short and interpretable.

Waste management networks are essential for environmental protection and public health, but vulnerable to regulatory evasion, fraud, and illegal trading. Detecting potentially illicit activities in the network requires robust anomaly detection systems. However, the complexity of interactions between heterogeneous entities such as recycling companies, individuals, and other organisations combined with temporal irregularities and network dynamics makes conventional fraud detection approaches less effective. In this study, we introduce a dynamic graph-based framework that combines statistical change detection methods, the Page-Hinkley and CUSUM tests, alongside a deep learning model, LSTM-VAE, to detect suspicious activities in the Portuguese waste management network. Using real-world waste transfer records, we engineered temporal and network features to reveal a wide range of anomalies, including abrupt shifts in activity and unusual connectivity patterns, such as those involving collusive triangles. The evaluation was based on four pre-labeled anomalous companies identified by regulators. Our results show that while individual methods excel at detecting certain behaviors, their combination provides robust coverage of diverse anomaly types, with each anomalous company identified by at least three techniques. This approach demonstrates the importance of integrating temporal and network-based analysis, offering regulatory authorities a scalable tool to prioritize inspections, enhancing accountability in the waste management network.

As Artificial Intelligence (AI) systems increasingly permeate sensitive domains such as finance, healthcare, and media, ensuring their ethical deployment has become a central concern for researchers, policymakers, and practitioners. Current auditing tools often assess isolated principles, such as fairness or explainability, lacking a comprehensive view of the ethical risks involved. This paper presents a multidimensional framework for ethical evaluation of AI systems, designed to support responsible AI governance and alignment with the United Nations Sustainable Development Goals (SDGs). The proposed approach enables the simultaneous analysis of key ethical dimensions, including fairness, bias, explainability, robustness, transparency, and legal compliance. We demonstrate the applicability of this tool through one extensive case study: a credit scoring system, considered high-risk under the AI Act. This work contributes to operationalizing responsible AI governance, providing insight for policymakers, regulators, and practitioners to ensure ethical, legally compliant, and socially responsible AI deployment.

The Internet of Things generates massive data streams, with edge computing emerging as a key enabler for online IoT applications and 5G networks. Edge solutions facilitate real-time machine learning inference, but also require continuous adaptation to concept drifts. While extensions of the Very Fast Decision Tree (VFDT) remain state-of-the-art for tabular stream mining, their unregulated growth limit efficiency, particularly in ensemble settings where post-pruning at the individual tree level is seldom applied. This paper presents DFDT, a novel memory-constrained algorithm for online learning. DFDT employs activity-aware pre-pruning, dynamically adjusting splitting criteria based on leaf node activity: low-activity nodes are deactivated to conserve resources, moderately active nodes split under stricter conditions, and highly active nodes leverage a skipping mechanism for accelerated growth. Additionally, adaptive grace periods and tie thresholds allow DFDT to modulate splitting decisions based on observed data variability, enhancing the accuracy–memory–runtime trade-off while minimizing the need for hyperparameter tuning. An ablation study reveals three DFDT variants suited to different resource profiles. Fully compatible with existing ensemble frameworks, DFDT provides a drop-in alternative to standard VFDT-based learners.

Optimization of hyperparameters is a critical factor to obtain optimal model performance. While existing research has predominantly concentrated on batch-learning scenarios, addressing the complexities inherent in data streams presents a challenge. The deployment of sophisticated methodologies to manage data streams becomes highly important. Consequently, the capacity for self-adjusting hyperparameters during on-line learning phases emerges as a goal. Many hyperparameters exhibit constraints and are confined within bounded search spaces, rendering specific solutions unacceptable upon applying optimization operators. To solve this issue, employing boundary constraint- handling techniques becomes imperative to rectify invalid solutions. This paper presents strategies for effectively managing boundary constraints within constrained numerical optimization problems. Recent methodologies, including heuristic and evolutionary-based optimization, employ a "boundary" strategy, wherein values that surpass boundary thresholds for a given hyperparameter are realigned to the respective limits. Our study introduces four strategies to navigate boundary constraints in online optimization algorithms. Through empirical investigations conducted on established datasets, we demonstrate that adopting boundary strategies outperforms the "boundary" strategy.

This study aims to develop a model for detecting dynamic changes in land by analyzing aerial images over time. In scenarios where collected labels, annotations, and change maps for a sequence of images are expensive and not easily accessible, unsupervised change detection methods are valuable. The goal is to leverage an agnostic segmentation model to gain insights into performing change detection without annotations, detect small objects in large images, and pinpoint changes within specified areas relative to historical images. This research aims to contribute to environmental protection and land management advancements. To demonstrate the effectiveness of our model, we utilize two public datasets and a case study from the northern region of Portugal.

The rise of environmental crimes has become a major concern globally as they cause significant damage to ecosystems, public health and result in economic losses. The availability of vast sensor data provides an opportunity to analyze environmental data proactively. This helps to detect irregularities and uncover potential criminal activities. This paper highlights the critical role played by machine learning (ML) and remote sensing technologies in the continuously evolving scenarios of environmental crime. By examining some case studies on detecting illegal fishing, illegal oil spills, illegal landfills, and illegal logging, we delve into the practical implementation of data-driven approaches for environmental crime detection. Our goal with this study is to provide an overview of the existing research in this area and foster the use of ML and data science techniques to enhance environmental crime detection.