https://www.mdu.se/

Artificial Intelligence (AI) is reshaping decision-making across industries, but in life-critical domains like Air Traffic Control (ATC), performance alone is not enough - AI must also be transparent, accountable, and human-centered. At the same time, ecological sustainability (e.g., fuel efficiency, emissions reduction, noise abatement) is becoming a key operational priority. Yet under high workload or time pressure, these goals are often deprioritized. This paper introduces a novel framework for bias-aware human-AI teaming in ATC, integrating Generative Explainable AI (genXAI), Predictive Telemetry (PT), multimodal machine learning, and mechanistic interpretability. Designed for Air Traffic Controllers (ATCOs), the system anticipates future traffic states, detects bias-prone conditions, and delivers adaptive, context-sensitive explanations. Through bias-aware interfaces, serious-game training, and neuroadaptive feedback loops, the framework aligns decision support with cognitive state and operational complexity. The framework targets three key objectives: (1) mitigating cognitive biases, (2) improving ground routing decisions, and (3) validating anticipatory AI models. By reframing sustainability as a human-AI collaboration challenge, this work advances a new class of trustworthy, bias-aware AI that enhances both safety and ecological performance in Air Traffic Management (ATM). 

Learning over time for machine learning (ML) models is emerging as a new field, often called continual learning or lifelong Machine learning (LML). Today, deep learning and neural networks are the prevalent approaches for LML models. However, they are often criticized for being “black box” methods, and catastrophic forgetting has remained a persistent challenge throughout their development. This paradigm represents a significant shift from traditional static learning models, enabling systems to adapt to new data continuously while retaining previously acquired knowledge. In this paper, an LML approach is proposed that combines a Random Forest (RF) with a Genetic Algorithm (GA) to transfer the knowledge from an existing RF model to a new learning model. Here, the GA is applied to the RF model so that the weights of this model get balanced more steadily. The approach is evaluated here for classification problems on three benchmark datasets. The initial results present knowledge retention in the new model, indicating the success of the model. These methods are regularization-based and effective in mitigating catastrophic forgetting. However, they rely on Fisher Information to estimate parameter importance or similar measures, which are computationally demanding and suitable for deep neural networks. While many NN-based lifelong learning approaches have been studied, RFs remain comparatively underexplored in this paradigm. Given their robustness, interpretability, and effectiveness in tabular datasets with limited samples, RFs present a compelling alternative. This motivates our work on developing an RF-based lifelong learning approach. 

Explainability is crucial for establishing user trust in Artificial Intelligence (AI), particularly within safety-critical domains such as Air Traffic Management (ATM) and Air Traffic Control (ATC). This study empirically investigates the effects of Explainable AI (XAI), specifically HeatMap-based visual explanations, on cognitive workload, user acceptance, and intention to use AI-driven decision-support systems among Air Traffic Control Officers (ATCOs). Despite significant theoretical advancements in the broader XAI domain, empirical evidence addressing the specific impact of visual explanations on human-AI interactions in safety-critical environments like ATC remains limited. To address these critical gaps, an experimental comparison was conducted between explainable (HeatMap) and non-explainable (BlackBox) AI conditions, involving two user groups: expert and student ATCOs. Both objective neurophysiological measures (Electroencephalography) and subjective questionnaires were employed to capture comprehensive user responses. Key findings revealed that the presence of visual explanations significantly reduced cognitive workload and enhanced users' willingness to adopt the AI system, regardless of participants' level of expertise. However, explicit perceptions of AI's impact on work performance were predominantly influenced by expertise, with less experienced controllers reporting a greater perceived impact than their expert counterparts. By combining objective neurometrics with subjective user assessments, this research advances methodological rigor in evaluating human-AI interactions and highlights the importance of tailored, user-centric explanations. These findings directly contribute to practical guidelines for designing cognitively compatible and trustworthy AI tools in ATC, providing nuanced insights for targeted training and deployment strategies based on user expertise. 

Fault detection and diagnosis in complex industrial systems, such as slurry pumps used in mining, is impractical with lack of labeled data. However, most of the existing studies rely on labelled data and the black-box nature of machine learning or deep learning approaches. While some studies have focused on model-specific explanations, domain-specific explanations are still missing, which hinders actionable maintenance decisions. To address those challenges, this study focuses on an explainable multi-stage self-supervised learning framework for intelligent fault discovery and diagnosis with three sequential phases: (1) a self-supervised module that generates high-confidence labels by fusing vibration sensor and process data through autoencoders, Isolation Forest, and Gaussian Mixture Models with cross-modality consensus, (2) a supervised classification phase enhanced with SHAP-based explainability to distinguish between healthy and anomalous operation with high accuracy, and (3) a fault confirmation and diagnosis layer that categorizes severity (Tolerable, Moderate, Severe) and identifies likely fault types using domain knowledge and shallow decision trees. An experimental study evaluated on real-world slurry pump data demonstrates that the framework successfully generated 19,369 healthy and 654 anomalous training labeled samples. The supervised models achieved exceptional performance, with 99.9% accuracy and perfect recall (100%) in distinguishing healthy from anomalous states. The severity categorization identified 58.6% cases as tolerable (potentially edge-case operations), 27.8% as severe, and 13.6% as moderate, while fault type identification revealed cavitation or impeller damage as the most prevalent fault (46%). This approach bridges data-driven learning and expert knowledge, enabling trustworthy, explainable, and actionable fault discovery and diagnosis in safety-critical industrial environments.

Predictive maintenance is critical for minimizing downtime and operational costs in mining industries, where slurry pumps operate under abrasive and highly variable conditions. Traditional machine learning models, while accurate, often lack interpretability, limiting their adoption in safety-critical environments. This paper presents an Adaptive Neuro-Fuzzy Inference System (ANFIS) based approach for anomaly detection in slurry pumps using vibration-based features such as displacement, velocity, crest factor, kurtosis, skewness, peak, and peak-to-peak values. ANFIS combines the transparency of fuzzy logic with the learning capability of neural networks, enabling interpretable IF-THEN rules and adaptive tuning of membership functions. A dataset of 33,104 vibration samples was analyzed under four balancing strategies to address class imbalance. Models were evaluated using accuracy, precision, recall, F1-score, RMSE, and clustering quality metrics (Dunn Index and Silhouette Score). The results demonstrate that ANFIS achieves high accuracy (>99%) and strong interpretability, outperforming traditional black-box models. The proposed approach enhances trustworthiness and adaptability in predictive maintenance systems, offering an explainable solution for Industry 4.0 applications. Future work will explore hybrid models, real-time IoT integration, and edge deployment for dynamic operational environments.

Rectified linear unit (ReLU) based neural networks (NNs) are recognised for their remarkable accuracy. However, the decision-making processes of these networks are often complex and difficult to understand. This complexity can lead to challenges in error identification, establishing trust, and conducting thorough analyses. Existing methods often fail to provide clear insights into the actual computations occurring within each layer of these networks. To address this challenge, this study introduces a mechanistic interpretability method called ReLU Region Reasoning (Re3). This method uses the known piecewise-linear characteristics of ReLU networks to offer insights into neuron activation and accurately assess how each feature contributes to the final output and probability. Re3 effectively determines neuron activations and evaluates the contribution of each feature within a specified linear region. Experiments conducted on multiple benchmark datasets, including both tabular and image data, demonstrate that Re3 can replicate individual predictions without error, align feature importance with domain expertise, and maintain consistency with current explanatory methods, thereby avoiding the typical randomness. Analysing neurons reveals activation sparsity and identifies dominant units, thus providing clear targets for model simplification and troubleshooting. By ensuring transparency and algebraic accessibility in each stage of a ReLU-based NN's decision process, Re3 can be a valuable practical tool for achieving precise mechanistic interpretability.

High-voltage direct current (HVDC) systems rely on extensive and complex cooling networks that incorporate both dry coolers and chillers. Designing these systems is very challenging because many parameters interact in nonlinear ways, and simulation-based optimization requires significant computational resources. This paper presents a machine learning framework incorporating physics-based constraints for the efficient optimization of parametric cooling systems. The framework includes three main stages: data exploration, modeling, and optimization. In the first stage, simulation data are analyzed to extract key parameters such as Cooling Efficiency, Power Consumption, Cooling Power, Chiller Capacity, Water Inlet Temperature, etc. The modeling stage uses machine learning models to predict a composite performance score that combines cooling effectiveness, energy efficiency, and CO2 savings. Finally, a physics-constrained optimization algorithm (L-BFGS-B: Limited-memory Broyden–Fletcher–Goldfarb–Shanno with Bounds) finds the best parameter combinations while ensuring physical consistency in energy balance, temperature limits, and COP values. The results show that the proposed AI model can accurately predict system performance and identify optimal configurations. For 20 system configurations, the model achieved an R2 of 0.93, showing strong predictive capability. Key influential factors include Fan Power, Cooling Efficiency, COP (Chiller) and Power Consumption. This approach has the potential to provide a accurate and reliable alternative to full-scale simulations.

Trustworthy decision support systems utilizing a multimodal approach (MMA) integrate diverse data modalities to enhance robustness, transparency, and fairness in artificial intelligence (AI) applications. In this study, we present an MMA for decision support in the Air Traffic Management (ATM) domain, particularly within Remote Digital Towers (RDTs). RDTs replace traditional control towers with AI-driven digital solutions, enhancing operational efficiency. Our approach addresses key multimodal challenges—translation, alignment, and co-learning—by implementing (a) an open-vocabulary-based object detection model for video processing and (b) an audio-to-text transcription and semantic word identification model. The YOLO-World deep-learning model is employed for object detection, while audio data analysis takes advantage of a benchmark data set, semantic identification techniques, and explainability. Additionally, the system integrates robust machine learning techniques, including data augmentation and perturbation, to maintain consistent performance across varied operational conditions. This proof-of-concept demonstrates the potential of multimodal AI systems to enhance decision support and improve safety in ATM environments.

This study uses Generative Artificial Intelligence (gAI) to advance industrial digitization. Although the use of gAI looks promising for industrial digitization, there are significant gaps in current Explainable Artificial Intelligence (XAI) methods, which limit their applicability to such applications. By developing a theoretical framework, the aim is to provide explanations for gAI to improve decision-making processes with actionable insights and explanations for their intended outcomes. The proposed work has an impact on facilitating inspection, monitoring, optimization, and maintenance of industrial equipment and machinery. The theoretical framework proposed in this paper will address this challenge by following a three-step approach: 1) learning prior and posterior from data, 2) feature attribution and counterfactual explanation-based methods, and 3) integrated XAI. While the current study is theoretical, future work will focus on applying the approach to real-world industrial scenarios.

Reasoning is a vital process in machine learning (ML), involving making inferences and drawing conclusions based on data. This capability is important for developing intelligent systems which can understand and predict complex patterns. The study investigates reasoning through two distinct methodologies: multimodal reasoning and transfer learning based reasoning. In the first approach, multimodal reasoning is used with a semi-supervised method to label unlabelled datasets. In the second approach, transfer learning has been used to transfer knowledge of data from one model to another. Both approaches are demonstrated using unlabelled vehicular telemetry data. During processing, three sets of telemetry data are used to extract features separately through the autoencoder. These features are then clustered and aligned to create labelled and unlabelled datasets. The eXtreme Gradient Boosting (XGBoost) algorithm achieved over 98% test accuracy when applied to the labelled datasets and was then used to predict labels for the unlabelled datasets, which were later added to the labelled dataset to form three datasets for further processing. In transfer learning, a transformer model specifically designed to handle continuous features is developed. Labelled datasets are applied to the transformer model, one after the other, resulting in three final models, with each model achieving over 80% accuracy. The model’s prediction confidence is also validated using conformal learning, where the final models achieved over 80% accuracy. The transformer model is also separately trained on the datasets and compared with traditional ML models, outperforming the others by achieving an accuracy of 98%. By building on the groundwork laid by this study, future research can push the boundaries of what is possible with reasoning approaches, opening up new paths for scientific exploration and practical applications in different fields.