Automatic fault detection and diagnosis (FDD) are critical for maintaining reliable and efficient industrial systems. However, conventional methods rely heavily on manual inspections or threshold-based techniques, which often fail to capture the dynamic patterns in time series (TS) sensor data. As a result, faults persist for extended periods, leading to suboptimal system operations, increased energy waste, and significant economic losses. This work proposes a cross-modal framework that facilitates the efficient deployment of state-of-the-art pretrained vision models for enhanced FDD, with two novel TS-to-image transformations: first, an adapter deep encoder that learns optimal, task-specific representations from raw sensor data while generating outputs that are input-compliant with pretrained models. Second, an enhanced line plot that creates geometric shapes of two related signals. Comparative experiments against fixed methods, including spectrograms, Gramian angular fields, Markov transition fields, recurrence plots, and five deep learning baseline models, showed substantial performance gains across diverse domains. InceptionTime achieved the highest average baseline performance with an F<inf>1</inf> of 88.6%, while the adapter and shapes achieved 94.4% and 92.4%, respectively. The findings highlight the potential of the cross-modal framework for FDD to facilitate early intervention and efficient system maintenance in industrial settings.

Fault detection in district heating (DH) substations is critical for energy efficiency and reliability. However, it is challenged by scarce fault labels, low-frequency data, privacy concerns, and battery-constrained gateways. We propose a novel hybrid semi-supervised federated domain adaptation architecture for fault detection in DH. We use a one-class variational autoencoder (VAE) to leverage heterogeneous sensor streams from 434 distributed substations. First, we perform cross-network unsupervised pre-training on multi-sourced data from two independent real-world DH networks, fusing their return temperature dynamics into a robust shared manifold. Second, we leverage maintenance metadata to selectively allow verified-normal clients for per-round fine-tuning of the model. Third, we drastically reduce uplink costs by compressing each client's weight delta using 10% top-k sparsification and demonstrate that our pipeline enables robust few-shot finetuning with 20% of the normal operational data while retaining high detection performance. By strategically training, our method achieves F1 and G-mean scores of up to 97% and an AUC ≥ 99% on real-world DH data. To our knowledge, this is the first work to study cross-domain data fusion in the DH field for fault detection, aiming to enhance and enable effective, scalable, and energy-efficient monitoring of substations.

Federated learning (FL) offers a promising solution for human activity recognition (HAR) in healthcare by enabling model training on decentralized data, thereby preserving privacy in compliance with regulations such as GDPR and HIPAA. This study investigates the privacy vs performance trade-offs of FL with centralized machine learning (CML) using the UCI HAR dataset. We focus on three aggregation methods: federated averaging (FedAvg), federated proximal (FedProx), and Krum, under both independent and identically distributed (IID) and non-IID data settings. We evaluate their robustness to poisoning attacks and the impact of local differential privacy (LDP).

Our results show that FL outperforms CML in HAR tasks. In non-IID settings, FedAvg achieves up to 97\% accuracy, outperforming FedProx (91\%) and Krum (88\%). Interestingly, non-IID data yields better performance across all methods. While Krum demonstrates strong resilience against poisoning attacks in the absence of LDP, FedProx maintains greater stability when LDP is applied. However, higher privacy levels reduce accuracy to 58–65\%. These findings position FedProx as a balanced option for privacy-preserving healthcare HAR, emphasizing the importance of carefully tuning privacy mechanisms to maintain optimal performance.

The growing adoption of wearable fitness devices and health applications has led to an exponential increase in fitness recommendations. However, privacy concerns remain significant barriers to user trust and regulatory compliance. Federated Learning (FL) offers a privacy-preserving paradigm by training models across decentralized devices without exposing raw data. However, FL introduces new challenges, including data heterogeneity, computational overhead, and the need for explainable AI (XAI). This work presents XFL, an integrated, explainable FL approach for personalized fitness recommendation systems. Our approach integrates FL with XAI techniques, SHAP, and LIME, to enhance transparency and interpretability while preserving privacy. By leveraging global and client-specific explanations, our framework empowers users to understand the rationale behind personalized recommendations, fostering trust and usability. Experimental results demonstrate that XFL performs better than centralized models while maintaining strong privacy guarantees. Furthermore, we evaluated the computational impact of integrating XAI in FL environments, providing insights into the efficiency of different explainability techniques. Our findings contribute to developing user-centric, privacy-aware, and interpretable AI-driven fitness solutions. 

The Internet of Things (IoT) and Artificial Intelligence (AI) has enabled the development of innovative applications. The deployment of those applications is a complex process that should take into consideration multiple factors, including the applications' scale, complexity, distribution, and non-functional requirements (e.g., energy consumption, performance, and security). Moreover, deployment environments over the edge-cloud continuum are heterogeneous w.r.t. their processing capabilities, communication latencies, and energy consumption. Towards enabling efficient scheduling of tasks in such environments, we formulate the task scheduling problem as a multi-objective optimization task balancing energy efficiency and deadline adherence. To tackle this problem, we employ the Equilibrium Optimizer (EO)-a physics-inspired meta-heuristic algorithm that utilizes an equilibrium pool of top-performing solutions to guide its population toward high-quality schedules. To validate the feasibility of our approach, we run experiments where we compare our proposed approach against the multiple existing optimizers. The results demonstrate that EO exhibits a superior performance reflecting its potential to improve IoT systems' quality of service and reduce their operational costs in large-scale and time-sensitive IoT scenarios. 

Repairing code smells detected in the code or design of the system is one of the activities contributing to increasing the software quality. In this study, we investigate the impact of non-numerical information of software, such as project status information combined with machine learning techniques, on improving code smell detection. For this purpose, we constructed a dataset consisting of 22 systems with various project statuses, 12,040 classes, and 18 features that included 1935 large classes. A set of experiments was conducted with ten different machine learning techniques by dividing the dataset into training, validation, and testing sets to detect the large class code smell. Feature selection and data balancing techniques have been applied. The classifier’s performance was evaluated using six indicators: precision, recall, F-measure, MCC, ROC area, and Kappa tests. The preliminary experimental results reveal that feature selection and data balancing have poor influence on the accuracy of machine learning classifiers. Moreover, they vary their behavior when utilized in sets with different values for the selected project status information of their classes. The average value of classifiers performance when fed with status information is better than without. The Random Forest achieved the best behavior according to all performance indicators (100%) with status information, while AdaBoostM1 and SMO achieved the worst in most of them (> 86%). According to the findings of this study, providing machine learning techniques with project status information about the classes to be analyzed can improve the results of large class detection. © The Author(s) 2024.

Fault Detection and Diagnosis (FDD) in District Heating (DH) systems is vital for improving operational efficiency. As DH networks evolve towards Fourth-Generation District Heating (4GDH), their reliance on lower operational temperatures intensifies the need for robust FDD. However, implementing effective FDD faces challenges due to the lack of labelled fault data and the complexity of DH substations. This paper introduces a novel FDD methodology using Transfer Learning (TL) to bridge the gap between faulty bearings, controlled DH substation experiments and real-world operational data. We propose a fault signature method that aligns the data to reduce the domain gap, revealing similarities between faulty bearings’ vibration patterns and ΔT readings in DH substations. The TL-enhanced models demonstrated robust performance, achieving F1 scores up to 98% on lab data and 91% on real-world operational data, respectively. These results mark a notable advancement in FDD of DH substations, as our method offers accurate fault detection and valuable insights across diverse operational contexts, ranging from valve issues, faulty sensors, wrong control strategies and normal behaviour. Notably, temperature dynamics resemble behaviour akin to faulty bearing vibrations, highlighting their potential as a critical indicator of a faulty substation, enabling more effective FDD in DH systems.

This study introduces FLAME (Fault Localization using Augmented Model Enhancement), a novel fault diagnosis framework for District Heating (DH) substations. Automated Fault Detection and Diagnosis (FDD) has become imperative as many DH substations perform sub-optimal due to faults. The main challenges complicating accurate fault diagnosis are increasing operational complexities and a scarcity of labelled data.

FLAME integrates a hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) model with an attention mechanism and introduces the Fault Augmentation Signature Technique (FAST). FAST overcomes the limitations of traditional stochastic data augmentation methods by leveraging pattern mixing of the time series. The FLAME framework uses transfer learning, initially trained on augmented data using FAST and fine-tuned using original substation data.

Experimental results reveal that FLAME outperforms conventional methods, obtaining F1 scores of approximately 0.95 and 0.92 on lab-simulated and real-world datasets, respectively. Additionally, the research found the importance of the temperature difference measurement (ΔT) and median-based sampling strategies for optimal fault pattern identification.

These findings establish FLAME as a new benchmark in DH system diagnostics, offering a robust framework to enhance fault diagnosis accuracy and operational efficiency of DH substations. 

Automating test case specification generation is vital for improving the efficiency and accuracy of software testing, particularly in complex systems like high-performance Electronic Control Units (ECUs). This study investigates the use of Natural Language Processing (NLP) techniques, including Rule-Based Information Extraction and Named Entity Recognition (NER), to transform natural language requirements into structured test case specifications. A dataset of 400 feature element documents from the Polarion tool was used to evaluate both approaches for extracting key elements such as signal names and values. The results reveal that the Rule-Based method outperforms the NER method, achieving 95% accuracy for more straightforward requirements with single signals, while the NER method, leveraging SVM and other machine learning algorithms, achieved 77.3% accuracy but struggled with complex scenarios. Statistical analysis confirmed that the Rule-Based approach significantly enhances efficiency and accuracy compared to manual methods. This research highlights the potential of NLP-driven automation in improving quality assurance, reducing manual effort, and expediting test case generation, with future work focused on refining NER and hybrid models to handle greater complexity. 

Fault detection in district heating (DH) substations is crucial for maintaining energy efficiency. However, existing methods often fall short and rely on labelled data or global analysis that may miss subtle anomalies. We introduce HEAT, a Hierarchical-constrained Encoder-Assisted Time series clustering method designed to enhance fault detection in DH substations. HEAT operates in a two-phase approach: first, it approximates a relative network topology using a constraint hierarchical clustering algorithm on supply temperature profiles. HEAT incorporates a Convolutional AutoEncoder (CAE) for dimensionality reduction of the time series data and uses adaptive soft constraints in the linkage function, enabling both minimum and maximum cluster size constraints while supporting domain knowledge, e.g., must-link and cannot-link constraints, using a constraint matrix. Second, we use the topology approximation to perform intra-cluster analysis using Mean Absolute Deviation (MAD) z-scores, with neighbouring substations serving as a validation mechanism, allowing for robust analysis without requiring labelled data. Experimental results demonstrate that HEAT outperforms conventional clustering methods while achieving 74.1% sensitivity and 95.5% specificity in fault detection, significantly improving over typical global analysis. HEAT not only identified major faults (e.g., sensor issues, valve failures) but also detected subtle anomalies (e.g., secondary leakages) while minimising false positives. This unsupervised method offers a viable and flexible solution for DH networks, improving operational efficiency and energy sustainability without disclosing sensitive information.