Search Results (117)

This article presents a preliminary study on the potential application of artificial intelligence methods for assessing the durability of HTS tapes in superconducting fault current limiters (SFCLs). Despite their importance for the selectivity and reliability of power networks, these devices remain at the prototype testing stage, and the phenomena occurring in HTS tapes during their operation—particularly the degradation of tapes due to cyclic transitions into the resistive state—are difficult to model owing to their highly non-linear and dynamic nature. A concept of an engineering decision support system (EDSS) has been proposed, which, based on macroscopically measurable parameters (dissipated energy and the number of transitions), aims to enable the prediction of tape parameter degradation. Within the scope of the study, five approaches were tested and compared: Gaussian process regression (GPR) with various kernel functions, k-nearest neighbours (k-NN) regression, the random forest (RF) algorithm, piecewise cubic hermite interpolating polynomial (PCHIP) interpolation, and polynomial approximation. All models were trained on a limited set of experimental data. Despite the quantitative limitations and simplicity of the adopted methods, the results indicate that even simple GPR models can support the detection of HTS tape degradation in scenarios where direct measurement of the critical current is not feasible. This work constitutes a first step towards the construction of a complete EDSS and outlines directions for further research, including the need to expand the dataset, improve validation, analyse uncertainty, and incorporate physical constraints into the models. Full article

Wireless Sensor Networks (WSNs) are specialised ad hoc networks composed of small, low-power, and often battery-operated sensor nodes with various sensors and wireless communication capabilities. These nodes collaborate to monitor and collect data from the physical environment, transmitting it to a central location or sink node for further processing and analysis. This study proposes two machine learning-based enhancements to the DEEC protocol for Wireless Sensor Networks (WSNs) by integrating the K-Nearest Neighbours (K-NN) and K-Means (K-M) machine learning (ML) algorithms. The Distributed Energy-Efficient Clustering with K-NN (DEEC-KNN) and with K-Means (DEEC-KM) approaches dynamically optimize cluster head selection to improve energy efficiency and network lifetime. These methods are validated through extensive simulations, demonstrating up to 110% improvement in packet delivery and significant gains in network stability compared with the original DEEC protocol. The adaptive clustering enabled by K-NN and K-Means is particularly effective for large-scale and dynamic WSN deployments where node failures and topology changes are frequent. These findings suggest that integrating ML with clustering protocols is a promising direction for future WSN design. Full article

Similarity-based decision support systems have become essential tools for providing tailored and adaptive guidance across various domains. In agriculture, where managing extensive land areas poses significant challenges, the primary objective is often to maximize harvest yields while reducing costs, preserving crop health, and minimizing the use of chemical adjuvants. The application of similarity-based analysis enables the development of personalized farming recommendations, refined through shared data and insights, which contribute to improved plant growth and enhanced annual harvest outcomes. This study employs two algorithms, K-Nearest Neighbour (KNN) and Approximate Nearest Neighbour (ANN) using Locality Sensitive Hashing (LSH) to evaluate their effectiveness in agricultural decision-making. The results demonstrate that, under comparable farming conditions, KNN yields more accurate recommendations due to its reliance on exact matches, whereas ANN provides a more scalable solution well-suited for large datasets. Both approaches support improved agricultural decisions and promote more sustainable farming strategies. While KNN is more effective for smaller datasets, ANN proves advantageous in real-time applications that demand fast response times. The implementation of these algorithms represents a significant advancement toward data-driven and efficient agricultural practices. Full article

Smart buildings’ role is crucial for advancing smart cities’ performance in achieving environmental sustainability, resiliency, and efficiency. The integration barriers continue due to technology, infrastructure, and operations misalignments and are escalated due to inadequate assessment frameworks and classification systems. The existing literature on assessment methodologies reveals diverging evaluation frameworks for smart buildings and smart cities, non-uniform metrics and taxonomies that hinder scalability, and the low use of machine learning in predictive integration modelling. To fill these gaps, this paper introduces a novel machine learning model to predict smart building integration into smart city levels and assess their impact on smart city performance by leveraging data from 147 smart buildings in 13 regions. Six optimised machine learning algorithms (K-Nearest Neighbours (KNNs), Support Vector Regression (SVR), Random Forest, Adaptive Boosting (AdaBoost), Decision Tree (DT), and Extra Tree (ET)) were employed to train the model and perform feature engineering and permutation importance analysis. The SVR-trained model substantially outperformed other models, achieving an R-squared of 0.81, Root Mean Square Error (RMSE) of 0.33 and Mean Absolute Error (MAE) of 0.27, enabling precise integration prediction. Case studies revealed that low-integration buildings gain significant benefits from progressive target upgrades, whilst those buildings that have already implemented some integrated systems tend to experience diminishing marginal benefits with further, potentially disruptive upgrades. The conclusion of this study states that by utilising the developed machine learning model, owners and policymakers are capable of significantly improving the integration of smart buildings to build better, more sustainable, and resilient urban environments. Full article

As early detection of voice disorders can significantly improve patients’ situation, the automated detection using Artificial Intelligence techniques can be crucial in various applications in this scope. This paper introduces a multi-objective bio-inspired, AI-based optimization approach for the automated detection of voice disorders. Different multi-objective evolutionary algorithms (the Non-dominated Sorting Genetic Algorithm (NSGA-II), Strength Pareto Evolutionary Algorithm (SPEA-II), and the Multi-Objective Evolutionary Algorithm based on Decomposition (MOEA/D)) have been compared to detect voice disorders by optimizing two conflicting objectives: error rate and the number of features. The optimization problem has been formulated as a wrapper-based algorithm for feature selection and multi-objective optimization relying on four machine learning algorithms: K-Nearest Neighbour algorithm (KNN), Random Forest (RF), Multilayer Perceptron (MLP), and Support Vector Machine (SVM). Three publicly available voice disorder datasets have been utilized, and results have been compared based on Inverted-Generational Distance, Hypervolume, spacing, and spread. The results reveal that NSGA-II with the MLP algorithm attained the best convergence and performance. Further, the conformal prediction is leveraged to quantify uncertainty in the feature-selected models, ensuring statistically valid confidence intervals for predictions. Full article

Triazolopyrimidine and its analogs represent an important scaffold in medicinal chemistry research. The heterocycle of 1,2,4-triazolo[1,5-a] pyrimidine (1,2,4-TAP) serves as a bioisostere candidate for purine scaffolds, N-acetylated lysine, and carboxylic acid. This study modeled the quantitative structure–activity relationship (QSAR) of 125 congeners of 1,2,4-TAP from the ChEMBL database in the inhibition of Plasmodium falciparum using six machine learning algorithms. The most significant features among 306 molecular descriptors, including one molecular outlier, were selected using recursive feature elimination. A ratio of 20% was used to split the x- and y-matrices into 99 training and 24 test compounds. The regression models were built using machine learning sci-kit-learn algorithms (multiple linear regression (MLR), k-nearest neighbours (kNN), support vector regressor (SVR), random forest regressor (RFR) RIDGE regression, and LASSO). Model performance was evaluated using the coefficient of determination (R²), mean squared error (MSE), mean absolute error (MAE), root mean squared error (RMSE), p-values, F-statistic, and variance inflation factor (VIF). Five significant variables were considered in constructing the model (p < 0.05) with the following regression equation: pIC₅₀ = 5.90 − 0.71npr1 − 1.52pmi3 + 0.88slogP − 0.57vsurf-CW2 + 1.11vsurf-W2. On five-fold cross-validation, three algorithms—kNN (MSE = 0.46, R² = 0.54, MAE = 0.54, RMSE = 0.68), SVR (MSE = 0.33, R² = 0.67, MAE = 0.46, RMSE = 0.57), and RFR (MSE = 0.43, R² = 0.58, MAE = 0.51, RMSE = 0.66)—showed strong robustness, efficiency, and reliability in predicting the pIC₅₀ of 1,2,4-triazolo[1,5-a]pyrimidine. The models provided useful data on the functionalities necessary for developing more potent 1,2,4-TAP analogs as anti-malarial agents. Full article

Traditional methods for predicting pavement performance rely on complex finite element modelling and empirical equations, which are computationally expensive and time-consuming. However, machine learning models offer a time-efficient solution for predicting pavement performance. This study utilizes a range of machine learning algorithms, including linear regression, decision tree, random forest, gradient boosting, K-nearest neighbour, Support Vector Regression, LightGBM and CatBoost, to analyse their effectiveness in predicting pavement performance. The input variables include axle load, truck load, traffic speed, lateral wander modes, asphalt layer thickness, traffic lane width and tire types, while the output variables consist of number of passes to fatigue damage, number of passes to rutting damage, fatigue life reduction in number of years and rut depth at 1.3 million passes. A k-fold cross-validation technique was employed to optimize hyperparameters. Results indicate that LightGBM and CatBoost outperform other models, achieving the lowest mean squared error and highest R² values. In contrast, linear regression and KNN demonstrated the lowest performance, with MSE values up to 188% higher than CatBoost. This study concludes that integrating machine learning with finite element analysis provides further improvements in pavement performance predictions. Full article

Pipeline filling and emptying are critical hydraulic procedures involving transient two-phase air–water interactions, which can cause pressure surges and structural risks. Traditional Digital Twin models rely on one-dimensional (1D) approaches, which cannot capture air–water interactions. This study integrates Computational Fluid Dynamics (CFD) models into a Digital Twin framework for improved predictive analysis. A CFD-based Digital Twin is developed and validated using real-time pressure measurements, incorporating 2D and 3D CFD models, mesh sensitivity analysis, and calibration procedures. Key contributions include a CFD-driven Digital Twin for real-time monitoring and machine learning (ML) techniques to optimise pressure surges. ML models trained with experimental and CFD data reduce reliance on computationally expensive CFD simulations. Among the 31 algorithms tested, decision trees, efficient linear models, and ensemble classifiers achieved 100% accuracy for filling processes, while k-Nearest Neighbours (KNN) provided 97.2% accuracy for emptying processes. These models effectively predict hazardous pressure peaks and vacuum conditions, confirming their reliability in optimising pipeline operations while significantly reducing computational time. Full article

Wireless Sensor Networks are formed by tiny, self-contained, battery-powered computers with radio links that can sense their surroundings for events of interest and store and process the sensed data. Sensor nodes wirelessly communicate with each other to relay information to a central base station. Energy consumption is the most critical parameter in Wireless Sensor Networks (WSNs). Network lifespan is directly influenced by the energy consumption of the sensor nodes. All sensors in the network send and receive data from the base station (BS) using different routing protocols and algorithms. These routing protocols use two main types of clustering: hierarchical clustering and flat clustering. Consequently, effective clustering within Wireless Sensor Network (WSN) protocols is essential for establishing secure connections among nodes, ensuring a stable network lifetime. This paper introduces a novel approach to improve energy efficiency, reduce the length of network connections, and increase network lifetime in heterogeneous Wireless Sensor Networks by employing the K-Nearest Neighbours (KNN) algorithm to optimise node selection and clustering mechanisms for four protocols: Low-Energy Adaptive Clustering Hierarchy (LEACH), Stable Election Protocol (SEP), Threshold-sensitive Energy Efficient sensor Network (TEEN), and Distributed Energy-efficient Clustering (DEC). Simulation results obtained using MATLAB (R2024b) demonstrate the efficacy of the proposed K-Nearest Neighbours algorithm, revealing that the modified protocols achieve shorter distances between cluster heads and nodes, reduced energy consumption, and improved network lifetime compared to the original protocols. The proposed KNN-based approach enhances the network’s operational efficiency and security, offering a robust solution for energy management in WSNs. Full article

Coal and gas outbursts pose significant threats to underground personnel, making the development of accurate prediction models crucial for reducing casualties. By addressing the challenges of highly nonlinear relationships among predictive parameters, poor interpretability of models, and limited sample data in existing studies, this paper proposes an interpretable Ali Baba and the Forty Thieves–Transformer–Support Vector Machine (AFT-Transformer-SVM) model with high predictive accuracy. The Ali Baba and the Forty Thieves (AFT) algorithm is employed to optimise a Transformer-based feature extraction, thereby reducing the degree of nonlinearity among sample data. A Transformer-SVM model is constructed, wherein the Support Vector Machine (SVM) model provides negative feedback to refine the Transformer feature extraction, enhancing the prediction accuracy of coal and gas outbursts. Various classification assessment methods, such as TP, TN, FP, FN tables, and SHAP analysis, are utilised to improve the interpretability of the model. Additionally, the permutation feature importance (PFI) method is applied to conduct a sensitivity analysis, elucidating the relationship between the sample data and outburst risks. Through a comparative analysis with algorithms such as eXtreme gradient boosting (XGBoost), k-nearest neighbour (KNN), radial basis function networks (RBFNs), and Bayesian classifiers, the proposed method demonstrates superior accuracy and effectively predicts coal and gas outburst risks, achieving 100% accuracy in the sample dataset. The influence of parameters on the model is analysed, highlighting that the coal seam gas content is the primary factor driving the outburst risks. The proposed approach provides technical support for coal and gas outburst predictions across different mines, enhancing emergency response and prevention capabilities for underground mining operations. Full article

Resistance spot-welded joints are crucial parts in contemporary manufacturing technology due to their ubiquitous use in the automobile industry. The necessity of improving manufacturing efficiency and quality at an affordable cost requires deep knowledge of the resistance spot welding (RSW) process and the development of artificial neural network (ANN)- and machine learning (ML)-based modelling techniques, apt for providing essential tools for design, planning, and incorporation in the welding process. Tensile shear force and nugget diameter are the most crucial outputs for evaluating the quality of a resistance spot-welded specimen. This study uses ML and ANN models to predict shear force and nugget diameter responses to RSW parameters. The RSW analysis was executed on similar and dissimilar AISI 304 and grade 2 titanium alloy joints with equal and unequal thicknesses. The input parameters included welding current, pressure, welding duration, squeezing time, holding time, pulse welding, and sheet thickness. Linear regression, Decision tree, Support vector machine (SVM), Random forest (RF), Gradient-boosting, CatBoost, K-Nearest Neighbour (KNN), Ridge, Lasso, and ElasticNet machine learning algorithms, along with two different structures of Multilayer Perceptron, were utilized for studying the impact of the RSW parameters on the shear force and nugget diameter. Different validation metrics were applied to assess each model’s quality. Two equations were developed to determine the shear force and nugget diameter based on the investigation parameters. The current research also presents a prediction of the Relative Importance (RI) of RSW factors. Shear force and nugget diameter predictions were examined using SHapley (SHAP) Additive Explanations for the first time in the RSW field. Trainbr as the training function and Logsig as the transfer function delivered the best ANN model for predicting shear force in a one-output structure. Trainrp with Tansig made the most accurate predictions for nugget diameter in a one-output structure and for shear force and diameter in a two-output structure. Depending on validation metrics, the Random forest model outperformed the other ML algorithms in predicting shear force or nugget diameter in a one-output model, while the Decision tree model gave the best prediction using a two-output structure. Linear regression made the worst ML predictions for shear force, while ElasticNet made the worst nugget diameter forecasts in a one-output model. However, in two-output models, Lasso made the worst predictions. Full article

Developing interfaces for seizure diagnosis, often challenging to detect visually, is rising. However, their effectiveness is constrained by the need for diverse and extensive databases. This study aimed to create a seizure detection methodology incorporating detailed information from each EEG channel and accounts for frequency band variations linked to the primary brain pathology leading to ICU admission, enhancing our ability to identify epilepsy onset. This study involved 460 video-electroencephalography recordings from 71 patients under monitoring. We applied signal preprocessing and conducted a numerical quantitative analysis in the frequency domain. Various machine learning algorithms were assessed for their efficacy. The k-nearest neighbours (KNN) model was the most effective in our overall sample, achieving an average F1 score of 0.76. For specific subgroups, different models showed superior performance: Decision Tree for ‘Epilepsy’ (average F1 score of 0.80) and ‘Craniencephalic Trauma’ (average F1 score of 0.84), Random Forest for ‘Cardiorespiratory Arrest’ (average F1 score of 0.89) and ‘Brain Haemorrhage’ (average F1 score of 0.84). In the categorisation of seizure types, Linear Discriminant Analysis was most effective for focal seizures (average F1 score of 0.87), KNN for generalised (average F1 score of 0.84) and convulsive seizures (average F1 score of 0.88), and logistic regression for non-convulsive seizures (average F1 score of 0.83). Our study demonstrates the potential of using classifier models based on quantified EEG data for diagnosing seizures in ICU patients. The performance of these models varies significantly depending on the underlying cause of the seizure, highlighting the importance of tailored approaches. The automation of these diagnostic tools could facilitate early seizure detection. Full article

Internet of Things (IoT) devices are ubiquitous in various applications, such as smart homes, asset and people tracking, and city management systems. However, their deployment in adverse conditions, including unstable internet connectivity and power sources, present new cybersecurity challenges through new attack vectors. The LoRaWAN protocol, with its open and distributed network architecture, has gained prominence as a leading LPWAN solution, presenting novel security challenges. This paper proposes the implementation of machine learning algorithms, specifically the K-Nearest Neighbours (KNN) algorithm, within an Intrusion Detection System (IDS) for LoRaWAN networks. Through behavioural analysis based on previously observed packet patterns, the system can detect potential intrusions that may disrupt critical tracking services. Initial simulated packet classification attained over 90% accuracy. By integrating the Suricata IDS and extending it through a custom toolset, sophisticated rule sets are incorporated to generate confidence metrics to classify packets as either presenting an abnormal or normal behaviour. The current work uses third-party multi-vendor sensor data obtained in the city of Lisbon for training and validating the models. The results show the efficacy of the proposed technique in evaluating received packets, logging relevant parameters in the database, and accurately identifying intrusions or expected device behaviours. We considered two use cases for evaluating our work: one with a more traditional approach where the devices and network are static, and another where we assume that both the devices and the network are mobile; for example, when we need to report data back from sensors on a rail infrastructure to a mobile LoRaWAN gateway onboard a train. Full article

Accurately predicting grapevine yield and quality is critical for optimising vineyard management and ensuring economic viability. Numerous studies have reported the complexity in modelling grapevine yield and quality due to variability in the canopy structure, challenges in incorporating soil and microclimatic factors, and management practices throughout the growing season. The use of multimodal data and machine learning (ML) algorithms could overcome these challenges. Our study aimed to assess the potential of multimodal data (hyperspectral vegetation indices (VIs), thermal indices, and canopy state variables) and ML algorithms to predict grapevine yield components and berry composition parameters. The study was conducted during the 2019/20 and 2020/21 grapevine growing seasons in two South Australian vineyards. Hyperspectral and thermal data of the canopy were collected at several growth stages. Simultaneously, grapevine canopy state variables, including the fractional intercepted photosynthetically active radiation (fiPAR), stem water potential (Ψ_stem), leaf chlorophyll content (LCC), and leaf gas exchange, were collected. Yield components were recorded at harvest. Berry composition parameters, such as total soluble solids (TSSs), titratable acidity (TA), pH, and the maturation index (IMAD), were measured at harvest. A total of 24 hyperspectral VIs and 3 thermal indices were derived from the proximal hyperspectral and thermal data. These data, together with the canopy state variable data, were then used as inputs for the modelling. Both linear and non-linear regression models, such as ridge (RR), Bayesian ridge (BRR), random forest (RF), gradient boosting (GB), K-Nearest Neighbour (KNN), and decision trees (DTs), were employed to model grape yield components and berry composition parameters. The results indicated that the GB model consistently outperformed the other models. The GB model had the best performance for the total number of clusters per vine (R² = 0.77; RMSE = 0.56), average cluster weight (R² = 0.93; RMSE = 0.00), average berry weight (R² = 0.95; RMSE = 0.00), cluster weight (R² = 0.95; RMSE = 0.13), and average berries per bunch (R² = 0.93; RMSE = 0.83). For the yield, the RF model performed the best (R² = 0.97; RMSE = 0.55). The GB model performed the best for the TSSs (R² = 0.83; RMSE = 0.34), pH (R² = 0.93; RMSE = 0.02), and IMAD (R² = 0.88; RMSE = 0.19). However, the RF model performed best for the TA (R² = 0.83; RMSE = 0.33). Our results also revealed the top 10 predictor variables for grapevine yield components and quality parameters, namely, the canopy temperature depression, LCC, fiPAR, normalised difference infrared index, Ψ_stem, stomatal conductance (g_s), net photosynthesis (P_n), modified triangular vegetation index, modified red-edge simple ratio, and ANT_gitelson index. These predictors significantly influence the grapevine growth, berry quality, and yield. The identification of these predictors of the grapevine yield and fruit composition can assist growers in improving vineyard management decisions and ultimately increase profitability. Full article

Indoor positioning based on Wi-Fi signals has gained a lot of attention lately. There are many advantages related to the use of Wi-Fi signals for positioning, including the availability of Wi-Fi access points in indoor environments and the integration of Wi-Fi transceivers into consumer devices. However, since Wi-Fi uses an unlicensed spectrum, anyone can create their own access points. Therefore, it is possible to affect the function of the localization system by spoofing signals from access points and thus alter positioning accuracy. Previously published works focused mainly on the evaluation of spoofing on localization systems and the detection of anomalies when updating the radio map. Spoofing mitigation solutions were proposed; however, their application to systems that use off-the-shelf items is not straightforward. In this paper filtering algorithms are proposed to minimize the impact of access point spoofing. The filtering was applied with a combination of the widely used K-Nearest Neighbours (KNN) localization algorithm and their performance is evaluated using the UJIIndoorLoc dataset. During the evaluation, the spoofing of Access Points was performed in two different scenarios and the number of spoofed access points ranged from 1 to 10. Based on the achieved results proposed SFKNN provided good detection of the spoofing and helped to reduce the mean localization error by 2–5 m, especially when the number of spoofed access points was higher. Full article