Search Results (4,852)

Urinary tract infections (UTIs) are among the most common pathologies, with a high incidence in women and hospitalized patients. Their diagnosis is based on the presence of clinical symptoms and signs in addition to the detection of microorganisms in urine trough urine cultures, a time-consuming and resource-intensive test. The goal was to optimize UTI detection through artificial intelligence (machine learning) using non-microbiological laboratory parameters, thereby reducing unnecessary cultures and expediting diagnosis. A total of 4283 urine cultures from patients with suspected UTIs were analyzed in the Microbiology Laboratory of the University Hospital Virgen de las Nieves (Granada, Spain) between 2016 and 2020. Various machine learning algorithms were applied to predict positive urine cultures and the type of isolated microorganism. Random Forest demonstrated the best performance, achieving an accuracy (percentage of correct positive and negative classifications) of 82.2% and an area under the ROC curve of 87.1%. Moreover, the Tree algorithm successfully predicted the presence of Gram-negative bacilli in urine cultures with an accuracy of 79.0%. Among the most relevant predictive variables were the presence of leukocytes and nitrites in the urine dipstick test, along with elevated white cells count, monocyte count, lymphocyte percentage in blood and creatinine levels. The integration of AI algorithms and non-microbiological parameters within the diagnostic and management pathways of UTI holds considerable promise. However, further validation with clinical data is required for integration into hospital practice. Full article

Accurate forecasting and management are crucial as obesity represents a global health issue linked to many chronic diseases. This research examines the use of machine learning algorithms such as Decision Tree, Random Forest, K-NN (K Nearest Neighbor), and Naive Bayes for predicting obesity by using a carefully selected dataset that includes factors like height, weight, dietary choices, and activity levels. The data processing stage involved feature selection, normalizing values, and dealing with missing data to improve the performance of the models. Among all evaluated algorithms, the Decision Tree method outperformed the other algorithms with an accuracy of 98.33%, surpassing Random Forest (98.27%), K-NN (98.03%), and Naive Bayes (90.08%). The findings reveal that tree-based models are more effective for obesity classification than traditional BMI-based approaches. The results indicate that tree-based models perform more accurate classification for obesity than traditional BMI-based methods, which makes them good substitutes. This study demonstrates the potential utility of machine learning in better managing obesity and indicates points of potential improvement, including using more data sources and complex models to increase the accuracy of the predictions. Full article

Despite advances in diagnostics, the objective and repeatable assessment of patients with neurological deficits (e.g., stroke) remains a major challenge. Modern methods based on artificial intelligence (AI) are of interest to researchers and clinicians in this area. This study presents a comparative analysis of different AI approaches used to analyze gait of stroke patients using a retrospective dataset of 120 individuals. The main objective is to evaluate the effectiveness, accuracy, and clinical relevance of machine learning (ML) and deep learning (DL) models in identifying gait abnormalities and predicting rehabilitation outcomes. Multiple AI techniques—including support vector machines (SVM), random forests (RF), k-nearest neighbors (k-NN), and convolutional neural networks (CNN)—were trained and tested on time-series gait data with spatiotemporal parameters. Performance metrics such as accuracy, precision, recall, and area under the curve (AUC) were used to compare model results. Initial results indicate that DL models, particularly CNNs, outperform traditional ML methods in capturing complex gait patterns and providing reliable classification. However, simpler models showed advantages in interpretability and computational efficiency. This study highlights the potential and shortcomings of AI-based gait analysis tools in supporting clinical decision-making and planning personalized stroke rehabilitation. Full article

The flat peach, an important commercial crop in the 143rd Regiment of Shihezi, China, is overwintered using plastic film mulching. Flat peaches are cultivated to boost the local temperate rural economy. The development of accurate maps of the spatial distribution of flat peach plantations is crucial for the intelligent management of economic orchards. This study evaluated the performance of pixel-based and object-based random forest algorithms for mapping flat peaches using the GF-1 image acquired during the overwintering period. A total of 45 variables, including spectral bands, vegetation indices, and texture, were used as input features. To assess the importance of different features on classification accuracy, the five different sets of variables (5, 15, 25, and 35 input variables and all 45 variables) were classified using pixel/object-based classification methods. Results of the feature optimization suggested that vegetation indices played a key role in the study, and the mean and variance of Gray-Level Co-occurrence Matrix (GLCM) texture features were important variables for distinguishing flat peach orchards. The object-based classification method was superior to the pixel-based classification method with statistically significant differences. The optimal performance was achieved by the object-based method using 25 input variables, with an overall accuracy of 94.47% and a Kappa coefficient of 0.9273. Furthermore, there were no statistically significant differences between the image-derived flat peach cultivated area and the statistical yearbook data. The result indicated that high-resolution images based on the overwintering period can successfully achieve the mapping of flat peach planting areas, which will provide a useful reference for temperate lands with similar agricultural management. Full article

Obstructive sleep apnea (OSA) is a commonly underdiagnosed condition that not only increases the risk of accidents but also significantly contributes to a wide range of health complications, including heightened perioperative morbidity and mortality risks during surgeries under general anesthesia. Polysomnography (PSG), which is the diagnostic gold standard, is costly, requires skilled technicians, is time-consuming, and is not always accessible. This study presents a fast, objective, and non-invasive method for detecting OSA severity by analyzing tracheal breathing sounds (TBS) recorded during wakefulness in supine position. Features were extracted from six binary (1-vs-1) severity comparisons—Non-OSA, Mild, Moderate, and Severe—and combined with anthropometric characteristics for classification. The data of 199 subjects (74 Non-OSA, 35 Mild, 50 Moderate, and 40 Severe) were analyzed, the data of 169 and 30 was used for training and blind testing, respectively, and the training dataset was shuffled 10 times to avoid any bias during training. Multiple machine learning models were evaluated, and the best-performing model for each was saved. Across six experimental models comparing OSA severity levels, the most balanced performance was achieved by the Base Model of Non-OSA vs. Severe-OSA using the support vector machine algorithm, with 88.2% accuracy, 83.3% sensitivity, and 90.9% specificity. While Random Forests in the Base Model of Non-OSA vs. Mild-OSA achieved 100% sensitivity, its accuracy was lower (81.2%). The results confirm the reliability and robustness of the proposed approach, providing a basis for OSA severity screening in under 10 min during wakefulness. Full article

The desert riparian forest oasis, dominated by Populus euphratica and Tamarix chinensis, is an important barrier to protect the economic production and habitat of the Tarim River Basin. However, there is still a lack of high-precision spatial distribution data of desert ri-parian forest species below 10 m. The recently launched PlanetScope CubeSat constella-tion, which provides daily earth observation imagery with a resolution of 3 m, offers a highly favorable dataset for mapping the high-resolution distribution of P. euphratica and T. chinensis and an unprecedented opportunity to explore the optimal phenology window to distinguish between them. In this study, time-series PlanetScope images were first used to extract phenological metrics of P. euphratica, dividing the annual life cycle into four phenology windows: duration of leaf expansion (DLE), duration of leaf maturity (DLM), duration of leaf fall (DLF), and duration of the dormancy period (DDP). The random forest model was used to obtain the classification accuracy of 16 phenological window combinations. Results indicate that after gap filling of vegetation index time series, the identification accuracy for P. euphratica and T. chinensis exceeded 0.90. Among individual phenology windows, the DLE window exhibited the highest classification accuracy (average F1-score 0.87). Among the two phenology window combinations, the DLE-DLF and DLE-DLM windows have the highest classification accuracy (average F1-score 0.90). Among the three phenology window combinations, DLE-DLM-DLF displayed the highest classification accuracy (average F1-score 0.91). Nevertheless, the inclusion of features within the DDP window led to a decrease in accuracy by 1–2% points, which was unfavorable for discriminating tree species. Additionally, features observed during the phenology asynchrony period were found to be more valuable for distinguishing between tree species. Our findings highlight the potential of PlanetScope constellation imagery in tree species classification, offering guidance for selecting optimal image acquisition timing and identifying the most valuable images within time series data for future large-scale tree mapping. Full article

The Global Trade Alert (GTA) website, managed by the United Nations, releases a large number of industrial policy (IP) announcements daily. Recently, leading nations including the United States and China have increasingly turned to IPs to protect and promote their domestic corporate interests. They use both offensive and defensive tools such as tariffs, trade barriers, investment restrictions, and financial support measures. To evaluate how these policy announcements may affect national interests, many countries have implemented logistic regression models to automatically classify them as either IP or non-IP. This study proposes ensemble models—widely recognized for their superior performance in binary classification—as a more effective alternative. The random forest model (a bagging technique) and boosting methods (gradient boosting, XGBoost, and LightGBM) are proposed, and their performance is compared with that of logistic regression. For evaluation, a dataset of 2000 randomly selected policy documents was compiled and labeled by domain experts. Following data preprocessing, hyperparameter optimization was performed using the Optuna library in Python. To enhance model robustness, cross-validation was applied, and performance was evaluated using key metrics such as accuracy, precision, and recall. The analytical results demonstrate that ensemble models consistently outperform logistic regression in both baseline (default hyperparameters) and optimized configurations. Compared to logistic regression, LightGBM and random forest showed baseline accuracy improvements of 3.5% and 3.8%, respectively, with hyperparameter optimization yielding additional performance gains of 2.4–3.3% across ensemble methods. In particular, the analysis based on alternative performance indicators confirmed that the LightGBM and random forest models yielded the most reliable predictions. Full article

Children with Autism Spectrum Disorder (ASD) often experience cognitive difficulties that impact learning. This study explores the use of electroencephalogram data collected with the MUSE 2 headband during task-based cognitive sessions to understand how cognitive states in children with ASD change across three structured tasks: Shape Matching, Shape Sorting, and Number Matching. Following signal preprocessing using Independent Component Analysis (ICA), power across various frequency bands was extracted using the Welch method. These features were used to analyze cognitive states in children with ASD in comparison to typically developing (TD) peers. To capture dynamic changes in attention over time, Morlet wavelet transform was applied, revealing distinct brain signal patterns. Machine learning classifiers were then developed to accurately distinguish between ASD and TD groups using the EEG data. Models included Support Vector Machine, K-Nearest Neighbors, Random Forest, an Ensemble method, and a Neural Network. Among these, the Ensemble method achieved the highest accuracy at 0.90. Feature importance analysis was conducted to identify the most influential EEG features contributing to classification performance. Based on these findings, an ASD map was generated to visually highlight the key EEG regions associated with ASD-related cognitive patterns. These findings highlight the potential of EEG-based models to capture ASD-specific neural and attentional patterns during learning, supporting their application in developing more personalized educational approaches. However, due to the limited sample size and participant heterogeneity, these findings should be considered exploratory. Future studies with larger samples are needed to validate and generalize the results. Full article

COVID-19 remains a global health challenge, with severe cases often leading to complications and fatalities. The objective of this study was to assess supervised machine learning algorithms for predicting severe COVID-19 based on demographic, clinical, biochemical, and genetic variables, with the aim of identifying the most informative prognostic markers. For Machine Learning (ML) analysis, we utilized a dataset comprising 226 observations with 68 clinical, biochemical, and genetic features collected from 226 patients with confirmed COVID-19 (54—moderate, 142—severe and 30 with mild disease). The target variable was disease severity (mild, moderate, severe). The feature set included demographic variables (age, sex), genetic markers (single-nucleotide polymorphisms (SNPs) in FGB (rs1800790), NOS3 (rs2070744), and TMPRSS2 (rs12329760)), biochemical indicators (IL-6, endothelin-1, D-dimer, fibrinogen, among others), and clinical parameters (blood pressure, body mass index, comorbidities). The target variable was disease severity. To identify the most effective predictive models for COVID-19 severity, we systematically evaluated multiple supervised learning algorithms, including logistic regression, k-nearest neighbors, decision trees, random forest, gradient boosting, bagging, naïve Bayes, and support vector machines. Model performance was assessed using accuracy and the area under the receiver operating characteristic curve (AUC-ROC). Among the predictors, IL-6, presence of depression/pneumonia, LDL cholesterol, AST, platelet count, lymphocyte count, and ALT showed the strongest correlations with severity. The highest predictive accuracy, with negligible error rates, was achieved by ensemble-based models such as ExtraTreesClassifier, HistGradientBoostingClassifier, BaggingClassifier, and GradientBoostingClassifier. Notably, decision tree models demonstrated high classification precision at terminal nodes, many of which yielded a 100% probability for a specific severity class. Full article

In this paper, the authors analyze the applicability of artificial intelligence algorithms for classifying file encryption methods based on statistical features extracted from the binary content of files. The prepared datasets included both unencrypted files and files encrypted using selected cryptographic algorithms in Electronic Codebook (ECB) and Cipher Block Chaining (CBC) modes. These datasets were further diversified by varying the number of encryption keys and the sample sizes. Feature extraction focused solely on basic statistical parameters, excluding an analysis of file headers, keys, or internal structures. The study evaluated the performance of several models, including Random Forest, Bagging, Support Vector Machine, Naive Bayes, K-Nearest Neighbors, and AdaBoost. Among these, Random Forest and Bagging achieved the highest accuracy and demonstrated the most stable results. The classification performance was notably better in ECB mode, where no random initialization vector was used. In contrast, the increased randomness of data in CBC mode resulted in lower classification effectiveness, particularly as the number of encryption keys increased. This paper provides a comprehensive analysis of the classifiers’ performance across various encryption configurations and suggests potential directions for further experiments. Full article

The advancement of smart grid technologies necessitates the integration of cutting-edge computational methods to enhance predictive energy optimization. This study proposes a multi-faceted approach by incorporating (1) Deep Reinforcement Learning (DRL) agents trained using data from digital twins (DTs) to optimize energy consumption in real time, (2) Physics-Informed Neural Networks (PINNs) to seamlessly embed physical laws within the optimization process, ensuring model accuracy and interpretability, and (3) blockchain (BC) technology to facilitate secure and transparent communication across the smart grid infrastructure. The model was trained and validated using comprehensive datasets, including smart meter energy consumption data, renewable energy outputs, dynamic pricing, and user preferences collected from IoT devices. The proposed framework achieved superior predictive performance with a Mean Absolute Error (MAE) of 0.237 kWh, Root Mean Square Error (RMSE) of 0.298 kWh, and an R-squared (R²) value of 0.978, indicating a 97.8% explanation of data variance. Classification metrics further demonstrated the model’s robustness, achieving 97.7% accuracy, 97.8% precision, 97.6% recall, and an F1 Score of 97.7%. Comparative analysis with traditional models like Linear Regression, Random Forest, SVM, LSTM, and XGBoost revealed the superior accuracy and real-time adaptability of the proposed method. In addition to enhancing energy efficiency, the model reduced energy costs by 35%, maintained a 96% user comfort index, and increased renewable energy utilization to 40%. This study demonstrates the transformative potential of integrating PINNs, DT, and blockchain technologies to optimize energy consumption in smart grids, paving the way for sustainable, secure, and efficient energy management systems. Full article

Advances in machine learning have improved the ability to predict critical environmental conditions, including solar radiation levels that, while essential for life, can pose serious risks to human health. In Ecuador, due to its geographical location and altitude, UV radiation reaches extreme levels. This study presents the development of a chatbot system driven by a hybrid artificial intelligence model, combining Random Forest, CatBoost, Gradient Boosting, and a 1D Convolutional Neural Network. The model was trained with meteorological data, optimized using hyperparameters (iterations: 500–1500, depth: 4–8, learning rate: 0.01–0.3), and evaluated through MAE, MSE, R², and F1-Score. The hybrid model achieved superior accuracy (MAE = 13.77 W/m², MSE = 849.96, R² = 0.98), outperforming traditional methods. A 15% error margin was observed without significantly affecting classification. The chatbot, implemented via Telegram and hosted on Heroku, provided real-time personalized alerts, demonstrating an effective, accessible, and scalable solution for health safety and environmental awareness. Furthermore, it facilitates decision-making in the efficient generation of renewable energy and supports a more sustainable energy transition. It offers a tool that strengthens the relationship between artificial intelligence and sustainability by providing a practical instrument for integrating clean energy and mitigating climate change. Full article

Psychogenic non-epileptic seizures (PNES) are often misdiagnosed as epileptic seizures (ES), leading to inappropriate treatment and delayed psychological care. To address this challenge, we analysed electroencephalogram (EEG) data from 74 patients (46 PNES, 28 ES) using one-minute preictal and interictal recordings per subject. Nine entropy measures (Sample, Fuzzy, Permutation, Dispersion, Conditional, Phase, Spectral, Rényi, and Wavelet entropy) were evaluated individually to classify PNES from ES using k-nearest neighbours, Naïve Bayes, linear discriminant analysis, logistic regression, support vector machine, random forest, multilayer perceptron, and XGBoost within a leave-one-subject-out cross-validation framework. In addition, a dynamic state, defined as the entropy difference between interictal and preictal periods, was examined. Sample, Fuzzy, Conditional, and Dispersion entropy were higher in PNES than in ES during interictal recordings (not significant), but significantly lower in the preictal (p < 0.05) and dynamic states (p < 0.01). Spatial mapping and permutation-based importance analyses highlighted O1, O2, T5, F7, and Pz as key discriminative channels. Classification performance peaked in the dynamic state, with Fuzzy entropy and support vector machine achieving the best results (balanced accuracy = 72.4%, F1 score = 77.8%, sensitivity = 74.5%, specificity = 70.4%). These results demonstrate the potential of entropy features for differentiating PNES from ES. Full article

Urban water distribution networks (WDNs) are increasingly vulnerable to diverse disruptions, including pipe leaks/bursts and cyber–physical failures. A critical step in a resilience-based approach against these disruptions is the rapid and reliable identification of failures and their types for the timely implementation of emergency or recovery actions. This study proposes a framework for sensor placement and multiple failure type classification in WDNs. It applies a wrapper-based feature selection (recursive feature elimination) with Random Forest (RF–RFE) to find the best sensor locations and employs an Autoencoder–Random Forest (AE–RF) framework for failure type identification. The framework was tested on the C-town WDN using the failure type scenarios of pipe leakage, cyberattacks, and physical attacks, which were generated using EPANET-CPA and WNTR models. The results showed a higher performance of the framework for single failure events, with accuracy of 0.99 for leakage, 0.98 for cyberattacks, and 0.95 for physical attacks, while the performance for multiple failure classification was lower, but still acceptable, with a performance accuracy of 0.90. The reduced performance was attributed to the model’s difficulty in distinguishing failure types when they produced hydraulically similar consequences. The proposed framework combining sensor placement and multiple failure identification will contribute to advance the existing data-driven approaches and to strengthen urban WDN resilience to conventional and cyber–physical disruptions. Full article

Oxide semiconductor gas sensors are widely used due to their low cost, rapid response, small footprint, and ease of integration. However, in complex gas mixtures their selectivity is often limited by inherent cross-sensitivity. To address this, we developed a reconfigurable sensor-array system that supports up to 12 chemiresistive sensors with four- or six-electrode configurations, independent thermal control, and programmable gas paths. As a representative case study, we designed a customized array for fish-spoilage biomarkers, intentionally leveraging the cross-sensitivity and broad-spectrum responses of metal-oxide sensors. Following principal component analysis (PCA) preprocessing, we evaluated convolutional neural network (CNN), random forest (RF), and particle swarm optimization–tuned support vector machine (PSO-SVM) classifiers. The RF model achieved 94% classification accuracy. Subsequent channel optimization (correlation analysis and feature-importance assessment) reduced the array from 12 to 8 sensors and improved accuracy to 96%, while simplifying the system. These results demonstrate that deliberately leveraging cross-sensitivity within a carefully selected array yields an information-rich odor fingerprint, providing a practical platform for complex gas-mixture identification and food-freshness assessment. Full article