Search

Objective: By utilizing machine learning, we can identify genes that are associated with recurrence, invasion, and tumor stemness, thus uncovering new therapeutic targets. Methods: To begin, we obtained a gene set related to recurrence and invasion from the GEO database, a comprehensive gene expression database. We then employed the Weighted Gene Co-expression Network Analysis (WGCNA) to identify core gene modules and perform functional enrichment analysis on them. Next, we utilized the random forest and random survival forest algorithms to calculate the genes within the key modules, resulting in the identification of three crucial genes. Subsequently, one of these key genes was selected for prognosis analysis and potential drug screening using the Kaplan-Meier tool. Finally, in order to examine the role of CDC20 in lung adenocarcinoma (LUAD), we conducted a variety of in vitro and in vivo experiments, including wound healing assay, colony formation assays, Transwell migration assays, flow cytometric cell cycle analysis, western blotting, and a mouse tumor model experiment. Results: First, we collected a total of 279 samples from two datasets, GSE166722 and GSE31210, to identify 91 differentially expressed genes associated with recurrence, invasion, and stemness in lung adenocarcinoma. Functional enrichment analysis revealed that these key gene clusters were primarily involved in microtubule binding, spindle, chromosomal region, organelle fission, and nuclear division. Next, using machine learning, we identified and validated three hub genes (CDC45, CDC20, TPX2), with CDC20 showing the highest correlation with tumor stemness and limited previous research. Furthermore, we found a close association between CDC20 and clinical pathological features, poor overall survival (OS), progression-free interval (PFI), progression-free survival (PFS), and adverse prognosis in lung adenocarcinoma patients. Lastly, our functional research demonstrated that knocking down CDC20 could inhibit cancer cell migration, invasion, proliferation, cell cycle progression, and tumor growth possibly through the MAPK signaling pathway. Conclusion: CDC20 has emerged as a novel biomarker for monitoring treatment response, recurrence, and disease progression in patients with lung adenocarcinoma. Due to its significance, further research studying CDC20 as a potential therapeutic target is warranted. Investigating the role of CDC20 could lead to valuable insights for developing new treatments and improving patient outcomes. [ABSTRACT FROM AUTHOR]

In order to increase the likelihood of obtaining treatment and achieving a complete recovery, early illness identification and diagnosis are crucial. Artificial intelligence is helpful with this process by allowing us to rapidly start the necessary protocol for treatment in the early stages of disease development. Artificial intelligence is a major contributor to the improvement of medical treatment for patients. In order to prevent and foresee this problem on the individual, family, and generational levels, Monitoring the patient's therapy and recovery is crucial. This study's objective is to outline a non-invasive method for using mammograms to detect breast abnormalities, classify breast disorders, and identify cancerous or benign tumor tissue in the breast. We used classification models on a dataset that has been pre-processed so that the number of samples is balanced, unlike previous work on the same dataset. Identifying cancerous or benign breast tissue requires the use of supervised learning techniques and algorithms, such as random forest (RF) and decision tree (DT) classifiers, to examine up to thirty features, such as breast size, mass, diameter, circumference, and the nature of the tumor (solid or cystic). To ascertain if the tissue is malignant or benign, the examination's findings are employed. These features are mostly what determines how effectively anything may be categorized. The DT classifier was able to get a score of 95.32%, while the RF satisfied a far higher 98.83 percent. [ABSTRACT FROM AUTHOR]

Background: The clinical presentation of Community-acquired pneumonia (CAP) in hospitalized patients exhibits heterogeneity. Inflammation and immune responses play significant roles in CAP development. However, research on immunophenotypes in CAP patients is limited, with few machine learning (ML) models analyzing immune indicators. Methods: A retrospective cohort study was conducted at Xinhua Hospital, affiliated with Shanghai Jiaotong University. Patients meeting predefined criteria were included and unsupervised clustering was used to identify phenotypes. Patients with distinct phenotypes were also compared in different outcomes. By machine learning methods, we comprehensively assess the disease severity of CAP patients. Results: A total of 1156 CAP patients were included in this research. In the training cohort (n=809), we identified three immune phenotypes among patients: Phenotype A (42.0%), Phenotype B (40.2%), and Phenotype C (17.8%), with Phenotype C corresponding to more severe disease. Similar results can be observed in the validation cohort. The optimal prognostic model, SuperPC, achieved the highest average C-index of 0.859. For predicting CAP severity, the random forest model was highly accurate, with C-index of 0.998 and 0.794 in training and validation cohorts, respectively. Conclusion: CAP patients can be categorized into three distinct immune phenotypes, each with prognostic relevance. Machine learning exhibits potential in predicting mortality and disease severity in CAP patients by leveraging clinical immunological data. Further external validation studies are crucial to confirm applicability. [ABSTRACT FROM AUTHOR]

Background: Neuropathic pain (NP) is a debilitating and refractory chronic pain with a higher prevalence especially in elderly patients. Cell senescence considered a key pathogenic factor in NP. The objective of this research is to discover genes associated with aging in peripheral blood of individuals with NP using bioinformatics techniques. Methods: Two cohorts (GSE124272 and GSE150408) containing peripheral blood samples of NP were downloaded from the GEO database. By merging the two cohorts, differentially expressed aging-related genes (DE-ARGs) were obtained by intersection with aging-related genes. The potential biological mechanisms of DE-ARGs were further analyzed through GO and KEGG. Three machine learning methods, namely, LASSO, SVM-RFE, and Random Forest, were utilized to identify diagnostic biomarkers. A Nomogram model was developed to assess their diagnostic accuracy. The validation of biomarker expression and diagnostic effectiveness was conducted in three distinct pain cohorts. The CIBERSORT algorithm was employed to evaluate the immune cell composition in the peripheral blood of patients with NP and investigate its association with the expression of diagnostic biomarkers. Results: This study identified a total of 24 DE-ARGs, mainly enriched in “Chemokine signaling pathway,” “Inflammatory mediator regulation of TRP channels,” “HIF-1 signaling pathway” and “FOXO signaling pathway”. Three machine learning algorithms identified a total of four diagnostic biomarkers (CEBPA, CEACAM1, BTG3 and IL-1R1) with good diagnostic performance and the similar expression difference trend in different types of pain cohorts. The expression levels of CEACAM1 and IL-1R1 exhibit a positive correlation with the percentage of neutrophils. Conclusion: Using machine learning techniques, our research identified four diagnostic biomarkers related to aging in peripheral blood, providing innovative approaches for the diagnosis and treatment of NP. [ABSTRACT FROM AUTHOR]

Strengthening industrial pollution control in the Yangtze River is a fundamental national policy of China. There is a lack of detailed distribution of chemical industrial parks (CIPs). This Study utilized random forest (RF) and active learning to generate the distribution map of CIPs along the Yangtze River at 10-m resolution. Based on Sentinel-2 imagery, spectral and texture features are extracted. Combined with the Points of Interest (POI), a multidimensional feature space is constructed. By employing partitioned training, classification of CIPs map is achieved on Google Earth Engine (GEE). Technical validation along the entire Yangtze River demonstrates a model accuracy of 80%. Compared to traditional manual survey methods, this approach saves significant time and economic costs while also being timelier. As the first publicly available CIPs map within a 5-km range along the Yangtze River, this research will provide a scientific basis for the fine governance of chemical industries in the region. Additionally, it offers a model guide for the accurate identification of the chemical industry. [ABSTRACT FROM AUTHOR]

Introduction: Clinical reasoning in veterinary medicine is often based on clinicians' personal experience in combination with information derived from publications describing cohorts of patients. Studies on the use of scientific methods for patient individual decision making are largely lacking. This applies to the prediction of the individual underlying pathology in seizuring dogs as well. The aim of this study was to apply machine learning to the prediction of the risk of structural epilepsy in dogs with seizures. Materials and methods: Dogs with a history of seizures were retrospectively as well as prospectively included. Data about clinical history, neurological examination, diagnostic tests performed as well as the final diagnosis were collected. For data analysis, the Bayesian Network and Random Forest algorithms were used. A total of 33 features for Random Forest and 17 for Bayesian Network were available for analysis. The following four feature selection methods were applied to select features for further analysis: Permutation Importance, Forward Selection, Random Selection and Expert Opinion. The two algorithms Bayesian Network and Random Forest were trained to predict structural epilepsy using the selected features. Results: A total of 328 dogs of 119 different breeds were identified retrospectively between January 2017 and June 2021, of which 33.2% were diagnosed with structural epilepsy. An overall of 89,848 models were trained. The Bayesian Network in combination with the Random feature selection performed best. It was able to predict structural epilepsy with an accuracy of 0.969 (sensitivity: 0.857, specificity: 1.000) among all dogs with seizures using the following features: age at first seizure, cluster seizures, seizure in last 24 h, seizure in last 6 month, and seizure in last year. Conclusion: Machine learning algorithms such as Bayesian Networks and Random Forests identify dogs with structural epilepsy with a high sensitivity and specificity. This information could provide some guidance to clinicians and pet owners in their clinical decision-making process. [ABSTRACT FROM AUTHOR]

Sea surface gage height (SSGH) data are commonly measured at sparsely deployed tidal stations while coastal resources management requires spatially distributed SSGH data. This paper presents three different machine learning models, including a Random Forest (RF) model, an Extreme Gradient Boosting (XGBoost) model, and an Artificial Neural Network (ANN) model, for retrieving and mapping spatially distributed SSGH. The models were originally developed and independently validated using 10 years of VIIRS satellite remote sensing data and corresponding in-situ gage height (GH) data within the MATLAB ANN toolbox and RStudio. The paper made two major new contributions to the determination of SSGH, including a scientific contribution and a technical contribution. Scientifically, this paper has provided new insights into important factors affecting SSGH. The SSGH varies significantly with the location (GPS coordinates) and Julian Day with both factors affecting the tide and thus SSGH. SSGH is also affected by sea surface waves that affect the reflectance of light from different wavelengths of satellite sensors, which are described with the VIIRS remote sensing reflectance (Rrs) bands including Rrs 410, 443, 486, 551, and 671. Technically, the machine learning models, particularly the ANN model, are capable of providing the most accurate and spatially distributed SSGH data particularly for coastal waters, as characterized by the model performance metrics including the correlation coefficient R value of 0.94 for training, 0.94 for validation, and 0.93 for testing and the low root mean square error (RMSE) value of 0.113 m for training, 0.113 m for validation, and 0.118 m for testing. [ABSTRACT FROM AUTHOR]

The lack of soil erosion data and other information about watersheds continues to limit soil erosion modeling. To overcome these limitations, many researchers have turned to machine learning models to analyze and model the complex water erosion processes and integrate them with empirical models. The Beni Haroun dam watershed faces soil erosion due to specific geo-environmental settings and land practices. It poses serious threats to agricultural and natural resource development. For these reasons, this study attempts to identify soil erosion susceptible zones using the Revised Universal Soil Loss Equation (RUSLE) using five key factors (rainfall erosivity, soil erodibility, topography, cover management and conservation practice factor) in GIS environment. Furthermore, we integrated the five RUSLE parameters and the model outputs into two machine learning (ML) algorithms, namely Random Forest (RF) and Random Tree (RT). The proposed models underwent training on 70% of the dataset and were subsequently validated on the remaining 30%. Our results indicated that the most vulnerable to severe soil erosion was concentrated in northwest regions, in contrast to the southeastern regions, which most occupy low erosion and moderate erosion. RUSLE and RT-based RUSLE models yielded nearly identical results in classifying erosion severity, estimating the annual average soil erosion at 17.5 and 17.69 (t ha–1y–1), respectively. In contrast, the Random Forest RF-based RUSLE model presented slightly divergent findings 23.89 (t ha–1y–1). Overall, these findings contribute to the identification of the area's most vulnerable to soil erosion, providing valuable insights to inform land management and conservation strategies. [ABSTRACT FROM AUTHOR]

This research presents our application of artificial intelligence (AI) in predicting urolithiasis risk. Previous applications, including AI for stone disease, have focused on stone composition and aiding diagnostic imaging. AI applications centered around patient-specific characteristics, lifestyle considerations, and diet have been limited. Our study comprised a robust sample size of 976 Chilean participants, with meticulously analyzed demographic, lifestyle, and health data through a comprehensive questionnaire. We developed a predictive model using various classifiers, including logistic regression, decision trees, random forests, and extra trees, reaching high accuracy (88%) in identifying individuals at risk of kidney stone formation. Key protective factors highlighted by the algorithm include the pivotal role of hydration, physical activity, and dietary patterns that played a crucial role, emphasizing the protective nature of higher fruit and vegetable intake, balanced dairy consumption, and the nuanced impact of specific protein sources on kidney stone risk. In contrast, identified risk factors encompassed gender disparities with males found to be 2.31 times more likely to develop kidney stones than females. Thirst and self-perceived dark urine color emerged as strong predictors, with a significant increase in the likelihood of stone formation. The development of predictive tools with AI, in urolithiasis management signifies a paradigm shift toward more precise and personalized health care. The algorithm's ability to process extensive datasets, including dietary habits, heralds a new era of data-driven medical practice. This research underscores the transformative impact of AI in medical diagnostics and prevention, paving the way for a future where health care interventions are not only more effective but also tailored to individual patient needs. In this case, AI is an important tool that can help patients stay healthy, prevent diseases, and make informed decisions about their overall well-being. [ABSTRACT FROM AUTHOR]

BACKGROUND: The field of toxicology has witnessed substantial advancements in recent years, particularly with the adoption of new approach methodologies (NAMs) to understand and predict chemical toxicity. Class-based methods such as clustering and classification are key to NAMs development and application, aiding the understanding of hazard and risk concerns associated with groups of chemicals without additional laboratory work. Advances in computational chemistry, data generation and availability, and machine learning algorithms represent important opportunities for continued improvement of these techniques to optimize their utility for specific regulatory and research purposes. However, due to their intricacy, deep understanding and careful selection are imperative to align the adequate methods with their intended applications. OBJECTIVES: This commentary aims to deepen the understanding of class-based approaches by elucidating the pivotal role of chemical similarity (structural and biological) in clustering and classification approaches (CCAs). It addresses the dichotomy between general end point–agnostic similarity, often entailing unsupervised analysis, and end point–specific similarity necessitating supervised learning. The goal is to highlight the nuances of these approaches, their applications, and common misuses. DISCUSSION: Understanding similarity is pivotal in toxicological research involving CCAs. The effectiveness of these approaches depends on the right definition and measure of similarity, which varies based on context and objectives of the study. This choice is influenced by how chemical structures are represented and the respective labels indicating biological activity, if applicable. The distinction between unsupervised clustering and supervised classification methods is vital, requiring the use of end point–agnostic vs. end point–specific similarity definition. Separate use or combination of these methods requires careful consideration to prevent bias and ensure relevance for the goal of the study. Unsupervised methods use end point– agnostic similarity measures to uncover general structural patterns and relationships, aiding hypothesis generation and facilitating exploration of datasets without the need for predefined labels or explicit guidance. Conversely, supervised techniques demand end point–specific similarity to group chemicals into predefined classes or to train classification models, allowing accurate predictions for new chemicals. Misuse can arise when unsupervised methods are applied to end point–specific contexts, like analog selection in read-across, leading to erroneous conclusions. This commentary provides insights into the significance of similarity and its role in supervised classification and unsupervised clustering approaches. [ABSTRACT FROM AUTHOR]

Efficient forecasting of solar flares is of significant importance for better risk prevention. Currently, there is relatively rare research on multi/four-classification of flares, and the influence of the number of time steps and data feature dimensions on the prediction performance of multi-class models has not been considered. In this study, we utilize the Space-weather HMI Active Region Patch (SHARP) data to develop two categories of models for multiclass flare prediction within 24 hr, including direct output four-classification models and four-classification models using a cascading scheme. The former encompasses Random Forest (RF) model, Long Short-Term Memory (LSTM) model, and Bidirectional LSTM (BLSTM) model, while the latter includes BLSTM Cascade (BLSTM-C) model and BLSTM Cascade with Attention Mechanism (BLSTM-C-A) model. These two categories of models are employed to contrast the impact of different numbers of time steps and the predictive performance in solar flare multi/four-classification. Additionally, we conduct, for the first time, feature importance analysis for multi/four-classification solar flare prediction using deep learning models. The main results are as follows: (1) As the number of time steps increases, the True Skill Statistic (TSS) scores of the four deep learning models improve, showing an overall upward trend in predictive performance. The models achieve their optimal performance when the number of time steps reaches 120. (2) Among the direct output four-class models, deep learning models (LSTM and BLSTM) outperform traditional machine learning model (RF). In both multi-class and binary-class predictions using deep learning, the BLSTM-C model performs better than other deep learning models (LSTM, BLSTM, and BLSTM-C-A). (3) In the feature importance analysis, the top-ranked important features include SAVNCPP and R_VALUE, while the least important features include SHRGT45 and MEANPOT. [ABSTRACT FROM AUTHOR]

In vivo assessments of influenza A virus (IAV) pathogenicity and transmissibility in ferrets represent a crucial component of many pandemic risk assessment rubrics, but few systematic efforts to identify which data from in vivo experimentation are most useful for predicting pathogenesis and transmission outcomes have been conducted. To this aim, we aggregated viral and molecular data from 125 contemporary IAV (H1, H2, H3, H5, H7, and H9 subtypes) evaluated in ferrets under a consistent protocol. Three overarching predictive classification outcomes (lethality, morbidity, transmissibility) were constructed using machine learning (ML) techniques, employing datasets emphasizing virological and clinical parameters from inoculated ferrets, limited to viral sequence-based information, or combining both data types. Among 11 different ML algorithms tested and assessed, gradient boosting machines and random forest algorithms yielded the highest performance, with models for lethality and transmission consistently better performing than models predicting morbidity. Comparisons of feature selection among models was performed, and highest performing models were validated with results from external risk assessment studies. Our findings show that ML algorithms can be used to summarize complex in vivo experimental work into succinct summaries that inform and enhance risk assessment criteria for pandemic preparedness that take in vivo data into account. Use of machine learning to summarize complex in vivo data and provide predictive utility for Influenza A virus ferret lethality, morbidity, and transmission models. [ABSTRACT FROM AUTHOR]

Predicting crystal symmetry simply from chemical composition has remained challenging. Several machine‐learning approaches can be employed, but the predictive value of popular crystallographic databases is relatively modest due to the paucity of data and uneven distribution across the 230 space groups. In this work, virtually all crystallographic information available to science has been compiled and used to train and test multiple machine‐learning models. Composition‐driven random‐forest classification relying on a large set of descriptors showed the best performance. The predictive models for crystal system, Bravais lattice, point group and space group of inorganic compounds are made publicly available as easy‐to‐use software downloadable from https://gitlab.com/vishsoft/cosy. [ABSTRACT FROM AUTHOR]

Functional mobility tests, such as the L test of functional mobility, are recommended to provide clinicians with information regarding the mobility progress of lower-limb amputees. Smartphone inertial sensors have been used to perform subtask segmentation on functional mobility tests, providing further clinically useful measures such as fall risk. However, L test subtask segmentation rule-based algorithms developed for able-bodied individuals have not produced sufficiently acceptable results when tested with lower-limb amputee data. In this paper, a random forest machine learning model was trained to segment subtasks of the L test for application to lower-limb amputees. The model was trained with 105 trials completed by able-bodied participants and 25 trials completed by lower-limb amputee participants and tested using a leave-one-out method with lower-limb amputees. This algorithm successfully classified subtasks within a one-foot strike for most lower-limb amputee participants. The algorithm produced acceptable results to enhance clinician understanding of a person's mobility status (>85% accuracy, >75% sensitivity, >95% specificity). [ABSTRACT FROM AUTHOR]

A deep-seated landslide could release numerous microseismic signals from creep-slip movement, which includes a rock-soil slip from the slope surface and a rock-soil shear rupture in the subsurface. Machine learning can effectively enhance the classification of microseismic signals in landslide seismic monitoring and interpret the mechanical processes of landslide motion. In this paper, eight sets of triaxial seismic sensors were deployed inside the deep-seated landslide, Jiuxianping, China, and a large number of microseismic signals related to the slope movement were obtained through 1-year-long continuous monitoring. All the data were passed through the seismic event identification mode, the ratio of the long-time average and short-time average. We selected 11 days of data, manually classified 4131 data into eight categories, and created a microseismic event database. Classical machine learning algorithms and ensemble learning algorithms were tested in this paper. In order to evaluate the seismic event classification performance of each algorithmic model, we evaluated the proposed algorithms through the dimensions of the accuracy, precision, and recall of each model. The validation results demonstrated that the best performing decision tree algorithm among the classical machine learning algorithms had an accuracy of 88.75%, while the ensemble algorithms, including random forest, Gradient Boosting Trees, Extreme Gradient Boosting, and Light Gradient Boosting Machine, had an accuracy range from 93.5% to 94.2% and also achieved better results in the combined evaluation of the precision, recall, and F1 score. The specific classification tests for each microseismic event category showed the same results. The results suggested that the ensemble learning algorithms show better results compared to the classical machine learning algorithms. [ABSTRACT FROM AUTHOR]

Cyber-security challenges are growing globally and are specifically targeting critical infrastructure. Conventional countermeasure practices are insufficient to provide proactive threat hunting. In this study, random forest (RF), support vector machine (SVM), multi-layer perceptron (MLP), AdaBoost, and hybrid models were applied for proactive threat hunting. By automating detection, the hybrid machine learning-based method improves threat hunting and frees up time to concentrate on high-risk warnings. These models are implemented on approach devices, access, and principal servers. The efficacy of several models, including hybrid approaches, is assessed. The findings of these studies are that the AdaBoost model provides the highest efficiency, with a 0.98 ROC area and 95.7% accuracy, detecting 146 threats with 29 false positives. Similarly, the random forest model achieved a 0.98 area under the ROC curve and a 95% overall accuracy, accurately identifying 132 threats and reducing false positives to 31. The hybrid model exhibited promise with a 0.89 ROC area and 94.9% accuracy, though it requires further refinement to lower its false positive rate. This research emphasizes the role of machine learning in improving cyber-security, particularly for critical infrastructure. Advanced ML techniques enhance threat detection and response times, and their continuous learning ability ensures adaptability to new threats. [ABSTRACT FROM AUTHOR]

The detection performance of radar is significantly impaired by active jamming and mutual interference from other radars. This paper proposes a radio signal modulation recognition method to accurately recognize these signals, which helps in the jamming cancellation decisions. Based on the ensemble learning stacking algorithm improved by meta-feature enhancement, the proposed method adopts random forests, K-nearest neighbors, and Gaussian naive Bayes as the base-learners, with logistic regression serving as the meta-learner. It takes the multi-domain features of signals as input, which include time-domain features including fuzzy entropy, slope entropy, and Hjorth parameters; frequency-domain features, including spectral entropy; and fractal-domain features, including fractal dimension. The simulation experiment, including seven common signal types of radar and active jamming, was performed for the effectiveness validation and performance evaluation. Results proved the proposed method's performance superiority to other classification methods, as well as its ability to meet the requirements of low signal-to-noise ratio and few-shot learning. [ABSTRACT FROM AUTHOR]

Investigating the fluctuations of uterine contractions is an indispensable diagnostic practice to evaluate the onset of labor. This work aims to differentiate the fluctuations associated with Term (gestation ≥ 37 weeks) pregnancies during varied gestational ages using electrohysterography (EHG) signals. The signals in the second and third trimesters are subjected to Multifractal-Empirical Mode Decomposition-based Detrended Fluctuation Analysis (MF-EMDDFA). Multifractal spectrum is estimated and features namely, Holder exponents ( α L , α R ), broadness (BD), root slopes (LS, RS) and tangential slopes (TL, TR) are extracted. Machine learning methods, such as Naïve Bayes, adaptive boosting and random forest (RF) classifiers, are utilized to discriminate the contractions during different weeks of gestation. Results show that five multifractal features, namely α L , α R , BD, LS and TL, show significant differences between the considered gestational ages. An increase in regularity of the uterine contractions is observed as the gestational age increases. These features along with the RF classifier provide an accuracy, sensitivity, precision, recall and F1-score of greater than 98.30%. As the differentiation of uterine contractions during different weeks of gestation is vital to understanding the pregnancy progress, the proposed multifractal features could be used as potential biomarkers in clinical practices. [ABSTRACT FROM AUTHOR]

With the ongoing challenge of air pollution posing serious health and environmental threats, particularly in rapidly industrializing regions, accurate forecasting and effective pollutant identification are crucial for enhancing public health and ecological stability. This study aimed to optimize air quality management through the prediction of the Air Quality Index (AQI) and identification of air pollutants. Our study spans nine representative cities (Hohhot, Yinchuan, Lanzhou, Beijing, Taiyuan, Xi'an, Shanghai, Nanjing, Wuhan) in China, with data collected from January 1, 2015, to November 30, 2021. We proposed a new model for daily AQI prediction, termed VMD-CSA-CNN-LSTM, which employed advanced machine learning techniques, including convolutional neural networks (CNN) and long short-term memory (LSTM) networks, and leveraged the chameleon swarm algorithm (CSA) for hyperparameter optimization, integrated through a variational mode decomposition approach. The model was developed using data from Lanzhou, with a split ratio of 8:1:1 into training, validation, and test sets, achieving an RMSE of 2.25, MAPE of 0.02, adjusted R-squared of 98.91%, and training efficiency of 5.31%. The model was further externally validated in the other eight cities, yielding comparable results, with an adjusted R-squared above 96%, MAPE below 0.1, and RMSE below 7.5. Additionally, we employed a random forest algorithm to identify the primary pollutants contributing to AQI levels. Our results indicated that PM2.5 was the most significant pollutant in Beijing, Taiyuan, and Xi'an, while PM10 was dominant in Hohhot, Yinchuan, and Lanzhou. In Shanghai, Nanjing, and Wuhan, both PM2.5 and PM10 were critical, with ozone also identified as a major air pollutant. This study not only advances the predictive accuracy of AQI models but also aids policymakers by providing a reliable tool for air quality management and strategic planning aimed at pollution reduction. The integration of these advanced computational techniques into environmental monitoring practices offers a promising avenue for enhancing air quality and mitigating pollution-related risks. [ABSTRACT FROM AUTHOR]

The navigational accuracy of sea animals and trans-ocean birds provides inspiration in using geo-magnetic field (GMF) for realizing strategic truly autonomous underwater vehicles (AUV) capable of determining their absolute position on earth, without the aid of ship-referenced acoustic baseline systems. Supervised Machine Learning algorithms are applied on the GMF intensity data obtained from NOAA World Magnetic Model for a 900 km2 within the Indian mineral exploratory area in the Central Indian Ocean, with a resolution of 50 m, considering the sensitivity of commercially available magnetometers. It is identified that, for AUVs equipped with magnetometers with a detection sensitivity of 0.1 nT, the supervisory random forest regression and decision tree algorithm trained with priori GMF data, could provide trajectory guidance to AUVs with an absolute mean position accuracy in 2D plane, with reference to the last known position from Integrated Navigation system aided initially with GPS and with acoustic positioning in underwater. Circular Error Probable (CEP 50) of 53 m and 56 m, respectively. The scalar GMF anomaly navigation demonstrated to be a viable GPS-alternative navigation system could be extended to larger areas with inclination and declination vectors, as unique identifiers. [ABSTRACT FROM AUTHOR]

Wildfire susceptibility maps play a crucial role in preemptively identifying regions at risk of future fires and informing decisions related to wildfire management, thereby aiding in mitigating the risks and potential damage posed by wildfires. This study employs eXplainable Artificial Intelligence (XAI) techniques, particularly SHapley Additive exPlanations (SHAP), to map wildfire susceptibility in Izmir Province, Türkiye. Incorporating fifteen conditioning factors spanning topography, climate, anthropogenic influences, and vegetation characteristics, machine learning (ML) models (Random Forest, XGBoost, LightGBM) were used to predict wildfire-prone areas using freely available active fire pixel data (MODIS Active Fire Collection 6 MCD14ML product). The evaluation of the trained ML models showed that the Random Forest (RF) model outperformed XGBoost and LightGBM, achieving the highest test accuracy (95.6%). All of the classifiers demonstrated a strong predictive performance, but RF excelled in sensitivity, specificity, precision, and F-1 score, making it the preferred model for generating a wildfire susceptibility map and conducting a SHAP analysis. Unlike prevailing approaches focusing solely on global feature importance, this study fills a critical gap by employing a SHAP summary and dependence plots to comprehensively assess each factor's contribution, enhancing the explainability and reliability of the results. The analysis reveals clear associations between factors such as wind speed, temperature, NDVI, slope, and distance to villages with increased fire susceptibility, while rainfall and distance to streams exhibit nuanced effects. The spatial distribution of the wildfire susceptibility classes highlights critical areas, particularly in flat and coastal regions near settlements and agricultural lands, emphasizing the need for enhanced awareness and preventive measures. These insights inform targeted fire management strategies, highlighting the importance of tailored interventions like firebreaks and vegetation management. However, challenges remain, including ensuring the selected factors' adequacy across diverse regions, addressing potential biases from resampling spatially varied data, and refining the model for broader applicability. [ABSTRACT FROM AUTHOR]

Site-specific weed management employs image data to generate maps through various methodologies that classify pixels corresponding to crop, soil, and weed. Further, many studies have focused on identifying specific weed species using spectral data. Nonetheless, the availability of open-access weed datasets remains limited. Remarkably, despite the extensive research employing hyperspectral imaging data to classify species under varying conditions, to the best of our knowledge, there are no open-access hyperspectral weed datasets. Consequently, accessible spectral weed datasets are primarily RGB or multispectral and mostly lack the temporal aspect, i.e., they contain a single measurement day. This paper introduces an open dataset for training and evaluating machine-learning methods and spectral features to classify weeds based on various biological traits. The dataset comprises 30 hyperspectral images, each containing thousands of pixels with 204 unique visible and near-infrared bands captured in a controlled environment. In addition, each scene includes a corresponding RGB image with a higher spatial resolution. We included three weed species in this dataset, representing different botanical groups and photosynthetic mechanisms. In addition, the dataset contains meticulously sampled labeled data for training and testing. The images represent a time series of the weed's growth along its early stages, critical for precise herbicide application. We conducted an experimental evaluation to test the performance of a machine-learning approach, a deep-learning approach, and Spectral Mixture Analysis (SMA) to identify the different weed traits. In addition, we analyzed the importance of features using the random forest algorithm and evaluated the performance of the selected algorithms while using different sets of features. [ABSTRACT FROM AUTHOR]

Effective planning and management strategies for restoring and conserving tropical peat swamp ecosystems require accurate and timely estimates of aboveground biomass (AGB), especially when monitoring the impacts of restoration interventions. The aim of this research is to assess changes in AGB and evaluate the effectiveness of restoration efforts in the North Selangor Peat Swamp Forest (NSPSF), one of the largest remaining peat swamp forests in Peninsular Malaysia, using advanced remote sensing techniques. A Random Forest machine learning method was employed to upscale AGB estimates, derived from a 'LiDAR AGB model', to larger landscape-scale areas with Sentinel-2 spectral and textural variables. The time period under investigation (2015–2018) marked a concentrated phase of restoration and regeneration efforts in NSPSF. The results demonstrate an overall increase in tropical peat swamp AGB during these years, where the total amount of estimated AGB stored in NSPSF increased from 19.3 Tg in 2015 to an estimated 19.8 Tg in 2018. The research found that a tailored variable selection approach improved predictions of AGB, with optimised input variables (n = 62) and parameter adjustments producing a good plausible result (R2 = 0.80; RMSE = 55.2 Mg/ha). This paper concludes by emphasizing the importance of long-term studies (>5 years) for analyzing the success of tropical peat swamp restoration methods, with a potential for integrating remote sensing technology. [ABSTRACT FROM AUTHOR]

To establish a predictive model for prostate cancer bone metastasis utilizing multiple machine learning algorithms. Retrospective analysis of the clinical data of prostate cancer initially diagnosed in the Department of Urology of Gansu Provincial People's Hospital from June 2017 to June 2022. Logistic regression (LR) and least absolute shrinkage and selection operator (LASSO) are used to jointly screen the model features. The filtered features are incorporated into algorithms including LR, random forest (RF), extreme gradient boosting (XGBoost), naive Bayes (NB), k-nearest neighbor (KNN), and decision tree (DT), to develop prostate cancer bone metastasis models. A total of 404 patients were finally screened. Gleason score, T stage, N stage, PSA, and ALP were used as features for modeling. The average AUC of the 5-fold cross-validation for each machine learning model in the training set is as follows: LR (AUC = 0.9054), RF (AUC = 0.9032), NB (AUC = 0.8961), KNN (AUC = 0.8704), DT (AUC = 0.8526), XGBoost (AUC = 0.8066). The AUC of each machine learning model in the test set is KNN (AUC = 0.9390, 95%CI: 0.8760-1), RF (AUC = 0.9290, 95%CI: 0.8718-0.9861), NB (AUC = 0.9268, 95%CI: 0.8615-0.9920), LR (AUC = 0.9212, 95%CI: 0.8506-0.9917), XGBoost (AUC = 0.8292, 95%CI: 0.7442-0.9141), DT (AUC = 0.8057, 95%CI: 0.7100-0.9014). A comprehensive evaluation showed that LR performed well in interpretability and clinical applications. A bone metastasis model of prostate cancer was established, and it was observed that indicators such as inflammation and nutrition had a weak correlation with bone metastasis. [ABSTRACT FROM AUTHOR]

Machine learning (ML) accurately predicts the shear bearing capacity of steel tube‐reinforced concrete (STRC) shear walls, aiding optimization design. However, creating a database for STRC shear walls experimentally is time‐consuming and costly. The aim of this study is to propose a method for high‐accuracy prediction of STRC shear wall shear bearing capacity using a small‐sample dataset. This study employs generative adversarial network (GAN) data augmentation techniques to address the issues of insufficient ML model training and low prediction accuracy in small‐sample databases. Based on the stacking framework, a fusion model (Stacking‐XRL) combining extreme gradient boosting (XGBoost), random forest (RF), and least absolute shrinkage and selection operator (LASSO) is established to predict the shear bearing capacity of STRC shear walls. Results show that after augmenting the training set with GAN, the prediction performance of K‐nearest neighbors (KNN), backpropagation neural network (BPNN), RF, light gradient boosting machine (LightGBM), XGBoost, and stacking‐XRL models significantly improve, with average increases of 10% in R2 and average decreases of 30% and 25% in MAE and RMSE, respectively. The proposed stacking‐XRL fusion model outperforms tested models, existing formulas, and Abaqus numerical simulations for the shear bearing capacity of STRC shear walls. Model interpretation reveals that the shear span ratios as the most important factors in predicting shear bearing capacity, followed by axial force ratio and whole section configuration steel tubular index. [ABSTRACT FROM AUTHOR]

Understanding charging vehicles, charging stations, and built environment concerning idle connection times significantly guided the management of charging infrastructure. However, the interplay between these factors had remained incompletely understood. This study addressed this gap by investigating public charging stations in Changshu, Suzhou, China, as a case study. The random forest regression and partial dependence plots were employed to explore the nonlinear relationships between idle connection times of vehicles at public fast-charging stations and the built environment, charging stations, and charging vehicles. The exploration encompassed two typical scenarios: workdays and weekends. The findings reveal the distinct influences of various factors in different scenarios. Notably, catering service points of interests in the proximity of charging stations, significantly impact the idle connection time on both workdays and weekends. Furthermore, government groups and residential areas have a notable influence on idle connection times during workdays. Shopping service and Leisure sport have a significant impact on idle connection time during the weekends. Variables such as the charging start time and charged energy also exhibit significant effects. Importantly, these influencing factors demonstrate heterogeneity and exhibit different threshold effects. This research can offer valuable insights to planning authorities and charging facility operators for formulating strategies to enhance charging infrastructure utilization. [ABSTRACT FROM AUTHOR]

Accurate and timely prediction of crop yields is crucial for ensuring food security and promoting sustainable agricultural practices. This study developed a winter wheat yield prediction model using machine learning techniques, incorporating remote sensing data and statistical yield records from Henan Province, China. The core of the model is an ensemble voting regressor, which integrates ridge regression, gradient boosting, and random forest algorithms. This study optimized the hyperparameters of the ensemble voting regressor and conducted an in-depth comparison of its yield prediction performance with that of other mainstream machine learning models, assessing the impact of key hyperparameters on model accuracy. This study also explored the potential of yield prediction at different growth stages and its application in yield spatialization. The results demonstrate that the ensemble voting regressor performed exceptionally well throughout the entire growth period, with an R2 of 0.90, an RMSE of 439.21 kg/ha, and an MAE of 351.28 kg/ha. Notably, during the heading stage, the model's prediction performance was particularly impressive, with an R2 of 0.81, an RMSE of 590.04 kg/ha, and an MAE of 478.38 kg/ha, surpassing models developed for other growth stages. Additionally, by establishing a yield spatialization model, this study mapped county-level yield predictions to the pixel level, visually illustrating the spatial differences in land productivity. These findings provide reliable technical support for winter wheat yield prediction and valuable references for crop yield estimation in precision agriculture. [ABSTRACT FROM AUTHOR]

Crop models are instrumental in simulating resource utilization in agriculture, yet their complexity necessitates extensive calibration, which can impact the accuracy of yield predictions. Machine learning shows promise for enhancing yield estimations but relies on vast amounts of training data. This study aims to improve the pakchoi yield prediction accuracy of simulation models. We developed a stacking ensemble learning model that integrates three base models—EU-Rotate_N, Random Forest Regression and Support Vector Regression—with a Multi-layer Perceptron as the meta-model for the pakchoi dry matter yield prediction. To enhance the training dataset and bolster machine learning performance, we employed the EU-Rotate_N model to simulate daily dry matter yields for unsampled data. The test results revealed that the stacking model outperformed each base model. The stacking model achieved an R² value of 0.834, which was approximately 0.1 higher than that of the EU-Rotate_N model. The RMSE and MAE were 0.283 t/ha and 0.196 t/ha, respectively, both approximately 0.6 t/ha lower than those of the EU-Rotate_N model. The performance of the stacking model, developed with the expanded dataset, showed a significant improvement over the model based on the original dataset. [ABSTRACT FROM AUTHOR]

Timely and accurate predictions of winter wheat yields are key to ensuring food security. In this research, winter wheat yield prediction models for six provinces were established using a random forest (RF) model. Two methods were employed to analyze feature variables. RF partial dependence plots were generated to demonstrate the nonlinear relationships between the feature variables and yield, and bivariate Moran's I was considered to identify the spatial associations between variables. Results showed that when environmental data from key growth periods were used for prediction model establishment, the root mean square error (RMSE) varied between 200 and 700 kg/ha, and the coefficient of determination (R2) exceeded 0.5. Feature variable analysis results indicated that the longitude, latitude, topography and normalized difference vegetation index (NDVI) were important variables. Below the threshold, the yield gradually increased with increasing NDVI. Bivariate Moran's I results showed that there was zonal distribution of meteorological elements. Within a large spatial range, the change in environmental variables due to the latitude and longitude should be accounted for in modeling, but the influence of collinearity between the feature variables should be eliminated via variable importance analysis. [ABSTRACT FROM AUTHOR]

Machine learning-based prediction of the output characteristics of a negative capacitance (NC) double gate (DG) Tunnel FET (TFET) (NC DG TFET) has been demonstrated in this paper. On current (ION), OFF current (IOFF) and sub-threshold slope (SS) have been predicted for different values of the body thickness (TSi), oxide thickness (TOX) and channel length (LCh) and the work function (WF). Random Forest Regression (RFR) model is used in the ML framework to explore the device characteristics. A total of 5444 simulated data has been generated by using the SILVACO ATLAS tool. After pre-processing the data, RFR-ML has been applied to obtain maximum accuracy. Root means square error (RMSE) (~0.34), R2 score (~0.965) and accuracy (~98.51%) parameter have been used as the figures of merit (FOM) to judge the efficiency of the proposed model with respect to the state-of-the-art literature. Besides, with higher accuracy, the model is capable of predicting the data within a few seconds compared to the few hundred hours using TCAD tools. This fast and accurate design strategy will surely be efficacious for the present VLSI industries. [ABSTRACT FROM AUTHOR]

Due to Prolonged operation and external environmental factors, composite insulators may develop various defects, which can potentially lead to serious accidents in power systems. Detecting and analyzing these defects is critically important. In this study, we combine machine learning with laser‐induced breakdown spectroscopy (LIBS) to identify defects in composite insulators and obtain spectral data from both defective and nondefective samples. The Uniform Manifold Approximation and Projection algorithm was employed to reduce the dimensionality of the data, thereby enhancing detection accuracy and efficiency. Decision tree, random forest (RF), K‐nearest neighbor, and support vector machine algorithms were used to classify the dimensionality‐reduced data. The results indicate that the RF algorithm achieved the best classification performance, with accuracies of 100% and 95.46% for the training and test sets, respectively. Furthermore, the precision, recall, and F1 scores, which reflect model performance, also showed superior results with the RF algorithm. These findings suggest that the combination of LIBS technology and machine learning can rapidly and accurately detect and analyze defects in composite insulators, offering new insights and methods for defect detection in composite insulators. [ABSTRACT FROM AUTHOR]

Problematic pornography use (PPU) is the most common manifestation of the newly introduced compulsive sexual behavior disorder diagnosis in the 11th revision of the International Classification of Diseases. Research related to PPU has proliferated in the past two decades, but most prior studies were characterized by several shortcomings (e.g., using homogenous, small samples), resulting in crucial knowledge gaps and a limited understanding concerning empirically based risk factors for PPU. This study aimed to identify the most robust risk factors for PPU using a preregistered study design. Independent laboratories' 74 preexisting self-report data sets (Nparticipants = 112,397; Ncountries = 16) were combined to identify which factors can best predict PPU using an artificial intelligence-based method (i.e., machine learning). We conducted random forest models on each data set to examine how different sociodemographic, psychological, and other characteristics predict PPU, and combined the results of all data sets using random-effects meta-analysis with meta-analytic moderators (e.g., community vs. treatment-seeking samples). Predictors explained 45.84% of the variance in PPU scores. Out of the 700+ potential predictors, 17 variables emerged as significant predictors across data sets, with the top five being (a) pornography use frequency, (b) emotional avoidance pornography use motivation, (c) stress reduction pornography use motivation, (d) moral incongruence toward pornography use, and (e) sexual shame. This study is the largest and most integrative data analytic effort in the field to date. Findings contribute to a better understanding of PPU's etiology and may provide deeper insights for developing more efficient, cost-effective, empirically based directions for future research as well as prevention and intervention programs targeting PPU. General Scientific Summary: This study suggests that the top five predictors of problematic pornography use (PPU) were frequency of use, emotional avoidance pornography use motivation, stress reduction pornography use motivation, moral incongruence, and sexual shame. These findings provide empirically based key insights to develop effective, scientifically driven prevention and intervention programs for PPU that are currently absent from the literature and health care systems. [ABSTRACT FROM AUTHOR]

Typical Pulmonary Carcinoid (TPC) is defined by its slow growth, frequently necessitating surgical intervention. Despite this, the long-term outcomes following tumor resection are not well understood. This study examined the factors impacting Overall Survival (OS) in patients with TPC, leveraging data from the Surveillance, Epidemiology, and End Results database spanning from 2000 to 2018. We employed Lasso-Cox analysis to identify prognostic features and developed various models using Random Forest, XGBoost, and Cox regression algorithms. Subsequently, we assessed model performance using metrics such as Area Under the Curve (AUC), calibration plot, Brier score, and Decision Curve Analysis (DCA). Among the 2687 patients, we identified five clinical features significantly affecting OS. Notably, the Random Forest model exhibited strong performance, achieving 5- and 7-year AUC values of 0.744/0.757 in the training set and 0.715/0.740 in the validation set, respectively, outperforming other models. Additionally, we developed a web-based platform aimed at facilitating easy access to the model. This study presents a machine learning model and a web-based support system for healthcare professionals, assisting in personalized treatment decisions for patients with TPC post-tumor resection. [ABSTRACT FROM AUTHOR]

(1) Background: Artificial intelligence using machine learning techniques may help us to predict and prevent obesity. The aim was to design an interpretable prediction algorithm for overweight/obesity risk based on a combination of different machine learning techniques. (2) Methods: 38 variables related to sociodemographic, lifestyle, and health aspects from 1179 residents in Madrid were collected and used to train predictive models. Accuracy, precision, and recall metrics were tested and compared between nine classical machine learning techniques and the predictive model based on a combination of those classical machine learning techniques. Statistical validation was performed. The shapely additive explanation technique was used to identify the variables with the greatest impact on weight gain. (3) Results: Cascade classifier model combining gradient boosting, random forest, and logistic regression models showed the best predictive results for overweight/obesity compared to all machine learning techniques tested, reaching an accuracy of 79%, precision of 84%, and recall of 89% for predictions for weight gain. Age, sex, academic level, profession, smoking habits, wine consumption, and Mediterranean diet adherence had the highest impact on predicting obesity. (4) Conclusions: A combination of machine learning techniques showed a significant improvement in accuracy to predict risk of overweight/obesity than machine learning techniques separately. [ABSTRACT FROM AUTHOR]

This study introduces an innovative scheme for classifying uncrewed aerial vehicle (UAV)-derived vehicle trajectory behaviors by employing machine learning (ML) techniques to transform original trajectories into various sequences: space–time, speed–time, and azimuth–time. These transformed sequences were subjected to normalization for uniform data analysis, facilitating the classification of trajectories into six distinct categories through the application of three ML classifiers: random forest, time series forest (TSF), and canonical time series characteristics. Testing was performed across three different intersections to reveal an accuracy exceeding 90%, underlining the superior performance of integrating azimuth–time and speed–time sequences over conventional space–time sequences for analyzing trajectory behaviors. This research highlights the TSF classifier's robustness when incorporating speed data, demonstrating its efficiency in feature extraction and reliability in intricate trajectory pattern handling. This study's results indicate that integrating direction and speed information significantly enhances predictive accuracy and model robustness. This comprehensive approach, which leverages UAV-derived trajectories and advanced ML techniques, represents a significant step forward in understanding vehicle trajectory behaviors, aligning with the goals of enhancing traffic control and management strategies for better urban mobility. [ABSTRACT FROM AUTHOR]

Correlation between burglary crime and urban environmental characteristics is crucial for understanding the causes of crime events. Mathematical relationships can be linked between crime and crime‐causing events with the help of the machine learning (ML) model and geographic information system (GIS). The main objective of this research is to analyze and predict burglary crime events by applying ML‐based GIS models for Trabzon and Turkey. Random forest regression (RFR) and support vector regression (SVR) were implemented to predict crime. Correlation between crime and urban physical environmental metrics was used in the prediction model. Due to the result of the analysis, the R2 value was measured as 0.78 with the RFR and 0.71 with the SVR algorithm. The height of the building, the proportion of floor area, the density of buildings, and the density of intersection of streets are the four most important variables that affect the burglary crime rate positively. Conversely, the variable with the lowest effect on burglary crime is the ratio of the park to the residential area. [ABSTRACT FROM AUTHOR]

Integrating renewable energy sources (RESs), such as offshore wind turbines (OWTs), into the power grid demands advanced control strategies to enhance efficiency and stability. Consequently, a Deep Fractional-order Wind turbine eXpert control system (DeepFWX) model is developed, representing a hybrid proportional/integral (PI) fractional-order (FO) model predictive random forest alternating current (AC) bus voltage controller designed explicitly for OWTs. DeepFWX aims to address the challenges associated with offshore wind energy systems, focusing on achieving the smooth tracking and state estimation of the AC bus voltage. Extensive comparative analyses were performed against other state-of-the-art intelligent models to assess the effectiveness of DeepFWX. Key performance indicators (KPIs) such as MAE, MAPE, RMSE, RMSPE, and R2 were considered. Superior performance across all the evaluated metrics was demonstrated by DeepFWX, as it achieved MAE of [15.03, 0.58], MAPE of [0.09, 0.14], RMSE of [70.39, 5.64], RMSPE of [0.34, 0.85], as well as the R2 of [0.99, 0.99] for the systems states [X1, X2]. The proposed hybrid approach anticipates the capabilities of FO modeling, predictive control, and random forest intelligent algorithms to achieve the precise control of AC bus voltage, thereby enhancing the overall stability and performance of OWTs in the evolving sector of renewable energy integration. [ABSTRACT FROM AUTHOR]

One key aspect of the human experience is our ongoing stream of thoughts. These thoughts can be broadly categorized into various dimensions, which are associated with different impacts on mood, well-being, and productivity. While the past literature has often identified eye movements associated with a specific thought dimension (task-relatedness) during experimental tasks, few studies have determined if these various thought dimensions can be classified by oculomotor activity during naturalistic tasks. Employing thought sampling, eye tracking, and machine learning, we assessed the classification of nine thought dimensions (task-relatedness, freely moving, stickiness, goal-directedness, internal–external orientation, self-orientation, others orientation, visual modality, and auditory modality) across seven multi-day recordings of seven participants during self-selected computer tasks. Our analyses were based on a total of 1715 thought probes across 63 h of recordings. Automated binary-class classification of the thought dimensions was based on statistical features extracted from eye movement measures, including fixation and saccades. These features all served as input into a random forest (RF) classifier, which was then improved with particle swarm optimization (PSO)-based selection of the best subset of features for classifier performance. The mean Matthews correlation coefficient (MCC) values from the PSO-based RF classifier across the thought dimensions ranged from 0.25 to 0.54, indicating above-chance level performance in all nine thought dimensions across participants and improved performance compared to the RF classifier without feature selection. Our findings highlight the potential of machine learning approaches combined with eye movement measures for the real-time prediction of naturalistic ongoing thoughts, particularly in ecologically valid contexts. [ABSTRACT FROM AUTHOR]

Objective: This study used machine learning methods to analyze data on treatment outcomes from individuals with anorexia nervosa admitted to a specialized eating disorders treatment program. Methods: Of 368 individuals with anorexia nervosa (209 adolescents and 159 adults), 160 individuals had data available for a 6‐month follow‐up analysis. Participants were treated in a 6‐day‐per‐week partial‐hospital program. Participants were assessed for eating disorder‐specific and non‐specific psychopathology. The analyses used established machine learning procedures combined in an ensemble model from support vector machine learning, random forest prediction, and the elastic net regularized regression with an exploration (training; 75%) and confirmation (test; 25%) split of the data. Results: The models predicting body mass index (BMI) at 6‐month follow‐up explained a 28.6% variance in the training set (n = 120). The model had good performance in predicting 6‐month BMI in the test dataset (n = 40), with predicted BMI significantly correlating with actual BMI (r =.51, p = 0.01). The change in BMI from admission to discharge was the most important predictor, strongly correlating with reported BMI at 6‐month follow‐up (r =.55). Behavioral variables were much less predictive of BMI outcome. Results were similar for z‐transformed BMI in the adolescent‐only group. Length of stay was most predictive of weight gain in treatment (r =.56) but did not predict longer‐term BMI. Conclusions: This study, using an agnostic ensemble machine learning approach in the largest to‐date sample of individuals with anorexia nervosa, suggests that achieving weight gain goals in treatment predicts longer‐term weight‐related outcomes. Other potential predictors, personality, mood, or eating disorder‐specific symptoms were relatively much less predictive. Public Significance: The results from this study indicate that the amount of weight gained during treatment predicts BMI 6 months after discharge from a high level of care. This suggests that patients require sufficient time in a higher level of care treatment to meet their specific weight goals and be able to maintain normal weight. [ABSTRACT FROM AUTHOR]

This paper studies the combination of random forest (RF) and classical statistical modeling. We propose two algorithms: RF cluster + ridge and RF regression + ridge, in which the RF reduces overfitting and has a good anti-noise ability. The ridge regression can effectively handle the correlated data by the ridge penalty. To test the performance of the proposed techniques, we model and track the S&P 500 index. Index tracking aims to replicate the returns of an index fund and is very popular in finance. We compare the performance of the proposed methods with those of several existing methods. The portfolio obtained by each technique is quantified using the tracking error. We find that this combination always has higher accuracy. Empirical results show that the proposed methods are qualified for index funds. Our findings shed light on the synthesis of machine learning and statistical modeling techniques and provide an effective practice of this combination. [ABSTRACT FROM AUTHOR]

Along with the rapid development of industries and the acceleration of urbanisation, the problem of air pollution is becoming more serious. Exploring the relevant factors affecting air quality and accurately predicting the air quality index are significant in improving the overall environmental quality and realising green economic development. Machine learning algorithms and statistical models have been widely used in air quality prediction and ranking assessment. In this paper, based on daily air quality data for the city of Xi'an, China, from 1 October 2022 to 30 September 2023, we construct support vector regression (SVR), gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), random forests (RF), neural network (NN) and long short-term memory (LSTM) models to analyse the influence of the air quality index for Xi'an and to conduct comparative tests. The predicted values and 95% prediction intervals of the AQI for the next 15 days for Xi'an, China, are given based on the Bootstrap-XGBoost algorithm. Further, the ordinal logit regression and ordinal probit regression models are constructed to evaluate and accurately predict the AQI ranks of the data from 1 October 2023 to 15 October 2023 for Xi'an. Finally, this paper proposes some suggestions and policy measures based on the findings of this paper. [ABSTRACT FROM AUTHOR]

One of the primary challenges in the railway industry revolves around achieving a comprehensive and insightful understanding of track conditions. The geometric parameters and stiffness of railway tracks play a crucial role in condition monitoring as well as maintenance work. Hence, this study investigated the relationship between vertical ballast stiffness and the track longitudinal level. Initially, the ballast stiffness and track longitudinal level data were acquired through a series of experimental measurements conducted on a reference test track along the Tehran–Mashhad railway line, utilizing recording cars for geometric track and stiffness recordings. Subsequently, the correlation between the track longitudinal level and ballast stiffness was surveyed using both frequency-based techniques and machine learning (ML) algorithms. The power spectrum density (PSD) as a frequency-based technique was employed, alongside ML algorithms, including linear regression, decision trees, and random forests, for correlation mining analyses. The results showed a robust and statistically significant relationship between the vertical ballast stiffness and longitudinal levels of railway tracks. Specifically, the PSD data exhibited a considerable correlation, especially within the 1–4 rad/m wave number range. Furthermore, the data analyses conducted using ML methods indicated that the values of the root mean square error (RMSE) were about 0.05, 0.07, and 0.06 for the linear regression, decision tree, and random forest algorithms, respectively, demonstrating the adequate accuracy of ML-based approaches. [ABSTRACT FROM AUTHOR]

Several machine learning (ML) techniques have demonstrated efficacy in precisely forecasting HIV risk and identifying the most eligible individuals for HIV testing in various countries. Nevertheless, there is a data gap on the utility of ML algorithms in strengthening HIV testing worldwide. This systematic review aimed to evaluate how effectively ML algorithms can enhance the efficiency and accuracy of HIV testing interventions and to identify key outcomes, successes, gaps, opportunities, and limitations in their implementation. This review was guided by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis guidelines. A comprehensive literature search was conducted via PubMed, Google Scholar, Web of Science, Science Direct, Scopus, and Gale OneFile databases. Out of the 845 identified articles, 51 studies were eligible. More than 75% of the articles included in this review were conducted in the Americas and various parts of Sub-Saharan Africa, and a few were from Europe, Asia, and Australia. The most common algorithms applied were logistic regression, deep learning, support vector machine, random forest, extreme gradient booster, decision tree, and the least absolute shrinkage selection operator model. The findings demonstrate that ML techniques exhibit higher accuracy in predicting HIV risk/testing compared to traditional approaches. Machine learning models enhance early prediction of HIV transmission, facilitate viable testing strategies to improve the efficiency of testing services, and optimize resource allocation, ultimately leading to improved HIV testing. This review points to the positive impact of ML in enhancing early prediction of HIV spread, optimizing HIV testing approaches, improving efficiency, and eventually enhancing the accuracy of HIV diagnosis. We strongly recommend the integration of ML into HIV testing programs for efficient and accurate HIV testing. [ABSTRACT FROM AUTHOR]

Analyzing electrocardiographic (ECG) signals is crucial for evaluating heart function and diagnosing cardiac pathology. Traditional methods for detecting ECG changes often rely on offline analysis or subjective visual inspection, which may overlook subtle variations, particularly in the case of artifacts. In this theoretical, proof-of-concept study, we investigated the potential of five different machine learning algorithms [random forests (RFs), gradient boosting methods (GBMs), deep neural networks (DNNs), an ensemble learning technique, as well as logistic regression] to detect subtle changes in the morphology of synthetically generated ECG beats despite artifacts. Following the generation of a synthetic ECG beat using the standardized McSharry algorithm, the baseline ECG signal was modified by changing the amplitude of different ECG components by 0.01–0.06 mV. In addition, a Gaussian jitter of 0.1–0.3 mV was overlaid to simulate artifacts. Five different machine learning algorithms were then applied to detect differences between the modified ECG beats. The highest discriminatory potency, as assessed by the discriminatory accuracy, was achieved by RFs and GBMs (accuracy of up to 1.0), whereas the least accurate results were obtained by logistic regression (accuracy approximately 10% less). In a second step, a feature importance algorithm (Boruta) was used to discriminate which signal parts were responsible for difference detection. For all comparisons, only signal components that had been modified in advance were used for discretion, demonstrating that the RF model focused on the appropriate signal elements. Our findings highlight the potential of RFs and GBMs as valuable tools for detecting subtle ECG changes despite artifacts, with implications for enhancing clinical diagnosis and monitoring. Further studies are needed to validate our findings with clinical data. [ABSTRACT FROM AUTHOR]

This study focuses on estimating the lead times of various processes in wind tower factories. Accurate estimation of these times allows for more efficient sequencing of activities, proper allocation of resources, and setting of realistic delivery dates, thus avoiding delays and bottlenecks in the production flow and improving process quality and efficiency. In addition, accurate estimation of these times contributes to a proper assessment of costs, overcoming the limitations of traditional techniques; this allows for the establishment of tighter quotations. The data used in this study were collected at wind tower manufacturing facilities in Spain and Brazil. Data preprocessing was conducted rigorously, encompassing cleaning, transformation, and feature selection processes. Following preprocessing, machine learning regression analysis was performed to estimate lead times. Nine algorithms were employed: decision trees, random forest, Ridge regression, Lasso regression, Elastic Net, support vector regression, gradient boosting, XGBoost, LightGBM, and multilayer perceptron. Additionally, the performance of two deep learning models, TabNet and NODE, designed specifically for tabular data, was evaluated. The results showed that gradient boosting-based algorithms were the most effective in predicting processing times and optimizing resource allocation. The system is designed to retrain models as new information becomes available. [ABSTRACT FROM AUTHOR]

In recent years, healthcare monitoring systems (HMS) have increasingly integrated the Internet of Medical Things (IoMT) with cloud computing, leading to challenges related to data latency and efficient processing. This paper addresses these issues by introducing a Machine Learning-based Medical Data Segmentation (ML-MDS) approach that employs a k-fold random forest technique for efficient health data classification and latency reduction in a fog-cloud environment. Our method significantly improves latency issues, enhancing the Quality of Service (QoS) in healthcare systems and demonstrating its adaptability in heterogeneous network scenarios. We specifically employ the Random Forest algorithm to mitigate the common problem of overfitting in machine learning models, ensuring broader applicability across various healthcare contexts. Additionally, by optimizing data processing in fog computing layers, we achieve a substantial reduction in overall latency between healthcare sensors and cloud servers. This improvement is evidenced through a comparative performance analysis with existing models. The proposed framework not only ensures secure and scalable management of IoMT health data but also incorporates a stochastic approach to mathematically formulate performance indicators for the HMS queuing model. This model effectively predicts system response times and assesses the computing resources required under varying workload conditions. Our simulation results show a classification accuracy of 92%, a 56% reduction in latency compared to existing models, and an overall enhancement in e-healthcare service quality. [ABSTRACT FROM AUTHOR]

This empirical investigation delves into the influence of machine learning (ML) algorithms in the realm of cross-project defect prediction, employing the AEEEEM dataset as a foundation. The primary objective is to discern the nuanced influences of various algorithms on predictive performance, with a specific focus on the F1 score metric as evaluation criterion. Four ML algorithms have been carefully assessed in this study: random forest (RF), support vector machines (SVM), k-nearest neighbors (KNN), and logistic regression (LR). The choice of these algorithms reflects their prevalence in software defect prediction literature and their diversity. Through rigorous experimentation and analysis, the investigation unveils compelling evidence affirming the superiority of RF over its counterparts. The F1 score utilized as evaluation metric, capturing the delicate balance between precision and recall, essential in defect prediction scenarios. The nuanced examination of algorithmic efficacy provides practical insights for developers and practitioners navigating the challenges of cross-project defect prediction. By leveraging the rich and diverse AEEEEM dataset, this study ensures a comprehensive exploration of algorithmic influences across varied software projects. The findings not only contribute to the academic discourse on defect prediction but also offer practical guidance for real-world application, emphasizing the pivotal role of RF as a tool in enhancing predictive accuracy and reliability. [ABSTRACT FROM AUTHOR]

Air temperature holds significant importance in microclimate and environmental health studies, playing a crucial role in weather regulation. There is a need to develop a reliable model capable of accurately capturing air temperature variations. In this study, we focused on the Amazon-Cerrado transitional forest, constructing a robust predictive model for hourly temperature fluctuations. This forest, situated approximately 50 km northwest of Sinop, Mato Grosso, Brazil, is a transitional area, making it important to investigate its climatic behavior and ecosystems. We estimated air temperature using machine learning techniques such as Random Forest, Gradient Boosting, Multilayer Perceptron, and Support Vector Regressor, aiming to evaluate the most effective models based on relevant metrics. Performance assessments were conducted during both dry and rainy seasons to verify their adaptability. The top-performing Random Forest model demonstrated Willmott and Spearman indexes above 0.97. The air relative humidity, solar radiation, and volumetric soil water content were identified as the most important features, evaluated with Willmott and Spearman indexes above 0.95 in a model with such dimensionality reduction. These results underscore the efficacy of machine learning techniques in accurately estimating air temperature. [ABSTRACT FROM AUTHOR]

Access to high-resolution historical climate data is vital for both theoretical and applied climatology. The aim of this paper is to propose a hybrid algorithm, which consists of two main steps. At the first step, using temperature lapse rate, the temperature data of ERA5, MERRA2 and CFS were downscaled. The temperature lapse rate was calculated using MODIS temperature data. Then, at the second step, the ability of machine learning algorithms was examined in generating daily 2m temperature data with spatial resolution of 1km for Iran during 1980-2021. The inputs of the machine learning algorithms include the downscaled outputs of ERA5, MERRA2 and CFS data (which were calculated at the first step), elevation, aspect and Julian day. Several machine learning algorithms were examined including multi-layered perceptron neural networks (MLPNN), Random Forest (RF), Gradient Boosting (GB), Adaptive Boosting (AB) and Cubist Regression (CB). The results indicated that the MLPNN outperforms other techniques. Also, the final temperature map was depicted for Feb and Jul and also the MLPNN output predictions were evaluated for six different climate regions in the country. Evaluation results in regional section indicated that the MLPNN best performance was in very warm region with low rainfall while its worst performance was in mountainous and cold region. [ABSTRACT FROM AUTHOR]

Electrolytic hydrogen production from water is a promising approach for obtaining clean energy. The development of efficient oxygen evolution reaction (OER) electrocatalysts is crucial for the generation of hydrogen through water electrolysis. Transition metal oxides, such as Fe, Co, and Mn, have shown potential as efficient OER electrocatalysts for water splitting. However, accurately predicting their electrocatalytic performance in complex compositional spaces remains a challenge, impeding the precise design of compositions and processes for optimal performance. Herein, a machine learning-based method is proposed for predicting the OER activity of (FeCoMn)Ox catalysts across a wide range of compositions. Physical features that are highly relevant to the OER overpotential (OP) are identified and analyzed. The random forest algorithm is successfully used to establish the relationship between composition and overpotential. The model demonstrates good accuracy in predicting the outcomes of new experiments, with a mean relative error (MRE) of 9.3%. The features based on covalent radius (RC) and the number of electrons in the outermost d orbitals (DEs) are the primary factors. Their variances (δRC and δDE) exhibit a linearly decreasing relationship with the overpotential (OP), providing direct guidance for designing OP-oriented components. This work presents an effective and innovative approach for predicting and analyzing the physical factors of transition metal oxide electrocatalysts, which can enhance the design of highly catalytic materials for electrocatalysis. [ABSTRACT FROM AUTHOR]