Search

In ordinal classification problems, the class value exhibits a natural order. Usually, these problems are solved as multiclass classification problems while discarding the ordering form of the class. Recently, several research studies have proposed novel methods for ordinal classification problems while aiming to predict a predefined objective value. These methods are based on modification of the splitting criteria of decision tree-based algorithms. These methods consider the ordinal nature of the data and the magnitude of the potential classification error from a predefined predicted objective. This research aims to consolidate these methods and generalize them for any decision tree-based method while constructing decision trees according to any predefined objective value calculated from the training dataset. Furthermore, to evaluate the proposed method, a comprehensive experimental study is performed based on known ordinal datasets. The proposed method is found to significantly outperform its counterpart nonordinal models. This observation confirms that ordering information benefits ordinal methods and improves their performance. Additionally, the ordinal decision tree-based methods achieved competitive performance compared to state-of-the-art ordinal techniques. The results are validated with various performance measures that are commonly used for ordinal and non-ordinal classification problems. [ABSTRACT FROM AUTHOR]

Traditional landslide susceptibility assessment methods often rely on single models, which can be biased and less accurate. In this article, we introduce a two-tiered strategy to enhance landslide susceptibility predictions. Initially, we employ an ensemble stacking technique that combines the strengths of three machine learning classifiers. This combination leverages the support vector classifier (SVC) as the key meta-classifier to optimize and refine predictions. Subsequently, we integrate the extreme gradient boosting (XGB), random forest (RF) and gradient boosting decision tree (GBDT) models with SVC to create hybrid approaches. In this study, we evaluate and compare the effectiveness of six machine learning algorithms for predicting landslide susceptibility in Anhua County, Hunan Province, China. The results demonstrated that the stacking ensemble model outperforms traditional models. The XBGþSVC model achieves the highest AUC value (0.9468), which is followed by the GBDTþSVC (0.9316), RFþSVC (0.9162), XGB (0.9393), GBDT (0.9009), and RF (0.8693). These findings indicate that stacking machine learning approaches hold promise for landslide susceptibility mapping. [ABSTRACT FROM AUTHOR]

Detecting building rooftops with very high-resolution (VHR) images is an important issue in many fields, including disaster management, urban planning, and climate change research. Buildings with varying geometrical features are challenging to detect accurately from VHR image due to complicated image scenes containing spectrally similar objects, illumination, occlusions, viewing angles, and shadows. This study aims to detect building rooftops with high accuracy using a new framework that includes VHR image, visible band difference vegetation index, digital surface and elevation models, the terrain ruggedness and the topographic position index. Five distinct feature sets were generated in order of importance by exposing the ten related stacking features to a feature selection procedure using the maximum relevance minimum redundancy method. Then, Auto-Encoder, k-NN, decision tree, RUSBoost, and random forest machine learning algorithms were utilized for binary classification. Random forest yielded the highest accuracy (97.2% F-score, 98.72% accuracy) when all features (F10) were used, while decision tree was the least successful (59.16% F-score, 83.56% accuracy) for RGB feature set (FRGB). It was revealed that classification of F10 with random forest increased F-score by about 23% compared to classification with FRGB. Additionally, McNemar's tests showed no statistically significant difference between random forest vs k-NN and decision tree vs RUSBoost. [ABSTRACT FROM AUTHOR]

This article shows that decision trees constructed with Classification and Regression Trees (CART) and C4.5 methodology are consistent for regression and classification tasks, even when the number of predictor variables grows sub-exponentially with the sample size, under natural 0-norm and 1-norm sparsity constraints. The theory applies to a wide range of models, including (ordinary or logistic) additive regression models with component functions that are continuous, of bounded variation, or, more generally, Borel measurable. Consistency holds for arbitrary joint distributions of the predictor variables, thereby accommodating continuous, discrete, and/or dependent data. Finally, we show that these qualitative properties of individual trees are inherited by Breiman's random forests. A key step in the analysis is the establishment of an oracle inequality, which allows for a precise characterization of the goodness of fit and complexity tradeoff for a mis-specified model. for this article are available online. [ABSTRACT FROM AUTHOR]

Heart disease is one of the most dangerous diseases in the world. People with these diseases, most of them end up losing their lives. Therefore, machine learning algorithms have proven to be useful in this sense to help decision-making and prediction from the large amount of data generated by the healthcare sector. In this work, we have proposed a novel method that allows increasing the performance of the classical random forest technique so that this technique can be used for the prediction of heart disease with its better performance. We used in this study other classifiers such as classical random forest, support vector machine, decision tree, Naïve Bayes, and XGBoost. This work was done in the heart dataset Cleveland. According to the experimental results, the accuracy of the proposed model is better than that of other classifiers with 83.5%.This study contributed to the optimization of the random forest technique as well as gave solid knowledge of the formation of this technique. [ABSTRACT FROM AUTHOR]

In this paper, we develop a new dataset on indirect state rivalry relations based on different matrix calculations for 154 countries, over the period 1970-2015, and demonstrate their importance in explaining civil wars. After controlling for spatial distances between rival countries, we demonstrate that 1) the presence of direct and indirect rivals exerts a positive and significant effect on the risk of civil war; 2) decreasing levels of military capacity of one state relative to its rivals (direct and indirect) also influence the probability of internal conflict. Finally, we confirm the significance of our indicators by using on the one hand the random forest algorithm, a machine learning method using decision trees and on the other hand, the Kaplan-Meier estimate for the duration of the civil wars. [ABSTRACT FROM AUTHOR]

The rapid expansion of technical infrastructure has brought about transformative changes in business operations. A notable consequence of this digital evolution is the proliferation of subscription-based services. With an increasing array of options for goods and services, customer churn has emerged as a significant challenge, posing a threat to businesses across sectors. The direct impact on earnings has prompted businesses to proactively develop tools for predicting potential client turnover. Identifying the underlying factors contributing to churn is crucial for implementing effective retention strategies. Our research makes a pivotal contribution by presenting a churn prediction model designed to assist businesses in identifying clients at risk of churn. The proposed model leverages machine learning classification techniques, with the customer data undergoing thorough pre-processing phases prior to model application. We systematically evaluated ten classification techniques, including Logistic Regression, Support Vector Classifier, Kernel SVM, KNN, Gaussian Naïve Bayes, Decision Tree Classifier, Random Forest, ADA Boost, XGBoost, and Gradient Boost. The assessment encompassed various evaluation metrics, such as ROC AUC Mean, ROC AUC STD, Accuracy Mean, Accuracy STD, Accuracy, Precision, Recall, F1 Score, and F2 Score. Employing 10-fold cross-validation and hyper parameter tuning through GridSearchCV and RandomizedSearchCV, we identified Random Forest as the most effective classifier, achieving an 85% Area Under the Curve (AUC) for optimal results. [ABSTRACT FROM AUTHOR]

The introduction of smart meters, sensors and integrated electronic devices in the electrical secondary distribution network (ESDN) has led to the collection of massive amounts of data. Accurate prediction of faults from this data can help to improve the reliability, safety and operational efficiency of ESDN. Due to its complexity, ESDN big data are hard to process and manage using traditional technologies and tools. The difficulties posed by dataset complexity arise from issues including high dimensionality, imbalance and variability, and one current challenge is to address them simultaneously. Currently, the capability of fault prediction techniques to address this challenge remains limited. New approaches are needed to overcome it. To this purpose, this article presents a big data-based ensemble for fault prediction in ESDN (BDEFP-ESDN) on Apache Spark with gradient-boosted trees, random forest, decision tree and binomial logistic regression base models. BDEFP-ESDN is optimized for the complexity of the ESDN dataset by dimension reduction, bootstrap sampling and hyperparameter optimization approaches in the training process and a weighted voting approach in the prediction process. Our experimental results illustrate the efficiency of BDEFP-ESDN against traditional classifiers like ANN, SVM, RF and XGB, achieving an accuracy of 99.6% for both binary and multiclass classification. [ABSTRACT FROM AUTHOR]

In recent years, the solitary reasons for mortality in the world are chronic diseases such as heart disease, diabetes, and chronic kidney disease. These diseases should be diagnosed earlier; however, the technique is costly as well as it leads to many complications. Considering the complexity, datamining performs a major part in accurately classifying chronic disease. A new approach to classify chronic disease is by merging the multi-objective firefly optimisation algorithm (MOFFA) and random forest (RF). The main goal is generating an efficient and heterogeneous decision trees, while determining the optimum training sets to run at the same time. Rather utilising traditional approach like bootstrap, multi-objective firefly optimisation algorithm and random forest algorithm are proposed in this method. As a result, to train random forest, various training sets are generated with alternative instances and attributes. As a result, the performance of random forests can be improved and thus the prediction accuracy. The effectiveness of the proposed method is explored by juxtaposing the effectiveness of the proposed method with other classifiers for different datasets. The proposed work is tested on six UCI datasets. According to the findings, the proposed MOFFA-RF algorithm surpass other classifiers by the accuracy of 88% on CKD, 87% on CVD, 82% on diabetes, 88% on hepatitis, 88% on WBC, and 76% on ILPD. [ABSTRACT FROM AUTHOR]

Land cover classification (LCC) refers to the task of classifying each pixel in satellite/aerial imagery by predicting a label carrying information about its nature. Despite the importance of having transparent, symbolic decision models, in the recent literature, LCC has been mainly approached with black-box functional models, that are able to leverage the spatial dimensions within the data. In this article, we argue that standard symbolic decision models can be extended to perform a form of spatial reasoning that is adequate for LCC. We propose a generalization of a classical decision tree learning model, based on replacing propositional logic with a modal spatial logic, and provide a CART-like learning algorithm for it. We evaluate its performance at five different LCC tasks, showing that this technique leads to classification models whose performances are superior to those of their propositional counterpart, and at least comparable with those of non-symbolic ones. Ultimately, we show that spatial decision trees and random forests are able to extract complex, but interpretable spatial patterns. [ABSTRACT FROM AUTHOR]

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder, often associated with social and communication challenges and whose prevalence has increased significantly over the past two decades. The variety of different manifestations of ASD makes the condition difficult to diagnose, especially in the case of highly independent adults. A large body of work is dedicated to developing new and improved diagnostic techniques, emphasising approaches that rely on objective markers. One such paradigm is investigating eye-tracking data as a promising and objective method to capture attention-related differences between people with and without autism. This study builds upon prior work in this area that focussed on developing a machine-learning classifier trained on gaze data from web-related tasks to detect ASD in adults. Using the same data, we show that a new data pre-processing approach, combined with an exploration of the performance of different classification algorithms, leads to an increased classification accuracy compared to prior work. The proposed approach to data pre-processing is stimulus-independent, suggesting that the improvements in performance shown in these experiments can potentially generalise over other studies that use eye-tracking data for predictive purposes. [ABSTRACT FROM AUTHOR]

Tree ensembles can be interpreted as implicit kernel generators, where the ensuing proximity matrix represents the data-driven tree ensemble kernel. Focus of our work is the utility of tree based ensembles as kernel generators that (in conjunction with a regularized linear model) enable kernel learning. We elucidate the performance of the tree based random forest (RF) and gradient boosted tree (GBT) kernels in a comprehensive simulation study comprising of continuous and binary targets. We show that for continuous targets (regression), this kernel learning approach is competitive to the respective tree ensemble in higher dimensional scenarios, particularly in cases with larger number of noisy features. For the binary target (classification), the tree ensemble based kernels and their respective ensembles exhibit comparable performance.We provide the results fromseveral real life datasets for regression and classification relevant for biopharmaceutical and biomedical applications, that are in line with the simulations to show how these insights may be leveraged in practice. We discuss general applicability and extensions of the tree ensemble based kernels for survival targets and interpretable landmarking in classification and regression. Finally, we outline future research for kernel learning due to feature space partitionings. [ABSTRACT FROM AUTHOR]

Wearable devices equipped with a multitude of compact, lightweight, biometric sensors are helpful in tracking the real-time physiological data for healthcare-related analysis. However, a survey of devices under the smart-wearable market segment revealed that the contemporary focus is limited to capturing and displaying some of the biometrics like pulse rate, movement of the user, calorie counter, etc. on a smart screen. Employing machine learning techniques can be particularly helpful in analyzing the trends of user-specific biometric data for pre-emptive actions. This paper presents a meaningful analysis in real-time by using machine learning approaches to interpret this physiological data and alert the user about his behavioral pattern through IoT. This research focuses on classifying the mood of the user as agitated or non-agitated, by analyzing the biometrics to help the user decipher meaningful conclusions and take suitable pre-emptive measures to refrain from any unintentional impulsive outburst. Machine learning algorithms like Polynomial regression with threshold, Decision Tree, Random Forest ensemble and variants of Deep Neural Networks (DNN) have been employed to analyse the biometric patterns from the experimental data acquired under different circumstances and detect the user's mood to assign a score to the user. The proposed approach uses a reinforcement learning algorithm to calibrate the user's current temperament by taking intermediate user feedback and comparing the score with the temperament. The results reveal that the proposed system detects the user's mood fluctuations with higher accuracy and relevance compared to any contemporary model. [ABSTRACT FROM AUTHOR]

We present a Bayesian nonparametric model for conditional distribution estimation using Bayesian additive regression trees (BART). The generative model we use is based on rejection sampling from a base model. Like other BART models, our model is flexible, has a default prior specification, and is computationally convenient. To address the distinguished role of the response in our BART model, we introduce an approach to targeted smoothing of BART models which is of independent interest. We study the proposed model theoretically and provide sufficient conditions for the posterior distribution to concentrate at close to the minimax optimal rate adaptively over smoothness classes in the high-dimensional regime in which many predictors are irrelevant. To fit our model, we propose a data augmentation algorithm which allows for existing BART samplers to be extended with minimal effort. We illustrate the performance of our methodology on simulated data and use it to study the relationship between education and body mass index using data from the medical expenditure panel survey (MEPS). for this article are available online. [ABSTRACT FROM AUTHOR]

Mapping and monitoring the distribution of croplands and crop types support policymakers and international organizations by reducing the risks to food security, notably from climate change and, for that purpose, remote sensing is routinely used. However, identifying specific crop types, cropland, and cropping patterns using space-based observations is challenging because different crop types and cropping patterns have similarity spectral signatures. This study applied a methodology to identify cropland and specific crop types, including tobacco, wheat, barley, and gram, as well as the following cropping patterns: wheat-tobacco, wheat-gram, wheat-barley, and wheat-maize, which are common in Gujranwala District, Pakistan, the study region. The methodology consists of combining optical remote sensing images from Sentinel-2 and Landsat-8 with Machine Learning (ML) methods, namely a Decision Tree Classifier (DTC) and a Random Forest (RF) algorithm. The best time-periods for differentiating cropland from other land cover types were identified, and then Sentinel-2 and Landsat 8 NDVI-based time-series were linked to phenological parameters to determine the different crop types and cropping patterns over the study region using their temporal indices and ML algorithms. The methodology was subsequently evaluated using Landsat images, crop statistical data for 2020 and 2021, and field data on cropping patterns. The results highlight the high level of accuracy of the methodological approach presented using Sentinel-2 and Landsat-8 images, together with ML techniques, for mapping not only the distribution of cropland, but also crop types and cropping patterns when validated at the county level. These results reveal that this methodology has benefits for monitoring and evaluating food security in Pakistan, adding to the evidence base of other studies on the use of remote sensing to identify crop types and cropping patterns in other countries. [ABSTRACT FROM AUTHOR]

Malware is the term used to describe any malicious software or code that is harmful to systems. From day to day, new malicious programs appear. To classify malware according to its characteristics, machine learning is now being used; this is because most new malware contains patterns that are similar to old ones. This paper proposes two feature selection methods based on Genetic Programming (GP) for predicting malware; the first is called Genetic Programming-Mean (GPM), and the second is called Genetic Programming-Mean Plus (GPMP). The results of these two methods were compared with three state-of-the-art popular feature selection techniques: filter-based, wrapper-based, and Chi-square. In this work, we compare the two proposed methods (GPM and GPMP) with these three widely used feature selection techniques. The results demonstrate that the proposed techniques beat these state-of-the-art ones in terms of accuracy and F-score. The results also revealed that the proposed methods employed less computation time and hence an enhanced performance when compared with filter-based, and wrapper-based feature selection. The proposed methods were evaluated using four datasets. Two classifiers were used to evaluate the proposed feature selection methods: Random Forest and Decision Tree. When a Random Forest classifier is used, our results showed that it outperformed the Decision Tree classifier in indicators, such as F1-score, recall, and precision. The analysis of results using Random Forest and Decision Tree proves that the proposed method is highly efficient. [ABSTRACT FROM AUTHOR]

The Billboard chart is a clear barometer for measuring a song's success in the music industry. Therefore, a number of artists and affiliated marketers in the music industry have attempted to determine how to emerge at the top of the chart. In the current study, artist-fan interactions on social media are examined as one of the possible indicators to predict the success of songs on the Billboard Hot 100 chart. The performance of a song on the Billboard chart was predicted based on the artist-fan interaction using the artist-fan dataset composed of posts, comments, and quote tweets, their sentimental levels, and the interaction styles of each post. Overall, the XGBoost model with the quote-tweet interaction data exhibited the highest classification performance (F1-score: 80.75% on Top 1 label), showing that the interaction features extracted from quote-tweets show the strongest relevance to a song's success. We present a simplified approach for observing and understanding public perception for the entertainment industry, specifically for the music industry, through social media interactions. We also suggest the facilitation of artist-fan interactions on social media with similar functions of quote-tweet function on Twitter as a valid strategy to make songs more successful. [ABSTRACT FROM AUTHOR]

It is still a challenging task to objectively evaluate the fabric smoothness appearance due to the complexity and variety of fabrics. Innovative methods that can accurately quantify the surface smoothness in a practical and repeatable way are desideratum. To address this challenge, we put forward a new mechanical testing method, that is, mechanical test system for fabric shape retention (MTS-FSR). The design details and testing principle of the MTS-FSR were presented. The measured force-displacement curves were fitted and eight characteristic indices related to fabric wrinkling were determined and interpreted by their physical meanings. The repeatability and accuracy of the system were studied to verify the reliability of the method. Moreover, a prediction model for fabric smoothness appearance was established based on decision tree algorithm that was proved superior to other common used learning algorithms (e.g. support vector machine (SVM), random forest (RF) and Back-Propagation neural network (BPNN)) based on comparison analysis. The experimental results show that the designed instrument provides a feasible and effective measurement method for the objective evaluation of fabric smoothness appearance with good accuracy and resolution. [ABSTRACT FROM AUTHOR]

This study uses five machine learning algorithms (Stochastic gradient descent (SGD), Decision tree, Random forest, Gradient boosting decision tree (GBDT), and Convolutional neural networks (CNN)) to explore their prediction effects on China's stock market. It constructs a monthly rolling model for stock return prediction. Selecting stocks of the CSI 300 index from January to June 2021 as specific monthly samples and classifying three factors – fundamentals, volatility(risk) and technical indicators, the results demonstrate that (1) machine learning brings favorable investment returns in simulated quantitative trading of China's A-share market (2) the technical indicator factor is the most valuable, with the momentum technical factor having greatest influence, followed by the volatility (risk) factor and fundamental factors. Therefore, this study has a critical reference value and is significant in guiding yield forecasting in intricate stock markets. [ABSTRACT FROM AUTHOR]

To effectively explore the impacts of several key factors on taxi drivers' traffic violations and provide traffic management departments with scientific decisions to reduce traffic fatalities and injuries. 43,458 electronic enforcement data about taxi drivers' traffic violations in Nanchang City, Jiangxi Province, China, from July 1, 2020, to June 30, 2021, were utilized to explore the characteristics of traffic violations. A random forest algorithm was used to predict the severity of taxi drivers' traffic violations and 11 factors affecting traffic violations, including time, road conditions, environment, and taxi companies were analyzed using the Shapley Additionality Explanation (SHAP) framework. Firstly, the ensemble method Balanced Bagging Classifier (BBC) was applied to balance the dataset. The results showed that the imbalance ratio (IR) of the original imbalanced dataset reduced from 6.61% to 2.60%. Moreover, a prediction model for the severity of taxi drivers' traffic violations was established by using the Random Forest, and the results showed that accuracy, m_F1, m_G-mean, m_AUC, and m_AP obtained 0.877, 0.849, 0.599, 0.976, and 0.957, respectively. Compared with the algorithms of Decision Tree, XG Boost, Ada Boost, and Neural Network, the performance measures of the prediction model based on Random Forest were the best. Finally, the SHAP framework was used to improve the interpretability of the model and identify important factors affecting taxi drivers' traffic violations. The results showed that functional districts, location of the violation, and road grade were found to have a high impact on the probability of traffic violations; their mean SHAP values were 0.39, 0.36, and 0.26, respectively. Findings of this paper may help to discover the relationship between the influencing factors and the severity of traffic violations, and provide a theoretical basis for reducing the traffic violations of taxi drivers and improving the road safety management. [ABSTRACT FROM AUTHOR]

Approximately one-third of the veteran population suffers from post-traumatic stress disorder, a mental illness that is often co-morbid with social anxiety disorder. Student veterans are especially vulnerable as they struggle to adapt to a new, less structured lifestyle with few peers who understand their difficulties. To support mental health experts in the treatment of social anxiety disorder, this study utilized machine learning to detect anxiety in text transcribed from interviews with patients and applied topic modeling to highlight common stress factors for student veterans. We approach our anxiety detection task by exploring both deep learning and traditional machine learning strategies such as transformers, transfer learning, and support vector classifiers. Our models provide a tool to support psychologists and social workers in treating social anxiety. The results detailed in this paper could also have broader impacts in fields such as pedagogy and public health.1 [ABSTRACT FROM AUTHOR]

In this letter, a novel method for change detection is proposed using neighbourhood structure correlation. Because structure features are insensitive to the intensity differences between bi-temporal images, we perform the correlation analysis on structure features rather than intensity information. First, we extract the structure feature maps by using multi-orientated gradient information. Then, the structure feature maps are used to obtain the Neighbourhood Structural Correlation Image (NSCI), which can represent the context structure information. In addition, we introduce a measure named matching error, which can be used to improve neighbourhood information. Subsequently, a change detection model based on the random forest is constructed. The NSCI features and matching error (ME) are together used as the model inputs for training and prediction. Finally, the decision tree voting is used to produce the change detection result. To evaluate the performance of the proposed method, it is compared with three state-of-the-art change detection methods. The experimental results on two datasets demonstrate the effectiveness and robustness of the proposed method. [ABSTRACT FROM AUTHOR]

Emergency response decision-making for maritime accidents needs to consider the possible consequences and scenarios of an accident to develop an effective emergency response strategy to reduce the severity of the accident. This paper proposes a novel machine learning-based methodology for predicting accident scenarios and analysing its factors to assist emergency response decision-making from an emergency rescue perspective. Specifically, the accident data used are collected from maritime accident investigation reports, and then two types of decision tree (DT) algorithms, classification and regression tree (CART) and random forest (RF), are used to develop scenario prediction models for three accident consequences including ship damage, casualty, and environmental damage. The hyper-parameters of these two DT algorithms are optimized using two state-of-the-art optimization algorithms, namely random search (RS) and Bayesian optimization (BO), respectively, aiming to obtain the prediction model with the highest accuracy. Experimental results reveal that BO-RF algorithm produces the best accuracy as compared to others. In addition, an analysis of feature importance shows that the number of people involved in an accident is the most important driving factor affecting the final accident scenario. Finally, decision rules are generated from the obtained optimal prediction model, which can provide decision support for emergency response decisions. [ABSTRACT FROM AUTHOR]

The Karakoram Highway (KKH) is a pivotal gateway within the framework of the China-Pakistan Economic Corridor. Nevertheless, its distinct and intricate geographical characteristics make it susceptible to recurrent landslides. As an essential tool, landslide susceptibility mapping (LSM) is significant in managing and alleviating landslides near the KKH. Moreover, landslide conditioning factors (LCFs) are crucial determinants influencing the outcomes of LSM. However, existing methods primarily rely on machine learning algorithms, which do not adequately account for the intricate spatial characteristics and patterns between LCFs and landslide occurrences. In response, this study introduces the feature fusion transformer (FFTR) module, constructed based on the foundations of the transformer framework, to fuse the spatial information features of all LCFs. Subsequently, the abstract high-level spatial features obtained are fed into diverse machine learning classifiers, including random forest (RF), extreme gradient boosting (XGBoost), gradient boosting decision trees (GBDT), categorical boosting (CatBoost), and extremely randomized trees (ET), to generate landslide susceptibility maps. Displacement velocity calculated by Persistent Scatterer Interferometric Synthetic Aperture Radar (PSInSAR) is incorporated in the LSM. The results demonstrate that FFTR-RF achieves premium performance in the area under the curve (AUC) (94%), accuracy (87.31%), precision (87.21%), recall (88.02%), and F1-score (87.61%). Incorporating displacement velocity into LSM results predicted by models enhances the comprehensiveness of LSM. These methods will furnish early warning systems for landslide disasters along the KKH, thus aiding recommendations for mitigating landslides' social and economic losses. [ABSTRACT FROM AUTHOR]

Our aim was to explore the possibility of using machine learning (ML) in predicting the onset and trajectories of depressive symptom in home-based older adults over a 7-year period. Depressive symptom data (collected in the year 2011, 2013, 2015 and 2018) of home-based older Chinese (n = 2650) recruited in the China Health and Retirement Longitudinal Study (CHARLS) were included in the current analysis. The latent class growth modeling (LCGM) and growth mixture modeling (GMM) were used to classify different trajectory classes. Based on the identified trajectory patterns, three ML classification algorithms (i.e. gradient boosting decision tree, support vector machine and random forest) were evaluated with a 10-fold cross-validation procedure and a metric of the area under the receiver operating characteristic curve (AUC). Four trajectories were identified for the depressive symptoms: no symptoms (63.9%), depressive symptoms onset {incident increasing symptoms [new-onset increasing (16.8%)], chronic symptoms [slowly decreasing (12.5%), persistent high (6.8%)]}. Among the analyzed baseline variables, the 10-item Center for Epidemiologic Studies Depression Scale (CESD-10) score, cognition, sleep time, self-reported memory were the top five important predictors across all trajectories. The mean AUCs of the three predictive models had a range from 0.661 to 0.892. ML techniques can be robust in predicting depressive symptom onset and trajectories over a 7-year period with easily accessible sociodemographic and health information. Supplemental data for this article is available online at http://dx.doi.org/10.1080/13607863.2022.2031868 [ABSTRACT FROM AUTHOR]

The past landslides from landslide inventory are essential for machine learning (ML)-based landslide susceptibility assessment (LSA). They determine not only the positive samples (characterized by the past landslides) but also the negative samples (randomly generated based on past landslides) for training and validating the ML models. However, the number of past landslides is often limited because of the constraints of time, budget, and resources available, etc. In other words, the available data for establishing landslide susceptibility ML models are limited, which indicates that the accuracy and reliability of the corresponding models are insufficient. This article, therefore, proposes using a new landslide susceptibility index-based sampling strategy to enhance the positive and negative samples for model training and validation to reach an improved ML-based LSA. To realize this idea, landslide susceptibility analysis based on initial datasets compiled from landslide inventory by using three ML models, i.e., random forest (RF), gradient boosting decision tree (GBDT) and support vector machine (SVM), are first conducted to obtain the initial landslide susceptibility indices at different space locations. Then, the landslide susceptibility indices are analyzed with the proposed sampling strategy which considers directly the grid units with very high and very low landslide susceptibility indices as potential positive and negative samples, respectively, to enrich the initial dataset; and the number of these positive/negative samples is determined by a Bayesian optimization algorithm. Thereafter, the ML models are updated with the enriched datasets. Finally, to verify the effectiveness of the proposed strategy, the improved models are applied to assess the landslide susceptibility of Taojiang County, China, and the results are compared with those from initial corresponding models without updating. The results show that compared with the initial RF, GBDT and SVM models, the corresponding improved models have a better performance in accuracy, precision, recall rate, and specificity. In particular, the AUC values of the three models are increased by 11.94%, 10.72% and 0.57%, respectively. [ABSTRACT FROM AUTHOR]

Dengue Fever (DF) is a common vector-borne disease with catastrophic health implications. DF prediction modelling is a challenging task, although technologies such as Geographical Information Systems (GIS) and spatial statistics have improved our understanding of dengue dynamics. In this paper, we create a robust data analysis model to (i) provide a better understanding of confirmed dengue fever cases despite missing data, (ii) obtain better insights into risk factors associated with confirmed cases, and (iii) by means of machine learning, create clusters of patients with comparable characteristics. The last was accomplished with a self-organizing feature map (SOFM) and the densitybased spatial clustering of applications with noise (DBSCAN). The approaches used to classify confirmed cases were: Decision Tree, k-nearest neighbours, Random Forest, AdaBoost, Support Vector Classification (SVC), CatBoost, and Naive Bayes. The CatBoost classifier achieved the best accuracy for the analysis of confirmed cases. Spatial analysis was conducted using the ordinary least square (OLS) and geographically weighted regression (GWR) models to identify high-risk areas. SOM can group patients with similar features into clusters, then DBSCAN detects and retrieves six clusters from this data. The clustering of confirmed cases increases CatBoost’s modelling prediction accuracy and reveals complex factors that influence prediction accuracy. Because confirmed cases in each cluster have different features, CatBoost is applied to each cluster individually to improve the prediction accuracy. Variable values in each cluster are analysed to clarify the confirmed cases of a specific subset of DF incidents. Overall, OLS outperforms GWR when identifying hotspot areas. The proposed novel, data-driven and machine-learningbased strategy facilitates the understanding and identification of patterns associated with confirmed DF cases. The study’s findings can be utilized to cluster historical patient data into groups or subgroups sharing similar variables. Using identifiable patient clusters rather than raw history data improves the model accuracy provided by CatBoost. [ABSTRACT FROM AUTHOR]

A stroke is a medical disorder in which blood arteries in the brain rupture, causing brain damage. Symptoms may appear when the brain's blood supply and other nutrients are cut off. According to the World Health Organization, Stroke is the leading cause of death and disability globally. Early recognition of the multiple warning signs of a stroke helps reduce the severity of the stroke. The paper presents a modified version of the Genetic Folding algorithm to predict stroke based on symptoms. Considerable Machine Learning models, including Logistic Regression, Decision Tree, Random Forest, Naïve Bayes, Support Vector Machine, and the proposed Minimal Genetic Folding, were compared to forecast the probability of having a stroke in the brain using a variety of physiological characteristics. The proposed minimal Genetic Folding approach has been developed using the open-access Stroke Prediction dataset using minimal kernel operators. The datasets generated and/or analyzed during the current study are available in the Kaggle repository. With an accuracy of 83.2%, the proposed minimal Genetic Folding approach outperformed Logistic Regression by 4.2%, Naïve Bayes by 1.2%, Decision Tree by 17.2%, and Support Vector Machine by 83.2%. The area under the curve of the proposed model is much more significant than earlier research by 7%, demonstrating that this model is more dependable and was the top-performing algorithm. [ABSTRACT FROM AUTHOR]

High-entropy alloys (HEAs) can have superior properties due to the intermetallic (IM) or solid solution (SS) phase formation. In this work, machine learning (ML) based models have been implemented to categorise and estimate the phase prediction in HEAs with the objective of appreciably enhancing the model accuracy. Various features, VEC, δr, Δχ, λ, Ω, ΔS, ΔH, and Tmelt, are considered. With correlation matrix, enthalpy is observed to be the least significant feature. These datasets were used as inputs to four various ML algorithms, where all these models were optimised by hyper parameter tuning. The Algorithms implemented are: Support Vector Machine (SVM), Logistic Regression, Decision Tree, Random Forest, Artificial Neural Network (ANN) and Gradient Boosting algorithm. Gradient Boosting has demonstrated the best performance of more than 90% accuracy for the given data. It is established that Gradient Boosting predictions are found to be in good match with experimental data. [ABSTRACT FROM AUTHOR]

Smartphones with embedded Global Positioning System (GPS) technology provide an opportunity to passively collect individuals' travel trajectory data, which can be utilized to identify critical aspects of travel behavior such as transport modes. This paper presents a mode detection algorithm developed to infer modes from smartphone GPS data. The algorithm is designed to classify single-mode trip segments into one of six modes. There are 31 features selected for the algorithm, which are divided into two categories: general features and transit-specific features. General features are needed to classify all available modes. Transit-specific features representing proximity to the nearest transit lines enhance the classification of the three transit modes. Four tree-based ensemble learning models are evaluated: Random Forest (RF), Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). The results show that LightGBM performs the best in terms of detection accuracy and computation time. [ABSTRACT FROM AUTHOR]

In this paper, we use the Eurozone yield curve in an effort to forecast the deviations of the euro-area output (IPI) from its long-run trend. We use various short- and long-term interest rates spanning the period from 2004:9 to 2020:6 in monthly frequency. The interest rates are fed to three machine learning methodologies: Decision Trees, Random Forests, and Support Vector Machines (SVM). These Machine Learning methodologies are then compared to an Elastic-Net Logistic Regression (Logit) model from the area of Econometrics. According to the results, the optimal SVM model coupled with the RBF kernel outperforms the competition reaching an in-sample accuracy of 85.29% and an out-of-sample accuracy of 94.74%. [ABSTRACT FROM AUTHOR]

This article presents direct regression models for forecasting photovoltaic (PV) system output power based on machine learning (ML) methods, in which the Cleanness Index (CI) was introduced as an indicator of the PV panel soiling level. Three different ML methods based on decision trees were used: random forests (RF), extra trees (ET) and gradient boosting (GB). The research results showed that the introduction of the CI has significant potential to improve the forecasting of tree-based ML models. The mean average error of forecasts of the best model, which contained CI, and the model created by excluding CI from the set of input variables were 0.22% and 1.24%, respectively, as related to the nominal power of the PV panel. For the observed models, it was shown that the CI is the second-most important input variable and more significant than the PV panel temperature. [ABSTRACT FROM AUTHOR]

Wrong-way driving (WWD) crashes result in more fatalities per crash, involve more vehicles, and cause extended road closures compared to other types of crashes. Previous studies have used descriptive and parametric statistical models to identify factors that affect WWD crash severity on limited access facilities. This study adopted a combination of non-parametric data mining techniques aiming to recognize the pattern of contributing factors that affect the WWD crash severity on non-limited access facilities. These non-parametric methods can handle heterogeneity in crash datasets well. In this study, hierarchical clustering was used to divide the crash dataset into homogeneous clusters. A random forests analysis was used to select important variables, and decision trees and decision rules were generated to show the underlying pattern and interactions between different factors that affect WWD crash severity. The analysis was based on 1,475 WWD crashes that occurred on arterial streets from 2012-2016 in Florida. Results show that head-on collisions, weekend days, high-speed facilities, crashes involving vehicles entering from a driveway, dark-not lighted roadways, older drivers, and driver impairment are important factors that play a crucial role in WWD crash severity on non-limited access facilities. [ABSTRACT FROM AUTHOR]

This study aims to assess the potential of multi-temporal Sentinel-1 and RADARSAT-2 data for pearl millet discrimination using various classifiers—machine learning and knowledge-based decision tree (m-DT and k-DT), Support Vector Machine (SVM), and Random Forest (RF). Results show that the RF classifier outperformed the other classifiers in terms of overall accuracy (OA) and kappa coefficient. The highest Overall Accuracy (OA) of 89.1% and kappa coefficients of 0.822 and 0.814 were achieved by the RF classifier for both the Sentinel-1 and RADARSAT-2 data, respectively. The Variable Importance (VI) of the RF classifier revealed that the polarimetric parameters—volume scattering, double bounce, entropy and alpha angle were crucial for pearl millet discrimination. Polarimetric parameters, when ingested with the RF machine learning classifier, achieved better classification accuracies. [ABSTRACT FROM AUTHOR]

This paper proposes an ensemble learning model that deploys a Gradient Boosting Decision Tree (GBDT) to predict two relevant functional indices, the International roughness index (IRI) and the rut depth (RD), considering multiple influence factors. To train and validate the proposed models, more than 1600 different records were extracted from Long-Term Pavement Performance database. The most suitable hyper parameters for the GBDT model are determined through a grid search and 5-fold cross-validation. Then, a sensitivity analysis is performed to determine the final input variables among the initial considered factors. Further, the optimized models utilise SHAP (Shapley Additive explanation) to interpret the results and analyse the importance of influencing factors. Finally, a comparison experiment with reference artificial intelligence approaches demonstrates that, the GBDT model can outperform the artificial neural network (ANN) and the random forest regression (RFR) methods in terms of quality of prediction results, reaching a coefficient of determination (R2) equal to 0.9. The proposed model can provide more precise pavement performance values and may be useful for providing accurate reference for pavement maintenance and optimising the available budget for road administrations. [ABSTRACT FROM AUTHOR]

Flash flooding is a type of global devastating hydrometeorological disaster that seriously threatens people's property and physical safety, as well as the normal operation of water conservancy facilities, such as reservoirs, so an accurate assessment of reservoir risk for certain areas is necessary. Therefore, the purpose of this study was to propose a novel methodological approach for reservoir risk modelling based on the feature selection method (FSM) and tree-based ensemble methods (Bagging and Random Forest [RF]). The results showed that: (1) the J48-GA based ensemble models achieved higher learning and predictive capabilities compared to conventional ensemble models without the FSM. (2) For the classification accuracy, the J48-GA-RF (96.4%) outperformed RF (96.0%), J48-GA-Bagging (93.9%) and Bagging (93.5%). And the J48-GA-RF achieved the highest prediction AUC value (0.995), an almost perfect Kappa indexes value (0.926) and the best practicality value (30.88%). (3) In particular, the results indicated that all of the models showed high performance, both in training and in the validation of a dataset. Additionally, this study could provide a reference for disaster managers, hydraulic engineers and policy makers to implement location-specific flash flood risk reduction strategies. [ABSTRACT FROM AUTHOR]

Neuropsychiatric disorders in brain tumor patients are commonly observed. It is difficult to anticipate these disorders in different types of brain tumors. The goal of the study was to see how well machine learning (ML)-based decision algorithms might predict neuropsychiatric problems in different types of brain tumors. 145 histopathologically-confirmed primary brain tumors of both gender aged 25–65 years of age, were included for neuropsychiatric assessments. The datasets of brain tumor patients were employed for building the models. Four different decision ML classification trees/models (J48, Random Forest, Random Tree & Hoeffding Tree) with supervised learning were trained, tested, and validated on class labeled data of brain tumor patients. The models were compared in order to determine the best accurate classifier in predicting neuropsychiatric problems in various brain tumors. Following categorical attributes as independent variables (predictors) were included from the data of brain tumor patients: age, gender, depression, dementia, and brain tumor types. With the machine learning decision tree/model techniques, a multi-target classification was performed with classes of neuropsychiatric diseases that were predicted from the selected attributes. 86 percent of patients were depressed, and 55 percent were suffering from dementia. Anger was the most often reported neuropsychiatric condition in brain tumor patients (92.41%), followed by sleep disorders (83%), apathy (80%), and mood swings (76.55%). When compared to other tumor types, glioblastoma patients had a higher rate of depression (20%) and dementia (20.25%). The developed models Random Forest and Random Tree were found successful with an accuracy of up to 94% (10-folds) for the prediction of neuropsychiatric disorders in brain tumor patients. The multiclass target (neuropsychiatric ailments) accuracies were having good measures of precision (0.9–1.0), recall (0.9–1.0), F-measure (0.9–1.0), and ROC area (0.9–1.0) in decision models. Random Forest Trees can be used to accurately predict neuropsychiatric illnesses. Based on the model output, the ML-decision trees will aid the physician in pre-diagnosing the mental issue and deciding on the best therapeutic approach to avoid subsequent neuropsychiatric issues in brain tumor patients. [ABSTRACT FROM AUTHOR]

The routine maintenance and rehabilitation of road pavement is vital to keep up with the service level and bearing capacity. However, the current problem is that, with the continuous increase of the scale of maintenance data, the traditional decision-making cannot satisfy the requirements in terms of accuracy and efficiency. The objectives of this paper were to improve the accuracy and efficiency of the maintenance decisions, overcome the decision error caused by insufficient human experience, and develop the mapping process for decision plans. This paper presented a decision-making method for asphalt pavement maintenance using improved weight random forest algorithm (IWRF) based on the correlation analysis (CA) and the analytic hierarchy process (AHP). Firstly, appropriate features were selected through CA of road detection data, and then decision trees were constructed based on Bootstrapping. Finally, qualified decision trees were chosen and weighted by AHP to form a random forest. To examine the feasibility, the algorithm was applied in a maintenance decision of the 80 km highway in Jiangsu province. The results showed that IWRF had a decision-making accuracy of up to 90%. Comparing with the traditional random forest algorithm, the IWRF algorithm had a 4.35% higher accuracy and saved 75% computation time. [ABSTRACT FROM AUTHOR]

The present study compared the performance of logistic regression models with that of machine learning classification models (classification trees and random forests) in the context of predicting training attrition from the Delayed Enlistment Program in the United States Marine Corps (USMC) with scores from the Tailored Adaptive Personality Assessment System (TAPAS). Performance was assessed according to the type of misclassification error and across a variety of different reasons for attrition. The base rate of attrition was low, which impeded the training process, but the machine learning models outperformed logistic regression in predicting voluntary attrition in a stratified 50% attrition sample. [ABSTRACT FROM AUTHOR]

Urban landmarks play an important role as spatial references in spatial cognition, navigation, map design and urban planning. However, the current landmark extraction methods do not consider the imbalance between the landmark and non-landmarknon-landmark samples in a dataset, so the extraction results are biased toward the class with the majority of sample data, resulting in poor classification performance for the class with the fewest sample data. This study introduces a random forest (RF) classifier combined with cost-sensitive learning to extract urban landmarks automatically from a basic spatial database. First, the optimal feature set is determined according to the importance of features. Next, a cost-sensitive RF algorithm is applied to extract landmarks, which determines the misclassification cost according to the class distribution, and each decision tree is weighted by the classification results. The method has good performance, with a recall and area under the ROC curve (AUC) greater than 90%, and the model is also applicable to small sample sets, which can reduce the cost of manual labor. [ABSTRACT FROM AUTHOR]

Infidelity can be a disruptive event in a romantic relationship with a devastating impact on both partners' well-being. Thus, there are benefits to identifying factors that can explain or predict infidelity, but prior research has not utilized methods that would provide the relative importance of each predictor. We used a machine learning algorithm, random forest (a type of interpretable highly non-linear decision tree), to predict in-person and online infidelity across two studies (one individual and one dyadic, N = 1,295). We also used a game theoretic explanation technique, Shapley values, which allowed us to estimate the effect size of each predictor variable on infidelity. The present study showed that infidelity was somewhat predictable overall and interpersonal factors such as relationship satisfaction, love, desire, and relationship length were the most predictive of online and in person infidelity. The results suggest that addressing relationship difficulties early in the relationship may help prevent infidelity. [ABSTRACT FROM AUTHOR]

This article investigated household-level food security for Ghana, Liberia, and Senegal. Different agroclimatic, ecological, social, and farming conditions in West Africa were represented. Using data-driven Random Forest and Chi-Square Automatic Interaction Detection (CHAID) decision tree methodology, this study classified 644 Ghanaian, 323 Liberian, and 510 Senegalese households for comparison and interpretation on food security. The predictors growing Liberian and Senegalese decision trees imply community support, diverse selling channels outside villages, resolving the dispute over farmland, and increasing community-level investment for food availability and access demonstrate household food security. Predictor importance on food security for Ghana highlighted the role of independent producers and food suppliers toward stability. Household food security or insecurity was distinguished by location-specific and gender-led households in Liberia and Senegal. Practically, the results presented a need to step-up agricultural education and extension based on an empirical field survey and its interpretations. The results can add considerations to the role of farming households as independent and individual suppliers and consumers to long-standing dimensions of food security, i.e., food availability, access, and stability. [ABSTRACT FROM AUTHOR]

This study compares several advanced machine learning models to obtain the most accurate method for predicting the aeration efficiency (E20) through the Parshall flume. The required dataset is obtained from the laboratory tests using different flumes fabricated in National Institute Technology Kurukshetra, India. Besides, the potential of K Nearest Neighbor (KNN), Random Forest Regression (RFR), and Decision Tree Regression (DTR) models are evaluated to predict the aeration efficiency. In this way, several input combinations (e.g. M1-M15) are provided using the laboratory parameters (e.g. W/L, S/L, Fr, and Re). Different predictive models are obtained based on those input combinations and machine learning models proposed in the present study. The predictive models are assessed based on several performance metrics and visual indicators. Results show that the KNN-M11 model ( R M S E t e s t i n g = 0.002 , R t e s t i n g 2 = 0.929), which includes W/L, S/L, and Fr as predictive variables outperforms the other predictive models. Furthermore, an enhancement is observed in KNN model estimation accuracy compared to the previously developed empirical models. In general, the predictive model dominated in the present study provides adequate performance in predicting the aeration efficiency in the Parshall flume. [ABSTRACT FROM AUTHOR]

Cash is a very important property of an enterprise, but offers the lowest return of any asset. Nevertheless, firms do not invest all assets into higher-paying assets and hold part of their cash, especially firms in the high-tech electronics industry. Firms in this industry hold considerable amounts of cash because they have high expenses and recovery is uncertain, potentially leaving the firm without sufficient funds. It is therefore necessary to prepare a certain amount of cash. This study uses a decision tree algorithm including J48, LMT, Random Forest, REP Tree, Simple CART, Extra Tree, and BF Tree to measure the performance of predictions. This study has three experiments: (1) testing the predictive ability of the decision tree algorithm, (2) testing the decision tree algorithm with performance improvements, and (3) determining the best decision tree forecast rate comparison using the logistic regression model. The experiments indicate that the random forest has the highest and best prediction rate comparison with the logistic regression model. [ABSTRACT FROM AUTHOR]

This study compares the performance of gradient boosting decision tree (GBDT), artificial neural networks (ANNs), and random forests (RF) methods in LUC modeling in the Seoul metropolitan area. The results of this study showed that GBDT and RF have higher predictive power than ANN, indicating that tree-based ensemble methods are an effective technique for LUC prediction. Along with the outstanding predictive performance, the DT-based ensemble models provide insights for understanding which factors drive LUCs in complex urban dynamics with the relative importance and nonlinear marginal effects of predictor variables. The GBDT results indicate that distance to the existing residential site has the highest contribution to urban land use conversion (30.4% of the relative importance), while other significant predictor variables were proximity to industrial and public sites (combined 32.3% of relative importance). New residential development is likely to be adjacent to existing residential sites, but nonresidential development occurs at a distance (about 600 m) from such sites. The distance to the central business district (CBD) had increasing marginal effects on residential land use conversion, while no significant pattern was found for nonresidential land use conversion, indicating that Seoul has experienced more population suburbanization than employment decentralization. [ABSTRACT FROM AUTHOR]

Decision tree-based Rotation Forest could generate satisfactory but lower classification accuracy for a given training sample set and image data, owing to the inherent disadvantages in decision trees, namely myopic, replication and fragmentation problem. To improve performance of Rotation Forest technique, we propose to utilize two-hidden-layered-feedforward neural network as base classifier instead of decision tree. We examine the classification performance of proposed model under two situations, namely when free network parameters are maintained the same across all ensemble components and otherwise. The proposed model, where each component is initialized with different pair of initial weights and bias, performs better than decision tree-based Rotation Forest on three different Hyperspectral sensor datasets – AVIRIS, ROSIS and Hyperion. Improvements in classification accuracy are above 2% and up to 3% depending upon dataset. Also, the proposed model achieves improvement in accuracy over Random Forest in the range 4.2–8.8%. [ABSTRACT FROM AUTHOR]

A gradient boosting regression tree (GBT) approach is introduced for 1- and 3-month-ahead standardized precipitation–evapotranspiration index (SPEI) classification for Antalya and Ankara in Turkey. First, the numerical target series of SPEI-6 was converted into the categorical vectors of extreme wet, wet, near normal, dry, and extremely dry labels. Then, a GBT model was trained and validated using the lagged SPEI-6 series of four global grid points closest to each city. The model efficiency was surveyed in terms of kappa, overall accuracy, misclassification rate, class recall, class precision, and F1 score. The GBT was also compared with the traditional decision tree and state-of-the-art random forest models developed as the benchmarks. Despite facing the unbalanced label vectors, the GBT approach showed promising processing performance with an overall accuracy of 77% (83%) and 74% (72%) in Antalya (Ankara) at 1- and 3-month-ahead prediction scenarios, respectively. [ABSTRACT FROM AUTHOR]