Classification And Regression Tree Research Articles

Passive over active: How low-cost strategies influence urban energy equity

This study delves into the energy burden on households, a crucial aspect of energy justice, influenced by urban environment factors and buildings’ passive and active designs. It evaluates the effects of passive and active design features on household energy expenditures at the census tract scale. Applying advanced Machine Learning techniques, including multiple and decision tree regressions, random forests, support vector machines, XGBoost, and Neural Networks, the research assesses the impact of various factors on the energy burden. Findings reveal that passive design elements significantly outweigh active ones in reducing energy costs at the urban scale, as confirmed by a model with a 94.8 % R2 accuracy. The insights provided are vital for policymakers, urban planners, architects, and researchers, pushing for sustainable urban planning and energy justice by prioritizing effective design strategies. This contributes to a broader understanding and implementation of energy-efficient measures in urban development.

Deciphering nitrogen concentrations in Metasequoia glyptostroboides: a novel approach using RGB images and machine learning

Recent advances in spectral sensing techniques and machine learning (ML) methods have enabled the estimation of plant physiochemical traits. Nitrogen (N) is a primary limiting factor for terrestrial forest growth, but traditional methods for N determination are labor-intensive, time-consuming, and destructive. In this study, we present a rapid, non-destructive method to predict leaf N concentration (LNC) in Metasequoia glyptostroboides plantations under N and phosphorus (P) fertilization using ML techniques and unmanned aerial vehicle (UAV)- based RGB (red, green, blue) images. Nine spectral vegetation indices (VIs) were extracted from the RGB images. The spectral reflectance and VIs were used as input features to construct models for estimating LNC based on support vector machine, random forest (RF), and multiple linear regression, gradient boosting regression and classification and regression trees (CART). The results show that RF is the best fitting model for estimating LNC with a coefficient of determination (R2) of 0.73. Using this model, we evaluated the effects of N and P treatments on LNC and found a significant increase with N and a decrease with P. Height, diameter at breast height (DBH), and crown width of all M. glyptostroboides were analyzed by Pearson correlation with the predicted LNC. DBH was significantly correlated with LNC under N treatment. Our results highlight the potential of combining UAV RGB images with an ML algorithm as an efficient, scalable, and cost-effective method for LNC quantification. Future research can extend this approach to different tree species and different plant traits, paving the way for large-scale, time-efficient plant growth monitoring.

Data-Driven Entrepreneurship in Green Hydrogen Economy: An Integrated Framework for Entrepreneurial Enterprises in the Era of Big Data

In the era of big data, in order to improve the aggregation effect of start-ups, a digital framework with a promoting role has been formed. This paper proposes a data-driven approach in the context of the green hydrogen economy. Firstly, the data function was used to collect, classify and sort out the entrepreneurial data to form an orderly data set. Then, with the help of data-driven functions, the nonlinear reorganization of start-ups is carried out to verify their discreteness, the correlation between the hydrogen economy and start-up data is mined, and an integrated framework is formed through iterative calculation. The results show that there is a significant correlation between the hydrogen economy and start-ups, and big data can drive the integrated development of start-ups, and the data-driven method proposed in this paper can accurately identify start-up data, with a recognition rate of 90%, which is better than the previous machine learning methods and decision tree methods, and has strong big data mining capabilities. Therefore, there is a significant correlation between the hydrogen economy, big data, and start-ups, and a data-driven approach can identify the relationship between the two and facilitate the construction of an integrated framework.

Classification and Regression Trees to Predict for Survival for Patients With Hepatocellular Carcinoma Treated With Atezolizumab and Bevacizumab.

Systemic therapy with atezolizumab and bevacizumab can extend life for patients with advanced hepatocellular carcinoma (HCC). However, there is substantial variability in response to therapy and overall survival. Although current prognostic models have been validated in HCC, they primarily consider covariates that may be reflective of the severity of the underlying liver disease of patients with HCC. We developed and internally validated a classification and regression tree (CART) to identify patient characteristics associated with risks of early mortality, at or before 6 months from treatment initiation. This retrospective cohort study used the nationwide Flatiron Health electronic health record-derived deidentified database and included patients with a diagnosis of HCC after January 1, 2020, who received initial systemic therapy with atezolizumab and bevacizumab. CART was developed from available baseline clinical and demographic information to predict mortality within 6 months from treatment initiation. Model characteristics were compared to the albumin-bilirubin (ALBI) model and was further validated against a contemporary validation cohort of patients after a data update. A total of 293 patients were analyzed. The CART identified seven cohorts of patients from baseline demographic and laboratory characteristics. The model had an area under the receiver operating curve (AUROC) of 0.739 (95% CI, 0.683 to 0.794) for predicting 6-month mortality. This model was internally valid and performed more favorably than the ALBI model, which had an AUROC of 0.608 (95% CI, 0.557 to 0.660). The model applied to the contemporary validation cohort (n = 111) had an AUROC of 0.666 (95% CI, 0.506 to 0.826). Using CART, we identified unique cohorts of patients with HCC treated with atezolizumab and bevacizumab with distinct risks of early mortality. This approach outperformed the ALBI model and used clinical and laboratory characteristics that are readily available to oncologists caring for these patients.

Spatio‐temporal analysis of snow depth and snow water equivalent in a mountainous catchment: Insights from in‐situ observations and statistical modelling

AbstractThis research, conducted in the mountainous catchment near Abant Lake in the Western Black Sea region of Türkiye, aimed to investigate the spatiotemporal variations of snow depth (SD) and snow water equivalent (SWE) throughout the snow season from December 2019 to March 2020, encompassing both accumulation and melting periods. In total, 14 snow surveys were conducted, covering 58 permanent snow measurement points (PSMP) marked with snow poles. The classification and regression tree (CART) method was employed to statistically analyse their relationships with eight variables: snow period, forest canopy, aspect, slope, elevation, slope position, plan and profile curvature. The root mean square error (RMSE) for SD and SWE was determined to be 0.15 m and 46 mm, respectively. The study findings revealed that mean SD and SWE values were higher in forest gaps compared with under‐forest and open areas. Although the snow cover disappeared earliest in under‐forest areas, the melting rate was observed to be 43% and 17% slower compared with forest gaps and open areas, respectively. Wind redistribution resulted in minimum snow accumulation on western aspects, upper slope positions and ridges, while maximum accumulation was observed on southern aspects, valleys and lower slope positions. Higher elevations (>1580 meters) experienced faster snow melting rates, leading to earlier disappearance of snow cover. PSMPs located on slopes with lower degrees (<15°) exhibited lesser accumulation and earlier snow disappearance. The CART model identified the snow period as the most significant factor in predicting SD and SWE, based on variations in snowfall and air temperature. Other significant variables included forest canopy, aspect and elevation. The study suggests that the CART method is well‐suited for modelling complex snow dynamics, providing valuable insights into spatiotemporal variations in SD and SWE in mountainous regions.

Landslide susceptibility and building exposure assessment using machine learning models and geospatial analysis techniques

Landslides are among the most dangerous hazards in Asia, posing a significant threat to human lives, infrastructure, and sustainable development. Landslide susceptibility maps provide useful insights into hazard potential but lack quantitative exposure assessments to develop targeted mitigation strategies and resource allocation. This study aims to propose an integrated approach for landslide hazards and exposure evaluation using machine learning models on the Google Earth Engine environment and geospatial analysis techniques. A geospatial database was established to predict hazards and evaluate exposure, including data on topography, geology, hydrology, climate features, land use, and building data. The landslide susceptibility map was created with advanced machine-learning algorithms, including Classification And Regression Tree (CART), Random Forest (RF), Gradient Boosting (GB), and Support Vector Machine (SVM). The ROC curve and the Wilcoxon signed-rank test were employed to evaluate the performance differences among the CART, GB, RF, and SVM models. The results indicated that the RF model demonstrated the highest performance, leading to its selection for creating a landslide susceptibility map. Landslide exposure was evaluated by overlaying the landslide susceptibility map with building data to quantify the number of affected houses by landslides across districts and communes. The analysis results identified the Cho Don district as the most exposed, with 46,237 households located in high and very high landslide susceptibility zones, followed by Ba Be district (39,631 households), Bac Kan city (37,266 households), Bach Thong district (28,495 households), Cho Moi district (28,436 households), Na Ri district (17,723 households), Ngan Son district (14,142 households), and Pac Nam district (13,034 households). These findings enable the identification of the potential consequences of landslides on infrastructure, human settlements, and livelihoods, contributing to the promotion of disaster reduction and prevention strategies.

Cropping intensity mapping in Sentinel-2 and Landsat-8/9 remote sensing data using temporal transfer of a stacked ensemble machine learning model within google earth engine

This article aimed to map Cropping Intensity Patterns (CIPs) in the southwest region of Iran using Google Earth Engine and monthly composites of Sentinel-2 and Landsat-8/9 data. To detect CIPs with high inter- and intra-class variability of crops, a heterogeneous Stack ensemble of machine learning model was developed. The model incorporated the Minimum Distance (MD) approach as a meta-classifier, combining multiple base models, including Support Vector Machines (SVM), Random Forest (RF), Classification and Regression Trees (CART), and Gradient Boosted Trees (GBT). In 2021, the Stack model was trained and evaluated using Ground Truth (GT) samples from the same year, achieving an Overall Accuracy (OA) of 94.24%. This performance surpassed the base models by about 4% in OA and was also reflected in the detection accuracies, including User’s Accuracy (UA), Producer’s Accuracy (PA), and F1-score, of the target classes. Subsequently, the trained stack model was temporally transferred to generate CIP maps for other years. The model achieved high OAs of 91.82% and 90.97% based on GT samples from 2020 and 2022, respectively. Finally, the time series of CIP maps (2019-2023) were utilized by the Cellular Automata-Markov model to forecast the map for 2024.

Amorphous stabilization of BCS II drugs using mesoporous silica

This study aimed to investigate the amorphous stabilization of BCS Class II drugs using mesoporous silica as a carrier to produce amorphous solid dispersions. Ibuprofen, fenofibrate, and budesonide were selected as model drugs to evaluate the impact of molecular weight and partition coefficient on the solid state of drug-loaded mesoporous silica (MS) particles. The model drugs were loaded into three grades of MS, SYLYSIA SY730, SYLYSIA SY430, and SYLYSIA SY350, with pore diameters of 2.5 nm, 17 nm, and 21 nm, respectively, at 1:1, 2:1, and 3:1, carrier to drug ratios, and three different loading concentrations using solvent immersion and spray drying techniques. Differential scanning calorimetry (DSC) thermograms of SY430 and SY350 samples exhibited melting point depressions indicating constricted crystallization inside the pores, whereas SY730 samples with melting points matching the pure API may be a result of surface crystallization. Powder x-ray diffraction (PXRD) diffractograms showed all crystalline samples matched the diffraction patterns of the pure API indicating no polymorphic transitions and all 3:1 ratio samples exhibited amorphous halo profiles. Response surface regression analysis and Classification and Regression Tree (CART) analysis suggest carrier to drug ratios, followed by molecular weight, have the most significant impact on the crystallinity of a drug loaded into MS particles.

IDENTIFYING IMPORTANT GENES IN OVARIAN CANCER FROM HIGH-DIMENSIONAL MICROARRAY DATA USING SIFS-CART METHOD

Ovarian cancer can be identified from microarray data using machine learning. Many studies only focus on improving the machine learning classification algorithms to achieve higher performance. The purpose of classification is not only to obtain high performance but also to seek new knowledge from the results. This research focuses on both. By using a hybrid Supervised Infinite Feature Selection (SIFS) method with Classification and Regression Tree (CART) or SIFS-CART, this research aims to predict ovarian cancer and identify potential genes for ovarian cancer cases. The data used is the OVA_ovary dataset. SIFS in the best SIFS-CART model reduced 10935 genes in the initial OVA_ovary dataset to 1000 genes. Then, CART was built with these 1000 genes. Based on the balanced accuracy (BA) metric for imbalanced microarray data, the best SIFS-CART model achieves 85.7% BA in training and 83.2% in testing. The optimal CART in the best SIFS-CART model only needs four genes from 1000 selected genes to build it. Those genes are STAR, WT1, PEG3, and ASPN. Based on studies of several pieces of literature in the medical field, it can be concluded that STAR, WT1, and PEG3 play an important role in ovarian cancer cases. However, the relationship between ASPN and ovarian cancer in more detail has not been studied by medical researchers.

Impact of the COVID-19 pandemic on suicide-related risk among college students: A cross-sectional analysis

This study aimed to investigate the factors contributing to suicide-related risks among college students during a stressful life event, specifically the COVID-19 pandemic. Employing a Classification and Regression Tree (CART) model, data from 808 college students were analyzed, revealing key interactions and predictive insights into suicide-related risk. Results indicated that preexisting depression emerged as the most significant risk factor, followed by anxiety, discrimination, stress, and younger age. These findings emphasize the importance of preventive measures targeting depression and anxiety to enhance college students’ mental health and well-being. The study’s implications extend to informing future research, practical interventions, and policy-making efforts addressing suicide-related risk among college students.

Integrative approach to pedobarography and pelvis-trunk motion for knee osteoarthritis detection and exploration of non-radiographic rehabilitation monitoring.

Osteoarthritis (OA) is a highly prevalent global musculoskeletal disorder, and knee OA (KOA) accounts for four-fifths of the cases worldwide. It is a degenerative disorder that greatly affects the quality of life. Thus, it is managed through different methods, such as weight loss, physical therapy, and knee arthroplasty. Physical therapy aims to strengthen the knee periarticular muscles to improve joint stability. Pedobarographic data and pelvis and trunk motion of 56 adults are recorded. Among them, 28 subjects were healthy, and 28 subjects were suffering from varying degrees of KOA. Age, sex, BMI, and the recorded variables are used together to identify subjects with KOA using machine learning (ML) models, namely, logistic regression, SVM, decision tree, and random forest. Surface electromyography (sEMG) signals are also recorded bilaterally from two muscles, the rectus femoris and biceps femoris caput longus, bilaterally during various activities for two healthy and six KOA subjects. Cluster analysis is then performed using the principal components obtained from time-series features, frequency features, and time-frequency features. KOA is successfully identified using the pedobarographic data and the pelvis and trunk motion with the highest accuracy and sensitivity of 89.3% and 85.7%, respectively, using a decision tree classifier. In addition, sEMG data have been successfully used to cluster healthy subjects from KOA subjects, with wavelet analysis features providing the best performance for the standing activity under different conditions. KOA is detected using gait variables not directly related to the knee, such as pedobarographic measurements and pelvis and trunk motion captured by pedobarography mats and wearable sensors, respectively. KOA subjects are also distinguished from healthy individuals through clustering analysis using sEMG data from knee periarticular muscles during walking and standing. Gait data and sEMG complement each other, aiding in KOA identification and rehabilitation monitoring. It is important because wearable sensors simplify data collection, require minimal sample preparation, and offer a non-radiographic, safe method suitable for both laboratory and real-world scenarios. The decision tree classifier, trained with stratified k-fold cross validation (SKCV) data, is observed to be the best for KOA identification using gait data.

Comparison of Algorithms and Optimal Feature Combinations for Identifying Forest Type in Subtropical Forests Using GF-2 and UAV Multispectral Images

The composition and spatial distribution of tree species are pivotal for biodiversity conservation, ecosystem productivity, and carbon sequestration. However, the accurate classification of tree species in subtropical forests remains a formidable challenge due to their complex canopy structures and dense vegetation. This study addresses these challenges within the Jiangxi Lushan National Nature Reserve by leveraging high-resolution GF-2 remote sensing imagery and UAV multispectral images collected in 2018 and 2022. We extracted spectral, texture, vegetation indices, geometric, and topographic features to devise 12 classification schemes. Utilizing an object-oriented approach, we employed three machine learning algorithms—Random Forest (RF), k-Nearest Neighbor (KNN), and Classification and Regression Tree (CART)—to identify 12 forest types in these regions. Our findings indicate that all three algorithms were effective in identifying forest type in subtropical forests, and the optimal overall accuracy (OA) was more than 72%; RF outperformed KNN and CART; S12 based on feature selection was the optimal feature combination scheme; and the combination of RF and Scheme S12 (S12) yielded the highest classification accuracy, with OA and Kappa coefficients for 2018-RF-S12 of 90.33% and 0.82 and OA and Kappa coefficients for 2022-RF-S12 of 89.59% and 0.81. This study underscores the utility of combining multiple feature types and feature selection for enhanced forest type recognition, noting that topographic features significantly improved accuracy, whereas geometric features detracted from it. Altitude emerged as the most influential characteristic, alongside significant variables such as the Normalized Difference Greenness Index (NDVI) and the mean value of reflectance in the blue band of the GF-2 image (Mean_B). Species such as Masson pine, shrub, and moso bamboo were accurately classified, with the optimal F1-Scores surpassing 89.50%. Notably, a shift from single-species to mixed-species stands was observed over the study period, enhancing ecological diversity and stability. These results highlight the effectiveness of GF-2 imagery for refined, large-scale forest-type identification and dynamic diversity monitoring in complex subtropical forests.

Expression of CD163 and major histocompatibility complex class I as diagnostic markers for idiopathic inflammatory myopathies

BackgroundTo develop an inflammation-related immunohistochemistry marker-based algorithm that confers higher diagnostic ability for idiopathic inflammatory myopathies (IIMs) than IIM-related histopathologic features.MethodsMuscle biopsy tissues from 129 IIM patients who met the 2017 EULAR/ACR criteria and 73 control tissues from patients with non-inflammatory myopathies or healthy muscle specimens were evaluated for histological features and immunostaining results of CD3, CD4, CD8, CD20, CD68, CD163, MX1, MHC class I, MHC class II, and HLA-DR. Diagnostic algorithms for IIM were developed based on the results of the classification and regression tree (CART) analysis, which used immunostaining results as predictor variables for classifying patients with IIMs.ResultsIn the analysis set (IIM, n = 129; control, n = 73), IIM-related histopathologic features had a diagnostic accuracy of 87.6% (sensitivity 80.6%; specificity 100.0%) for IIMs. Notably, muscular expression of CD163 (99.2% vs. 20.8%, p < 0.001) and MHC class I (87.6% vs. 23.1%, p < 0.001) was significantly higher in the IIM group than in controls. Based on the CART analysis results, we developed an algorithm combining CD163 and MHC class I expression that conferred a diagnostic accuracy of 95.5% (sensitivity 96.1%; specificity 94.5%). In addition, our algorithm was able to correctly diagnose IIM in 94.1% (16/17) of patients who did not meet the 2017 EUALR/ACR criteria but were diagnosed as having IIMs by an expert physician.ConclusionsCombination of CD163 and MHC class I muscular expression may be useful in diagnosing IIMs.

Predicting grout’s uniaxial compressive strength (UCS) for fully grouted rock bolting system by applying ensemble machine learning techniques

This study proposes a novel system for accurately predicting grout’s uniaxial compressive strength (UCS) in fully grouted rock bolting systems. To achieve this, a database comprising 73 UCS values with varying water-to-grout (W/G) ratios ranging from 22 to 42%, curing times from 1 to 28 days, the admixture of fly ash contents ranging from 0 to 30%, and two Australian commercial grouts, Stratabinder HS, and BU-100, was built after conducting comprehensive series of experimental tests. After building the dataset, a metaheuristic technique, the jellyfish search (JS) algorithm was employed to determine the weight of base models in the ensemble system. This system combined various data and modelling techniques to enhance the accuracy of the UCS predictions. What sets this technique apart is the comprehensive database and the innovative use of the JS algorithm to create a weighted averaging ensemble model, going beyond traditional methods for predicting grout strength. The proposed ensemble model was called the weighted averaging ensemble model (WAE-JS), in which the obtained results of several soft computing models such as multi-layer perceptron (MLP), Bayesian regularized (BR) neural networks, generalized feed-forward (GFF) neural networks, classification and regression tree (CART), and random forest (RF) were weighted based on JS and the new results were then generated. Eventually, the result of WAE-JS was compared to other models, including MLP, BR, GFF, CART, and RF, based on some statistical parameters, such as R-squared coefficients, RMSE, and VAF as indices for evaluating the performance and capability of the proposed model. The results suggested the superiority of the ensemble WAE-JS system over the base models. In addition, the proposed WAE-JS model effectively improved the predicting accuracy achieved from the MLP, BR, GFF, CART, and RF. Furthermore, the sensitivity analysis revealed that the W/G had the most significant impact on the grout’s UCS values.

The association between potential predictors and death of patients during the COVID-19 pandemic in Shiraz: a hierarchical multiple regression analysis

IntroductionIdentifying clinical factors that increase the risk of mortality in COVID-19 patients is crucial. This enables targeted screening, optimizing treatment, and prevention of severe complications, ultimately reducing death rates. This study aimed to develop prediction models for the death of patients (i.e., survival or death) during the COVID-19 pandemic in Shiraz, exploring the main influencing factors.MethodWe conducted a retrospective cohort study using hospital-based records of 1030 individuals diagnosed with COVID-19, who were hospitalized for treatment between March 21, 2021, and March 21, 2022, in Shiraz, Iran. Variables related to the final outcome were selected based on criteria and univariate logistic regression. Hierarchical multiple logistic regression and classification and regression tree (CART) models were utilized to explore the relationships between potential influencing factors and the final outcome. Additionally, methods were employed to identify the high-risk population for increased mortality rates during COVID-19. Finally, accuracy was evaluated the performance of the models, with the area under the receiver operator characteristic curve(AUC), sensitivity, and specificity metrics.ResultsIn this study, 558 (54.2%) individuals infected with COVID-19 died. The final model showed that the type of medicine antiviral (OR: 11.10, p = 0.038) than reference (antiviral and corticosteroid), and discharge oxygen saturation(O2) (OR: 1.10, p < 0.001) had a positive association with the chance of survival, but other variables were not considered as predictive variables. Predictive models for the final outcome(death) achieved accuracies ranging from 81 to 87% for hierarchical multiple logistic regression and from 87 to 94% for the CART model. Therefore, the CART model performed better than the hirerical multiple logistic regression model.ConclusionThese findings firstly elucidate the incidence and associated factors of the outcome (death) among patients in Shiraz, Iran. Furthermore, we demonstrated that antiviral medication alone (without corticosteroids) and high O2 increase the survival chances of COVID patients.

Outcome risk model development for heterogeneity of treatment effect analyses: a comparison of non-parametric machine learning methods and semi-parametric statistical methods

BackgroundIn randomized clinical trials, treatment effects may vary, and this possibility is referred to as heterogeneity of treatment effect (HTE). One way to quantify HTE is to partition participants into subgroups based on individual’s risk of experiencing an outcome, then measuring treatment effect by subgroup. Given the limited availability of externally validated outcome risk prediction models, internal models (created using the same dataset in which heterogeneity of treatment analyses also will be performed) are commonly developed for subgroup identification. We aim to compare different methods for generating internally developed outcome risk prediction models for subject partitioning in HTE analysis.MethodsThree approaches were selected for generating subgroups for the 2,441 participants from the United States enrolled in the ASPirin in Reducing Events in the Elderly (ASPREE) randomized controlled trial. An extant proportional hazards-based outcomes predictive risk model developed on the overall ASPREE cohort of 19,114 participants was identified and was used to partition United States’ participants by risk of experiencing a composite outcome of death, dementia, or persistent physical disability. Next, two supervised non-parametric machine learning outcome classifiers, decision trees and random forests, were used to develop multivariable risk prediction models and partition participants into subgroups with varied risks of experiencing the composite outcome. Then, we assessed how the partitioning from the proportional hazard model compared to those generated by the machine learning models in an HTE analysis of the 5-year absolute risk reduction (ARR) and hazard ratio for aspirin vs. placebo in each subgroup. Cochran’s Q test was used to detect if ARR varied significantly by subgroup.ResultsThe proportional hazard model was used to generate 5 subgroups using the quintiles of the estimated risk scores; the decision tree model was used to generate 6 subgroups (6 automatically determined tree leaves); and the random forest model was used to generate 5 subgroups using the quintiles of the prediction probability as risk scores. Using the semi-parametric proportional hazards model, the ARR at 5 years was 15.1% (95% CI 4.0–26.3%) for participants with the highest 20% of predicted risk. Using the random forest model, the ARR at 5 years was 13.7% (95% CI 3.1–24.4%) for participants with the highest 20% of predicted risk. The highest outcome risk group in the decision tree model also exhibited a risk reduction, but the confidence interval was wider (5-year ARR = 17.0%, 95% CI= -5.4–39.4%). Cochran’s Q test indicated ARR varied significantly only by subgroups created using the proportional hazards model. The hazard ratio for aspirin vs. placebo therapy did not significantly vary by subgroup in any of the models. The highest risk groups for the proportional hazards model and random forest model contained 230 participants each, while the highest risk group in the decision tree model contained 41 participants.ConclusionsThe choice of technique for internally developed models for outcome risk subgroups influences HTE analyses. The rationale for the use of a particular subgroup determination model in HTE analyses needs to be explicitly defined based on desired levels of explainability (with features importance), uncertainty of prediction, chances of overfitting, and assumptions regarding the underlying data structure. Replication of these analyses using data from other mid-size clinical trials may help to establish guidance for selecting an outcomes risk prediction modelling technique for HTE analyses.

Performance Comparison of CART And KNN Algorithms for Analyzing Early Predictions of Mental Health

Currently, mental health is an unresolved mental health problem both at the national and international levels. Mental health disorders are conditions where a person has difficulty in adjusting to the conditions around them. Mental Health is an important aspect of overall health. Efforts to maintain and improve it can help a person achieve better well-being in everyday life. This research aims to conduct Early Prediction Analysis related to mental health problems experienced by students by measuring the accuracy level of the analysis. This research was conducted using the CART (Classification and Regression Trees) and KNN (K-Nearest Neighbor) algorithms with a set of Mental Health Datasets consisting of 11 attributes and 101 data. The data is processed using the Weka Application and the accuracy results of each algorithm are obtained, amounting to 94.0594% for the CART Algorithm and 91.0891% for the KNN Algorithm. From this achievement, it can be concluded that the performance of the CART and KNN algorithms falls into the Excellent Classification category. Judging from the accuracy obtained, the CART algorithm has a higher accuracy value than the KNN algorithm, so the CART algorithm has a high performance for analyzing early prediction of mental health of students who do not take steps in seeking mental health support.

Modeling Proboscis monkey conservation sites on Borneo using ensemble machine learning

This study aimed to analyze the habitat suitability of the endangered Proboscis monkey (Nasalis larvatus) on Borneo using a multi-machine-learning approach. This study integrated physical, vegetational, meteorological, and human activity data to develop a comprehensive habitat suitability model. Four machine-learning algorithms, namely, maximum entropy (MaxEnt), random forest (RF), support vector machine (SVM), gradient tree boosting (GTB), and classification and regression trees (CART), were employed to model the habitat suitability index. A total of 1943 sample points were divided into training (70 %) and validation (30 %) sets for the analysis. This study included three main stages: geospatial database creation, spatial habitat modeling using multi-machine-learning algorithms, and habitat suitability evaluation. In addition, the pressure from human development on the habitat suitability index model was analyzed. This study identified a high level of suitability for Proboscis monkey habitats in nearshore areas. The maximum habitat suitability for Proboscis monkeys was observed to be 11.54 %, as evidenced by the consensus of the MaxEnt value and four machine-learning algorithms. Conversely, the minimum habitat suitability was recorded at 13.27 %, as indicated by disagreement among all algorithms. The AUC values for the machine-learning models ranged from 74 % to 90 %, indicating moderate to high predictive performance. This study provides valuable insights for the formulation of well-planned development programs for Proboscis monkeys. The results of this study will contribute to the accurate identification of potential Proboscis monkey habitats, thereby providing support for conservation efforts aimed at safeguarding this endangered species.

What factors preventing the older adults in China from living longer: a machine learning study

BackgroundThe fact that most older people do not live long means that they do not have more time to pursue self-actualization and contribute value to society. Although there are many studies on the longevity of the elderly, the limitations of traditional statistics lack the good ability to study together the important influencing factors and build a simple and effective prediction model.MethodsBased on the the data of Chinese Longitudinal Healthy Longevity Survey (CLHLS), 2008–2018 cohort and 2014–2018 cohort were selected and 16 features were filtered and integrated. Five machine learning algorithms, Elastic-Net Regression (ENR), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), and eXtreme Gradient Boosting (XGBoost), were used to develop models and assessed by internal validation with CLHLS 2008–2018 cohort and temporal validation with CLHLS 2014–2018 cohort. Besides, the best performing model was explained and according to the variable importance results, simpler models would be developed.ResultsThe results showed that the model developed by XGBoost algorithm had the best performance with AUC of 0.788 in internal validation and 0.806 in temporal validation. Instrumental activity of daily living (IADL), leisure activity, marital status, sex, activity of daily living (ADL), cognitive function, overall plant-based diet index (PDI) and psychological resilience, 8 features were more important in the model. Finally, with these 8 features simpler models were developed, it was found that the model performance did not decrease in both internal and temporal validation.ConclusionsThe study indicated that the importance of these 8 factors for predicting the death of elderly people in China and built a simple machine learning model with good predictive performance. It can inspire future key research directions to promote longevity of the elderly, as well as in practical life to make the elderly healthy longevity, or timely end-of-life care for the elderly, and can use predictive model to aid decision-making.

Rice Phenology Classification Model Based on Sentinel-1 Using Machine Learning Method on Google Earth Engine

Rice phenology information is important in supporting planning systems, land management, and making the right decisions to sustainably carry out rice production. This study aimed to determine the best rice phenology classification model by combining VV and VH polarizations on Sentinel-1 images, which produce polarization indices such as the ratio polarization index (RPI), normalized different polarization index (NDPI), and average polarization index (API) using the ensemble random forest (RF) using the Google Earth Engine (GEE) application. This research was conducted in the rice fields of PT Sang Hyang Seri, Subang Regency, West Java. The research data comprised Sentinel-1 SAR GRD satellite imagery data with acquisition modes interferometric wide swath (IW) for 2021–2022 obtained from the GEE platform. In this study, the performance of two machine learning methods for classification was compared: classification and regression trees (CART) and RF. This study found that the best rice phase classification model could be acquired from the RF method with four predictors, namely, API, RPI, NDPI, and slope, with a statistical value of kappa of 98.22%. The RF classification model has better accuracy than the CART classification model.