Application Of Random Forest Research Articles

The Application of a Random Forest Classifier to ToF-SIMS Imaging Data.

Time-of-flight secondary ion mass spectrometry (ToF-SIMS) imaging is a potent analytical tool that provides spatially resolved chemical information on surfaces at the microscale. However, the hyperspectral nature of ToF-SIMS datasets can be challenging to analyze and interpret. Both supervised and unsupervised machine learning (ML) approaches are increasingly useful to help analyze ToF-SIMS data. Random Forest (RF) has emerged as a robust and powerful algorithm for processing mass spectrometry data. This machine learning approach offers several advantages, including accommodating nonlinear relationships, robustness to outliers in the data, managing the high-dimensional feature space, and mitigating the risk of overfitting. The application of RF to ToF-SIMS imaging facilitates the classification of complex chemical compositions and the identification of features contributing to these classifications. This tutorial aims to assist nonexperts in either machine learning or ToF-SIMS to apply Random Forest to complex ToF-SIMS datasets.

Exploring the Major Predictors Affecting Creativity of High School Students Using Explainable Artificial Intelligence: Application of Random Forest and SHAP

Exploring the Major Predictors Affecting Creativity of High School Students Using Explainable Artificial Intelligence: Application of Random Forest and SHAP

Machine learning and global vegetation: random forests for downscaling and gap filling

Abstract. Drought is a devastating natural disaster, during which water shortage often manifests itself in the health of vegetation. Unfortunately, it is difficult to obtain high-resolution vegetation drought impact information that is spatially and temporally consistent. While remotely sensed products can provide part of this information, they often suffer from data gaps and limitations with respect to their spatial or temporal resolution. A persistent feature among remote-sensing products is the trade-off between the spatial resolution and revisit time: high temporal resolution is met with coarse spatial resolution and vice versa. Machine learning methods have been successfully applied in a wide range of remote-sensing and hydrological studies. However, global applications to resolve drought impacts on vegetation dynamics still need to be made available, as there is significant potential for such a product to aid with improved drought impact monitoring. To this end, this study predicted global vegetation dynamics based on the enhanced vegetation index (evi) and the popular Random forest (RF) regressor algorithm at 0.1°. We assessed the applicability of RF as a gap-filling and downscaling tool to generate global evi estimates that are spatially and temporally consistent. To do this, we trained an RF regressor with 0.1° evi data, using a host of features indicative of the water and energy balances experienced by vegetation, and evaluated the performance of this new product. Next, to test whether the RF is robust in terms of spatial resolution, we downscale the global evi: the model trained on 0.1° data is used to predict evi at a 0.01° resolution. The results show that the RF can capture global evi dynamics at both a 0.1° resolution (RMSE: 0.02–0.4) and at a finer 0.01° resolution (RMSE: 0.04–0.6). Overall errors were higher in the downscaled 0.01° product compared with the 0.1° product. Nevertheless, relative increases remained small, demonstrating that RF can be used to create downscaled and temporally consistent evi products. Additional error analysis revealed that errors vary spatiotemporally, with underrepresented land cover types and periods of extreme vegetation conditions having the highest errors. Finally, this model is used to produce global, spatially continuous evi products at both a 0.1 and 0.01° spatial resolution for 2003–2013 at an 8 d frequency.

Application of Random Forest in a Predictive Model of PM10 Particles in Mexico City

Over time, predictive models tend to become more accurate but also more complex, thus achieving better predictive accuracy. When the data is improved by increasing its quantity and availability, the models are also better, which implies that the data must be processed to filter and adapt it for initial analysis and then modeling. This work aims to apply the Random Forest model to predict PM10 particles. For this purpose, data were obtained from environmental monitoring stations in Mexico City, which operates 29 stations of which 12 belong to the State of Mexico. The pollutants analyzed were CO carbon monoxide, NO nitrogen oxide, and PM10 particulate matter equal to or less than 10 μg.m-3, NOx nitrogen oxide, NO2 nitrogen dioxide, SO2 sulfur dioxide, O3 ozone, and PM2.5 particulate matter equal to or less than 2.5 μg.m-3. The result was that when calculating the certainty of our model, we have a value of 80.40% when calculating the deviation from the mean, using 15 reference variables.

Application of Random Forest in Modeling the Prevalence of Depression among Murang’a University of Technology Students

Around the world, depression is a prevalent mental illness and it affects the way people think, feel, talk and conduct their daily activities. The associated stigma often leads to misdiagnosis, posing risks such as disability and suicide. The study employed random forest algorithm to model the prevalence of depression among Murang’a University of technology (MUT) students. A sample of 1448 students from the different schools at the university participated in the study by completing questionnaires on sociodemographic and other factors associated with depression. The questionnaires were administered through social media platforms. Participants were selected using proportionate stratified random sampling and simple random sampling to ensure that a representative sample was chosen from each school. The data gathered was examined using descriptive and inferential statistics. Depression was measured using the Patient Health Questionnaire scale (PHQ-9). Using a cut-off point of 10, 25.97% students had depressive symptoms. This comprised of 19.61% moderate symptoms and 6.35% severe symptoms. The confusion matrix criteria were used to assess the performance of random forest in modeling depression prevalence among MUT students. Metrics for random forest included, accuracy (0.9868), sensitivity (0.95), specificity (1.00), positive predictive value (1.00), and negative predictive value (0.9824). Implementing targeted interventions founded on identified risk and protective factors and exploring the long-term outcomes of these interventions would contribute to the evolving field of mental health research within academic settings.

Exploring the predictors affecting the sense of community of Korean high school students: application of random forests and SHAP.

Adolescence is a stage during which individuals develop social adaptability through meaningful interactions with others. During this period, students gradually expand their social networks outside the home, forming a sense of community. The aim of the current study was to explore the key predictors related to sense of community among Korean high school students and to develop supportive policies that enhance their sense of community. Accordingly, random forests and SHapley Additive exPlanations (SHAP) were applied to the 7th wave (11th graders) of the Korean Education Longitudinal Study 2013 data (n = 6,077). As a result, 6 predictors positively associated with sense of community were identified, including self-related variables, "multicultural acceptance," "behavioral regulation strategy," and "peer attachment," consistent with previous findings. Newly derived variables that predict sense of community include "positive recognition of volunteering," "creativity," "observance of rules" and "class attitude," which are also positively related to sense of community. The implications of these results and some suggestions for future research are also discussed.

Prediction of HR Employee Attrition with Machine Learning: Bagging and Random Forest Application.

Employee attrition, the loss of valuable employees, presents a significant challenge for human resource (HR) departments in global corporations. Despite substantial investments in attracting and hiring top talent, companies often face high turnover rates. Traditional retention strategies, such as blanket incentives offered to all employees, can be resource-intensive and may not be equally effective for everyone. This research aims to develop a more targeted employee retention strategy by leveraging machine learning (ML) algorithms. The objective is to identify employees at a high risk of leaving the organization and priorities retention efforts for this specific group.

Application of Random Forest and Support Vector Machine for Investigation of Pressure Filtration Performance, a Zinc Plant Filter Cake Modelling

Application of Random Forest and Support Vector Machine for Investigation of Pressure Filtration Performance, a Zinc Plant Filter Cake Modelling

Accurate identification of sludge contamination sources by classification-based PMF and machine learning with consideration of sewer network distribution differences

The application of source identification such as PMF for large-scale pollution source analysis frequently produces ambiguous outcomes. In this study, we utilized a classification-based method to accurately track key pollution sources in the sludge. In the study, we categorized the wastewater treatment plants into two groups: T1 and T2, according to the pipeline network. T1 sewage treatment plants are the main sewage plants in urban areas, covering a large area and connected to industrial wastewater treatment plants for secondary treatment. T2 sewage treatment plants are typically smaller in size and usually responsible for treating sewage in rural or township areas. The PMF analysis indicates that industrial pollution sources contribute 3.4 times more to T1 sludge than to T2 sludge, making industrial pollution the primary factor causing the disparity. The application of Random Forest and Adaboost based on pollutant concentrations for classification and fitting of sludge resulted in the identification of the main pollutants: Zn, Cu, Ni, and Cyanide, which align with characteristic pollutants from the electroplating industry. The GIS analysis shows a significant correlation between the distance of wastewater treatment plants with abnormal environmental risk and electroplating industrial parks, all within a 20 km radius. Indeed, when conducting large-scale pollution source identification studies, utilizing classification-based analysis can effectively improve the accuracy of pollution source identification, leading to more valuable analysis results.

Development of Flood-Hazard-Mapping Model Using Random Forest and Frequency Ratio in Sumedang Regency, West Java, Indonesia

Flooding, often triggered by heavy rainfall, is a common natural disaster in Indonesia, and is the third most common type of disaster in Sumedang Regency. Hence, flood-susceptibility mapping is essential for flood management. The primary challenge in this lies in the complex, non-linear relationships between indices and risk levels. To address this, the application of random forest (RF) and frequency ratio (FR) methods has been explored. Ten flood-conditioning factors were determined from the references: the distance from a river, elevation, geology, geomorphology, lithology, land use/land cover, rainfall, slope, soil type, and topographic wetness index (TWI). The 35 flood locations from the flood-inventory map were selected, and the remaining 18 flood locations were used for justifying the outcomes. The flooded areas from the RF model were 28.39%; the rest (71.61%) were non-flooded areas. Also, the flooded areas from the FR method were 8.02%, and the non-flooded areas were 91.98%. The AUC for both methods was a similar value – 83.0%. This result is quite accurate and can be used by policymakers to prevent and manage future flooding in the Sumedang area. These results can also be used as materials for updating existing flood-susceptibility maps.

Application of random forest (RF) for flood levels prediction in Lower Ogun Basin, Nigeria

Application of random forest (RF) for flood levels prediction in Lower Ogun Basin, Nigeria

Foreign Versus Local Ownership and Performance in Eastern Versus Western EU: A Random Forest Application

Our paper proposes the machine learning Random Forest algorithm for classifying economic activity within the European Union, building on the relevance of a reduced set of variables alongside location and industry of origin for the differences in performance between foreign versus locally-owned companies. We find a diverse landscape of business performance within the European Union that does not indicate a clear-cut dominance of foreign-owned companies against their locally-owned peers. Locally-owned companies from the Eastern European Union have been more dynamic than their foreign-owned peers in the region, which suggests a process of learning from foreign competitors and business partners. The Random Forests model performs surprisingly well given the low number of predictors and indicates that personnel costs per employee is the most important variable that discriminates between foreign and locally-owned companies. The importance of the rest of the variables, including the regional location and the industry, has a relatively uniform distribution.

Towards landslide space-time forecasting through machine learning: the influence of rainfall parameters and model setting

Landslide susceptibility assessment using machine learning models is a popular and consolidated approach worldwide. The main constraint of susceptibility maps is that they are not adequate for temporal assessments: they are generated from static predisposing factors, allowing only a spatial prediction of landslides. Recently, some methodologies have been proposed to provide spatiotemporal landslides prediction starting from machine learning algorithms (e.g., combining susceptibility maps with rainfall thresholds), but the attempt to obtain a dynamic landslide probability map directly by applying machine learning models is still in the preliminary phase. This work provides a contribution to fix this gap, combining in a Random Forest (RF) algorithm a static indicator of the spatial probability of landslide occurrence (i.e., a classical susceptibility index) and a number of dynamic variables (i.e., seasonality and the rainfall amount cumulated over different reference periods). The RF implementation used in this work allows the calculation of the Out-of-Bag Error and depicts Partial Dependence Plots, two indices that were used to quantify the variables’ importance and to comprehend if the model outcomes are consistent with the triggering mechanism observed in the case of study (Metropolitan City of Florence, Italy). The goal of this research is not to set up a landslide probability map, but to 1) understand how to populate training and test datasets with observations sampled over space and time, 2) assess which rainfall variables are statistically more relevant for the identification of the time and location of landslides, and 3) test the dynamic application of RF in a forecasting model for the spatiotemporal prediction of landslides. The proposed dynamic methodology shows encouraging results, consistent with the actual knowledge of the physical mechanism of the triggering of shallow landslides (mainly influenced by short and intense rainfalls) and identifies some benchmark configurations that represents a promising starting point for future regional-scale applications of machine learning models to dynamic landslide probability assessment and early warning.

Exploring the Major Predictors Affecting Academic Helplessness of High School Students: Application of Random Forest and SHAP

본 연구는 고등학생의 학업무기력(능동수행 결여, 학습동기 결여, 긍정정서 결여, 능동수행 결여) 관련 주요 예측변인을 탐색하기 위해 수행되었다. 이를 위해 한국아동·청소년패널조사 2018(Korean Children and Youth Panel Survey 2018; KCYPS 2018)의 중1패널 4차년도(고등학교 1학년) 자료에 랜덤포레스트를 적용하였고, 주요 예측변인의 중요도와 학업무기력의 관계를 파악하기 위해 SHAP 분석을 실시하였다. 주요 연구결과는 다음과 같다. 첫째, 학업무기력 하위요인에 공통적으로 도출된 주요 예측변인으로, ‘학습시간-학원 및 과외 시간’, ‘학업열의-헌신’, ‘진로호기심’, ‘진로관심’, ‘자아존중감’, ‘협동심-집단촉진·갈등문제해결’, ‘교사관계-신뢰성’이 학업무기력 변화와 부적인 관계가 있는 것으로 나타났으며, ‘우울’, ‘스마트폰 의존도’, ‘친구관계-부정적 관계’는 학업무기력 변화와 정적인 관계가 있는 상위 변인으로 도출되었다. 둘째, 학업무기력 하위요인에 따라 특징적으로 나타난 변인을 살펴보면, ‘부모양육태도-거부’와 ‘부모양육태도-강요’는 통제신념 결여에서만 도출되었으며, 정적인 관계를 갖는 것으로 나타났다. 학습동기 결여의 경우, ‘여가시간-스마트폰을 가지고 노는 시간’과 ‘학업열의-활기’가 주요 변인인 것으로 나타났으며, ‘여가시간-스마트폰을 가지고 노는 시간’은 학습동기 결여와 정적인 관계가 있는 것으로 나타났고 ‘학업열의-활기’는 부적인 관계성을 보이는 것으로 확인되었다. 긍정정서 결여에서는 ‘신체증상’과 ‘학교생활 만족도’, ‘교사관계-민감성’이 상위 변인에 포함되었으며, 모두 긍정정서 결여와 부적인 관계가 있는 것으로 나타났다. 능동수행 결여의 경우 ‘전 교과 성취도의 주관적 평가’와 ‘그릿-노력지속’이 주요 변인인 것으로 확인되었고, 부적인 관계를 보이는 것으로 나타났다. 이와 같은 연구결과를 바탕으로 고등학생의 학업무기력를 감소를 위한 방안과 후속연구를 위한 제언을 제시하였다.This study was designed to explore major predictors related to four sub-factors of academic helplessness in high school students: lack of locus of control, lack of learning motivation, lack of positive emotions, and lack of active performance. To do this, random forest was applied to 4th wave data (10th graders) of the Korea Children and Youth Panel Survey 2018 (KCYPS 2018), and Shapley addictive explanations (SHAP) analysis was conducted to explore the importance of major predictors and the relationship between academic helplessness and the predictors. The main results are as follows. First, the predictors commonly derived from the sub-factors of academic helplessness were “learning time−academy and tutoring time”, “academic engagement−dedication”, “career curiosity”, “career interest”, “self-esteem”, “cooperation−group promotion and conflict resolution” and “teacher relationship and reliability” which had a negative relationship with academic helplessness. However, “depression”, “smartphone dependence”, and “friend relationship−negative relationship” were derived as top variables that had a positive relationship with academic helplessness. Second, “parenting attitude−rejection” and “parenting attitude−force” were derived only from lack of locus of control. “leisure time−playing with smartphones” and “academic engagement−energy” were derived only from lack of learning motivation. In the case of lack of positive emotions, “physical symptoms”, “school satisfaction” and “teacher relationship−sensitivity” were included in the top variables, and “subjective evaluation of all subject achievement” and “grit−continuation of effort” were the main variables that were derived only from lack of active performance. Based on these findings, implications for reducing academic helplessness and suggestions for future research are discussed.

Improvement of spatial prediction of soil depth via earth observation

Soil depth is one of the most critical factors which impact on culture productivity and makes difficult appropriate management decisions. However, assessing this parameter is also the most challenging tasks in the agronomic field. The objective of this work was to predict the spatial distribution of soil depth from space techniques (remote sensing, RS) and machine learning. A total of 292 sites were allocated (based on the toposequence approach) and drilled (0–2 m depth) at three different locations in Brazil. Based on these, in-situ traditional depth maps (denominated field-map) were elaborated for validation. Afterwards, we created a strategy to achieve these different depths by RS (RS) approach. Landsat 8 OLI bands, Land Surface Temperature (LST), Normalized Difference Vegetation Index (NDVI) and emissivity in dry and rainy seasons as well as terrain attributes were applied to predict soil depth. For this purpose, the most important covariates were selected using Recursive Feature Selection (RFE) based on Random Forest (RF) and Support Vector Machine (SVM). Afterwards, the application of RF and SVM by selected covariates were compared based on tenfold cross validation for each location. The best model was selected based on R2, RMSE and MAE, accuracy and bootstrapping approach and uncertainties. Terrain attributes were important to discriminate soil depth. Although, LST and NDVI also presented important contribution to this task. Different seasons implies on water and plant dynamics in deep and shallow soils. This impacted on NDVI and LST as detected by RS. Thus, the method brings more variables to infer soil depth. The RF model performed better than SVM to predict soil depth with an average of 0.77 R2. The accuracy between a digital soil mapping and a field-map reached 0.58 to 0.81 indicating an important result considering the difficulty of the objective This may help pedologists and farmers as well as water and plants environmental monitoring.

Apply RF-LSTM to Predicting Future Share Price

In recent years, share has become a more and more heated topic in the whole world. As one of the most significant items, the data is featured by great complexity, especially in price prediction. According to the previous relevant study, its prediction has high requirements for the model, which indicates using a single model cannot acquire relatively accurate prediction results. With regard to this problem, integrating random forest and long short-term memory is illustrated to solve that. The first step is the normalization of related share data, which is to reduce the influence caused by the discrepancy of different data. And then, random forest is used for choosing relatively optimal feature rally. In contrast to single decision tree, the application of random forest has simplified the complexity of training. After that, long short-term memory is used for forecasting the price and optimize plentiful important parameters in the model. According to test consequence, the error rate of the integrated model is decreased obviously.

Application of Random Forest in Multi-Factor Stock Selection

Application of Random Forest in Multi-Factor Stock Selection

Application of Random Forest in Choosing a Method of Recovering the Age of Social Network Users

Application of Random Forest in Choosing a Method of Recovering the Age of Social Network Users

Prediction of compressive strength of alkali-activated construction demolition waste geopolymers using ensemble machine learning

This paper mainly employed the random forest (RF), gradient boosting (GB) and extreme gradient boosting (XGB) to predict the compressive strength of alkali-activated construction demolition waste geopolymers (CDWG). The performances of three ensemble machine learning (ML) models were evaluated and the effects of eight different input features on the compressive strength of CDWG were deeply analyzed. The results confirm the applicability of RF, GB and XGB algorithms in aspect of strength prediction for the CDWG with the high predictive accuracy (R2 > 0.9). Among them, the performances of GB and XGB models are better than RF model. The liquid to solid ratio (L/S) has a negative correlation with the compressive strength of CDWG, while the pretreatment temperature, heat treatment time and curing age have a positive correlation with the compressive strength of CDWG. The obvious enhancement of compressive strength of CDWG mainly occurs in the early age. Decreasing L/S and raising pretreatment temperature have a significant positive gain on the compressive strength of CDWG. In the preparation process of CDWG, it is suggested that the L/S and %Na2O of Na2SiO3-based alkaline activators are controlled at about 0.3 and 7 % respectively, and appropriately increasing pretreatment temperature and prolonging heat treatment time.

A novel landslide susceptibility optimization framework to assess landslide occurrence probability at the regional scale for environmental management

Landslide is a hazard that has drastic repercussions on population and the environment worldwide. Landslide susceptibility mapping (LSM) is vital for landslide disaster management and formulating mitigation strategies. In this study, with the support of geographic information system and remote sensing, a new LSM hybrid framework is developed based on random forest (RF) and cusp catastrophe model (CCM). Under the framework, 15 conditioning factors and 2082 historical landslides are selected to test and compare its performance in a landslide-prone area in Liangshan, Southwest China. The results depicted a better performance of the new LSM hybrid framework (RF-CCM) than those of RF or traditional application mode of catastrophe model (Catastrophe fuzzy membership functions, CFMFs) only. The RF-CCM achieved the highest accuracy (0.901), the narrowest confidence interval (0.895–0.907), and the smallest standard error (0.004) among all the models. Notably, RF-CCM successfully decreased the uncertainty of CFMFs in determining the relative importance of conditioning factors, overcame the dependence of the CFMFs on independence among the conditioning factors, and had a higher stability level than RF. Moreover, distance to human engineering activities and slope had the greatest impact on LSM in the modeling process. The study result can provide insights for developing reliable predictive models for other landslide-prone areas with similar geo-environmental conditions.