Random Forest Parameters Research Articles

Dynamic Response Prediction Model for Jack-Up Platform Pile Legs Based on Random Forest Algorithm

Jack-up offshore platforms are widely used in many fields, and it is of great importance to quickly and accurately predict the dynamic response of platform pile leg structures in real time. The current analytical techniques are founded upon numerical modelling of the platform structure. Although these methods can be used to accurately analyze the dynamic response of the platform, they require a large quantity of computational resources and cannot meet the requirements of real-time prediction. A predictive model for the dynamic response of the pile leg of a jack-up platform based on the random forest algorithm is proposed. Firstly, a pile leg dynamic response database is established based on high-fidelity numerical model simulation calculations. The data are subjected to cleaning and dimensional reduction in order to facilitate the training of the random forest model. Cross-checking and Bayesian optimization algorithms are used for the selection of random forest parameters. The results show that the prediction model is capable of outputting response results for new environmental load inputs within a few milliseconds, and the prediction results remain highly accurate and perform well at extreme values.

Integrating a machine learning-driven fraud detection system based on a risk management framework

This article explores the application of machine learning techniques, specifically focusing on ensemble methods like Random Forests, for detecting fraudulent activities in digital financial transactions. Highlighting the evolution from traditional statistical approaches to modern machine learning models, it underscores the effectiveness of Random Forests in handling the inherent challenges of imbalanced datasets typical in fraud detection scenarios. Using a Kaggle dataset of credit card transactions, the study optimizes Random Forest parameters through rigorous parameter tuning, achieving significant improvements in model performance metrics such as Area Under the Curve (AUC). The findings underscore the critical role of machine learning in enhancing fraud detection capabilities, emphasizing the ongoing evolution and future potential of these methodologies in financial risk management.

Transformer fault diagnosis based on the improved QPSO and random forest

Abstract Although dissolved gas analysis (DGA) is an effective method for transformer fault diagnosis, problems with the quality and accuracy of DGA characterization datasets often arise in practical industrial applications and face difficulties in adjusting the parameters of fault diagnosis models. To address the above problems, this paper proposes a fault diagnosis model (MD-IQPSO-RF) based on Mahalanobis distance (MD) data cleaning and improved quantum particle swarm (IQPSO) optimization of random forest (RF) parameters. Specifically, the abnormal samples of the DGA dataset are first processed by MD to improve the quality and accuracy of the dataset. Then, the RF parameters were optimized using the IQPSO algorithm to adjust the model parameters in order to improve the diagnostic performance of the RF. Finally, the optimal parameters of RF are output, and the training data are used to train the RF algorithm to construct the MD-IQPSO-RF transformer fault diagnosis model. The experimental results show that the model achieves an average accuracy of 93.631% for fault diagnosis, which is 6.92% higher than the unoptimized RF model. Comparison with other similar methods also achieved good results, which further validated the effectiveness of the fault diagnosis model.

A Prediction Model for Credit Risk Measurement of Small and Micro Enterprises Based On Particle Swarm Optimization random forest algorithm

In the context of rapid economic development, the credit risk assessment of small and micro enterprises has become the focus of attention in the financial field. The random forest algorithm is widely used in credit risk assessment due to its high accuracy and robustness, but it has some problems, such as difficulty in parameter selection and performance degradation in processing unbalanced datasets. In this study, we propose a credit risk prediction model for small and micro enterprises based on Particle Swarm Optimization Random Forest Algorithm (PSO-RF). The particle swarm optimization effectively solves the problem of random forest parameter selection and improves the prediction performance of the model through the balance of global search and local search. Experimental results show that the PSO-RF algorithm shows significant performance advantages in credit risk prediction, performs well in dealing with unbalanced datasets, and has certain advantages in feature selection. This study provides new ideas and methods for the credit risk assessment of small and micro enterprises, and is of great significance for improving the risk management capabilities of financial institutions and supporting the healthy development of small and micro enterprises.

Quantitative structure-activity relationship predicting toxicity of pesticides towards Daphnia magna.

Global pesticide usage reaching 2.7 million metric tons annually, brings a grave threat to non-target organisms, especially aquatic organisms, resulting in serious concerns. Predicting aquatic toxicity of pesticides towards Daphnia magna is significant. In this work, random forest (RF) algorithm, together with ten Dragon molecular descriptors, was successfully utilized to develop a quantitative structure-activity/toxicity relationship (QSAR/QSTR) model for the toxicity pEC50 of 745 pesticides towards Daphnia magna. The optimal QSTR model (RF Model I) based on the RF parameters of ntree = 50, mtry = 3 and nodesize = 5, yielded R2 = 0.877, MAE = 0.570, rms = 0.739 (training set of 596 pEC50), R2 = 0.807, MAE = 0.732, rms = 0.902 (test set of 149 pEC50), and R2 = 0.863, MAE = 0.602, rms = 0.774 (total set of 745 pEC50), which are accurate and satisfactory. The optimal RF model is comparable to other published QSTR models for Daphnia magna, although the optimal RF model possessed a small descriptor subset and dealt with a large dataset of pesticide toxicity pEC50. Thus, the investigation in this work provides a reliable, applicable QSTR model for predicting the toxicity pEC50 of pesticides towards Daphnia magna.

ESTIMATION OF SUGARCANE YIELD USING MULTI-TEMPORAL SENTINEL 2 SATELLITE IMAGERY AND RANDOM FOREST REGRESSION

Abstract. Advancements in remote sensing techniques have greatly enhanced crop monitoring and yield estimation, with spectral vegetation indices (VIs) serving as a key component. Our study investigates the use of Sentinel-2 data, notable for its red-edge bands, in estimating sugarcane yield in Ethiopia's Awash Basin. Utilizing 22 VIs from S2 imagery, our approach combines Random Forest (RF) regression with the Recursive Feature Elimination (RFE) algorithm to improve the accuracy of sugarcane yield predictions. The results demonstrate the superior performance of the RF-RFE method over traditional RF with full datasets and Stepwise Multiple Regression (SMR). Particularly, VIs focusing on the red-edge spectral bands of S2 - such as NDVIre1n, NDVIre2n, NDVIre3n, NDRE1 and NDRE2 - were crucial in enhancing prediction precision. These indices from the red-edge and NIR narrow bands consistently influenced yield estimations in both the Wonji-Shoa and Metehara estates. The study underscores the critical role of the RFE algorithm in optimal variable selection, reinforcing earlier findings that precise variable choice can substantially boost model accuracy. The enhanced performance of the RF model when paired with the RFE algorithm was evident, emphasizing the importance of variable selection in accurate yield predictions. Employing the Out-of-Bag RMSE (OOB_RMSE) error estimate for evaluation, we observed variations in OOB_RMSE performance with different RF parameters, identifying the ntree value of 500 as optimal for the studied regions. The RF-RFE model’s estimations showed lower errors and higher correlation coefficients, proving its efficacy over a full dataset approach, which faced challenges with traditional VIs' saturation. Our findings align with earlier studies, highlighting the efficiency of S2’s red-edge bands in diverse estimation tasks and a shift towards using freely available broadband images like S2, over hyperspectral imagery, due to reduced data redundancy and processing costs. In conclusion, our findings reveal that RF regression, particularly when integrated with the RFE algorithm, is a powerful tool in remote sensing applications. The S2 imagery is optimal VIs, predominantly from the red-edge bands, exhibit significant potential for sugarcane yield estimations. The impressive results of the RF-RFE method, evident in metrics like MAE, MAPE, RMSE, Mean percentage, and R2, advocate its invaluable role in sugarcane yield prediction, highlighting its potential for optimizing irrigation management strategies and broad-spectrum agricultural planning.

Modeling Equatorial to Mid‐Latitudinal Global Night Time Ionospheric Plasma Irregularities Using Machine Learning

AbstractThis study focuses on modeling the characteristics of nighttime topside Ionospheric Plasma Irregularities (PI) on a global scale. We utilize Random Forest (RF) and a one‐dimensional Convolutional Neural Network (1D‐CNN) model, incorporating data from the Swarm A, B, and C satellites, space weather data from the OMNIWeb data center, as well as zonal and meridional wind model data. Our objective is to simulate monthly global PI characteristics using a multilayer 1D‐CNN model trained on 12 space weather and ionospheric parameters. In addition, we investigate the most influential input parameters for predicting global nighttime PI characteristics. Our findings indicate that non‐equinox months exhibit the highest equatorial PI magnitude over the American‐African longitudinal sector, contrary to the expected higher Rayleigh‐Taylor instability growth rate during equinox months. Winter months display the most intense and widespread vertically and horizontally distributed equatorial PI patterns. We also observe double peaks across geomagnetic latitudes and longitudinally varying wavelike irregularity structures, particularly in May, August, and predominantly in September. Furthermore, north‐south hemispherical asymmetry in PI observed across different seasons. Through the RF parameter importance analysis method, we determine that temporal, geographical, and magnetic disturbance‐related factors play a crucial role in predicting global PI variabilities. These findings emphasize the significance of these variables in controlling the strongest PI characteristics observed in the Atlantic sector, which has garnered considerable attention in PI research. The employed 1D‐CNN model demonstrates exceptional predictive capabilities, exhibiting a strong correlation of 0.98 for global PI characteristics across all months and satellites.

A novel bearing current signal diagnosis method combining variational modal decomposition and improved random forests.

A new fault diagnosis approach based on bearing current signals is proposed in this paper. First, in view of strong background noise of the current signal, the variational modal decomposition method is applied to decompose the bearing current signal to obtain multiple intrinsic mode functions, and then the intrinsic mode functions are constructed as the input feature vector according to the kurtosis. Second, to avoid the influence of random forest parameters on the random forest classifier, a random forest faulty bearing diagnostic model optimized by the whale algorithm is established. Finally, the accuracy rate and confusion matrix are adopted to evaluate the prediction effects of both established and traditional models. The classification accuracy of the real damaged bearing fault type can reach 95.11%. The fault diagnosis accuracy of manually damaged bearings can reach 93.83%. The results show that the method proposed in this paper has high accuracy and good generalization ability for bearing fault diagnosis.

Gaussian mutation–orca predation algorithm–deep residual shrinkage network (DRSN)–temporal convolutional network (TCN)–random forest model: an advanced machine learning model for predicting monthly rainfall and filtering irrelevant data

Monitoring water resources requires accurate predictions of rainfall data. Our study introduces a novel deep learning model named the deep residual shrinkage network (DRSN)—temporal convolutional network (TCN) to remove redundant features and extract temporal features from rainfall data. The TCN model extracts temporal features, and the DRSN enhances the quality of the extracted features. Then, the DRSN–TCN is coupled with a random forest (RF) model to model rainfall data. Since the RF model may be unable to classify and predict complex patterns and data, our study develops the RF model to model outputs with high accuracy. Since the DRSN–TCN model uses advanced operators to extract temporal features and remove irrelevant features, it can improve the performance of the RF model for predicting rainfall. We use a new optimizer named the Gaussian mutation (GM)–orca predation algorithm (OPA) to set the DRSN–TCN–RF (DTR) parameters and determine the best input scenario. This paper introduces a new machine learning model for rainfall prediction, improves the accuracy of the original TCN, and develops a new optimization method for input selection. The models used the lagged rainfall data to predict monthly data. GM–OPA improved the accuracy of the orca predation algorithm (OPA) for feature selection. The GM–OPA reduced the root mean square error (RMSE) values of OPA and particle swarm optimization (PSO) by 1.4%–3.4% and 6.14–9.54%, respectively. The GM–OPA can simplify the modeling process because it can determine the most important input parameters. Moreover, the GM–OPA can automatically determine the optimal input scenario. The DTR reduced the testing mean absolute error values of the TCN–RAF, DRSN–TCN, TCN, and RAF models by 5.3%, 21%, 40%, and 46%, respectively. Our study indicates that the proposed model is a reliable model for rainfall prediction.

Skin cancer classification using improved transfer learning model‐based random forest classifier and golden search optimization

AbstractThe two complex skin cancer type is melanoma and non‐melanoma. However, the classification of skin cancer is not performed accurately due to the requirement of a huge time and the presence of noisy images. The severity level is not detected and this leads to generate serious issues. To overcome these entire issues GSO‐optimized kernel random forest (RF)‐based transfer learning (TL) is proposed to perform the classification of 12 different skin cancer types by using ImageNet and CNN architectures. The kernel decision tree is taken into account by the RF classifier throughout the classification process, and the RF parameters are modified using the GSO algorithm. The proposed algorithm not only effectively enhances the detection results based on previous adaptive thresholding segmentation techniques but also extends the skin cancer detection process. Compared to existing MMCL, SVM, Mask‐RCNN, and CNN methods the proposed technique attained better performance in classification of skin cancer.

Predictive model for identifying new CYP19A1 ligands on the KNIME analytical platform

The purpose of this study was to create a database of the chemical compounds – ligands of human steroid-hydroxylating cytochrome CYP19A1 (aromatase) in order to build a predictive model. The idea was to create a model on the basis of the machinery learning method such as random forest for two types of ligands – with steroidal (I type) and non-steroidal structure (II type). Two predictive models were built with the help of the KNIME analytical platform. Topological descriptors of the chemical structure were used as training data when building a model that takes into account their correlation between the structure of the molecule and the biological effect. The selection of the feature importance of the descriptors, optimal parameters of random forest and the definition of applicability domain of the models were carried out. The assessment of the ability to predict the results of a test sample was performed for each model. The quality marks of the obtained models indicated a rather high predictive ability of the models and the prospects of their use for identification of new human CYP19A1 ligands as potential drugs for treatment of hormone-dependent tumors.

Optimal parameters of random forest for land cover classification with suitable data type and dataset on Google Earth Engine

Exact land cover (LC) map is essential information for understanding the development of human societies and studying the impacts of climate and environmental change. To fulfill this requirement, an optimal parameter of Random Forest (RF) for LC classification with suitable data type and dataset on Google Earth Engine (GEE) was investigated. The research objectives were 1) to examine optimum parameters of RF for LC classification at local scale 2) to classify LC data and assess accuracy in model area (Hefei City), 3) to identify a suitable data type and dataset for LC classification and 4) to validate optimum parameters of RF for LC classification with a suitable data type and dataset in test area (Nanjing City). This study suggests that the suitable data types for LC classification were Sentinel-2 data with auxiliary data. Meanwhile, the suitable dataset for LC classification was monthly and seasonal medians of Sentinel-2, elevation, and nighttime light data. The appropriate values of the number of trees, the variable per split, and the bag fraction for RF were 800, 22, and 0.9, respectively. The overall accuracy (OA) and Kappa index of LC in model area (Hefei City) with suitable dataset was 93.17% and 0.9102. In the meantime, the OA and Kappa index of LC in test area (Nanjing City) was 92.38% and 0.8914. Thus, the developed research methodology can be applied to update LC map where LC changes quickly occur.

Large Dataset-Based Regression Model of Chemical Toxicity to Vibrio fischeri.

For the first time, a global regression quantitative structure-toxicity/activity relationship (QSTR/QSAR) model was developed for the toxicity of a large data set including 1236 chemicals towards Vibrio fischeri, by using random forest (RF) regression algorithm. The optimal RF model with RF parameters of mtry = 3, ntree = 150 and nodesize = 5 was based on 13 molecular descriptors. It can achieve accurate prediction for the toxicity of 99.1% of 1236 chemicals, and yield coefficients of determination R2 of 0.893 for 930 log(Mw/IBC50) in the training set, 0.723 for 306 log(Mw/IBC50) in the test se, and 0.865 for 1236 toxicity log(Mw/IBC50) in the total set. The optimal RF global model proposed in this work is comparable to other published local QSTR models on small datasets of the toxicity to Vibrio fischeri.

Blows or Falls? Distinction by Random Forest Classification.

In this study, we propose a classification method between falls and blows using random forests. In total, 400 anonymized patients presenting with fractures from falls or blows aged between 20 and 49 years old were used. There were 549 types of fractures for 57 bones and 12 anatomical regions observed. We first tested various models according to the sensibility of random forest parameters and their effects on model accuracies. The best model was based on the binary coding of 12 anatomical regions or 28 bones with or without baseline (age and sex). Our method achieved the highest accuracy rate of 83% in the distinction between falls and blows. Our findings pave the way for applications to help forensic experts and archaeologists.

Construction cost prediction system based on Random Forest optimized by the Bird Swarm Algorithm.

Predicting construction costs often involves disadvantages, such as low prediction accuracy, poor promotion value and unfavorable efficiency, owing to the complex composition of construction projects, a large number of personnel, long working periods and high levels of uncertainty. To address these concerns, a prediction index system and a prediction model were developed. First, the factors influencing construction cost were first identified, a prediction index system including 14 secondary indexes was constructed and the methods of obtaining data were presented elaborately. A prediction model based on the Random Forest (RF) algorithm was then constructed. Bird Swarm Algorithm (BSA) was used to optimize RF parameters and thereby avoid the effect of the random selection of RF parameters on prediction accuracy. Finally, the engineering data of a construction company in Xinyu, China were selected as a case study. The case study showed that the maximum relative error of the proposed model was only 1.24%, which met the requirements of engineering practice. For the selected cases, the minimum prediction index system that met the requirement of prediction accuracy included 11 secondary indexes. Compared with classical metaheuristic optimization algorithms (Particle Swarm Optimization, Genetic Algorithms, Tabu Search, Simulated Annealing, Ant Colony Optimization, Differential Evolution and Artificial Fish School), BSA could more quickly determine the optimal combination of calculation parameters, on average. Compared with the classical and latest forecasting methods (Back Propagation Neural Network, Support Vector Machines, Stacked Auto-Encoders and Extreme Learning Machine), the proposed model exhibited higher forecasting accuracy and efficiency. The prediction model proposed in this study could better support the prediction of construction cost, and the prediction results provided a basis for optimizing the cost management of construction projects.

Deformation Prediction System of Concrete Dam Based on IVM-SCSO-RF

Deformation prediction is an important part of concrete dam safety monitoring. In recent years, the random forest (RF) algorithm has attracted more and more attention in the field of dam safety monitoring because of its fast speed and strong generalization ability. However, the performance of RF is easily affected by many factors, such as the drift of measured value in displacement and the inappropriate setting of parameters of RF. To solve the above problems, the indicator variable model (IVM) is used to identify and eliminate the drift of measured values in this paper, and the sand cat swarm optimization (SCSO) is applied to optimize RF for the first time. On the grounds of this, a deformation prediction system of a concrete dam based on the IVM and RF algorithm optimized by SCSO is proposed. The case study shows that IVM can correct the interference of monitoring data accurately, and the maximum error rate is less than 3%; in the aspect of parameter optimization of RF, the results of the SCSO algorithm are obviously better than those of the TAE method and PSO algorithm, and the corresponding OOB error is the minimum; in terms of prediction performance, compared with TAE-RF, PSO-RF, LSTM and SVM, SCSO-RF has higher accuracy and stronger stability, and its SSE and MSE are reduced by at least 91%, MAE and RMSE are reduced by at least 71%, and R2 is very close to 1. The results of study provide a new method for the automatic online evaluation of dam safety performance.

Random forest algorithm-based accurate prediction of rat acute oral toxicity

ABSTRACT Predicting acute oral toxicity LD50 of chemicals in rats is a challenge since many factors affect toxicity data. In this paper, 40 descriptors were successfully used to develop a quantitative structure–activity relationship model for 8448 rat acute oral toxicity logLD50 by applying the random forest (RF) algorithm. To develop the optimal RF model, a training set (5914 chemicals) was used to establish models, a validation set (1267 chemicals) used to tune RF parameters and a test set (1267 chemicals) used to assess the performance of RF models. It yielded correlation coefficients R of 0.9695 and rms errors (log unit) of 0.3171 for the training set, R = 0.8322 and rms = 0.2889 for the validation set and R = 0.8335 and rms = 0.3060 for the test set. More than 99% of rat acute oral toxicity logLD50 in the dataset can be accurately predicted, although the dataset is large.

PREDICTION MODEL OF PUBLIC HOUSES’ HEATING SYSTEMS: A COMPARISON OF SUPPORT VECTOR MACHINE METHOD AND RANDOM FOREST METHOD

Data analysis and predicting play an important role in managing heat-supplying systems. Applying the models of predicting the systems’ parameters is possible for qualitative management, accepting appropriate decisions relating control that will be aimed at increasing energy efficiency and decreasing the amount of the consumed power source, diagnosing and defining non-typical processes in the functioning of the systems. The article deals with comparing two methods of ma-chine learning: random forest (RF) and support vector machine (SVM) for predicting the temperature of the heat-carrying agent in the heating system based on the data of electronic weather-dependent controller. The authors use the following parameters to compare the models: accuracy, source cost and the opportunity to interpret the results and non-obvious interrelations. The time spent for defining the optimal hyperparameters and conducting the SVM model training is deter-mined to exceed significantly the data of the RF parameter despite the close meanings of the root mean square error (RMSE). The change from 15-min data to once-a-minute ones is done to improve the RF model accuracy. RMSE of the RF model on the test data equals 0.41°С. The article studies the importance of the contribution of variables to the prediction accuracy.

A Hybrid Approach for Identification of Deficiencies in Enterprise Internal Control

Enterprise management and internal control are used to prevent and control risks and promote enterprises to achieve development strategy. This paper adopts comprehensive multidisciplinary research method to study the basic theory of prediction of major defects in enterprise internal control. Firstly, this paper proposes the prediction index system and sample selection standard of internal control major defects. Totally, 630 listed company and 12 indicators are collected and then use the random forest classification method based on principal component analysis. The parameters of random forest are optimized by genetic algorithm. Finally, the prediction model of major internal control defects of listed companies is established. The experimental results show that the average score of PCA-RF model in TPR value reaches 85%, which is nearly 20% higher than the 65% of RF model, proving that the PCA and GA can significantly improve the classification accuracy of ST Company and has important practical significance. Therefore, the proposed method system can reasonably solve the prediction problem of major defects in internal control.

Bearing Fault Diagnosis with Variable Speed Based on Fractional Hierarchical Range Entropy and Hunter–Prey Optimization Algorithm–Optimized Random Forest

It is difficult for rolling bearings to realize high-precision fault diagnosis with variable speed. To obtain the features of variable speed fault signal effectively and complete the classification work of high accuracy, robust local mean decomposition (RLMD), fractional hierarchical range entropy (FrHRE), hunter–prey optimization algorithm (HPO) and random forest (RF) are combined. Then the paper advances a model for fault diagnosis based on RLMD, FrHRE and HPO-RF. Firstly, RLMD is selected to reconstruct the signal to eliminate some noise interference in this paper. Secondly, FrHRE is chosen to extract the useful feature. Next step, HPO is used to optimize the important parameters of RF and enhance RF’s classification ability. Finally, these obtained features are imported into the optimized RFmodel to achieve the classification. The experimental data is provided by University of Ottawa. The experiment analysis demonstrates that the proposed method performs very well in classification.