Ensemble Prediction Model Research Articles

Machine Learning and Feature Selection Methods for EGFR Mutation Status Prediction in Lung Cancer

The evolution of personalized medicine has changed the therapeutic strategy from classical chemotherapy and radiotherapy to a genetic modification targeted therapy, and although biopsy is the traditional method to genetically characterize lung cancer tumor, it is an invasive and painful procedure for the patient. Nodule image features extracted from computed tomography (CT) scans have been used to create machine learning models that predict gene mutation status in a noninvasive, fast, and easy-to-use manner. However, recent studies have shown that radiomic features extracted from an extended region of interest (ROI) beyond the tumor, might be more relevant to predict the mutation status in lung cancer, and consequently may be used to significantly decrease the mortality rate of patients battling this condition. In this work, we investigated the relation between image phenotypes and the mutation status of Epidermal Growth Factor Receptor (EGFR), the most frequently mutated gene in lung cancer with several approved targeted-therapies, using radiomic features extracted from the lung containing the nodule. A variety of linear, nonlinear, and ensemble predictive classification models, along with several feature selection methods, were used to classify the binary outcome of wild-type or mutant EGFR mutation status. The results show that a comprehensive approach using a ROI that included the lung with nodule can capture relevant information and successfully predict the EGFR mutation status with increased performance compared to local nodule analyses. Linear Support Vector Machine, Elastic Net, and Logistic Regression, combined with the Principal Component Analysis feature selection method implemented with 70% of variance in the feature set, were the best-performing classifiers, reaching Area Under the Curve (AUC) values ranging from 0.725 to 0.737. This approach that exploits a holistic analysis indicates that information from more extensive regions of the lung containing the nodule allows a more complete lung cancer characterization and should be considered in future radiogenomic studies.

Comparing Regression Models with Count Data to Artificial Neural Network and Ensemble Models for Prediction of Generic Escherichia coli Population in Agricultural Ponds Based on Weather Station Measurements

Indicator microorganisms are monitored in agricultural waters to foster produce safety. Various prediction models are used to estimate the population of indicator microorganisms and pathogens when no observation is available. The purpose of this study was to compare the performance of regression models with count data (zero-inflated Poisson and hurdle negative binomial) to artificial neural network and ensemble models (random forest and AdaBoost) for the prediction of generic Escherichia coli population in agricultural surface waters in relation with weather station measurements. Two-part count data models were built on E. coli population count frequencies (0, [1,10), [10,100), [100,1000), [1000, 10000), (>=10000)) based on the data structure. The use of artificial neural network, AdaBoost, and random forest were determined based on the mean absolute error (MAE) value over pre-tested six models. The MAE was also used to compare the performance of two-part count data models with artificial neural network and ensemble models. Over-dispersed E. coli population count frequencies was calculated between 2.2 and 52.2% for all ponds. Observed and predicted zero E. coli population counts for all ponds were matched from 82 to 100% for zero-inflated Poisson and 100% for hurdle negative binomial regression models. Overdispersion reduced the performance of tested models. AdaBoost-Twelve Estimators had the best performance with the lowest MAE values for all ponds (from 0.87 to 46.60). The ensemble models used in this study provided more promising performance when compared to tested regression models with count data.

Dynamic ensemble wind speed prediction model based on hybrid deep reinforcement learning

Prediction of wind speed can provide a reference for the reliable utilization of wind energy. This study focuses on 1-hour, 1-step ahead deterministic wind speed prediction with only wind speed as input. To consider the time-varying characteristics of wind speed series, a dynamic ensemble wind speed prediction model based on deep reinforcement learning is proposed. It includes ensemble learning, multi-objective optimization, and deep reinforcement learning to ensure effectiveness. In part A, deep echo state network enhanced by real-time wavelet packet decomposition is used to construct base models with different vanishing moments. The variety of vanishing moments naturally guarantees the diversity of base models. In part B, multi-objective optimization is adopted to determine the combination weights of base models. The bias and variance of ensemble model are synchronously minimized to improve generalization ability. In part C, the non-dominated solutions of combination weights are embedded into a deep reinforcement learning environment to achieve dynamic selection. By reasonably designing the reinforcement learning environment, it can dynamically select non-dominated solution in each prediction according to the time-varying characteristics of wind speed. Four actual wind speed series are used to validate the proposed dynamic ensemble model. The results show that: (a) The proposed dynamic ensemble model is competitive for wind speed prediction. It significantly outperforms five classic intelligent prediction models and six ensemble methods; (b) Every part of the proposed model is indispensable to improve the prediction accuracy.

An Ensemble Model for Prediction of Vancomycin Trough Concentrations in Pediatric Patients.

PurposeThis study aimed to establish an optimal model to predict vancomycin trough concentrations by using machine learning.Patients and MethodsWe enrolled 407 pediatric patients (age < 18 years) who received vancomycin intravenously and underwent therapeutic drug monitoring from June 2013 to April 2020 at Xinhua Hospital affiliated to Shanghai Jiaotong University School of Medicine. The median (interquartile range) age and weight of the patients were 2 (0.63–5) years and 12 (7.8–19) kg. Vancomycin trough concentrations were considered as the target variable, and eight different algorithms were used for predictive performance comparison. The whole dataset (407 cases) was divided into training group and testing group at the ratio of 80%: 20%, which were 325 and 82 cases, respectively.ResultsUltimately, five algorithms (XGBoost, GBRT, Bagging, ExtraTree and decision tree) with high R2 (0.657, 0.514, 0.468, 0.425 and 0.450, respectively) were selected and further ensembled to establish the final model and achieve an optimal result. For missing data, through filling the missing values and model ensemble, we obtained R2=0.614, MAE=3.32, MSE=24.39, RMSE=4.94 and a prediction accuracy of 51.22% (predicted trough concentration within ±30% of the actual trough concentration). In comparison with the pharmacokinetic models (R2=0.3), the machine learning model works better in model fitting and has better prediction accuracy.ConclusionTherefore, the ensemble model is useful for the vancomycin concentration prediction, especially in the population of children with great individual variation. As machine learning methods evolve, the clinical value of the ensemble model will be demonstrated in the clinical practice.

Regional ensemble modeling reduces uncertainty for digital soil mapping

Recent country and continental-scale digital soil mapping efforts have used a single model to predict soil properties across large regions. However, different ecophysiographic regions within large-extent areas are likely to have different soil-landscape relationships so models built specifically for these regions may more accurately capture these relationships relative to a ‘global’ model. We ask the question: Is a single ‘global’ model sufficient or are regionally-specific models useful for accurate digital soil mapping? We test this question by modeling soil depth classes across the 432,000 km2 upper Colorado River Basin in the Western USA using a single global model, multiple ecophysiographic models, and ensembles of the ecophysiographic models.Effective soil depth class observations (n = 12,194) were derived from multiple soil databases. Fifty-seven environmental covariates were derived from a 30 m digital elevation model, climate data, satellite imagery, and aeroradiometric data. Three independent land classifications were used to stratify the area. Two expert-derived land classifications, USDA Major Land Resource Areas (MLRA) and US-EPA Level III ecoregions, divided the study area into multiple ecophysiographic regions based on vegetation and broad-scale physiographic differences. The third land classification divided the study area into broad landforms.Soil depth observations were split into separate training (n = 10,470) and validation (n = 1,724) datasets. First, a ‘global’ random forest model was used to model soil depth classes using all training observations and covariates. ‘Global’ denotes a model built with all training data across the extent of the area, not a model at world extent. Second, the land classifications were used to subset the observations into ecophysiographic sub-datasets and random forest models were refit for each region. Models fit by ecophysiographic region are referred to as regional models. Thirdly, predictions from each regional model were fused into regional-ensemble models. Accuracy, Brier scores, and Shannon’s entropy were used to compare model accuracy and uncertainty. Regional ecophysiographic models were also compared to models built for geographic areas that were defined solely to be approximately equal in area. Training dataset density and the imbalance ratio were investigated to determine if data characteristics influenced regional accuracy/uncertainty metrics.Accuracy for the global model using the validation set was 62.8%. Regional model accuracies ranged between 56.1% and 75.0%. We found: 1) useful inter-regional differences in global model accuracy were revealed when the global model was validated by region, 2) no consistent relationship between training observation density and accuracy/uncertainty metrics, 3) no meaningful differences in accuracy and uncertainty metrics between physiographic and geographic regions, 4) ensembles of regionally-specific models were approximately as accurate as global models, and 5) both region-specific models and ensembles of regional models were less uncertain than the global model. Overall, we recommend the use of soil depth class predictions made from MLRA regional ensemble models because this prediction had higher accuracy than the ecoregion ensemble model prediction, but lower uncertainty than both the global model and the landform ensemble model predictions. We answer our question: Ensembles of regionally-specific models are approximately as accurate as global models, but result in less uncertainty.

A sequential ensemble model for software fault prediction

Unlike several other engineering disciplines, software engineering lacks well-defined research strategies. However, with the exponential rise in automation, the demand for software has observed an enormous elevation. Simultaneously, it necessitates having zero failures in the software modules to maximize the availability and optimize the maintenance cost. This has attracted many researchers to try their hand in formalizing the strategies for testing of software. Numerous researchers have suggested various models in this context. The authors in this paper present a sequential ensemble model to predict software faults. The employment of ensemble modeling in software fault prediction is motivated by its competence in various domains. The proposed model is also implemented on the 8 datasets taken from PROMISE and ECLIPSE repository. The proposed model's performance is evaluated using various error metrics, viz. average absolute error, average relative error, and prediction. The obtained results are encouraging and thus establish the competence of the proposed model.

Long-term Exposure to PM2.5 and Mortality for the Older Population: Effect Modification by Residential Greenness.

Although many studies demonstrated reduced mortality risk with higher greenness, few studies examined the modifying effect of greenness on air pollution-health associations. We evaluated residential greenness as an effect modifier of the association between long-term exposure to fine particles (PM2.5) and mortality. We used data from all Medicare beneficiaries in North Carolina (NC) and Michigan (MI) (2001-2016). We estimated annual PM2.5 averages using ensemble prediction models. We estimated mortality risk per 1 μg/m3 increase using Cox proportional hazards modeling, controlling for demographics, Medicaid eligibility, and area-level covariates. We investigated health disparities by greenness using the Normalized Difference Vegetation Index with measures of urbanicity and socioeconomic status. PM2.5 was positively associated with mortality risk. Hazard ratios (HRs) were 1.12 (95% confidence interval (CI) = 1.12 to 1.13) for NC and 1.01 (95% CI = 1.00 to 1.01) for MI. HRs were higher for rural than urban areas. Within each category of urbanicity, HRs were generally higher in less green areas. For combined disparities, HRs were higher in low greenness or low SES areas, regardless of the other factor. HRs were lowest in high-greenness and high-SES areas for both states. In our study, those in low SES and high-greenness areas had lower associations between PM2.5 and mortality than those in low SES and low greenness areas. Multiple aspects of disparity factors and their interactions may affect health disparities from air pollution exposures. Findings should be considered in light of uncertainties, such as our use of modeled PM2.5 data, and warrant further investigation.

Development of deep learning algorithms for predicting blastocyst formation and quality by time-lapse monitoring

Approaches to reliably predict the developmental potential of embryos and select suitable embryos for blastocyst culture are needed. The development of time-lapse monitoring (TLM) and artificial intelligence (AI) may help solve this problem. Here, we report deep learning models that can accurately predict blastocyst formation and usable blastocysts using TLM videos of the embryo’s first three days. The DenseNet201 network, focal loss, long short-term memory (LSTM) network and gradient boosting classifier were mainly employed, and video preparation algorithms, spatial stream and temporal stream models were developed into ensemble prediction models called STEM and STEM+. STEM exhibited 78.2% accuracy and 0.82 AUC in predicting blastocyst formation, and STEM+ achieved 71.9% accuracy and 0.79 AUC in predicting usable blastocysts. We believe the models are beneficial for blastocyst formation prediction and embryo selection in clinical practice, and our modeling methods will provide valuable information for analyzing medical videos with continuous appearance variation.

Ensemble Machine Learning Model for Software Defect Prediction

Software defect prediction is a significant activity in every software firm. It helps in producing quality software by reliable defect prediction, defect elimination, and prediction of modules that are susceptible to defect. Several researchers have proposed different software prediction approaches in the past. However, these conventional software defect predictions are prone to low classification accuracy, time-consuming, and tasking. This paper aims to develop a novel multi-model ensemble machine-learning for software defect prediction. The ensemble technique can reduce inconsistency among training and test datasets and eliminate bias in the training and testing phase of the model, thereby overcoming the downsides that have characterized the existing techniques used for the prediction of a software defect. To address these shortcomings, this paper proposes a new ensemble machine-learning model for software defect prediction using k Nearest Neighbour (kNN), Generalized Linear Model with Elastic Net Regularization (GLMNet), and Linear Discriminant Analysis (LDA) with Random Forest as base learner. Experiments were conducted using the proposed model on CM1, JM1, KC3, and PC3 datasets from the NASA PROMISE repository using the RStudio simulation tool. The ensemble technique achieved 87.69% for CM1 dataset, 81.11% for JM1 dataset, 90.70% for PC3 dataset, and 94.74% for KC3 dataset. The performance of the proposed system was compared with that of other existing techniques in literature in terms of AUC. The ensemble technique achieved 87%, which is better than the other seven state-of-the-art techniques under consideration. On average, the proposed model achieved an overall prediction accuracy of 88.56% for all datasets used for experiments. The results demonstrated that the ensemble model succeeded in effectively predicting the defects in PROMISE datasets that are notorious for their noisy features and high dimensions. This shows that ensemble machine learning is promising and the future of software defect prediction.

Improving Individual Brain Age Prediction Using an Ensemble Deep Learning Framework.

Brain age is an imaging-based biomarker with excellent feasibility for characterizing individual brain health and may serve as a single quantitative index for clinical and domain-specific usage. Brain age has been successfully estimated using extensive neuroimaging data from healthy participants with various feature extraction and conventional machine learning (ML) approaches. Recently, several end-to-end deep learning (DL) analytical frameworks have been proposed as alternative approaches to predict individual brain age with higher accuracy. However, the optimal approach to select and assemble appropriate input feature sets for DL analytical frameworks remains to be determined. In the Predictive Analytics Competition 2019, we proposed a hierarchical analytical framework which first used ML algorithms to investigate the potential contribution of different input features for predicting individual brain age. The obtained information then served as a priori knowledge for determining the input feature sets of the final ensemble DL prediction model. Systematic evaluation revealed that ML approaches with multiple concurrent input features, including tissue volume and density, achieved higher prediction accuracy when compared with approaches with a single input feature set [Ridge regression: mean absolute error (MAE) = 4.51 years, R2 = 0.88; support vector regression, MAE = 4.42 years, R2 = 0.88]. Based on this evaluation, a final ensemble DL brain age prediction model integrating multiple feature sets was constructed with reasonable computation capacity and achieved higher prediction accuracy when compared with ML approaches in the training dataset (MAE = 3.77 years; R2 = 0.90). Furthermore, the proposed ensemble DL brain age prediction model also demonstrated sufficient generalizability in the testing dataset (MAE = 3.33 years). In summary, this study provides initial evidence of how-to efficiency for integrating ML and advanced DL approaches into a unified analytical framework for predicting individual brain age with higher accuracy. With the increase in large open multiple-modality neuroimaging datasets, ensemble DL strategies with appropriate input feature sets serve as a candidate approach for predicting individual brain age in the future.

Nonparametric machine learning for precision medicine with longitudinal clinical trials and Bayesian additive regression trees with mixed models.

Precision medicine is an active area of research that could offer an analytic paradigm shift for clinical trials and the subsequent treatment decisions based on them. Clinical trials are typically analyzed with the intent of discovering beneficial treatments if the same treatment is applied to the entire population under study. But, such a treatment strategy could be suboptimal if subsets of the population exhibit varying treatment effects. Identifying subsets of the population experiencing differential treatment effect and forming individualized treatment rules is a task well-suited to modern machine learning methods such as tree-based ensemble predictive models. Specifically, Bayesian additive regression trees (BART) has shown promise in this regard because of its exceptional performance in out-of-sample prediction. Due to the unique inferential needs of precision medicine for clinical trials, we have proposed the BART extensions explicated here. We incorporate random effects for longitudinal repeated measures and subject clustering within medical centers. The addition of a novel interaction detection prior to identify treatment heterogeneity among clinical trial patients and its association with patient characteristics. These extensions are unified under a framework that we call mixedBART. Simulation studies and applications of precision medicine based on real randomized clinical trials data examples are presented.

An Ensemble Model of Wind Speed Forecasting Based on Variational Mode Decomposition and Bare-Bones Fireworks Algorithm

Wind energy is one of the fastest growing renewable energy sources. Wind speed forecasting is essential to enhance the utilization of wind energy. Various prediction models have been developed to improve the prediction accuracy of wind speed. However, wind speed time series has nonlinearity, fluctuation, and intermittence, which makes the prediction difficult. Existing prediction models ignore data decomposition and feature reduction and suffer from the deficiency of individual models. This paper proposes a novel ensemble prediction model, which integrates data preprocessing, feature selection, parameter optimization, three intelligent prediction models, and an ensemble strategy. To improve prediction performance, a highly efficient optimization algorithm is applied to determine the individual models’ optimal parameters. Furthermore, partial least square regression is used to calculate combination weight. Additionally, two 10 min datasets from the National Renewable Energy Laboratory (NREL) are employed for one-step-ahead prediction. Among the involved models, the proposed model can obtain the best prediction accuracy. The experimental results indicate that the mean absolute percent errors of the proposed model are 7.97% and 9.99%, which are lower than the comparison methods. Pearson’s test reveals that the proposed approach can have the strongest association between the actual data and the prediction results.

Dynamic multi-objective evolutionary algorithm with center point prediction strategy using ensemble Kalman filter

Dynamic multi-objective optimization problems are the multi-objective optimization problems in which the objectives change with environment and time, and the optimization algorithm for solving such problems must be able to track the changed pareto optimal set and further explore the real pareto optimal front. It is a difficult and hot topic in dynamic multi-objective evolutionary algorithm to accurately predict the direction of population movement after environmental changes. In this paper, the ensemble Kalman filter is introduced into dynamic multi-objective optimization problems to predict the population center point after environmental changes. ensemble Kalman filter is a four-dimensional assimilation method that uses Monte Carlo short-term ensemble prediction method to estimate the prediction error covariance and has achieved great success in many fields. In the proposed algorithm, the new population center point is predicted by the ensemble Kalman filter prediction model according to the historical population information when the environment changes, and then the population is reinitialized according to the predicted population center point. The experimental results show that the proposed algorithm is superior to other comparison strategies in most test instances.

Ensemble Prediction Approach Based on Learning to Statistical Model for Efficient Building Energy Consumption Management

With the development of modern power systems (smart grid), energy consumption prediction becomes an essential aspect of resource planning and operations. In the last few decades, industrial and commercial buildings have thoroughly been investigated for consumption patterns. However, due to the unavailability of data, the residential buildings could not get much attention. During the last few years, many solutions have been devised for predicting electric consumption; however, it remains a challenging task due to the dynamic nature of residential consumption patterns. Therefore, a more robust solution is required to improve the model performance and achieve a better prediction accuracy. This paper presents an ensemble approach based on learning to a statistical model to predict the short-term energy consumption of a multifamily residential building. Our proposed approach utilizes Long Short-Term Memory (LSTM) and Kalman Filter (KF) to build an ensemble prediction model to predict short term energy demands of multifamily residential buildings. The proposed approach uses real energy data acquired from the multifamily residential building, South Korea. Different statistical measures are used, such as mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), and R2 score, to evaluate the performance of the proposed approach and compare it with existing models. The experimental results reveal that the proposed approach predicts accurately and outperforms the existing models. Furthermore, a comparative analysis is performed to evaluate and compare the proposed model with conventional machine learning models. The experimental results show the effectiveness and significance of the proposed approach compared to existing energy prediction models. The proposed approach will support energy management to effectively plan and manage the energy supply and demands of multifamily residential buildings.

Robotic Process Automation for Stock Selection Process and Price Prediction Model using Machine Learning Techniques

The usage of AI in the financial industry has increased the reliance on stochastic models for forecasting market behaviour. Quantitative analysts are constantly working to increase the precision with which machine learning models predict stock returns. Regression models using Support Vector Machine (SVM) and Random Forest are well renowned for their ability to predict closing prices with high accuracy. This study suggests a method for analysing and forecasting stock prices using an ensemble of these algorithms.Using basic market price data from India's National Stock Exchange (NSE), datasets are used that have been preprocessed to add common technical indicators as features. The size of the training dataset is decreased by using feature selection techniques to rank the features according to their impact on the final closing price. Sentiment analysis is also used in the study to examine the effect of investor sentiment on stock prices. Twitter postings with a specific corporate hashtag are rated as good or bad using a trained Word2Vec model. The ensemble model is then trained on a fresh dataset made up of counts of both positive and negative tweets across time as well as technical indicator data.This paper makes a contribution to the area by offering an ensemble model for stock price prediction that blends SVM and Random Forest regression models. The study illustrates the significance of feature selection in lowering dataset size as well as the limited influence of aggregated sentiment analysis from Twitter data on the performance of the model as a whole. For researchers and quantitative analysts looking to improve the precision of stock price prediction models in the financial industry, these findings offer invaluable insights.

Stacked KNN with hard voting predictive approach to assist hiring process in IT organizations

Effective candidates screening is critical for any IT firm as it impacts the future growth and productivity of that firm. Currently majority of these firms follow a manual approach of hiring employees which is more prone to errors and time consuming. Prime purpose of the research is to develop an intelligent predictive model to decide upon candidate’s suitability for an applied It based job. A sample size of 13,168 instances with 19 attributes of job seekers data are used for study. An ensemble predictive meta model approach is presented in the research where a stacked KNN (K-Nearest Neighbours) algorithm combined with hard voting approach is employed. The idea is to use a single unified predictive model in place of separate classification models by considering the predicted class with maximum votes against each class label. The proposed approach comprises two functional modules. ‘Stacked KNN Learner Module’ involves the use of five variants of KNN which include 1-NN, 3-NN, 5-NN, 7-NN and 9-NN. Individual prediction of the job seeker data from these variants of KNN algorithm are input to the ‘Hard Voting Ensemble Predictive unit’ which eventually aggregates majority of predicted class votes determined for each class label to generate the final output predicted class label on basis of maximum votes. The developed ensemble meta model is successfully implemented using python programming language and its performance evaluation is done using various metrics. The implemented model generated a 96.96% prediction accuracy rate. The specificity, sensitivity and f-score value recorded was 96.36%, 96.06% and 96.26% respectively. Mean Absolute Error (MAE) and Root mean Square Error (RMSE) value observed with our proposed meta model was 0.0048 and 0.0102 respectively. A comparative analysis of the proposed model was done by varying the data sample size and it gave a consistent performance throughout. It was observed that proposed ensemble model gave an impressive 96.96% mean accuracy rate and the overall performance of other variants was consistent. Performance of proposed meta model was also compared with some existing techniques like C.45, CART and K-Means. It outperformed other techniques in terms of accurately predicting the class label of candidates applying for job. This ensemble meta model can be of great help for growing IT firms and assist the organization unit in hiring right and deserving candidates in future. Proposed work can act as a decision making framework in multi sector units with enormous work force to streamline performance appraisal process thereby enabling in hiring right people for right job.

A point prediction method based automatic machine learning for day-ahead power output of multi-region photovoltaic plants

Solar power generation (SPG) is essentially dependent on spatial and meteorological characteristics which makes the planning and operation of power systems difficult. To promote the integration of solar power into electric power grid, accurate prediction of geographically distributed SPG is needed. In this paper, we present a combined method for day-ahead SPG prediction of multi-region photovoltaic (PV) plants. First, automatic machine learning (AML) is applied to generate the most suitable ensemble prediction model with optimal parameters and then an improved genetic algorithm (GA) is implemented which processes the candidate features by assigning appropriate operators. To achieve more accurate forecast results as well as mine the interpretable relationship between SPG and related weather or PV system factors, the SPG physical model is taken into account. The method performance is evaluated by the real SPG data along with meteorological variables of multi-region PV plants in Hokkaido from 2016 to 2018. Results indicate that the combined method provides acceptable accuracy and outperforms several baselines and other methods used for comparison.

A Probabilistic Ensemble Prediction Method for PV Power in the Nonstationary Period

Due to the large number of grid connection of distributed power supply, the existing scheduling methods can not meet the demand gradually. The proposed virtual power plant provides a new idea to solve this problem. The photovoltaic power prediction provides the data basis for the scheduling of the virtual power plant. Prediction intervals of photovoltaic power is a powerful statistical tool used for quantifying the uncertainty of photovoltaic power generation in power systems. To improve the interval prediction accuracy during the non-stationary periods of photovoltaic power, this paper proposes a probabilistic ensemble prediction model, which combines the modules of data preprocessing, non-stationary period discrimination, feature extraction, deterministic prediction, uncertainty prediction, and optimization integration into a general framework. More specifically, in the non-stationary period discrimination module, the method of discriminating the difference of the power ratio difference is introduced and applied for identifying the non-stationary period of the data of photovoltaic output; in the deterministic point prediction module, a stacking- long-short-term memory neural network model is used for point forecasts; in the uncertainty interval prediction module, a BAYES neural network is introduced for probabilistic forecasts; in the optimization integration module, an optimization algorithm named Non-dominated Sorting Genetic Algorithm-II is applied for integrating and optimizing the results of the point forecast and probabilistic forecast. The proposed model is tested using two photovoltaic outputs and weather data measured from a grid-connected photovoltaic system. The results show that the proposed model outperforms conventional forecast methods to predict short-term photovoltaic power outputs and associated uncertainties. The interval width is reduced by 10–20%, and the prediction accuracy is improved by at least 10%; this can be a useful tool for photovoltaic power forecasting.

Timely and Accurately Predict Rainfall by using Ensemble Predictive Models

Weather and rainfall are important factors for human life. By depends upon the rainfall agriculture, horticulture harvesting, and goods transportation. These all are goods and supply chain processes. If in supply chain process breaks any point, Ultimately, the farmer will get the loss. Timely predicting rainfall helps the farmers and agriculture and horticulture stock manage to maintain people require India’s coastal area. For these reasons, this paper proposes the Ensemble Models (Catboost, Boost). Most of the authors are working on rainfall prediction using statistical models. Using statistical models to analyze and predict a huge amount of data is very difficult, depending upon the features. But using Ensemble models is likely to boost up the elements, and apply the classification to prediction makes it easy. This paper discusses and Compares the statistical decision tree model with ensemble models to find out the difference between the characteristics of algorithms and how they impact the timely predict the rainfall.

The influence of environmental factors on the intensity of typhoon Mirinae in the South China Sea and its forecast analysis

The rapidly intensifying typhoon Mirinae (1603) originated in the South China Sea (SCS) has been selected to analyze the high and low level circulations, vertical wind shear (VWS) and ocean conditions in and around the SCS when Mirinae was strengthening. Further, the fuzzy neural network (FNN) ensemble model has been developed for 24-hour intensity prediction based on climatology and persistence factors and dynamic factors of numerical prediction products as potential predictors. The underlying conditions were favorable for Mirinae, however, it did not be intensified to a strong typhoon because of the weak high and low level circulations and strong VWS. For the FNN ensemble prediction model input, predictors were selected by employing both a novel stepwise variable selection algorithm based on the k-nearest mutual information estimation and Laplacian Eigenmaps of manifold learning, and then the main prediction information hidden in high dimensional data set was extracted with low-dimensional structure. Results show that, the predictions of the new model are stable and reliable, and the forecast accuracy is high, providing a new forecasting tool and modeling method for the objective forecast of typhoon intensity.