Optimal Ensemble Research Articles

Ensemble learning-based nonlinear time series prediction and dynamic multi-objective optimization of organic rankine cycle (ORC) under actual driving cycle

Complicated road conditions make organic Rankine cycle (ORC) operation characteristics show hysteresis and uncertainty. Under the strong coupling correlation of many operating parameters, how to realize the dynamic optimization of ORC comprehensive performance is the key to obtain practical application potential. Based on ensemble learning mechanism, neural network modeling, ensemble system, unsupervised learning, partial mutual information and optimization algorithm are integrated. This paper presents a nonlinear time series prediction and dynamic multi-objective optimization scheme. The average accuracy increased by at least 59.6%. Taking the thermodynamic performance and environmental impact as optimization objectives, dynamic multi-objective optimization is carried out under road conditions. The optimization scheme can effectively trade off the nonlinear correlation between thermal efficiency and emissions of CO2 equivalent.

Dynamic sales prediction with auto-learning and elastic-adjustment mechanism for inventory optimization

The ability to predict product sales is invaluable for improving enterprises’ routine decisions of inventory optimization. The most effective solution of sales prediction in real applications is ensemble learning. One challenge of the solution is that it is hard to make timely and accurate predictions because of inadequate decision information and complicated and changeable sales environments. Besides, seeking optimal model combinations from the candidate set is often inaccurate and time-consuming. Another important challenge is that the predicted sales seldom consider “replenishment” of the inventory, which may lead to even higher cost. To address the challenges, we propose a novel dynamic sales prediction model with Auto-Learning and Elastic-Adjustment mechanisms (DSP-FAE): Dynamic sales prediction model can capture dynamic changing patterns of sales time series more effectively. Auto-Learning is used to automatically customize the optimal ensemble learning strategy for each warehouse-product combination in a more efficient way. Elastic-Adjustment is proposed to design a deep neural network-based adjustment factor to correct the predicted sales, which can significantly reduce inventory costs. Extensive offline and online experiments are conducted to verify the performance of the proposed model on two real-world datasets: Galanz and Cainiao. Experimental results show that the proposed DSP-FAE performs better than the selected 10 state-of-the-art baselines significantly in terms of MAE, RRSE and CORR. More importantly, it can save more than 20% inventory cost compared with traditional solutions.

Optimal Extreme Random Forest Ensemble for Active Distribution Network Forecasting-Aided State Estimation Based on Maximum Average Energy Concentration VMD State Decomposition

As the penetration rate of distributed generators (DG) in active distribution networks (ADNs) gradually increases, it is necessary to accurately estimate the operating state of the ADNs to ensure their safe and stable operation. However, the high randomness and volatility of distributed generator output and active loads have increased the difficulty of state estimation. To solve this problem, a method is proposed for forecasting-aided state estimation (FASE) in ADNs, which integrates the optimal extreme random forest based on the maximum average energy concentration (MAEC) and variable mode decomposition (VMD) of states. Firstly, a parameter optimization model based on MAEC is constructed to decompose the state variables of the ADNs into a set of intrinsic mode components using VMD. Then, strongly correlated weather and date features in ADNs state prediction are selected using the multivariate rapid maximum information coefficient (RapidMIC) based on Schmidt orthogonal decomposition. Finally, by combining the set of intrinsic mode functions of the ADNs state, calendar rules, and weather features, an ensemble FASE method based on the extreme random tree (ERT) ensemble for the ADNs based on cubature particle filtering (CPF) is developed. An optimization model based on mean absolute error and root mean square error is established to obtain the optimal integration strategy and final estimation results. Simulation verification is performed on the IEEE 118-bus standard distribution system. The results show that the proposed method achieves higher accuracy compared to other estimation methods, with root mean square errors of 1.4902 × 10−4 for voltage magnitude and 4.8915 × 10−3 for phase angle.

Ensemble of kernel extreme learning machine based elimination optimization for multi-label classification

Multi-label learning is a class of machine learning algorithms that study the classification problem of data associated with multiple labels simultaneously. Ensemble-based method is one of the representative methods in multi-label learning. In the existing ensemble-based multi-label classification methods, the essence of its base learner is still a binary or multi-class classifier. At present, there is no ensemble-based multi-label method that uses a multi-label classifier based on algorithm adaptation as a base learner. Multi-label algorithms suffer from expensive time costs, and ensemble-based methods further exacerbate the time cost. To address these issues, we propose an efficient multi-label classification method based on kernel extreme learning machine and ensemble learning. Firstly, to solve the problem of high time complexity of multi-label classifiers, we use a Gaussian kernel function to generate a kernel extreme learning machine based multi-label classifier (KELM_ML). Then, based on random sampling, we construct the base classifier, i.e., KELM_ML, in ensemble learning. Finally, to build an ensemble model of multi-label classifiers, an elimination optimization ensemble strategy is proposed by defining an encoding vector of the base classifiers and updating it. Although our method is an ensemble model, it inherits the advantages of good time complexity of ELM, i.e., fast learning time. The experimental and statistical results show that compared with baseline methods and other ensemble-based multi-label methods, our proposed method has better classification performance and stable results.

Automated Segmentation of Sacral Chordoma and Surrounding Muscles Using Deep Learning Ensemble

The manual segmentation of organ structures in radiation oncology treatment planning is a time-consuming and highly skilled task, particularly when treating rare tumors like sacral chordomas. This study evaluates the performance of automated deep learning (DL) models in accurately segmenting the gross tumor volume (GTV) and surrounding muscle structures of sacral chordomas. An expert radiation oncologist contoured 5 muscle structures (gluteus maximus, gluteus medius, gluteus minimus, paraspinal, piriformis) and sacral chordoma GTV on computed tomography images from 48 patients. We trained 6 DL auto-segmentation models based on 3-dimensional U-Net and residual 3-dimensional U-Net architectures. We then implemented an average and an optimally weighted average ensemble to improve prediction performance. We evaluated algorithms with the average and standard deviation of the volumetric Dice similarity coefficient, surface Dice similarity coefficient with 2- and 3-mm thresholds, and average symmetric surface distance. One independent expert radiation oncologist assessed the clinical viability of the DL contours and determined the necessary amount of editing before they could be used in clinical practice. Quantitatively, the ensembles performed the best across all structures. The optimal ensemble (volumetric Dice similarity coefficient, average symmetric surface distance) was (85.5 ± 6.4, 2.6 ± 0.8; GTV), (94.4 ± 1.5, 1.0 ± 0.4; gluteus maximus), (92.6 ± 0.9, 0.9 ± 0.1; gluteus medius), (85.0 ± 2.7, 1.1 ± 0.3; gluteus minimus), (92.1 ± 1.5, 0.8 ± 0.2; paraspinal), and (78.3 ± 5.7, 1.5 ± 0.6; piriformis). The qualitative evaluation suggested that the best model could reduce the total muscle and tumor delineation time to a 19-minute average. Our methodology produces expert-level muscle and sacral chordoma tumor segmentation using DL and ensemble modeling. It can substantially augment the streamlining and accuracy of treatment planning and represents a critical step toward automated delineation of the clinical target volume in sarcoma and other disease sites.

Optimizing convection‐permitting ensemble via selection of the coarse ensemble driving members

AbstractNowadays, several global ensembles (GEs) which consist of several tens of members are being run operationally. In order to locally improve the probabilistic forecasts, various forecasting centers and research institutes utilize the GEs as initial and boundary conditions to drive regional convection permitting ensembles (RCPEs). RCPEs demand significant computer resources and often a limited number of ensemble members is affordable, which is smaller than the size of the driving GE. Since each RCPE member obtains the initial and boundary conditions from a specific GE member, there are many options to select the GE members. The study uses the European Centre for Medium‐Range Weather Forecasts (ECMWF) GE consisting of 50 members, to drive 20 members of COSMO model RCPE over the Eastern Mediterranean. We compare various approaches for automatic selection of the GE members and propose several optimal methods, including a random selection, which consistently lead to a better performance of the driven RCPE. The comparison includes verification of near surface variables and precipitation using various verification metrics. The results are validated using several methods of model physics perturbation. Besides the selection of the optimal ensemble configurations, we show that at high precipitation intensities spatial up‐scaling is recommended in order to obtain useful probabilistic forecasts.

RNA design via structure-aware multifrontier ensemble optimization.

RNA design is the search for a sequence or set of sequences that will fold to desired structure, also known as the inverse problem of RNA folding. However, the sequences designed by existing algorithms often suffer from low ensemble stability, which worsens for long sequence design. Additionally, for many methods only a small number of sequences satisfying the MFE criterion can be found by each run of design. These drawbacks limit their use cases. We propose an innovative optimization paradigm, SAMFEO, which optimizes ensemble objectives (equilibrium probability or ensemble defect) by iterative search and yields a very large number of successfully designed RNA sequences as byproducts. We develop a search method which leverages structure level and ensemble level information at different stages of the optimization: initialization, sampling, mutation, and updating. Our work, while being less complicated than others, is the first algorithm that is able to design thousands of RNA sequences for the puzzles from the Eterna100 benchmark. In addition, our algorithm solves the most Eterna100 puzzles among all the general optimization based methods in our study. The only baseline solving more puzzles than our work is dependent on handcrafted heuristics designed for a specific folding model. Surprisingly, our approach shows superiority on designing long sequences for structures adapted from the database of 16S Ribosomal RNAs. Our source code and data used in this article is available at https://github.com/shanry/SAMFEO.

OEDL: an optimized ensemble deep learning method for the prediction of acute ischemic stroke prognoses using union features.

Early stroke prognosis assessments are critical for decision-making regarding therapeutic intervention. We introduced the concepts of data combination, method integration, and algorithm parallelization, aiming to build an integrated deep learning model based on a combination of clinical and radiomics features and analyze its application value in prognosis prediction. The research steps in this study include data source and feature extraction, data processing and feature fusion, model building and optimization, model training, and so on. Using data from 441 stroke patients, clinical and radiomics features were extracted, and feature selection was performed. Clinical, radiomics, and combined features were included to construct predictive models. We applied the concept of deep integration to the joint analysis of multiple deep learning methods, used a metaheuristic algorithm to improve the parameter search efficiency, and finally, developed an acute ischemic stroke (AIS) prognosis prediction method, namely, the optimized ensemble of deep learning (OEDL) method. Among the clinical features, 17 features passed the correlation check. Among the radiomics features, 19 features were selected. In the comparison of the prediction performance of each method, the OEDL method based on the concept of ensemble optimization had the best classification performance. In the comparison to the predictive performance of each feature, the inclusion of the combined features resulted in better classification performance than that of the clinical and radiomics features. In the comparison to the prediction performance of each balanced method, SMOTEENN, which is based on a hybrid sampling method, achieved the best classification performance than that of the unbalanced, oversampled, and undersampled methods. The OEDL method with combined features and mixed sampling achieved the best classification performance, with 97.89, 95.74, 94.75, 94.03, and 94.35% for Macro-AUC, ACC, Macro-R, Macro-P, and Macro-F1, respectively, and achieved advanced performance in comparison with that of methods in previous studies. The OEDL approach proposed herein could effectively achieve improved stroke prognosis prediction performance, the effect of using combined data modeling was significantly better than that of single clinical or radiomics feature models, and the proposed method had a better intervention guidance value. Our approach is beneficial for optimizing the early clinical intervention process and providing the necessary clinical decision support for personalized treatment.

Improved Dipper-Throated Optimization for Forecasting Metamaterial Design Bandwidth for Engineering Applications

Metamaterials have unique physical properties. They are made of several elements and are structured in repeating patterns at a smaller wavelength than the phenomena they affect. Metamaterials’ exact structure, geometry, size, orientation, and arrangement allow them to manipulate electromagnetic waves by blocking, absorbing, amplifying, or bending them to achieve benefits not possible with ordinary materials. Microwave invisibility cloaks, invisible submarines, revolutionary electronics, microwave components, filters, and antennas with a negative refractive index utilize metamaterials. This paper proposed an improved dipper throated-based ant colony optimization (DTACO) algorithm for forecasting the bandwidth of the metamaterial antenna. The first scenario in the tests covered the feature selection capabilities of the proposed binary DTACO algorithm for the dataset that was being evaluated, and the second scenario illustrated the algorithm’s regression skills. Both scenarios are part of the studies. The state-of-the-art algorithms of DTO, ACO, particle swarm optimization (PSO), grey wolf optimizer (GWO), and whale optimization (WOA) were explored and compared to the DTACO algorithm. The basic multilayer perceptron (MLP) regressor model, the support vector regression (SVR) model, and the random forest (RF) regressor model were contrasted with the optimal ensemble DTACO-based model that was proposed. In order to assess the consistency of the DTACO-based model that was developed, the statistical research made use of Wilcoxon’s rank-sum and ANOVA tests.

Power system transient stability preventive control optimization method driven by Stacking Ensemble Learning

The dynamic characteristics of the power system are becoming more and more complex, and the difficulty of operation control is increasing. Preventive control is the main means of power system transient stability control. This paper proposes a stacking ensemble learning-driven power system transient stability preventive control optimization method. Firstly, a transient stability assessment model based on Stacking Ensemble Deep Belief Nets (SEDBN) network is established in this research. The performance of weak classifiers is improved by SEDBN’s multi-layer ensemble structure, and the created transient stability estimator can extract diverse features and has better robustness and generalization abilities. Secondly, the trained transient stability estimator is integrated into the Aptenodytes Forsteri Optimization (AFO) algorithm as a “transient stability constraint discriminator”. Finally, with the goal of minimizing the cost of preventive control, an optimization algorithm for the preventive control of power system transient stability driven by SEDBN is established. Simulation results on IEEE 39-bus systems show that the proposed method can achieve highly efficient control solutions.

Enhanced fault diagnosis of wind energy conversion systems using ensemble learning based on sine cosine algorithm

This paper investigates the problem of incipient fault detection and diagnosis (FDD) in wind energy conversion systems (WECS) using an innovative and effective approach called the ensemble learning-sine cosine optimization algorithm (EL-SCOA). The evolved strategy involves two primary steps: first, a sine-cosine algorithm is used to extract and optimize features in order to only select the most descriptive ones. Second, to further improve the capability, thereby providing the highest accuracy performance, the newly gathered dataset is introduced as input to an ensemble learning paradigm, which merges the benefits of boosting and bagging techniques with an artificial neural network classifier. The essential goal of the developed proposal is to discriminate between the diverse operating conditions (one healthy and six faulty conditions). Three potential and frequent types of faults that can affect the system behaviors including short-circuit, open-circuit, and wear-out are considered and thereby injected at diverse locations and sides (grid and generator sides) in order to evaluate the availability and performance of the proposed technique when compared to the conventional FDD methods. The diagnosis performance is analyzed in terms of accuracy, recall, precision, and computation time. The acquired outcomes demonstrate the efficiency of the suggested diagnostic paradigm compared to conventional FDD techniques (accuracy rate has been successfully achieved 98.35%).

Community Detection in Multiplex Networks Based on Evolutionary Multitask Optimization and Evolutionary Clustering Ensemble

Community detection in multiplex networks is an emerging research topic in the field of network science. Existing methods usually ignore the similarities among component layers of a multiplex network when detecting its community structures, which decreases the detection efficiency. In this paper, we decompose the community detection in multiplex networks into two problems and propose a novel algorithm which can detect both the specific community partition for each component layer (layer-level community structure) and the composite community structure shared by all layers. Firstly, by specifying the modularity optimization on a network layer as an optimization task, we model the layer-level community detection as a multi-task optimization problem and employ an evolutionary multi-task optimization algorithm to solve it. In this way, the topology correlations among different layers can be utilized to facilitate the community detection. Secondly, we propose an evolutionary clustering ensemble method to find the composite community structure based on the layer-level community partitions and the multiplex network. The proposed method is tested on both synthetic and real-world benchmark networks and compared with classical and state-of-the-art algorithms. Experimental results show that the proposed algorithm has superior community detection performances on multiplex networks.

Comparative Study on the Performance of the Bagging Algorithm in the Breast Cancer Dataset

Breast cancer remains a predominant health concern globally. Early detection, powered by advancements in medical imaging and computational methods, plays a vital role in enhancing survival rates. This research delved into the application and performance of the Bagging algorithm on a Breast Cancer dataset that underwent image segmentation using the Canny method and feature extraction through Hu-Moments. The Bagging algorithm demonstrated moderately consistent performance across a 5-fold cross-validation, with average metrics of 56.9% accuracy, 58.3% precision, 57.7% recall, and 56.6% F-measure. While the results showcased the potential of the Bagging algorithm in classifying breast cancer data, there remains an avenue for further optimization and exploration of other ensemble or deep learning techniques. The findings contribute to the broader domain of machine learning in medical imaging and offer insights for future research directions and clinical diagnostic tool development.

English

Ripeness-based categorization is a vital function after the harvest of fruits to balance the ripening treatment. Ripeness level is the significant factor determining the quality and lifetime of fruits. Various attributes are used to identify the ripeness level, of which the manual method of categorizing based on skin colour is predominantly used. This method is prone to error at many times. This paper implements an Ensemble Particle Swarm Optimization (EnPSO) algorithm to categorize the fruits based on the ripeness level. The comparison reveals that the proposed EnPSO algorithm outperforms the state-of-the-art algorithms used for the same problem. Categorization is done using the decision tree, which provides up to 98% classification accuracy.

Short-Term Load Forecasting Based on Outlier Correction, Decomposition, and Ensemble Reinforcement Learning

Short-term load forecasting is critical to ensuring the safe and stable operation of the power system. To this end, this study proposes a load power prediction model that utilizes outlier correction, decomposition, and ensemble reinforcement learning. The novelty of this study is as follows: firstly, the Hampel identifier (HI) is employed to correct outliers in the original data; secondly, the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) is used to extract the waveform characteristics of the data fully; and, finally, the temporal convolutional network, extreme learning machine, and gate recurrent unit are selected as the basic learners for forecasting load power data. An ensemble reinforcement learning algorithm based on Q-learning was adopted to generate optimal ensemble weights, and the predictive results of the three basic learners are combined. The experimental results of the models for three real load power datasets show that: (a) the utilization of HI improves the model’s forecasting result; (b) CEEMDAN is superior to other decomposition algorithms in forecasting performance; and (c) the proposed ensemble method, based on the Q-learning algorithm, outperforms three single models in accuracy, and achieves smaller prediction errors.

RETRACTED ARTICLE: Effective heart disease prediction using improved particle swarm optimization algorithm and ensemble classification technique

RETRACTED ARTICLE: Effective heart disease prediction using improved particle swarm optimization algorithm and ensemble classification technique

Adaptive Subspace Optimization Ensemble Method for High-Dimensional Imbalanced Data Classification.

It is hard to construct an optimal classifier for high-dimensional imbalanced data, on which the performance of classifiers is seriously affected and becomes poor. Although many approaches, such as resampling, cost-sensitive, and ensemble learning methods, have been proposed to deal with the skewed data, they are constrained by high-dimensional data with noise and redundancy. In this study, we propose an adaptive subspace optimization ensemble method (ASOEM) for high-dimensional imbalanced data classification to overcome the above limitations. To construct accurate and diverse base classifiers, a novel adaptive subspace optimization (ASO) method based on adaptive subspace generation (ASG) process and rotated subspace optimization (RSO) process is designed to generate multiple robust and discriminative subspaces. Then a resampling scheme is applied on the optimized subspace to build a class-balanced data for each base classifier. To verify the effectiveness, our ASOEM is implemented based on different resampling strategies on 24 real-world high-dimensional imbalanced datasets. Experimental results demonstrate that our proposed methods outperform other mainstream imbalance learning approaches and classifier ensemble methods.

Quantifying uncertainty of marine water quality forecasts for environmental management using a dynamic multi-factor analysis and multi-resolution ensemble approach

Unpredictable climate change and human activities pose enormous challenges to assessing the water quality components in the marine environment. Accurately quantifying the uncertainty of water quality forecasts can help decision-makers implement more scientific water pollution management strategies. This work introduces a new method of uncertainty quantification driven by point prediction for solving the engineering problem of water quality forecasting under the influence of complex environmental factors. The constructed multi-factor correlation analysis system can dynamically adjust the combined weight of environmental indicators according to the performance, thereby increasing the interpretability of data fusion. The designed singular spectrum analysis is utilized to reduce the volatility of the original water quality data. The real-time decomposition technique cleverly avoids the problem of data leakage. The multi-resolution-multi-objective optimization ensemble method is adopted to absorb the characteristics of different resolution data, so as to mine deeper potential information. Experimental studies are conducted using 6 actual water quality high-resolution signals with 21,600 sampling points from the Pacific islands and corresponding low-resolution signals with 900 sampling points, including temperature, salinity, turbidity, chlorophyll, dissolved oxygen, and oxygen saturation. The results illustrate that the model is superior to the existing model in quantifying the uncertainty of water quality prediction.

Interfacial Chemistry in the Electrocatalytic Hydrogenation of CO2 over C-Supported Cu-Based Systems.

Operando soft and hard X-ray spectroscopic techniques were used in combination with plane-wave density functional theory (DFT) simulations to rationalize the enhanced activities of Zn-containing Cu nanostructured electrocatalysts in the electrocatalytic CO2 hydrogenation reaction. We show that at a potential for CO2 hydrogenation, Zn is alloyed with Cu in the bulk of the nanoparticles with no metallic Zn segregated; at the interface, low reducible Cu(I)-O species are consumed. Additional spectroscopic features are observed, which are identified as various surface Cu(I) ligated species; these respond to the potential, revealing characteristic interfacial dynamics. Similar behavior was observed for the Fe-Cu system in its active state, confirming the general validity of this mechanism; however, the performance of this system deteriorates after successive applied cathodic potentials, as the hydrogen evolution reaction then becomes the main reaction pathway. In contrast to an active system, Cu(I)-O is now consumed at cathodic potentials and not reversibly reformed when the voltage is allowed to equilibrate at the open-circuit voltage; rather, only the oxidation to Cu(II) is observed. We show that the Cu-Zn system represents the optimal active ensembles with stabilized Cu(I)-O; DFT simulations rationalize this observation by indicating that Cu-Zn-O neighboring atoms are able to activate CO2, whereas Cu-Cu sites provide the supply of H atoms for the hydrogenation reaction. Our results demonstrate an electronic effect exerted by the heterometal, which depends on its intimate distribution within the Cu phase and confirms the general validity of these mechanistic insights for future electrocatalyst design strategies.

Mapping the Age of Subtropical Secondary Forest Using Dense Landsat Time Series Data: An Ensemble Model

Quantifying secondary forest age (SFA) is essential to evaluate the carbon processes of forest ecosystems at regional and global scales. However, the successional stages of secondary forests remain poorly understood due to low-frequency thematic maps. This study aimed to estimate SFA with higher frequency and more accuracy by using dense Landsat archives. The performances of four time-series change detection algorithms—moving average change detection (MACD), Continuous Change Detection and Classification (CCDC), LandTrendr (LT), and Vegetation Change Tracker (VCT)—for detecting forest regrowth were first evaluated. An ensemble model was then developed to determine more accurate timings for forest regrowth based on the evaluation results. Finally, after converting the forest regrowth year to the SFA, the spatiotemporal and topographical distributions of the SFA were analyzed. The proposed ensemble model was validated in Jiangxi province, China, which is located in a subtropical region and has experienced drastic forest disturbances, artificial afforestation, and natural regeneration. The results showed that: (1) the developed ensemble model effectively determined forest regrowth time with significantly decreased omission and commission rates compared to the direct use of the four single algorithms; (2) the optimal ensemble model combining the independent algorithms obtained the final SFA for Jiangxi province with the lowest omission and commission rates in the spatial domain (14.06% and 24.71%) and the highest accuracy in the temporal domain (R2 = 0.87 and root mean square error (RMSE) = 3.17 years); (3) the spatiotemporal and topographic distribution from 1 to 34 years in the 2021 SFA map was analyzed. This study demonstrated the feasibility of using change detection algorithms for estimating SFA at regional to national scales and provides a data foundation for forest ecosystem research.