Weighted Combination Method Research Articles

Research on Population Development Trend in Huizhou of China Forecast Based on Optimal Weighted Combination Method and Fractional Grey Model

In this paper, the optimal weighted combination model and fractional grey model are constructed. The coefficients of the optimal weighted combination model are determined by minimizing the sum of squares of resists of each model. On the other hand, the optimal conformable fractional order and dynamic background value coefficient are determined by the quantum inspired evolutionary algorithm (QIEA). Taking the resident population from 2008 to 2018 as the research object, the optimal weighted combination model and fractional grey model were used to study the estimated and predicted values. The results are compared and analyzed. The results show that the fractional grey model is better than the optimal weighted combination model in the estimation of the values. The optimal weighted combination model is better than the fractional grey model in predicting. Meanwhile, the fractional grey model is found to be very suitable for the data values that are large, and the changes between the data are relatively small. The research results expand the application of the fractional grey model and have important implications for the policy implementation activities of Huizhou government according to the population growth trend in Huizhou.

Prediction of PM2.5 Concentration Based on the LSTM-TSLightGBM Variable Weight Combination Model

PM2.5 is one of the main pollutants that cause air pollution, and high concentrations of PM2.5 seriously threaten human health. Therefore, an accurate prediction of PM2.5 concentration has great practical significance for air quality detection, air pollution restoration, and human health. This paper uses the historical air quality concentration data and meteorological data of the Beijing Olympic Sports Center as the research object. This paper establishes a long short-term memory (LSTM) model with a time window size of 12, establishes a T-shape light gradient boosting machine (TSLightGBM) model that uses all information in the time window as the next period of prediction input, and establishes a LSTM-TSLightGBM model pair based on an optimal weighted combination method. PM2.5 hourly concentration is predicted. The prediction results on the test set show that the mean squared error (MAE), root mean squared error (RMSE), and symmetric mean absolute percentage error (SMAPE) of the LSTM-TSLightGBM model are 11.873, 22.516, and 19.540%, respectively. Compared with LSTM, TSLightGBM, the recurrent neural network (RNN), and other models, the LSTM-TSLightGBM model has a lower MAE, RMSE, and SMAPE, and higher prediction accuracy for PM2.5 and better goodness-of-fit.

A novel hybrid model based on nonlinear weighted combination for short-term wind power forecasting

Wind power forecasting plays a vital role in enhancing the efficiency of power grid operation and increasing the competitiveness of power market. In this paper, a novel hybrid forecasting model is developed by using the decomposition strategy, nonlinear weighted combination, and two deep learning models to overcome the drawbacks of the linear weighted combination and further enhance wind power forecasting accuracy and stability. Firstly, the variational mode decomposition (VMD) technique is employed to decompose the original wind power series to extract local features. Then, the long short-term memory neural networks (LSTM) and deep belief networks based on particle swarm optimization (PSO-DBN) are utilized to construct sub-series prediction models. Finally, the multiple sub-series forecasting models are integrated by a nonlinear weighted combination method based on PSO-DBN to construct a hybrid model for short-term wind power forecasting. To verify the performance of the developed forecasting model, wind speed data of 10 min from a wind farm in Shaanxi Dingbian, China are selected as case studies. The results show that the proposed method in this paper is more effective than other existing methods.

Accurate prediction of multi-label protein subcellular localization through multi-view feature learning with RBRL classifier.

Multi-label proteins can participate in carrier transportation, enzyme catalysis, hormone regulation and other life activities. Meanwhile, they play a key role in the fields of biopharmaceuticals, gene and cell therapy. This article proposes a prediction method called Mps-mvRBRL to predict the subcellular localization (SCL) of multi-label protein. Firstly, pseudo position-specific scoring matrix, dipeptide composition, position specific scoring matrix-transition probability composition, gene ontology and pseudo amino acid composition algorithms are used to obtain numerical information from different views. Based on the contribution of five individual feature extraction methods, differential evolution is used for the first time to learn the weight of single feature, and then these original features use a weighted combination method to fuse multi-view information. Secondly, the fused high-dimensional features use a weighted linear discriminant analysis framework based on binary weight form to eliminate irrelevant information. Finally, the best feature vector is input into the joint ranking support vector machine and binary relevance with robust low-rank learning classifier to predict the SCL. After applying leave-one-out cross-validation, the overall actual accuracy (OAA) and overall location accuracy (OLA) of Mps-mvRBRL on the training set of Gram-positive bacteria are both 99.81%. The OAA on the test sets of plant, virus and Gram-negative bacteria datasets are 97.24%, 98.55% and 98.20%, respectively, and the OLA are 97.16%, 97.62% and 98.28%, respectively. The results show that the model achieves good prediction performance for predicting the SCL of multi-label protein.

Seismic vulnerability of prefabricated reinforced concrete frame structure based on local outsource steel tube bolted column–column connection

In this paper, the seismic performance of a prefabricated frame structure with a local outsource steel tube bolted column–column connect is evaluated from the perspective of seismic vulnerability theory. Firstly, a simplified model of the prefabricated frame structure was constructed and validated by experiments. Then, a six-story prefabricated reinforced concrete frame structure (PRCS) and a cast-in-situ reinforced concrete frame structure (CRCS) were designed as examples to get the increment dynamic analysis (IDA) of the structure under 12 ground motions, and the two-parameter damage model was used as the structural requirement index. As a traditional structural requirement index-the maximum inter-storey drift angle cannot accurately describe the mechanism of structural damage. Therefore, two types of damage models are compared and analyzed. In addition, in order to evaluate the damage of frame structure effectively, a new damage index weighted combination method is proposed, and its feasibility is verified. Finally, the IDA curve and vulnerability curve with Kunnath two-parameter damage model and the maximum inter-story displacement angle as the requirement index are drawn. The results show that the two-parameter damage model is more accurate than the maximum inter-storey drift angle model in evaluating the seismic performance of the PRCS and CRCS. It shows that the maximum inter-story displacement angle model can overestimate the collapse resistance of the PRCS by 60.7% on average, and the collapse resistance of the CRCS by 75.67% on average. The seismic performance of the CRCS is better than that of the PRCS as the seismic intensity increases. Although the seismic performance of fabricated columns is similar to that of cast-in-place columns, there is still a certain gap in the seismic performance of frame structures.

Short-term load forecasting based on LSTM-RF-SVM combined model

Aiming at the problem of low accuracy of single model forecasting power load, a combined LSTM-RF-SVM prediction model based on Long Short-Term Memory network (LSTM), Random Forest (RF) and Support Vector Machine (SVM) is designed. Firstly, the preprocessed load data, meteorological data and date data are input into the three models according to the sliding time window. The prediction results of each model are obtained through training. Then the optimal weighted combination method is uesd to calculate the weight coefficients of the three models in the prediction results. Finally, the final prediction results are obtained by integrating the weight coefficients. Experimental results show that compared with other methods, the established forecasting model improves the accuracy of short-term load forecasting.

Optimization of the Current Control for the Pulsed Power Cables of the Electromagnetic Railgun

The current control of the breech pulsed power cables and the stability of the total current are important factors which have an influence on the performance of the electromagnetic railgun system. In order to achieve these two targets, a two-objective optimization model through the genetic algorithms and weighted combination method is established. An optimization example of 20-mm railgun with 1-MJ fixed energy storage is given. The results show that the methods can be satisfied to the optimization design under the following premises. The reference value for the mean square error of the pulsed power cable peak current which represents the degree of the current control is selected between 1.5 and 4 kA, and the reference value of the compression ratio which represents the stability of the total current depends on the average compression ratio of the initial population. The mean square deviation of the best individual can be reduced to 600–750 A, and the compression ratio can be increased to 0.64–0.68 when the peak value of the total current is limited between 500 and 560 kA.

Selecting and Combining Classifiers Based on Centrality Measures

Centrality measures have been helping to explain the behavior of objects, given their relation, in a wide variety of problems, since sociology to chemistry. This work considers these measures to assess the importance of every classifier belonging to an ensemble of classifiers, aiming to improve a Multiple Classifier System (MCS). Assessing the classifier’s importance by employing centrality measures, inspired two different approaches: one for selecting classifiers and another for fusion. The selection approach, called Centrality Based Selection (CBS), adopts a trade-off between the classifier’s accuracy and their diversity. The sub-optimal selected subset presents good results against selection methods from the literature, being superior in 67.22% of the cases. The second approach, the integration, is named Centrality Based Fusion (CBF). This approach is a weighted combination method, which is superior to literature in 70% of the cases.

Assessment of seismic damage on frame structures across the earth fissure under earthquake

An accurate evaluation of structural damage is essential to performance-based seismic design for the structure across the earth fissure. By comparing the calculation results from three commonly used damage models and the experimental results, a weighted combination method using Chen model was selected in this paper as the seismic damage evaluation. A numerical model considering the soil-structure interaction (SSI) was proposed using ABAQUS software. The model was calibrated by comparing with the experimental results. The results from the analysis indicated that, for the structure across the earth fissure, the existence of earth fissure changed the damage distribution of the structural members. The damage of structural members in the hanging wall was greater than that in the foot wall. Besides, the earth fissure enlarged the damage degree of the structural members at the same location and changed the position of the weak story. Moreover, the damage degree of the structure across the earth fissure was greater than that of the structure without the earth fissure under the same excitation. It is expected that the results from this research would enhance the understanding of the performance-based seismic design for the structure across the earth fissure.

New dynamic two-layer model for predicting depth-averaged velocity in open channel flows with rigid submerged canopies of different densities

The depth-averaged velocity is the commonly used engineering quantity in natural rivers, and it needs to be predicted in advance, especially in flood seasons. A model that can provide a unified physical foundation for open channel flows with different canopy densities remains lacking despite ongoing researches. Here, we use the concept of the auxiliary bed to describe the influence of momentum exchange on rigid canopy elements with varying density and submergence. The auxiliary bed divides the vegetated flow into a basal layer and a suspension layer to predict average velocity in each layer separately. In the basal layer, the velocity profile is assumed to be uniform. In the suspension layer, a parameter called “penetration depth” is applied to present the variations in velocity distribution. We also apply a data-driven method, called genetic programming (GP), to derive Chezy-like predictors for average velocity in the suspension layer. Compared to the hydraulic resistance equation for rough-wall flows, the new formulae calculated by the weighted combination method show sound physical meanings. In addition, comparison with other models shows that the new dynamic two-layer model achieves high accuracy in flow rate estimation, especially for vegetated flow with sparse canopies.

Prediction of Agricultural plastic agricultural plastic film use based on combined prediction model

Although increasing the yield of crops, the large-scale use of agricultural plastic film in agricultural production, has caused damage to the ecological environment. This paper analyzes the current situation of the use of plastic agricultural plastic agricultural plastic film in China from 1999 to 2015. The GM(1, 1) model and the ARIMA(0, 2, 0) model are used to predict the mulch usage, and then the optimal weight combination method is used to obtain the grey-time series combination prediction model. The results show that the accuracy of synthetic prediction model is higher than that of the single model and has better applicability. The prediction results of the combined model can be used as a reference for the scientific use and management of agricultural plastic film in China.

Binary Genetic Swarm Optimization: A Combination of GA and PSO for Feature Selection

AbstractFeature selection (FS) is a technique which helps to find the most optimal feature subset to develop an efficient pattern recognition model under consideration. The use of genetic algorithm (GA) and particle swarm optimization (PSO) in the field of FS is profound. In this paper, we propose an insightful way to perform FS by amassing information from the candidate solutions produced by GA and PSO. Our aim is to combine the exploitation ability of GA with the exploration capacity of PSO. We name this new model as binary genetic swarm optimization (BGSO). The proposed method initially lets GA and PSO to run independently. To extract sufficient information from the feature subsets obtained by those, BGSO combines their results by an algorithm called average weighted combination method to produce an intermediate solution. Thereafter, a local search called sequential one-point flipping is applied to refine the intermediate solution further in order to generate the final solution. BGSO is applied on 20 popular UCI datasets. The results were obtained by two classifiers, namely,knearest neighbors (KNN) and multi-layer perceptron (MLP). The overall results and comparisons show that the proposed method outperforms the constituent algorithms in 16 and 14 datasets using KNN and MLP, respectively, whereas among the constituent algorithms, GA is able to achieve the best classification accuracy for 2 and 7 datasets and PSO achieves best accuracy for 2 and 4 datasets, respectively, for the same set of classifiers. This proves the applicability and usefulness of the method in the domain of FS.

Study on image reconstruction of capacitively coupled electrical impedance tomography (CCEIT)

The aim of this work is to study the image reconstruction of capacitively coupled electrical impedance tomography (CCEIT) by using total impedance of a gas–liquid two-phase flow. The results of image reconstruction that utilise the real part, the imaginary part, the amplitude of the impedance, and the image reconstruction results by making use of different parts of the total impedance are investigated and discussed. By combining a linear back projection (LBP) algorithm and a K-means clustering algorithm, a new image reconstruction algorithm for CCEIT is proposed. The LBP is used to obtain the original reconstructed image. The K-means is adopted to automatically obtain the gray level threshold. The final reconstructed image is acquired with an established gray level threshold filter. With the new algorithm (LBP + K-means), the images reconstructed by using different parts of the impedance are obtained. To make full use of total impedance information, an image fusion method based on the weighted combination method is presented. With a developed 12-electrode CCEIT prototype, the image reconstruction experiments are conducted. Experimental results show that all three parts of the impedance can reflect the phase distribution characteristics of the gas–liquid two-phase flow from different aspects. Image fusion results indicate that making full use of the different parts of the total impedance of the gas–liquid two-phase flow can effectively improve the quality of the image reconstruction. The experimental results also verify the feasibility and the effectiveness of the proposed new image reconstruction algorithm. Compared with conventional algorithms, the proposed image reconstruction method can obtain comparable/better image reconstruction results with less prior knowledge. The influence of manual intervention on the image reconstruction results can be effectively avoided.

Performance Evaluation of Non-GPS Based Localization Techniques under Shadowing Effects

Non-GPS localization has gained much interest from researchers and industries recently because GPS might fail to meet the accuracy requirements in shadowing environments. The two most common range-based non-GPS localization methods, namely Received Signal Strength Indicator (RSSI) and Angle-of-Arrival (AOA), have been intensively mentioned in the literature over the last decade. However, an in-depth analysis of the weighted combination methods of AOA and RSSI in shadowing environments is still missing in the state-of-the-art. This paper proposes several weighted combinations of the two RSSI and AOA components in the form of pAOA + qRSSI, devises the mathematical model for analyzing shadowing effects, and evaluates these weighted combination localization methods from both accuracy and precision perspectives. Our simulations show that increasing the number of anchors does not necessarily improve the precision and accuracy, that the AOA component is less susceptible to shadowing than the RSSI one, and that increasing the weight of the AOA component and reducing that of the RSSI component help improve the accuracy and precision at high Signal-to-Noise Ratios (SNRs). This observation suggests that some power control algorithm could be used to increase automatically the transmitted power when the channel experiences large shadowing to maintain a high SNR, thus guaranteeing both accuracy and precision of the weighted combination localization techniques.

Using OpenStreetMap (OSM) to enhance the classification of local climate zones in the framework of WUDAPT

The World Urban Database and Access Portal Tools (WUDAPT) project has adopted the Local Climate Zone (LCZ) scheme as a basic and consistent description of form and function of cities at neighbourhood scale. LCZs are classified using crowdsourced training samples, open data and open source software but the quality of the maps still needs improvement. The aim of this paper is to investigate the use of data from OpenStreetMap (OSM) to enhance the development of LCZs, complement the existing data sources, and improve the accuracy of the maps. Various features were derived from the OSM database and combined with seasonal LCZ maps. Therefore a methodology was developed and tested for Hamburg, Germany, using a fuzzy approach and then a weighted combination method was applied to combine the inputs from OSM with each of the seasonal LCZ maps. The results showed that improvements can be achieved for certain classes, either in terms of accuracy, e.g. rectifying the misclassification of agricultural areas as heavy industry, or representation on the map, e.g. a more detailed water network. The approach developed is flexible and allows for knowledge about which data sources are more reliable as inputs to the combination and weighting process.

Crash performance evaluation of a new movable median guardrail on highways

In this study, a new movable median guardrail is proposed to overcome the structural defects of and to improve the low anti-collision performance of two conventional central/ median guardrails comprising of the concrete and W-beam. The design parameters of this movable median guardrail are optimized based on the uniform design method and a linear weighted combination method in accordance with the requirements given in the National Cooperative Highway Research Program (NCHRP) Report 350. This proposed guardrail is systematically evaluated in terms of its energy absorbing capacity, vehicular acceleration, post-impact trajectory of the impacting vehicle, and behavior of the guardrail upon impact through a three dimensional computer simulation using LS-DYNA code. In the evaluation process, performance comparisons of the moveable median guardrail are made with the concrete and W-beam guardrails. The results shows that the performance of the proposed movable median guardrail is superior as compared to the conventional concrete and W-beam guardrails as it offers: a higher level of crash performance is exhibited, the occupants of the impacting vehicle is better protected, and the impacting vehicle exhibits better post collision stability.

An Innovative Minimum Hitting Set Algorithm for Model-Based Fault Diagnosis in Power Distribution Network

The distribution network plays a great role in the power system, and any fault in it may threaten the safe and stable operation of the power system. Hence, fault diagnosis has an important role in protecting the distribution network and maintaining power system stability. The model-based diagnosis (MBD) is one of the diagnostic methods that have some advantages compared with the common diagnosis methods. The latter, such as expert diagnosis systems depend on the professional experience and fault information. However, the inefficiency and incomplete calculation of the minimum hitting set (MHS) limits the performance of the MBD. In this paper, to overcome these limitations, an innovative MHS algorithm which considers the nature and characteristics of the distribution network is proposed. In the proposed algorithm, a new fitness function is constructed by a weighted combination method, which allows particles to move directly toward the MHS without the effect of non-hitting set particles. Finally, three cases studies and discussion on the distribution network are introduced to validate the advantages of the proposed algorithm, in terms of the computation efficiency and accuracy.

High dimensional expression of combined approximation model

In this paper, a new high dimensional model representation (HDMR), combined TPS, SVR and Kriging (TSK) by weighted combination method based on generalised mean square error (GMSE) is proposed called TSK-HDMR. The TSK-HDMR not only takes advantage of robustness of combined approximation model but also reveals the correlation relationships among input variables. The model and the algorithm fundamentally change the exponentially growing computation cost to be polynomial. Numerical examples are given to verify the robustness and modelling efficiency of the modelling method. Compared with the classical high-dimension model techniques, in the application of the modelling of air resistance characteristic of the car, the efficiency and accuracy are improved.

High dimensional expression of combined approximation model

In this paper, a new high dimensional model representation (HDMR), combined TPS, SVR and Kriging (TSK) by weighted combination method based on generalised mean square error (GMSE) is proposed called TSK-HDMR. The TSK-HDMR not only takes advantage of robustness of combined approximation model but also reveals the correlation relationships among input variables. The model and the algorithm fundamentally change the exponentially growing computation cost to be polynomial. Numerical examples are given to verify the robustness and modelling efficiency of the modelling method. Compared with the classical high-dimension model techniques, in the application of the modelling of air resistance characteristic of the car, the efficiency and accuracy are improved.

Synchronous Pattern Matching Principle-Based Residential Demand Response Baseline Estimation: Mechanism Analysis and Approach Description

Most current customer baseline load (CBL) estimation methods for incentive-based demand response (DR) rely heavily on historical data and are unable to adapt to the cases when the load patterns (LPs) in the DR event day are not similar enough to those in non-DR days. After the error generation mechanism of current methods is revealed, a synchronous pattern matching principle-based residential CBL estimation approach without historical data requirement is proposed. All customers are split into DR and CONTROL group, including DR participants and non-DR customers, respectively. First, all CONTROL group customers are clustered into several non-overlapping clusters according to LPs similarity in the DR event day. Second, each DR participant is matched to the most similar cluster in the CONTROL group according to the similarity between its load curve segments in DR event day, excluding DR part and cluster centroids. Third, the CBL of each DR participant is estimated with an optimized weight combination method using the load data within the DR event period of all the customers in the very matching cluster in the CONTROL group. A comparison with five well-known CBL estimation methods using a dataset of 736 residential customers indicates that the proposed approach has better overall performance than other current CBL estimation methods.