Search results
1 – 10 of 17Jianping Zhang, Leilei Wang and Guodong Wang
With the rapid advancement in the automotive industry, the friction coefficient (FC), wear rate (WR) and weight loss (WL) have emerged as crucial parameters to measure the…
Abstract
Purpose
With the rapid advancement in the automotive industry, the friction coefficient (FC), wear rate (WR) and weight loss (WL) have emerged as crucial parameters to measure the performance of automotive braking systems, so the FC, WR and WL of friction material are predicted and analyzed in this work, with an aim of achieving accurate prediction of friction material properties.
Design/methodology/approach
Genetic algorithm support vector machine (GA-SVM) model is obtained by applying GA to optimize the SVM in this work, thus establishing a prediction model for friction material properties and achieving the predictive and comparative analysis of friction material properties. The process parameters are analyzed by using response surface methodology (RSM) and GA-RSM to determine them for optimal friction performance.
Findings
The results indicate that the GA-SVM prediction model has the smallest error for FC, WR and WL, showing that it owns excellent prediction accuracy. The predicted values obtained by response surface analysis are closed to those of GA-SVM model, providing further evidence of the validity and the rationality of the established prediction model.
Originality/value
The relevant results can serve as a valuable theoretical foundation for the preparation of friction material in engineering practice.
Details
Keywords
Yanjie Wang, Zhengchao Xie, InChio Lou, Wai Kin Ung and Kai Meng Mok
The purpose of this paper is to examine the applicability and capability of models based on a genetic algorithm and support vector machine (GA-SVM) and a genetic algorithm and…
Abstract
Purpose
The purpose of this paper is to examine the applicability and capability of models based on a genetic algorithm and support vector machine (GA-SVM) and a genetic algorithm and relevance vector machine (GA-RVM) for the prediction of phytoplankton abundances associated with algal blooms in a Macau freshwater reservoir, and compare their performances with an artificial neural network (ANN) model.
Design/methodology/approach
The hybrid models GA-SVM and GA-RVM were developed for the optimal control of parameters for predicting (based on the current month’s variables) and forecasting (based on the previous three months’ variables) phytoplankton dynamics in a Macau freshwater reservoir, MSR, which has experienced cyanobacterial blooms in recent years. There were 15 environmental parameters, including pH, SiO2, alkalinity, bicarbonate (HCO3−), dissolved oxygen (DO), total nitrogen (TN), UV254, turbidity, conductivity, nitrate (NO3−), orthophosphate (PO43−), total phosphorus (TP), suspended solids (SS) and total organic carbon (TOC) selected from the correlation analysis, with eight years (2001-2008) of data for training, and the most recent three years (2009-2011) for testing.
Findings
For both accuracy performance and generalized performance, the ANN, GA-SVM and GA-RVM had similar predictive powers of R2 of 0.73-0.75. However, whereas ANN and GA-RVM models showed very similar forecast performances, GA-SVM models had better forecast performances of R2 (0.862), RMSE (0.266) and MAE (0.0710) with the respective parameters of 0.987, 0.161 and 0.032 optimized using GA.
Originality/value
This is the first application of GA-SVM and GA-RVM models for predicting and forecasting algal bloom in freshwater reservoirs. GA-SVM was shown to be an effective new way for monitoring algal bloom problem in water resources.
Details
Keywords
Yunjian Hu, Jie Sun, Wen Peng and Dianhua Zhang
In the cold rolling process, friction coefficient, oil film thickness and other factors vary dramatically with the change in the rolling speed, which seriously affects the strip…
Abstract
Purpose
In the cold rolling process, friction coefficient, oil film thickness and other factors vary dramatically with the change in the rolling speed, which seriously affects the strip thickness deviation. This paper aims to improve the strip control precision with the forecast roll gap model based on CF-PSO-SVM approach in the rolling process.
Design/methodology/approach
In this paper, a novel forecasting model of the roll gap based on support vector machine (SVM) optimized by particle swarm optimization with compression factor (CF-PSO) is proposed. Based on lots of online data, the roll gap models regressed by PSO-SVM, genetic algorithm (GA)-SVM and CF-PSO-SVM are obtained and verified through evaluating the performances with the decision coefficient (R2), mean absolute error and root mean square error. In addition, with the good forecasting performances of CF-PSO-SVM, a roll gap compensation model is studied.
Findings
The results indicate that the proposed CF-PSO-SVM has excellent learning regression ability compared with other optimization algorithms. Meanwhile, a roll gap compensation model based on the rolling speed and plastic coefficient is obtained, which has been proved validated in product.
Originality/value
In this paper, the SVM algorithm is combined with traditional rolling technology to solve the problems in actual production, which has great supporting significance for the improvement of production efficiency.
Details
Keywords
Anan Zhang, Pengxiang Zhang and Yating Feng
The study aims to accomplish the short-term load forecasting for microgrids. Short-term load forecasting is a vital component of economic dispatch in microgrids, and the…
Abstract
Purpose
The study aims to accomplish the short-term load forecasting for microgrids. Short-term load forecasting is a vital component of economic dispatch in microgrids, and the forecasting error directly affects the economic efficiency of operation. To some extent, short-term load forecasting is more difficult in microgrids than in macrogrids.
Design/methodology/approach
This paper presents the method of Dragonfly Algorithm-based support vector machine (DA-SVM) to forecast the short-term load in microgrids. This method adopts the combination of penalty factor C and kernel parameters of SVM which needs to be optimized as the position of dragonfly to find the solution. It takes the forecast accuracy calculated by SVM as the current fitness value of dragonfly and the optimal position of dragonfly obtained through iteration is considered as the optimal combination of parameters C and s of SVM.
Findings
DA-SVM algorithm was used to do short-term load forecast in the microgrid of an offshore oilfield group in the Bohai Sea, China and the forecasting results were compared with those of PSO-SVM, GA-SVM and BP neural network models. The experimental results indicate that the DA-SVM algorithm has better global searching ability. In the case of study, the root mean square errors of DA-SVA are about 1.5 per cent and its computation time is saved about 50 per cent.
Originality/value
The DA-SVM model presented in this paper provides an efficient and effective method of short-term load forecasting for a microgrid electric power system.
Details
Keywords
Haiyang Gu, Kaiqi Liu, Xingyi Huang, Quansheng Chen, Yanhui Sun and Chin Ping Tan
Parallel factor analysis (PARAFAC) coupled with support-vector machine (SVM) was carried out to identify and discriminate between the fluorescence spectroscopies of coconut water…
Abstract
Purpose
Parallel factor analysis (PARAFAC) coupled with support-vector machine (SVM) was carried out to identify and discriminate between the fluorescence spectroscopies of coconut water brands.
Design/methodology/approach
PARAFAC was applied to reduce three-dimensional data of excitation emission matrix (EEM) to two-dimensional data. SVM was applied to discriminate between six commercial coconut water brands in this study. The three largest variation data from fluorescence spectroscopy were extracted using the PARAFAC method as the input data of SVM classifiers.
Findings
The discrimination results of the six commercial coconut water brands were achieved by three SVM methods (Ga-SVM, PSO-SVM and Grid-SVM). The best classification accuracies were 100.00%, 96.43% and 94.64% for the training set, test set and CV accuracy.
Originality/value
The above results indicate that fluorescence spectroscopy combined with PARAFAC and SVM methods proved to be a simple and rapid detection method for coconut water and perhaps other beverages.
Details
Keywords
Wei Feng, Yuqin Wu and Yexian Fan
The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations (NSS). Because the conventional methods for the…
Abstract
Purpose
The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations (NSS). Because the conventional methods for the prediction of NSS, such as support vector machine, particle swarm optimization, etc., lack accuracy, robustness and efficiency, in this study, the authors propose a new method for the prediction of NSS based on recurrent neural network (RNN) with gated recurrent unit.
Design/methodology/approach
This method extracts internal and external information features from the original time-series network data for the first time. Then, the extracted features are applied to the deep RNN model for training and validation. After iteration and optimization, the accuracy of predictions of NSS will be obtained by the well-trained model, and the model is robust for the unstable network data.
Findings
Experiments on bench marked data set show that the proposed method obtains more accurate and robust prediction results than conventional models. Although the deep RNN models need more time consumption for training, they guarantee the accuracy and robustness of prediction in return for validation.
Originality/value
In the prediction of NSS time-series data, the proposed internal and external information features are well described the original data, and the employment of deep RNN model will outperform the state-of-the-arts models.
Details
Keywords
In order to improve the weak recognition accuracy and robustness of the classification algorithm for brain-computer interface (BCI), this paper proposed a novel classification…
Abstract
Purpose
In order to improve the weak recognition accuracy and robustness of the classification algorithm for brain-computer interface (BCI), this paper proposed a novel classification algorithm for motor imagery based on temporal and spatial characteristics extracted by using convolutional neural networks (TS-CNN) model.
Design/methodology/approach
According to the proposed algorithm, a five-layer neural network model was constructed to classify the electroencephalogram (EEG) signals. Firstly, the author designed a motor imagery-based BCI experiment, and four subjects were recruited to participate in the experiment for the recording of EEG signals. Then, after the EEG signals were preprocessed, the temporal and spatial characteristics of EEG signals were extracted by longitudinal convolutional kernel and transverse convolutional kernels, respectively. Finally, the classification of motor imagery was completed by using two fully connected layers.
Findings
To validate the classification performance and efficiency of the proposed algorithm, the comparative experiments with the state-of-the-arts algorithms are applied to validate the proposed algorithm. Experimental results have shown that the proposed TS-CNN model has the best performance and efficiency in the classification of motor imagery, reflecting on the introduced accuracy, precision, recall, ROC curve and F-score indexes.
Originality/value
The proposed TS-CNN model accurately recognized the EEG signals for different tasks of motor imagery, and provided theoretical basis and technical support for the application of BCI control system in the field of rehabilitation exoskeleton.
Details
Keywords
Building energy management systems use important information from indoor room temperature (IRT) forecasting to predict daily loads within smart buildings. IRT forecasting is a…
Abstract
Purpose
Building energy management systems use important information from indoor room temperature (IRT) forecasting to predict daily loads within smart buildings. IRT forecasting is a complex and challenging task, especially when energy demands are exponentially rising. The purpose of this paper is to review the relevant literature on indoor temperature forecasting in the past two decades and draw inferences on important methodologies with influencing variables and offer future directions.
Design/methodology/approach
The motivation for this work is based on the research work done in the field of intelligent buildings and energy related sector. The focus of this study is based on past literature on forecasting models and methodologies related to IRT forecasting for building energy management, with an emphasis on data-driven models (statistical and machine learning models). The methodology adopted here includes review of several journals, conference papers, reference books and PhD theses. Selected forecasting methodologies have been reviewed for indoor temperature forecasting contributing to building energy consumption. The models reviewed here have been earmarked for their benefits, limitations, location of study, accuracy along with the identification of influencing variables.
Findings
The findings are based on 62 studies where certain accuracy metrics and influencing explanatory variables have been reviewed. Linear models have been found to show explanatory relationships between the variables. Nonlinear models are found to have better accuracy than linear models. Moreover, IRT profiles can be modeled with enhanced accuracy and generalizability through hybrid models. Although deep learning models are found to have better performance for this study.
Research limitations/implications
This is accuracy-based study of data-driven models. Their run-time performance and cost implications review and review of physical, thermal and simulation models is future scope.
Originality/value
Despite the earlier work conducted in this field, there is a lack of organized and comprehensive evaluation of peer reviewed forecasting methodologies. Indoor temperature depends on various influencing explanatory variables which poses a research challenge for researchers to develop suitable predictive model. This paper presents a critical review of selected forecasting methodologies and provides a list of important methodologies along with influencing variables, which can help future researchers in the field of building energy management sector. The forecasting methods presented here can help to determine appropriate heating, ventilation and air-conditioning systems for buildings.
Details
Keywords
The purpose is to analyze and discuss the sustainable development (SD) and financing risk assessment (FRA) of resource-based industrial clusters under the Internet of Things (IoT…
Abstract
Purpose
The purpose is to analyze and discuss the sustainable development (SD) and financing risk assessment (FRA) of resource-based industrial clusters under the Internet of Things (IoT) economy and promote the application of Machine Learning methods and intelligent optimization algorithms in FRA.
Design/methodology/approach
This study used the Support Vector Machine (SVM) algorithm that is analyzed together with the Genetic Algorithm (GA) and Ant Colony Optimization (ACO) algorithm. First, Yulin City in Shaanxi Province is selected for case analysis. Then, resource-based industrial clusters are studied, and an SD early-warning model is implemented. Then, the financing Risk Assessment Index System is established from the perspective of construction-operation-transfer. Finally, the risk assessment results of Support Vector Regression (SVR) and ACO-based SVR (ACO-SVR) are analyzed.
Findings
The results show that the overall sustainability of resource-based industrial clusters and IoT industrial clusters is good in the Yulin City of Shaanxi Province, and the early warning model of GA-based SVR (GA-SVR) has been achieved good results. Yulin City shows an excellent SD momentum in the resource-based industrial cluster, but there are still some risks. Therefore, it is necessary to promote the industrial structure of SD and improve the stability of the resource-based industrial cluster for Yulin City.
Originality/value
The results can provide a direction for the research on the early warning and evaluation of the SD-oriented resource-based industrial clusters and the IoT industrial clusters, promoting the application of SVM technology in the engineering field.
Details
Keywords
Fuzan Chen, Harris Wu, Runliang Dou and Minqiang Li
The purpose of this paper is to build a compact and accurate classifier for high-dimensional classification.
Abstract
Purpose
The purpose of this paper is to build a compact and accurate classifier for high-dimensional classification.
Design/methodology/approach
A classification approach based on class-dependent feature subspace (CFS) is proposed. CFS is a class-dependent integration of a support vector machine (SVM) classifier and associated discriminative features. For each class, our genetic algorithm (GA)-based approach evolves the best subset of discriminative features and SVM classifier simultaneously. To guarantee convergence and efficiency, the authors customize the GA in terms of encoding strategy, fitness evaluation, and genetic operators.
Findings
Experimental studies demonstrated that the proposed CFS-based approach is superior to other state-of-the-art classification algorithms on UCI data sets in terms of both concise interpretation and predictive power for high-dimensional data.
Research limitations/implications
UCI data sets rather than real industrial data are used to evaluate the proposed approach. In addition, only single-label classification is addressed in the study.
Practical implications
The proposed method not only constructs an accurate classification model but also obtains a compact combination of discriminative features. It is helpful for business makers to get a concise understanding of the high-dimensional data.
Originality/value
The authors propose a compact and effective classification approach for high-dimensional data. Instead of the same feature subset for all the classes, the proposed CFS-based approach obtains the optimal subset of discriminative feature and SVM classifier for each class. The proposed approach enhances both interpretability and predictive power for high-dimensional data.
Details