Support Vector Machine Prediction Research Articles

High strength aluminium alloy fatigue damage alert of high speed train gearbox shell using acoustic emission instrument

As a key component of high speed train, the gearbox shell must be running safely. The main damage form of high speed train gearbox shell is fatigue, and to effectively predict the working state and give out safety alert is of great significance of operation safety. In this study, the acoustic emission instrument has been used for real-time and non-destruction monitoring fatigue damage progress of high strength aluminium alloy which is the material of high speed train gearbox shell. By comparing with the fatigue damage progress, the feature parameter and its threshold of acoustic emission (AE) signal for classifying the states has been defined. The consistence of the feature is discussed by Hurst index method. A particle swarm optimisation-least square support vector machines (PSO-LSSVM) prediction model has been designed to predict the feature of next step, and the safety alert is given by comparing with the threshold of the feature. In this study, the prediction result is about 600s to 1600s earlier than the critical time, and by comparing acceleration test and real condition, it can give enough time for the train to stop and evacuate passengers.

Combining the Multi‐Genetic Algorithm and Support Vector Machine for Fault Diagnosis of Bearings

Overstudy or understudy phenomena can sometimes occur due to the strong dependence of support vector machine (SVM) algorithms on particular parameters and the lack of systems theory relating to parameter selection. In this paper, a parameter optimization algorithm for the SVM is proposed based on multi‐genetic algorithm. The algorithm optimizes the correlation kernel parameters of the SVM using evolutionary search principles of multiple swarm genetic algorithms to obtain a superior SVM prediction model. The experimental results demonstrate that by combining the genetic algorithm and SVM algorithm, fault diagnosis can be effectively realized for bearings of rotating machinery.

Movie Genre Preference Prediction Using Machine Learning for Customer-Based Information

This work introduces a movie genre preference predictive model usable by small and medium-sized enterprises (SMEs) who are in need of a data-based and analytical approach to stock proper movies for local audiences and retain more customers. We used classification models to extract features from one thousand customers’ demographic, behavioral and social information to predict their movie genre preference. In the implementation, a Gaussian kernel support vector machine (SVM) classification model and a logistic regression model were established to extract features from sample data and their test error-in-sample were compared. Comparison of error-out-sample was also made under different Vapnik–Chervonenkis (VC) dimensions in the machine learning algorithm to find and prevent overfitting. Gaussian kernel SVM prediction model can correctly predict movie genre preferences in 85% of positive cases. The accuracy of the algorithm increased to 93% with a smaller VC dimension and less overfitting. These findings advance our understanding of how to use machine learning approach to predict customers’ preferences with a small data set and design prediction tools for these enterprises.

Intelligent control of a grain drying system using a GA-SVM-IMPC controller

ABSTRACTThe grain drying is difficult to control because of its characteristics of long delay, strong nonlinearity, and uncertainty parameters. The aim of the paper is to design a suitable controller for a newly designed grain dryer. First, a nonlinear math model of the wheat mixed flow drying was established and analyzed based on the fundamental laws of simultaneous heat and mass transfer. The simulations for the batch circulating drying process and the continuous grain drying process have been made and the simulation results show that it fits well with the actual drying process. Second, an internal model proportional integral derivative (PID) controller (IMPC) based on the support vector machine (SVM) algorithm and the genetic algorithm (GA-SVM-IMPC) was proposed from the view of the energy loss and the dried grain quality. The structure of the GA-SVM-IMPC controller consists of a SVM prediction model, a SVM inverse model controller, a PID controller and a genetic optimization algorithm. Finally, the effectiveness of this controller was demonstrated by computer simulations, and the comparative study with the other controllers further confirmed the superiority of the proposed dryer controller.

Identification of recurrent risk-related genes and establishment of support vector machine prediction model for gastric cancer

This study sought to investigate genes related to recurrent risk and establish a support vector machine (SVM) classifier for prediction of recurrent risk in gastric cancer (GC).Based on the gene expression profiling dataset GSE26253, feature genes that were significantly associated with survival time and status were screened out. Subsequently, protein-protein interaction (PPI) network was constructed for these feature genes, and genes in this network was optimized using betweenness centrality algorithm in order to identify genes potentially correlated with GC (named as GCGs). In total, 1202 feature genes were identified to be significantly associated with survival time and status of GC, among of which, 65 genes were identified as a classifier that was able to recognize recurrence and nonrecurrence GC cases with a high sensitivity and specificity, predictive value (PPV), negative predictive value (NPV) and area under the receiver operating characteristic curve (AUC). Furthermore, the classifier was able to reasonably classify tumor samples in GSE15459 into high and low recurrent risk groups. Among those genes, a set of genes were predicted to have interactions (e.g. RHOA interacting with TGFBR1, PRKACA and PLCG1; TGFBR1 interacting with TGFBR2) and be involved in pathways like MAPK signaling (e.g. TGFBR1 and TGFBR2), adherens junction (e.g. RHOA) and apoptosis (e.g. PRKACA).The genes in the classifier model may be related to GC recurrence, and the classifier model may contribute to the prediction of recurrent risk in GC.

DHSpred: support-vector-machine-based human DNase I hypersensitive sites prediction using the optimal features selected by random forest.

DNase I hypersensitive sites (DHSs) are genomic regions that provide important information regarding the presence of transcriptional regulatory elements and the state of chromatin. Therefore, identifying DHSs in uncharacterized DNA sequences is crucial for understanding their biological functions and mechanisms. Although many experimental methods have been proposed to identify DHSs, they have proven to be expensive for genome-wide application. Therefore, it is necessary to develop computational methods for DHS prediction. In this study, we proposed a support vector machine (SVM)-based method for predicting DHSs, called DHSpred (DNase I Hypersensitive Site predictor in human DNA sequences), which was trained with 174 optimal features. The optimal combination of features was identified from a large set that included nucleotide composition and di- and trinucleotide physicochemical properties, using a random forest algorithm. DHSpred achieved a Matthews correlation coefficient and accuracy of 0.660 and 0.871, respectively, which were 3% higher than those of control SVM predictors trained with non-optimized features, indicating the efficiency of the feature selection method. Furthermore, the performance of DHSpred was superior to that of state-of-the-art predictors. An online prediction server has been developed to assist the scientific community, and is freely available at: http://www.thegleelab.org/DHSpred.html

A multigene support vector machine predictor for metastasis of cutaneous melanoma.

Gene expression profiles of cutaneous melanoma were analyzed to identify critical genes associated with metastasis. Two gene expression datasets were downloaded from Gene Expression Omnibus (GEO) and another dataset was obtained from The Cancer Genome Atlas (TCGA). Differentially expression genes (DEGs) between metastatic and non-metastatic melanoma were identified by meta-analysis. A protein-protein interaction (PPI) network was constructed for the DEGs using information from BioGRID, HPRD and DIP. Betweenness centrality (BC) was calculated for each node in the network and the top feature genes ranked by BC were selected to construct the support vector machine (SVM) classifier using the training set. The SVM classifier was then validated in another independent dataset. Pathway enrichment analysis was performed for the feature genes using Fisher's exact test. A total of 798 DEGs were identified and a PPI network including 337 nodes and 466 edges was then constructed. Top 110 feature genes ranked by BC were included in the SVM classifier. The prediction accuracies for the three datasets were 96.8, 100 and 94.4%, respectively. A total of 11 KEGG pathways and 13 GO biological pathways were significantly over-represented in the 110 feature genes, including endometrial cancer, regulation of actin cytoskeleton, focal adhesion, ubiquitin mediated proteolysis, regulation of apoptosis and regulation of cell proliferation. A SVM classifier of high prediction accuracy was acquired. Several critical genes implicated in melanoms metastasis were also revealed. These results may advance understanding of the molecular mechanisms underlying metastasis, and also provide potential therapeutic targets.

Wind power prediction method based on hybrid kernel function support vector machine

The prediction accuracy of wind power affects the operation cost of the power grid, which is a direct result of the supply and demand balance of the grid. Therefore, how to improve the prediction accuracy of wind power is very important. Considering the prediction accuracy of current prediction methods is not high, a wind power prediction method based on a hybrid kernel function support vector machine is proposed. On the basis of the exhibited characteristics of different kernel functions, the hybrid kernel function is a linear combination of the radial basis function and the polynomial kernel function. The hybrid kernel function is selected as the kernel function of support vector machine. The global kernel function is used to fit the correlation of the distant sample data, while the partial kernel function is used to fit the correlation of the data in neighboring fields. The generalization performance of the support vector machine model is improved. At the same time, an improved particle swarm optimization algorithm is introduced to determine the optimal parameters of the hybrid kernel function and support vector machine prediction model. Finally, the built prediction model is used to predict the wind power. The simulation results demonstrate that the proposed prediction method has better prediction accuracy for wind power.

Structural health monitoring data reconstruction of a concrete cable-stayed bridge based on wavelet multi-resolution analysis and support vector machine

The accuracy and integrity of stress data acquired by bridge heath monitoring system is of significant importance for bridge safety assessment. However, the missing and abnormal data are inevitably existed in a realistic monitoring system. This paper presents a data reconstruction approach for bridge heath monitoring based on the wavelet multi-resolution analysis and support vector machine (SVM). The proposed method has been applied for data imputation based on the recorded data by the structural health monitoring (SHM) system instrumented on a prestressed concrete cable-stayed bridge. The effectiveness and accuracy of the proposed wavelet-based SVM prediction method is examined by comparing with the traditional autoregression moving average (ARMA) method and SVM prediction method without wavelet multi-resolution analysis in accordance with the prediction errors. The data reconstruction analysis based on 5-day and 1-day continuous stress history data with obvious preternatural signals is performed to examine the effect of sample size on the accuracy of data reconstruction. The results indicate that the proposed data reconstruction approach based on wavelet multi-resolution analysis and SVM is an effective tool for missing data imputation or preternatural signal replacement, which can serve as a solid foundation for the purpose of accurately evaluating the safety of bridge structures.

Identification of the Rice Wines with Different Marked Ages by Electronic Nose Coupled with Smartphone and Cloud Storage Platform.

In this study, a portable electronic nose (E-nose) was self-developed to identify rice wines with different marked ages—all the operations of the E-nose were controlled by a special Smartphone Application. The sensor array of the E-nose was comprised of 12 MOS sensors and the obtained response values were transmitted to the Smartphone thorough a wireless communication module. Then, Aliyun worked as a cloud storage platform for the storage of responses and identification models. The measurement of the E-nose was composed of the taste information obtained phase (TIOP) and the aftertaste information obtained phase (AIOP). The area feature data obtained from the TIOP and the feature data obtained from the TIOP-AIOP were applied to identify rice wines by using pattern recognition methods. Principal component analysis (PCA), locally linear embedding (LLE) and linear discriminant analysis (LDA) were applied for the classification of those wine samples. LDA based on the area feature data obtained from the TIOP-AIOP proved a powerful tool and showed the best classification results. Partial least-squares regression (PLSR) and support vector machine (SVM) were applied for the predictions of marked ages and SVM (R2 = 0.9942) worked much better than PLSR.

Quantification of sawgrass marsh aboveground biomass in the coastal Everglades using object-based ensemble analysis and Landsat data

Large-scale biomass quantification of sawgrass (Cladium jamaicense) marsh is critical to understand the carbon and energy cycle in the Florida Everglades. There is also a need to monitor biomass changes in the coastal Everglades due to continuing sea level rise. Previous research in biomass estimation of coastal marshes has focused on pixel-based parametric modeling methods. In this study, an object-based ensemble analysis approach was developed to map sawgrass biomass at multiple scales using Landsat data. Four machine learning regression algorithms including Support Vector Machine (SVM), Random Forest (RF), k-Nearest Neighbor (k-NN), and Artificial Neural Network (ANN) were evaluated and compared to the commonly used Multiple Linear Regression (MLR) method for both live and total sawgrass biomass estimation. A weighted combining scheme was developed to integrate predictions from comparable models for ensemble analysis. Nonparametric machine learning models had better performance than the parametric approach. ANN and SVM produced similar results in live biomass estimation with the correlation coefficient (r) larger than 0.9, while ANN achieved the best result for the total biomass estimation (r=0.94). Sawgrass biomass maps were produced for two harvest seasons in 2014 and 2016 at three detail levels, which successfully revealed the spatial and temporal (seasonal and interannual) sawgrass biomass variations. Ensemble analysis of the ANN and SVM predictions of live sawgrass biomass not only made the estimation more reliable, but also generated an uncertainty map to identify the regions with a robust biomass prediction, as well as challenging areas for biomass quantification. It is concluded that the object-based ensemble analysis is a promising alternative to the commonly used pixel-based biomass modeling techniques.

Performance evaluation of support vector machine (SVM)-based predictors in genomic selection

The aim was to compare predictive performance of SVM-based predictors constructed using different kernel functions (radial, sigmoid, linear and polynomial) in different genetic architectures of a trait (number of QTL, distribution of QTL effects) and heritability levels. To this end, a genome comprised of five chromosomes, oneMorgan each, was simulated on which 10,000 bi-allelic single nucleotide polymorphisms (SNP) were distributed.Cross validation employing a grid search was used to tune the meta-parameters of each kernel function. Pearson’scorrelation between the true and predicted genomic breeding values (rp,t) and mean squared error of predictedgenomic breeding values (MSEp) were used, respectively, as measures of the predictive accuracy and the overallfit. Meta-parameter optimization had a significant effect on predictive performance of SVM-based predictors insuch a way that by using improper meta-parameters, the predictive power of models decreased significantly. In allmodels, the accuracy of prediction increased following increase in heritability and decrease in the number ofQTLs. In most of scenarios, radial- and sigmoid-based SVM predictors outperformed polynomial and linear models.The linear-and polynomial-based SVM had lower rp,t and higher MSEp and, therefore, were not recommended forgenomic selection. The prediction accuracy of radial and sigmoid models was approximately the same in most ofthe studied scenarios; however, considering all pros and cons of radial and sigmoid kernels, radial kernel wasrecommended as the best kernel function for constructing SVM. All of studied SVM-based predictors were efficientusers of time and memory.

Virtual-view PSNR prediction based on a depth distortion tolerance model and support vector machine.

Quality prediction of virtual-views is important for free viewpoint video systems, and can be used as feedback to improve the performance of depth video coding and virtual-view rendering. In this paper, an efficient virtual-view peak signal to noise ratio (PSNR) prediction method is proposed. First, the effect of depth distortion on virtual-view quality is analyzed in detail, and a depth distortion tolerance (DDT) model that determines the DDT range is presented. Next, the DDT model is used to predict the virtual-view quality. Finally, a support vector machine (SVM) is utilized to train and obtain the virtual-view quality prediction model. Experimental results show that the Spearman's rank correlation coefficient and root mean square error between the actual PSNR and the predicted PSNR by DDT model are 0.8750 and 0.6137 on average, and by the SVM prediction model are 0.9109 and 0.5831. The computational complexity of the SVM method is lower than the DDT model and the state-of-the-art methods.

Support Vector Machine Classification and Regression Prioritize Different Structural Features for Binary Compound Activity and Potency Value Prediction.

In computational chemistry and chemoinformatics, the support vector machine (SVM) algorithm is among the most widely used machine learning methods for the identification of new active compounds. In addition, support vector regression (SVR) has become a preferred approach for modeling nonlinear structure–activity relationships and predicting compound potency values. For the closely related SVM and SVR methods, fingerprints (i.e., bit string or feature set representations of chemical structure and properties) are generally preferred descriptors. Herein, we have compared SVM and SVR calculations for the same compound data sets to evaluate which features are responsible for predictions. On the basis of systematic feature weight analysis, rather surprising results were obtained. Fingerprint features were frequently identified that contributed differently to the corresponding SVM and SVR models. The overlap between feature sets determining the predictive performance of SVM and SVR was only very small. Furthermore, features were identified that had opposite effects on SVM and SVR predictions. Feature weight analysis in combination with feature mapping made it also possible to interpret individual predictions, thus balancing the black box character of SVM/SVR modeling.

Measurement of lumber moisture content based on PCA and GS-SVM

Lumber moisture content (LMC) is the important parameter to judge the dryness of lumber and the quality of wooden products. Nevertheless the data acquired are mostly redundant and incomplete because of the complexity of the course of drying, by interference factors that exist in the dryness environment and by the physical characteristics of the lumber itself. To improve the measuring accuracy and reliability of LMC, the optimal support vector machine (SVM) algorithm was put forward for regression analysis LMC. Environmental factors such as air temperature and relative humidity were considered, the data of which were extracted with the principle component analysis method. The regression and prediction of SVM was optimized based on the grid search (GS) technique. Groups of data were sampled and analyzed, and simulation comparison of forecasting performance shows that the main component data were extracted to speed up the convergence rate of the optimum algorithm. The GS-SVM shows a better performance in solving the LMC measuring and forecasting problem.

Two-class support vector machine with new kernel function based on paths of features for predicting chemical activity

Information and computer science fields such as machine learning and graph theory are implemented in chemoinformatics to discover the properties of chemical compounds. This paper presents a new algorithm based on the two-class support vector machine (SVM) model, which has new kernel functions for paths of features, enabling the prediction of chemical compound activity. Initially, we extract all paths of features (star subgraphs) with certain lengths, and we encode them depending on their structure in the graphs. Then, we use these codes to construct two relationship matrices between those paths. These matrices contain common and different sub-paths between paths of stars. The number of sub-paths/paths for each compound is passed to the proposed kernel functions in the two-class SVM to predict the activity of chemical compounds. The relationship matrices created by the proposed algorithm help to reduce the number of features, which improves prediction accuracy. We apply the proposed algorithm with and without feature selection using two benchmark datasets, specifically, the monoamine oxidase (MAO) dataset and the AIDS antiviral screen database of active compound dataset, which have 68 and 2000 chemical compounds, respectively. We perform comparative experiments for the proposed kernel functions and many other two-class SVM prediction methods, and the results before feature selection show prediction accuracies of 94% and 99.5% for MAO and AIDS, respectively. After selection, the prediction accuracies are 96% and 99.5% for MAO and AIDS, respectively.

Load Forecasting Method Research Based on Improved K-means Algorithm and SVM

A short-term load forecasting method combining k-means clustering algorithm and SVM is proposed. Euclidean distance and waveform similarity clustering of double standards is used in improved k-means clustering algorithm. The different load curves is accurately classified and their typical load curve is extracted, realized the classification function of different types of user. Then according to the classification results, select the same type of load curves and load factors with the predicted load as input of support vector machine prediction model. This method is used to classify and predict the actual daily load curve of shanghai. It shows that the method can greatly improve the prediction accuracy and is practical.

Analysis and prediction of 100 km-scale atmospheric duct interference in TD-LTE networks

Atmospheric ducts are horizontal layers that occur under certain weather conditions in the lower atmosphere. Radio signals guided in atmospheric ducts tend to experience less attenuation and spread much farther, i.e, hundreds of kilometers. In a large-scale deployed TD-LTE (Time Division Long Term Evolution) network, atmospheric ducts cause faraway downlink wireless signals to propagate beyond the designed protection distance and interfere with local uplink signals, thus resulting in a large outage probability. In this paper, we analyze the characteristics of ADI atmospheric duct interference (Atmospheric Duct Interference) by the use of real network-side big data from the current operated TD-LTE network owned by China Mobile. The analysis results yield the time varying and directional characteristics of ADI. In addition, we proposed an SVM (Support Vector Machine)-classifier based spacial prediction method of ADI by machine learning over combination of real network-side big data and real meteorological data. Furthermore, an implementation of ADMM (Alternating Direction Methods of Multipliers) framework is proposed to implement a distributed SVM prediction scheme, which reduces data exchange among different regions/cities, maintains similar prediction accuracy and is thus of a more practical use to operators.

Echo State Network for Fast Channel Prediction in Ricean Fading Scenarios

A fast channel prediction scheme is proposed for Ricean fading scenarios. By employing an echo state network (ESN), the scheme is able to obtain smaller prediction error than previous designs. Simulation results show that the ESN prediction method has lower normalized mean squared error than the traditional autoregressive, discrete wavelet transform, and support vector machine prediction approaches. The symbol error rate gap between the perfect and predicted channel state information is small.

Study on specificity of colon carcinoma-associated serum markers and establishment of SVM prediction model.

We aimed to evaluate the specificity of 12 tumor markers related to colon carcinoma and identify the most sensitive index. Logistic regression and Bhattacharyya distance were used to evaluate the index. Then, different index combinations were used to establish a support vector machine (SVM) diagnosis model of malignant colon carcinoma. The accuracy of the model was checked. High accuracy was assumed to indicate the high specificity of the index. Through Logistic regression, three indexes, CEA, HSP60 and CA199, were screened out. Using Bhattacharyya distance, four indexes with the largest Bhattacharyya distance were screened out, including CEA, NSE, AFP, and CA724. The specificity of the combination of the above six indexes was higher than that of other combinations, so did the accuracy of the established SVM identification model. Using Logistic regression and Bhattacharyya distance for detection and establishing an SVM model based on different serum marker combinations can increase diagnostic accuracy, providing a theoretical basis for application of mathematical models in cancer diagnosis.