Gaussian kernel optimization: Complex problem and a simple solution

Yin, Jiang-Bo; Li, Tao; Shen, Hong‐Bin

doi:10.1016/j.neucom.2011.07.017

Cited by 23 publications

(8 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The optimal complexity parameter in the SVM classifier is fixed by grid search. Throughout, the radial basis kernel function (RBF) is used and the corresponding kernel parameter can be determined by grid search or automatic methods [58], [59]. We select the method GFO for the supervised case proposed in [59] due to its simplicity.…”

Section: Resultsmentioning

confidence: 99%

“…Throughout, the radial basis kernel function (RBF) is used and the corresponding kernel parameter can be determined by grid search or automatic methods [58], [59]. We select the method GFO for the supervised case proposed in [59] due to its simplicity. In GFO, the optimal kernel parameter is approximated by the mathematical expectation of distances between data points.…”

Section: Resultsmentioning

confidence: 99%

“…We used a grid search approach to find optimal feature subsets and optimize the SVM parameter using 5-fold cross validation on the training set for all binary classification models. For the SVM parameter , we use two kinds of methods to find the optimal value: grid search and GFO [59]. It is found that the number of elements of the optimal feature subset for each binary classification is generally less than 300.…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

An Ensemble Method for Predicting Subnuclear Localizations from Primary Protein Structures

Han

Anh

et al. 2013

PLoS ONE

View full text Add to dashboard Cite

BackgroundPredicting protein subnuclear localization is a challenging problem. Some previous works based on non-sequence information including Gene Ontology annotations and kernel fusion have respective limitations. The aim of this work is twofold: one is to propose a novel individual feature extraction method; another is to develop an ensemble method to improve prediction performance using comprehensive information represented in the form of high dimensional feature vector obtained by 11 feature extraction methods.Methodology/Principal FindingsA novel two-stage multiclass support vector machine is proposed to predict protein subnuclear localizations. It only considers those feature extraction methods based on amino acid classifications and physicochemical properties. In order to speed up our system, an automatic search method for the kernel parameter is used. The prediction performance of our method is evaluated on four datasets: Lei dataset, multi-localization dataset, SNL9 dataset and a new independent dataset. The overall accuracy of prediction for 6 localizations on Lei dataset is 75.2% and that for 9 localizations on SNL9 dataset is 72.1% in the leave-one-out cross validation, 71.7% for the multi-localization dataset and 69.8% for the new independent dataset, respectively. Comparisons with those existing methods show that our method performs better for both single-localization and multi-localization proteins and achieves more balanced sensitivities and specificities on large-size and small-size subcellular localizations. The overall accuracy improvements are 4.0% and 4.7% for single-localization proteins and 6.5% for multi-localization proteins. The reliability and stability of our classification model are further confirmed by permutation analysis.ConclusionsIt can be concluded that our method is effective and valuable for predicting protein subnuclear localizations. A web server has been designed to implement the proposed method. It is freely available at http://bioinformatics.awowshop.com/snlpred_page.php.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An Ensemble Method for Predicting Subnuclear Localizations from Primary Protein Structures

Han

Anh

et al. 2013

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The general mathematical form of the output nodes in an RBFN is as follows:

g_{j} (x) = \sum_{i = 1}^{k} w_{j i} ϕ (‖ x - μ_{i} ‖; σ_{i});

g j ( x )is the function corresponding to the j th output node and is a linear combination of k radial basis functions ϕ() with center µ i and bandwidth σ i ; The value of σ can be estimated with data‐driven methods and we used a fixed bandwidth of 5 for each kernel function, which showed the best performance. Also, w ji is the weight associated with the link between the j th output node and the i th hidden node.…”

Section: Methodsmentioning

confidence: 99%

Identification of efflux proteins using efficient radial basis function networks with position‐specific scoring matrices and biochemical properties

Chen

Chang

et al. 2013

Proteins

View full text Add to dashboard Cite

Efflux proteins are membrane proteins, which are involved in the transportation of multidrugs. The annotation of efflux proteins in genomic sequences would aid to understand the function. Although the percentage of membrane proteins in genomes is estimated to be 25-30%, there is no information about the content of efflux proteins. For annotating such class of proteins it is necessary to develop a reliable method to identify efflux proteins from amino acid sequence information. In this work, we have developed a method based on radial basis function networks using position specific scoring matrices (PSSM) and amino acid properties. We noticed that the C-terminal domain of efflux proteins contain vital information for discrimination. Our method showed an accuracy of 78 and 92% in discriminating efflux proteins from transporters and membrane proteins, respectively using fivefold cross-validation. We utilized our method for annotating the genomes E. coli and P. aeruginosa and it predicted 8.7 and 9.2% of proteins as efflux proteins in these genomes, respectively. The predicted efflux proteins have been compared with available experimental data and we observed a very good agreement between them. Further, we developed a web server for classifying efflux proteins and it is freely available at http://rbf.bioinfo.tw/∼sachen/EFFLUXpredict/Efflux-RBF.php. We suggest that our method could be an effective tool for annotating efflux proteins in genomic sequences.

show abstract

“…Because each sample is repeatedly used during iterations, the method consumes a large amount of computation time. Hence, we use Gaussian Kernel Optimization (GKO) [31] to optimize β in our experiments.…”

Section: Classification Using Svm With Gkomentioning

confidence: 99%

Dual-Encoded Features from Both Spatial and Curvelet Domains for Image Smoke Recognition

2019

KSII TIIS

View full text Add to dashboard Cite

Visual smoke recognition is a challenging task due to large variations in shape, texture and color of smoke. To improve performance, we propose a novel smoke recognition method by combining dual-encoded features that are extracted from both spatial and Curvelet domains. A Curvelet transform is used to filter an image to generate fifty sub-images of Curvelet coefficients. Then we extract Local Binary Pattern (LBP) maps from these coefficient maps and aggregate histograms of these LBP maps to produce a histogram map. Afterwards, we encode the histogram map again to generate Dual-encoded Local Binary Patterns (Dual-LBP). Histograms of Dual-LBPs from Curvelet domain and Completed Local Binary Patterns (CLBP) from spatial domain are concatenated to form the feature for smoke recognition. Finally, we adopt Gaussian Kernel Optimization (GKO) algorithm to search the optimal kernel parameters of Support Vector Machine (SVM) for further improvement of classification accuracy. Experimental results demonstrate that our method can extract effective and reasonable features of smoke images, and achieve good classification accuracy.

show abstract

Gaussian kernel optimization: Complex problem and a simple solution

Cited by 23 publications

References 4 publications

An Ensemble Method for Predicting Subnuclear Localizations from Primary Protein Structures

An Ensemble Method for Predicting Subnuclear Localizations from Primary Protein Structures

Identification of efflux proteins using efficient radial basis function networks with position‐specific scoring matrices and biochemical properties

Dual-Encoded Features from Both Spatial and Curvelet Domains for Image Smoke Recognition

Contact Info

Product

Resources

About