Multi-kernel Support Vector Machine Research Articles

Hypergraph based multi-task feature selection for multimodal classification of Alzheimer's disease

Multi-modality based classification methods are superior to the single modality based approaches for the automatic diagnosis of the Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, most of the multi-modality based methods usually ignore the structure information of data and simply squeeze them to pairwise relationships. In real-world applications, the relationships among subjects are much more complex than pairwise, and the high-order structure containing more discriminative information will be intuitively beneficial to our learning tasks. In light of this, a hypergraph based multi-task feature selection method for AD/MCI classification is proposed in this paper. Specifically, we first perform feature selection on each modality as a single task and incorporate group-sparsity regularizer to jointly select common features across multiple modalities. Then, we introduce a hypergraph based regularization term for the standard multi-task feature selection to model the high-order structure relationship among subjects. Finally, a multi-kernel support vector machine is adopted to fuse the features selected from different modalities for the final classification. The experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) demonstrate that our proposed method achieves better classification performance than the start-of-art multi-modality based methods.

RETRACTED ARTICLE: Prediction of pre-term groups from EHG signals using optimal multi-kernel SVM

Pre-term birth is the birth that carries out before the baby’s expected date. Sometimes, it augments the possibility of health problems or death. In this research, the abdominal EHG signal incorporates both the maternal heart beat signal and Fetal ECG signal. The removal of fetal ECG signal from the heart beat signal is difficult in pre-term detection. In this work, the EHG signal is pre-processed using wiener filter that is applied to enhance the signal quality. Then, the attributes are removed from the pre-processed signal to find the distinctive class. In addition, Opposition based Ant Lion Optimization is used to select the multi-kernel Support Vector Machine and training algorithms for predicting the pre-term birth. The proposed methodology is simulated by using MATLAB software and the results are investigated to verify the classification accuracy. From the experimental study, the proposed work enhanced the classification accuracy upto 3–19% related to the existing works.

Multi-modal neuroimaging feature selection with consistent metric constraint for diagnosis of Alzheimer's disease.

The accurate diagnosis of Alzheimer's disease (AD) and its early stage, e.g., mild cognitive impairment (MCI), is essential for timely treatment or possible intervention to slow down AD progression. Recent studies have demonstrated that multiple neuroimaging and biological measures contain complementary information for diagnosis and prognosis. Therefore, information fusion strategies with multi-modal neuroimaging data, such as voxel-based measures extracted from structural MRI (VBM-MRI) and fluorodeoxyglucose positron emission tomography (FDG-PET), have shown their effectiveness for AD diagnosis. However, most existing methods are proposed to simply integrate the multi-modal data, but do not make full use of structure information across the different modalities. In this paper, we propose a novel multi-modal neuroimaging feature selection method with consistent metric constraint (MFCC) for AD analysis. First, the similarity is calculated for each modality (i.e. VBM-MRI or FDG-PET) individually by random forest strategy, which can extract pairwise similarity measures for multiple modalities. Then the group sparsity regularization term and the sample similarity constraint regularization term are used to constrain the objective function to conduct feature selection from multiple modalities. Finally, the multi-kernel support vector machine (MK-SVM) is used to fuse the features selected from different models for final classification. The experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) show that the proposed method has better classification performance than the start-of-the-art multimodality-based methods. Specifically, we achieved higher accuracy and area under the curve (AUC) for AD versus normal controls (NC), MCI versus NC, and MCI converters (MCI-C) versus MCI non-converters (MCI-NC) on ADNI datasets. Therefore, the proposed model not only outperforms the traditional method in terms of AD/MCI classification, but also discovers the characteristics associated with the disease, demonstrating its promise for improving disease-related mechanistic understanding.

A Hybrid Fish – Bee Optimization Algorithm for Heart Disease Prediction using Multiple Kernel SVM Classifier

The patient’s heart disease status is obtained by using a heart disease detection model. That is used for the medical experts. In order to predict the heart disease, the existing technique use optimal classifier. Even though the existing technique achieved the better result, it has some disadvantages. In order to improve those drawbacks, the suggested technique utilizes the effective method for heart disease prediction. At first the input information is preprocessed and then the preprocessed result is forwarded to the feature selection process. For the feature selection process a proficient feature selection is used over the high dimensional medical data. Hybrid Fish Bee optimization algorithm (HFSBEE) is utilized. Thus, the proposed algorithm parallelizes the two algorithms such that the local behavior of artificial bee colony algorithm and global search of fish swarm optimization are effectively used to find the optimal solution. Classification process is performed by the transformation of medical dataset to the Multi kernel support vector machine (MKSVM). The process of our proposed technique is calculated based on the accuracy, sensitivity, specificity, precision, recall and F-measure. Here, for test analysis, the some datasets used i.e. Cleveland, Hungarian and Switzerland etc., that are given based on the UCI machine learning repository. The experimental outcome show that our presented technique is went better than the accuracy of 97.68%. This is for the Cleveland dataset when related with existing hybrid kernel support vector machine (HKSVM) method achieved 96.03% and optimal rough fuzzy classifier obtained 62.25%. The implementation of the proposed method is done by MATLAB platform.

Reduced Optimal Feature Based Biometric Authentication Using MALO-MKSVM Techniques

Biometric authentication is referred to as a realistic authentication which traits used is distinct, and quantifiable to recognize one individual. Depending on the level of security required, unimodal based authentication mechanisms are prone to numerous security attacks. In this paper, we propose a multimodal based biometric recognition framework which will improve the security level by using more than one type of biometric scanner. A new multimodal feature extraction technique has been proposed to reduce the features by utilizing Probabilistic Principal Component Analysis (PPCA) model by the way of choosing optimal features with the assistance of Modified Ant Lion Optimization (MALO). Finally, the recognized and non-recognized images are accomplished by the formation of a new classification model i.e. Multi Kernel Support Vector Machine (MKSVM). From this procedure, the result showed that a high recognition rate and also the most extreme accuracy accomplished in this work.

An ensemble learning model based on Bayesian model combination for solar energy prediction

To improve the reliability of solar irradiance prediction methods, an ensemble learning method based on the Bayesian model combination has been developed in this paper for solar utilization systems. First, a novel data sampling method has been proposed, including the advantages of clustering and cross validation, which can effectively ensure that the training subsets are different from each other and can cover a variety of different meteorological samples. Second, an ensemble learning model with multiple base learners has been designed. Each training subset is utilized to train the corresponding base learner. Then, a novel Bayesian model combination strategy expands hypothesis space E on Bayesian model averaging, which is applied to frame the combination strategy based on the accuracy of each base learner on the validation set. The prediction values of multiple learners are framed through the model combination strategy. Thus, a novel ensemble learning model based on Bayesian model combination has been established. Finally, experiments are carried out and the proposed method is compared with the Artificial Neural Network (ANN), K-means (Radial Basis Function) RBF, Support Vector Machine (SVM), and Multikernel SVM. The annual average mean absolute error of the ensemble learning method based on Bayesian model combination is reduced by 0.0374 MJ×m−2 compared with the ensemble learning method. The annual average mean absolute error of the proposed method is reduced by 42.6%, 38.2%, 52%, and 48.7%, respectively, compared with ANN, K-means RBF, SVM, and Multikernel SVM. The effectiveness as well as the reliability of the proposed method in solar energy prediction have been found to perform better and have verified our approach.

Adaptive Multi-Kernel SVM With Spatial–Temporal Correlation for Short-Term Traffic Flow Prediction

Accurate estimation of the traffic state can help to address the issue of urban traffic congestion, providing guiding advices for people’s travel and traffic regulation. In this paper, we propose a novel short-term traffic flow prediction algorithm based on an adaptive multi-kernel support vector machine (AMSVM) with spatial–temporal correlation, which is named as AMSVM-STC. First, we explore both the nonlinearity and randomness of the traffic flow, and hybridize Gaussian kernel and polynomial kernel to constitute the AMSVM. Second, we optimize the parameters of AMSVM with the adaptive particle swarm optimization algorithm, and propose a novel method to make the hybrid kernel’s weight adjust adaptively according to the change tendency of real-time traffic flow. Third, we incorporate the spatial–temporal correlation information with AMSVM to predict the short-term traffic flow. We evaluate our algorithm by doing thorough experiment on real data sets. The results demonstrate that our algorithm can do a timely and adaptive prediction even in the rush hour when the traffic conditions change rapidly. At the same time, the proposed AMSVM-STC outperforms the existing methods.

Multimodal classification of drug-naïve first-episode schizophrenia combining anatomical, diffusion and resting state functional resonance imaging

The accurate diagnosis in the early stage of schizophrenia (SZ) is of great importance yet remains challenging. The classification between SZ and control groups based on magnetic resonance imaging (MRI) data using machine learning method could be helpful for SZ diagnosis. Increasing evidence showed that the combination of multimodal MRI data might further improve the classification performance However, medication effect has a profound influence on patients’ anatomical and functional features and may reduce the classification efficiency. In this paper, we proposed a multimodal classification method to discriminate drug-naïve first-episode schizophrenia patients from healthy controls (HCs) by a combined structural MRI, diffusion tensor imaging (DTI) and resting state-functional MRI data. To reduce the feature dimension of multimodal data, we applied sparse coding (SC) for feature selection and multi-kernel support vector machine (SVM) for feature combination and classification. The best classification performance with the classification accuracy of 84.29% and area under the receiver operating characteristic (ROC) curve (AUC) of 81.64% was achieved when all modality data were combined. Interestingly, the identified functional markers were mainly found in default mode network (DMN) and cerebellar connections, while the structural markers were within limbic system and prefrontal–thalamo–hippocampal circuit.

Novel LBP based texture descriptor for rotation, illumination and scale invariance for image texture analysis and classification using multi-kernel SVM

In case of illumination change, the local binary pattern (LBP) descriptor have found to be used in analysis of texture of the image because of the ease of computation and robustness to such changes. However, the LBP technique also comes with limitations such as its inability to capture the discriminative information completely. For enhancing the LBP’s performance, we proposed a new texture descriptor for rotation, illumination and scale invariance (IRSLBP) for texture classification. The proposed approach extracts the color features through quantification of the RGB space into single channel, which is marked by a smaller number of shades to reduce computation and to improve the efficiency. The IRSLBP descriptor provides the scale invariance by considering the circular neighbor set of every central pixel other than the normal neighboring pixels. Moreover, the proposed IRSLBP decomposed the difference vector into sign part and magnitude part by local difference sign magnitude transform. In addition, these mitigated the influence of rotation, illumination or noise and demonstrated effective robustness. Using the proposed IRSLBP descriptor, we have classified the different textures using Multi kernel support vector machine (SVM) approach.

Optimal Region growing and Multi-kernel SVM for fault detection in Electrical Equipments using Infrared Thermography Images

Infrared thermography (IRT) has played an essential part in observing and examining thermal defects of electrical equipment without ending, which has vital enormity for the dependability of electrical recorded. This paper dissected the electrical parts are faulted or non-faulted with the help of segmentation and classification model. The features are calculated from the input thermal images and regions of interest (ROI) is segmented by utilising optimal region growing (ORG) technique and faults are classified using multi kernel support vector machine (MKSVM). In the tests, the classification performances from different input features are assessed. For enhancing the performance of the segmentation investigation optimisation procedure that is whale optimisation (WO) is used. Before classifying, the extracted electrical components are fused by using feature level fusion (FLF) procedure to fused vector in all images. These multi kernel classification performance indices, including sensitivity, specificity and accuracy are utilised to recognise the most appropriate input feature and the best arrangement of classifiers. The performance of SVM is contrasted with a neural network. The correlation comes about demonstrating that our technique can accomplish a superior performance with accuracy at 98.21%.

Identification of protein subcellular localization via integrating evolutionary and physicochemical information into Chou’s general PseAAC

Identifying the location of proteins in a cell plays an important role in understanding their functions, such as drug design, therapeutic target discovery and biological research. However, the traditional subcellular localization experiments are time-consuming, laborious and small scale. With the development of next-generation sequencing technology, the number of proteins has grown exponentially, which lays the foundation of the computational method for identifying protein subcellular localization. Although many methods for predicting subcellular localization of proteins have been proposed, most of them are limited to single-location. In this paper, we propose a multi-kernel SVM to predict subcellular localization of both multi-location and single-location proteins. First, we make use of the evolutionary information extracted from position specific scoring matrix (PSSM) and physicochemical properties of proteins, by Chou’s general PseAAC and other efficient functions. Then, we propose a multi-kernel support vector machine (SVM) model to identify multi-label protein subcellular localization. As a result, our method has a good performance on predicting subcellular localization of proteins. It achieves an average precision of 0.7065 and 0.6889 on two human datasets, respectively. All results are higher than those achieved by other existing methods. Therefore, we provide an efficient system via a novel perspective to study the protein subcellular localization.

Enhancing the representation of functional connectivity networks by fusing multi-view information for autism spectrum disorder diagnosis.

Functional connectivity network provides novel insights on how distributed brain regions are functionally integrated, and its deviations from healthy brain have recently been employed to identify biomarkers for neuropsychiatric disorders. However, most of brain network analysis methods utilized features extracted only from one functional connectivity network for brain disease detection and cannot provide a comprehensive representation on the subtle disruptions of brain functional organization induced by neuropsychiatric disorders. Inspired by the principles of multi-view learning which utilizes information from multiple views to enhance object representation, we propose a novel multiple network based framework to enhance the representation of functional connectivity networks by fusing the common and complementary information conveyed in multiple networks. Specifically, four functional connectivity networks corresponding to the four adjacent values of regularization parameter are generated via a sparse regression model with group constraint ( l2,1 -norm), to enhance the common intrinsic topological structure and limit the error rate caused by different views. To obtain a set of more meaningful and discriminative features, we propose using a modified version of weighted clustering coefficients to quantify the subtle differences of each group-sparse network at local level. We then linearly fuse the selected features from each individual network via a multi-kernel support vector machine for autism spectrum disorder (ASD) diagnosis. The proposed framework achieves an accuracy of 79.35%, outperforming all the compared single network methods for at least 7% improvement. Moreover, compared with other multiple network methods, our method also achieves the best performance, that is, with at least 11% improvement in accuracy.

Integrating the Local Property and Topological Structure in the Minimum Spanning Tree Brain Functional Network for Classification of Early Mild Cognitive Impairment.

Abnormalities in the brain connectivity in patients with neurodegenerative diseases, such as early mild cognitive impairment (EMCI), have been widely reported. Current research shows that the combination of multiple features of the threshold connectivity network can improve the classification accuracy of diseases. However, in the construction of the threshold connectivity network, the selection of the threshold is very important, and an unreasonable setting can seriously affect the final classification results. Recent neuroscience research suggests that the minimum spanning tree (MST) brain functional network is helpful, as it avoids the methodological biases while comparing networks. In this paper, by employing the multikernel method, we propose a framework to integrate the multiple properties of the MST brain functional network for improving the classification performance. Initially, the Kruskal algorithm was used to construct an unbiased MST brain functional network. Subsequently, the vector kernel and graph kernel were used to quantify the two different complementary properties of the network, such as the local connectivity property and the topological property. Finally, the multikernel support vector machine (SVM) was adopted to combine the two different kernels for EMCI classification. We tested the performance of our proposed method for Alzheimer's Disease Neuroimaging Initiative (ANDI) datasets. The results showed that our method achieved a significant performance improvement, with the classification accuracy of 85%. The abnormal brain regions included the right hippocampus, left parahippocampal gyrus, left posterior cingulate gyrus, middle temporal gyrus, and other regions that are known to be important in the EMCI. Our results suggested that, combining the multiple features of the MST brain functional connectivity offered a better classification performance in the EMCI.

Local and global characteristics-based kernel hybridization to increase optimal support vector machine performance for stock market prediction

In this paper, a novel multi-kernel support vector machine (MKSVM) combining global and local characteristics of the input data is proposed. Along with, a parameter tuning approach is developed using the fruit fly optimization (FFO), which is applied to stock market movement direction prediction problem. At first, factor analysis is used for identifying reduced key features called as factor scores from the raw stock index data which when applied to the model contributes to improvement in prediction performance. Subsequently, a hybrid kernel method combining local and global characteristics of input data is proposed, where polynomial is used for global kernel and radial basis function is utilized for local kernel. Additionally, FFO-based parameter tuning scheme is proposed to enhance the prediction performance further. Lastly, the evolving MKSVM with best feature subset and optimal parameters is used to predict stock market movement direction based upon historical data series. For evaluation and illustration purposes, three significant stock databases, NYSE, DJI and S&P 500 are used as testing targets. The effectiveness of this proposed approach is proved by three different stock market datasets, which demonstrate that the proposed approach outperforms the MKSVM with default parameter, MKSVM with PSO, MKSVM with GA and other methods. In addition, our findings reveal that the optimization strategy proposed here may be used as a promising choice forecasting tool for better generalization ability higher forecasting accuracy.

RETRACTED ARTICLE: Optimal feature-based multi-kernel SVM approach for thyroid disease classification

Thyroid diseases are across the board around the world. In India as well, there is a critical issue caused because of this disease. Different research studies estimate that around 42 million individuals in India suffer from the ill effects of “thyroid diseases.” Diagnosis of health situations is an energetic and testing undertaking in the field of therapeutic science. Our proposed model is to classify this thyroid data utilizing optimal feature selection and kernel-based classifier process. We will create classifications models and its group show for classification of data using “multi kernel support vector machine.” The novelty and objective of this proposed model as feature selection, it’s used to enhance the performance of classifying process with the help of improved gray wolf optimization. Reason for this optimal feature selection as the insignificant features from unique dataset and computationally increment the performance of the model. The proposed thyroid classification results in the accuracy, sensitivity, and specificity of 97.49, 99.05 and 94.5%, compared to the existing model. This performance measure is computed from the confusion matrix with the diverse measures contrasted with individual models and in addition to the existing classifier and optimization techniques.

Solenoid Valve Fault Diagnosis Based on Genetic Optimization MKSVM

In order to realize the accurate diagnosis of the solenoid valve fault and the accurate identification of the fault type, a fault diagnosis method of solenoid valve based on MKSVM (Multi-Kernel Support Vector Machine) is proposed. Firstly, through the analysis of support vector machine theory, a multiple-kernel learning support vector machine model is built, and the genetic algorithm is used to optimize the multiple-kernel learning weight coefficient and kernel parameter configuration. Then, the current signal of the solenoid valve driving terminal under the six common failure modes of the solenoid valve is obtained experimentally, and the characteristic information is extracted by EMD (Empirical Mode Decomposition) based on the current change rate. Finally, the multi-kernel learning SVM model was used to diagnose the state of the solenoid valve corresponding to each data, and its accuracy rate reached 98.9%. The comparison with the single-core diagnosis method shows that the method can accurately detect the solenoid valve fault Diagnosis, for similar studies with reference value.

Scene classification of remote sensing image based on deep network and multi-scale features fusion

Owing to the complexity of spatial and structural patterns of remote sensing images, scene classification of them is still an open problem and remains active in the community. The inadequacy of labeled samples leads to low accuracy of remote sensing image scene classification. To solve this problem, a classification method DCNN_MSFF is proposed based on deep convolutional neural networks (DCNN) and multi-scale features fusion (MSFF). Firstly, the remote sensing images are transformed to obtain a number of different scale ones for augmentation. Then, they are input into the DCNN for features extraction, and the different scale features of the convolutional and the fully-connected layers are encoded or pooled averagely. Finally, the processed features are fused, and the multi-kernel support vector machine (MKSVM) is used to classify the scenes. The test results in the commonly used remote sensing datasets show that, this proposed method outperforms the state-of-the-art ones in the scene classification of remote sensing images. In this paper, the multi-scale images and features of the convolutional and the fully-connected layers in the deep learning process are utilized to enhance the representation abilities of the classification features. At the same time, the MKSVM is used to improve the generalization ability of the fusion features, so the classification result is better.

Scene classification of remote sensing image based on deep network grading transferring

Aiming at low precision of remote sensing image scene classification, a classification method DCNN_GT based on deep convolutional neural network (DCNN) and grading transfer (GT) is proposed. First, the DCNN model pre-trained on a large dataset (such as ImageNet) was transferred to a relatively smaller target dataset to fine-tune and the first-level classification features of images are extracted. Then, the similar images in the target dataset are clustered into several high-similarity categories, and the DCNN model of the first-level transfer is fine-tuned again on them and the second- level classification features are extracted. Then, the two-level classification features are encoded and fused, and the multi-kernel support vector machine (MKSVM) is used for scene classification. The experimental results in the common remote sensing datasets show that the average classification accuracy of the proposed method is improved by at least 1.83% compared with the one-time transfer and fine-tuning, especially the classification of confusable images is increased by at least 4%. In this paper, the DCNN is transferred gradually and is advanced to enhance the representation ability of the extracted image features, which makes the fusion features more recognizable. At the same time, the MKSVM is used to improve the generalization ability of the fusion features, so the classification result is better.

Fault diagnosis of wind turbine bearing based on stochastic subspace identification and multi-kernel support vector machine

In order to accurately identify a bearing fault on a wind turbine, a novel fault diagnosis method based on stochastic subspace identification (SSI) and multi-kernel support vector machine (MSVM) is proposed. First, the collected vibration signal of the wind turbine bearing is processed by the SSI method to extract fault feature vectors. Then, the MSVM is constructed based on Gauss kernel support vector machine (SVM) and polynomial kernel SVM. Finally, fault feature vectors which indicate the condition of the wind turbine bearing are inputted to the MSVM for fault pattern recognition. The results indicate that the SSI-MSVM method is effective in fault diagnosis for a wind turbine bearing and can successfully identify fault types of bearing and achieve higher diagnostic accuracy than that of K-means clustering, fuzzy means clustering and traditional SVM.

Very large-scale data classification based on K-means clustering and multi-kernel SVM

When classifying very large-scale data sets, there are two major challenges: the first challenge is that it is time-consuming and laborious to label sufficient amount of training samples; the second challenge is that it is difficult to train a model in a time-efficient and high-accuracy manner. This is due to the fact that to create a high-accuracy model, normally it is required to generate a large and representative training set. A large training set may also require significantly more training time. There is a trade-off between the speed and accuracy when performing classification training, especially for large-scale data sets. To address this problem, a novel strategy of large-scale data classification is proposed by combining K-means clustering technology and multi-kernel support vector machine method. First, the K-means clustering method is used on a small portion of the original data set. The clustering stage is designed with a special strategy to select representative training instances. Such method reduces the needs of creating a large training set as well as the subsequent manual labeling work. K-means clustering method has two characteristics: (1) the result is greatly influenced by the cluster number k, and (2) the optimal result is difficult to achieve. In the proposed special strategy, the two characteristics are utilized to find the most representative instances by defining a relaxed cluster number k and doing K-means repeatedly. In each K-means clustering step, both the nearest and the farthest instance to each cluster center are selected into a set. Using this method, the selected instances will have a representative distribution of the original whole data set and reduce the need of labeling the original data set. An outlier detection method is applied to further delete the outlier instances according to their outlier scores. Finally, a multi-kernel SVM is trained using the selected instances and a classifier model can be obtained to predict subsequent new instances. The evaluation results show that the proposed instance selection method significantly reduces the size of training data sets as well as training time; in the meanwhile, it maintains a relatively good accuracy performance.