Search

Brain disorders, such as Autism Spectrum Disorder (ASD), alter brain functional (from fMRI) and structural (from diffusion MRI) connectivities at multiple levels and in varying degrees. While unraveling such alterations have been the focus of a large number of studies, morphological brain connectivity has been out of the research scope. In particular, shape-to-shape relationships across brain regions of interest (ROIs) were rarely investigated. As such, the use of networks based on morphological brain data in neurological disorder diagnosis, while leveraging the advent of machine learning, could complement our knowledge on brain wiring alterations in unprecedented ways. In this paper, we use conventional T1-weighted MRI to define morphological brain networks (MBNs), each quantifying shape relationship between different cortical regions for a specific cortical attribute at both low-order and high-order levels. While typical brain connectomes investigate the relationship between two ROIs, we propose high-order MBN which better captures brain complex interactions by modeling the morphological relationship between pairs of ROIs. For ASD identification, we present a connectomic manifold learning framework, which learns multiple kernels to estimate a similarity measure between ASD and normal controls (NC) connectional features, to perform dimensionality reduction for clustering ASD and NC subjects. We benchmark our ASD identification method against both supervised and unsupervised state-of-the-art methods, while depicting the most discriminative high- and low-order relationships between morphological regions in the left and right hemispheres.

Inference of space-time varying signals on graphs emerges naturally in a plethora of network science related applications. A frequently encountered challenge pertains to reconstructing such dynamic processes, given their values over a subset of vertices and time instants. The present paper develops a graph-aware kernel-based kriged Kalman filter that accounts for the spatio-temporal variations, and offers efficient online reconstruction, even for dynamically evolving network topologies. The kernel-based learning framework bypasses the need for statistical information by capitalizing on the smoothness that graph signals exhibit with respect to the underlying graph. To address the challenge of selecting the appropriate kernel, the proposed filter is combined with a multikernel selection module. Such a data-driven method selects a kernel attuned to the signal dynamics on-the-fly within the linear span of a preselected dictionary. The novel multikernel learning algorithm exploits the eigenstructure of Laplacian kernel matrices to reduce computational complexity. Numerical tests with synthetic and real data demonstrate the superior reconstruction performance of the novel approach relative to state-of-the-art alternatives. [ABSTRACT FROM AUTHOR]

For the management of wind energy, wind speed forecasting is often required. Accurate multi-step ahead wind speed forecasts make the power system be adjusted timely and properly to ensure the stable and efficient operation of power system. Currently, various techniques have been developed for multi-step ahead wind speed forecasting. However, the correlation among different forecasting steps is often neglected in current multi-step ahead wind speed forecasting approaches, and the characteristic of heteroscedasticity in wind speed forecasting errors is usually not taken into consideration. In this work, a novel multi-step ahead forecasting method based on multi-kernel learning is developed. This method considers the task correlation, which represented by the covariance of multi-step ahead forecasting tasks, as well as the heteroscedasticity of forecasting errors. The optimization is solved within the framework of variational Bayesian. Thus, a correlation aware multi-step ahead wind speed forecasting technique with heteroscedastic multi-kernel learning is designed. In this paper, the experimental results in different wind farms and different seasons prove that the regression model considering the characteristics of multi-step ahead wind speed forecasting, task correlation and heteroscedasticity, will produce more accurate forecasts than the other models as for two to six-ahead wind speed forecasting. However, it is difficult to tell which characteristic is more important from the forecasting results. So, the regression model considering both of them will be more reasonable. Moreover, the training time of the proposed model is more than 10 min but less than 20 min. Thus, two to six-step ahead wind speed forecasts can be used in some practical applications, such as the load dispatch planning and the load increment/decrement decisions. [ABSTRACT FROM AUTHOR]

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation. [ABSTRACT FROM AUTHOR]

One of the most important issues for the development of a motor-imagery based brain-computer interface (BCI) is how to design a powerful classifier with strong generalization capability. Extreme learning machine (ELM) has recently proven to be comparable or more efficient than support vector machine for many pattern recognition problems. In this study, we propose a multi-kernel ELM (MKELM)-based method for motor imagery electroencephalogram (EEG) classification. The kernel extension of ELM provides an elegant way to circumvent calculation of the hidden layer outputs and inherently encode it in a kernel matrix. We investigate effects of two different kernel functions (i.e., Gaussian kernel and polynomial kernel) on the performance of kernel ELM. The MKELM method is subsequently developed by integrating these two types of kernels with a multi-kernel learning strategy, which can effectively explore the supplementary information from multiple nonlinear feature spaces for more robust classification of EEG. An extensive experimental comparison with two public EEG datasets indicates that the MKELM method gives higher classification accuracy than those of the other competing algorithms. The experimental results confirm that superiority of the proposed MKELM-based method for accurate classification of EEG associated with motor imagery in BCI applications. Our method also provides a promising and generalized solution to investigate the complex and nonlinear information for various applications in the fields of expert and intelligent systems. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) and positron emission tomography (PET) are neuroimaging modalities typically used for evaluating brain changes in Alzheimer’s disease (AD). Due to their complementary nature, their combination can provide more accurate AD diagnosis or prognosis. In this work, we apply a multi-modal imaging machine-learning framework to enhance AD classification and prediction of diagnosis of subject-matched gray matter MRI and Pittsburgh compound B (PiB)-PET data related to 58 AD, 108 mild cognitive impairment (MCI) and 120 healthy elderly (HE) subjects from the Australian imaging, biomarkers and lifestyle (AIBL) dataset. Specifically, we combined a Dartel algorithm to enhance anatomical registration with multi-kernel learning (MKL) technique, yielding an average of >95% accuracy for three binary classification problems: AD-vs.-HE, MCI-vs.-HE and AD-vs.-MCI, a considerable improvement from individual modality approach. Consistent with t-contrasts, the MKL weight maps revealed known brain regions associated with AD, i.e., (para)hippocampus, posterior cingulate cortex and bilateral temporal gyrus. Importantly, MKL regression analysis provided excellent predictions of diagnosis of individuals by r2 = 0.86. In addition, we found significant correlations between the MKL classification and delayed memory recall scores with r2 = 0.62 (p < 0.01). Interestingly, outliers in the regression model for diagnosis were mainly converter samples with a higher likelihood of converting to the inclined diagnostic category. Overall, our work demonstrates the successful application of MKL with Dartel on combined neuromarkers from different neuroimaging modalities in the AIBL data. This lends further support in favor of machine learning approach in improving the diagnosis and risk prediction of AD.

Multi-kernel learning is a new research hotspot in current kernel machine learning field. By mapping data into the high dimensional space, kernel methods increase the computing performance of linear classifiers such as support vector machines, and it is a convenient and effective way to deal with nonlinear pattern recognition and classification. However, in some complex situations，such as heterogeneous data or irregular data? large sample size and non-flat sample distribution，the kernel learning method based on single kernel function cannot completely meet the requirement，so it is necessary to develop multiple kernel functions in order to get better results. We propose a new summation multi-kernel learning method based on sample weighting which can be weighted by the capability of how much a single kernel function can fit the sample. Experiment analysis on several data sets shows that the proposed method can obtain high classification accuracy. [ABSTRACT FROM AUTHOR]

The high cost for new medicines is hindering their development and machine learning is therefore being used to avoid carrying out physical experiments. Here, we present a comparison between three different machine learning approaches in a classification setting where learning and prediction follow a teaching schedule to mimic the drug discovery process. The approaches are standard SVM classification, SVM based multi-kernel classification and SVM classification based on learning using privileged information. Our two main conclusions are derived using experimental in-vitro data and compound structure descriptors. The in-vitro data is assumed to i) be completely absent in the standard SVM setting, ii) be available at all times when applying multi-kernel learning, or iii) be available as privileged information during training only. The structure descriptors are always available. One conclusion is that multi-kernel learning has higher odds than standard SVM in producing higher accuracy. The second is that learning using privileged information does not have higher odds than the standard SVM, although it may improve accuracy when the training sets are small. [ABSTRACT FROM AUTHOR]

The objective of this study is to demonstrate through empirical evaluation the potential of a number of computer vision (CV) methods for sex determination from human skull. To achieve this, six local feature representations, two feature learnings, and three classification algorithms are rigorously combined and evaluated on skull regions derived from skull partitions. Furthermore, we introduce for the first time the application of multi-kernel learning (MKL) on multiple features for sex prediction from human skull. In comparison to the classical forensic methods, the results in this study are competitive, attesting to the suitability of CV methods for sex estimation. The proposed approach is fully automatic. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) and positron emission tomography (PET) are neuroimaging modalities typically used for evaluating brain changes in Alzheimer's disease (AD). Due to their complementary nature, their combination can provide more accurate AD diagnosis or prognosis. In this work, we apply a multi-modal imaging machine-learning framework to enhance AD classification and prediction of diagnosis of subject-matched gray matter MRI and Pittsburgh compound B (PiB)- PET data related to 58 AD, 108 mild cognitive impairment (MCI) and 120 healthy elderly (HE) subjects from the Australian imaging, biomarkers and lifestyle (AIBL) dataset. Specifically, we combined a Dartel algorithm to enhance anatomical registration with multi-kernel learning (MKL) technique, yielding an average of >95% accuracy for three binary classification problems: AD-vs.-HE, MCI-vs.-HE and AD-vs.-MCI, a considerable improvement from individual modality approach. Consistent with t-contrasts, the MKL weight maps revealed known brain regions associated with AD, i.e., (para)hippocampus, posterior cingulate cortex and bilateral temporal gyrus. Importantly, MKL regression analysis provided excellent predictions of diagnosis of individuals by r² = 0.86. In addition, we found significant correlations between the MKL classification and delayed memory recall scores with r² = 0.62 (p < 0.01). Interestingly, outliers in the regression model for diagnosis were mainly converter samples with a higher likelihood of converting to the inclined diagnostic category. Overall, our work demonstrates the successful application of MKL with Dartel on combined neuromarkers from different neuroimaging modalities in the AIBL data. This lends further support in favor of machine learning approach in improving the diagnosis and risk prediction of AD. [ABSTRACT FROM AUTHOR]

In this paper, we investigate the problem of optimizing complex multivariate performance measures to learn classifiers for pattern classification problems. For the first time, the multi-kernel learning is considered to construct a classifier to optimize a given nonlinear and non-smooth multivariate classifier performance measure. We estimate and optimize the upper bound of the given multivariate performance measure, instead of optimizing it directly. Moreover, to solve the problem of kernel function selection and kernel parameter tuning, we proposed to construct an optimal kernel by weighted linear combination of some candidate kernels. The learning of the classifier parameter and the kernel weight are unified in a single objective function considering minimizing the upper bound of the given multivariate performance measure. The objective function is optimized with regard to classifier parameter and kernel weight alternately in an iterative algorithm. The developed algorithm is evaluated on two different pattern classification methods with regard to various multivariate performance measure optimization problems. The experiment results show the proposed algorithm outperforms the competing methods. [ABSTRACT FROM AUTHOR]

Magnetic resonance imaging (MRI) and positron emission tomography (PET) are neuroimaging modalities typically used for evaluating brain changes in Alzheimer's disease (AD). Due to their complementary nature, their combination can provide more accurate AD diagnosis or prognosis. In this work, we apply a multi-modal imaging machine-learning framework to enhance AD classification and prediction of diagnosis of subject-matched gray matter MRI and Pittsburgh compound B (PiB)-PET data related to 58 AD, 108 mild cognitive impairment (MCI) and 120 healthy elderly (HE) subjects from the Australian imaging, biomarkers and lifestyle (AIBL) dataset. Specifically, we combined a Dartel algorithm to enhance anatomical registration with multi-kernel learning (MKL) technique, yielding an average of >95% accuracy for three binary classification problems: AD-vs.-HE, MCI-vs.-HE and AD-vs.-MCI, a considerable improvement from individual modality approach. Consistent with t-contrasts, the MKL weight maps revealed known brain regions associated with AD, i.e., (para)hippocampus, posterior cingulate cortex and bilateral temporal gyrus. Importantly, MKL regression analysis provided excellent predictions of diagnosis of individuals by r2 = 0.86. In addition, we found significant correlations between the MKL classification and delayed memory recall scores with r2 = 0.62 (p < 0.01). Interestingly, outliers in the regression model for diagnosis were mainly converter samples with a higher likelihood of converting to the inclined diagnostic category. Overall, our work demonstrates the successful application of MKL with Dartel on combined neuromarkers from different neuroimaging modalities in the AIBL data. This lends further support in favor of machine learning approach in improving the diagnosis and risk prediction of AD. [ABSTRACT FROM AUTHOR]

With the increasing use of color images in the fields of pattern recognition, computer vision and machine learning, color face recognition technique becomes important, whose key problem is how to make full use of the color information and extract effective discriminating features. In this paper, we propose a novel nonlinear feature extraction approach for color face recognition, named dual multi-kernel discriminant analysis (DMDA), where we design a kernel selection strategy to select the optimal kernel mapping function for each color component of face images, further design a color space selection strategy to choose the most suitable space, then separately map different color components of face images into different high-dimensional kernel spaces, and finally perform multi-kernel learning and discriminant analysis not only within each component but also between different components. Experimental results in the public face recognition grand challenge (FRGC) version 2 and labeled faces in the wilds (LFW) databases illustrate that our approach outperforms several representative color face recognition methods. [ABSTRACT FROM AUTHOR]

Various types of social media make the people share their personal experience in different ways. In some social networking sites. Some users post their reviews, some users can support these reviews with comments, and some users just rate the reviews as kind of support or not. Unfortunately, there is rare explicit negative comments towards other reviews. This means if there is a link between two users, it must be positive link. Apparently, the negative link is invisible in these social network. Or in other word, the negative links are redundant to positive links. In this work, we first discuss the feature extraction from social media data and propose new method to compute the distance between each pair of comments or reviews on social media. Then we investigate whether we can predict negative links via regression analysis when only positive links are manifested from social media data. In particular, we provide a principled way to mathematically incorporate multi-facet data in a novel framework, Constructing Negative Links, CsNL to predict negative links for discovering the hidden information. Additionally, we investigate the ways of solution to general negative link predication problems with CsNL and its extension. Experiments are performed on real-world data and results show that negative links is predictable with multi-facet of social media data by the proposed framework CsNL. Essentially, high prediction accuracy suggests that negative links are redundant to positive links. Further experiments are performed to evaluate coefficients on different kernels. The results show that user generated content dominates the prediction performance of CsNL. [ABSTRACT FROM AUTHOR]

High dimensionality and classification of imbalanced data sets are two of the most interesting machine learning challenges. Both issues have been independently studied in the literature. In order to simultaneously explore the both issues of feature selection and oversampling, we efficiently combine two different methodological approaches in an unified kernel framework. Specifically, we proposed a novel ℓ 2 , 1 norm balanced multiple kernel feature selection ( ℓ 2 , 1 MKFS), and designed a proximal based optimization algorithm for efficiently learning the model. Moreover, multiple kernel oversampling (MKOS) was developed to generate synthetic instances in the optimal kernel space induced by ℓ 2 , 1 MKFS, so as to compensate for the class imbalanced distribution. Our experimental results on multiple UCI data and two real medical application demonstrate that jointly operating nonlinear feature selection and oversampling with ℓ 2 , 1 norm multi-kernel learning framework ( ℓ 2 , 1 MKFSOS) can lead to a promising classification performance. [ABSTRACT FROM AUTHOR]

Classification plays a critical role in False Positive Reduction (FPR) in lung nodule Computer Aided Detection (CAD). To achieve effective recognition of nodule, many machine learning methods have been proposed. However, multiple heterogeneous feature subsets, high dimensional irrelevant features, as well as imbalanced distribution between the nodule and non-nodule classes typically makes this problem challenging. To solve these challenges, we proposed a multi-kernel based framework for feature selection and imbalanced data learning in Lung nodule CAD, involving multiple kernel learning with a ℓ 2 , 1 norm regularizer for heterogeneous feature fusion and selection from the feature subset level, a multi-kernel feature selection based on pairwise similarities from the feature level, and a multi-kernel over-sampling for the imbalanced data learning. Experimental results demonstrate the effectiveness of the proposed method in terms of Geometric mean (G-mean) and Area under the ROC curve (AUC), and consistently outperform the competing methods. [ABSTRACT FROM AUTHOR]

Robot recognition tasks usually require multiple homogeneous or heterogeneous sensors which intrinsically generate sequential, redundant, and storage demanding data with various noise pollution. Thus, online machine learning algorithms performing efficient sensory feature fusion have become a hot topic in robot recognition domain. This paper proposes an online multi-kernel extreme learning machine (OM-ELM) which assembles multiple ELM classifiers and optimizes the kernel weights with a p-norm formulation of multi-kernel learning (MKL) problem. It can be applied in feature fusion applications that require incremental learning over multiple sequential sensory readings. The performance of OM-ELM is tested towards four different robot recognition tasks. By comparing to several state-of-the-art online models for multi-kernel learning, we claim that our method achieves a superior or equivalent training accuracy and generalization ability with less training time. Practical suggestions are also given to aid effective online fusion of robot sensory features. [ABSTRACT FROM AUTHOR]

Objective: The aim of this paper is to describe a novel algorithm for False Positive Reduction in lung nodule Computer Aided Detection(CAD). Methods: In this paper, we describes a new CT lung CAD method which aims to detect solid nodules. Specially, we proposed a multi-kernel classifier with a ℓ 2, 1 norm regularizer for heterogeneous feature fusion and selection from the feature subset level, and designed two efficient strategies to optimize the parameters of kernel weights in non-smooth ℓ 2, 1 regularized multiple kernel learning algorithm. The first optimization algorithm adapts a proximal gradient method for solving the ℓ 2, 1 norm of kernel weights, and use an accelerated method based on FISTA; the second one employs an iterative scheme based on an approximate gradient descent method. Results: The results demonstrates that the FISTA-style accelerated proximal descent method is efficient for the ℓ 2, 1 norm formulation of multiple kernel learning with the theoretical guarantee of the convergence rate. Moreover, the experimental results demonstrate the effectiveness of the proposed methods in terms of Geometric mean (G-mean) and Area under the ROC curve (AUC), and significantly outperforms the competing methods. Conclusions: The proposed approach exhibits some remarkable advantages both in heterogeneous feature subsets fusion and classification phases. Compared with the fusion strategies of feature-level and decision level, the proposed ℓ 2, 1 norm multi-kernel learning algorithm is able to accurately fuse the complementary and heterogeneous feature sets, and automatically prune the irrelevant and redundant feature subsets to form a more discriminative feature set, leading a promising classification performance. Moreover, the proposed algorithm consistently outperforms the comparable classification approaches in the literature. [ABSTRACT FROM AUTHOR]

The traditional scene analysis mainly focuses on outdoor scene recognition rather than indoor scene understanding. However, with the widespread use of depth cameras, we have a new opportunity to handle the indoor scene recognition problem. In this paper, we propose a multi-task metric multi-kernel learning algorithm that exploits the inter-source similarities and complementarities between color images and depth images to conduct the indoor scene recognition. Specifically, our method utilize multi-task metric learning to learn a Mahalanobis metric for RGB-D images. Multi-task metric learning can extract the common properties from color images and depth images to learn better metrics. Furthermore, the learned metrics are employed to transform features to a correcting feature space for obtaining a better representation. By exploiting multi-kernel learning, our method can leverage multiple feature representations to train a more discriminative classifier. We conduct experiments on NYU Depth Dataset and B3DO Dataset to evaluate the effectiveness of our approach. The experimental results have demonstrated that our proposed method can lead to better indoor scene recognition. [ABSTRACT FROM AUTHOR]

Introduction Pattern recognition analysis (PRA) applied to functional magnetic resonance imaging (fMRI) has been used to decode cognitive processes and identify possible biomarkers for mental illness. In the present study, we investigated whether the positive affect (PA) or negative affect (NA) personality traits could be decoded from patterns of brain activation in response to a human threat using a healthy sample. Methods fMRI data from 34 volunteers (15 women) were acquired during a simple motor task while the volunteers viewed a set of threat stimuli that were directed either toward them or away from them and matched neutral pictures. For each participant, contrast images from a General Linear Model (GLM) between the threat versus neutral stimuli defined the spatial patterns used as input to the regression model. We applied a multiple kernel learning (MKL) regression combining information from different brain regions hierarchically in a whole brain model to decode the NA and PA from patterns of brain activation in response to threat stimuli. Results The MKL model was able to decode NA but not PA from the contrast images between threat stimuli directed away versus neutral with a significance above chance. The correlation and the mean squared error (MSE) between predicted and actual NA were 0.52 (p-value = 0.01) and 24.43 (p-value = 0.01), respectively. The MKL pattern regression model identified a network with 37 regions that contributed to the predictions. Some of the regions were related to perception (e.g., occipital and temporal regions) while others were related to emotional evaluation (e.g., caudate and prefrontal regions). Conclusion These results suggest that there was an interaction between the individuals' NA and the brain response to the threat stimuli directed away, which enabled the MKL model to decode NA from the brain patterns. To our knowledge, this is the first evidence that PRA can be used to decode a personality trait from patterns of brain activation during emotional contexts. [ABSTRACT FROM AUTHOR]

Background and Objectives: The progression of pulmonary diseases is a complex progress. Timely predicting whether the patients will progress to the severe stage or not in its early stage is critical to take appropriate hospital treatment. However, this task suffers from the "insufficient and incomplete" data issue since it is clinically impossible to have adequate training samples for one patient at each day. Besides, the training samples are extremely imbalanced since the patients who will progress to the severe stage is far less than those who will not progress to the non-severe stage., Method: We consider the severity prediction of pulmonary diseases as a time estimation problem based on CT scans. To handle the issue of "insufficient and incomplete" training samples, we introduced label distribution learning (LDL). Specifically, we generate a label distribution for each patient, making a CT image contribute to not only the learning of its chronological day, but also the learning of its neighboring days. In addition, a cost-sensitive mechanism is introduced to explore the imbalance data issue. To identify the importance of pulmonary segments in pulmonary disease severity prediction, multi-kernel learning in composite kernel space is further incorporated and particle swarm optimization (PSO) is used to find the optimal kernel weights., Results: We compare the performance of the proposed CS-LD-MKSVR algorithm with several classical machine learning algorithms and deep learning (DL) algorithms. The proposed method has obtained the best classification results on the in-house data, fully indicating its effectiveness in pulmonary disease severity prediction., Contributions: The severity prediction of pulmonary diseases is considered as a time estimation problem, and label distribution is introduced to describe the conversion time from non-severe stage to severe stage. The cost-sensitive mechanism is also introduced to handle the data imbalance issue to further improve the classification performance., Competing Interests: Declaration of competing interest None Declared., (Copyright © 2023. Published by Elsevier Ltd.)

Forecasting by regression is a very important method for the prediction of continuous values. Generally, in order to increase the predictive accuracy and reliability, as many factors or features as possible are considered and added to the regression model, however, this leads to the poor efficiency, accuracy, and interpretability. Besides, some existing methods associated with support vector regression (SVR) usually require us to solve the convex quadratic programming problem with a higher computational complexity. In this paper, we proposed a novel two-phase multi-kernel SVR using linear programming method (MK-LP-SVR) for feature sparsification and forecasting so as to solve the aforementioned problems. The multi-kernel learning method is mainly utilized to carry out feature sparsification and find the important features by computing their contribution to forecasting while the whole model can be used to predict output values for given inputs. Based on a simulation, 6 small, and 6 big data sets, the experimental results and comparison with SVR, linear programming SVR (LP-SVR), least squares SVR (LS-SVR), and multiple kernel learning SVR (MKL-SVR) showed that our proposed model has considerably improved predictive accuracy and interpretability for the regression forecasting on the independent test sets. [ABSTRACT FROM AUTHOR]

Distinguishing progressive mild cognitive impairment (pMCI) from stable mild cognitive impairment (sMCI) is critical for identification of patients who are at risk for Alzheimer's disease (AD), so that early treatment can be administered. In this paper, we propose a pMCI/sMCI classification framework that harnesses information available in longitudinal magnetic resonance imaging (MRI) data, which could be incomplete, to improve diagnostic accuracy. Volumetric features were first extracted from the baseline MRI scan and subsequent scans acquired after 6, 12, and 18 months. Dynamic features were then obtained using the 18th month scan as the reference and computing the ratios of feature differences for the earlier scans. Features that are linearly or non-linearly correlated with diagnostic labels are then selected using two elastic net sparse learning algorithms. Missing feature values due to the incomplete longitudinal data are imputed using a low-rank matrix completion method. Finally, based on the completed feature matrix, we build a multi-kernel support vector machine (mkSVM) to predict the diagnostic label of samples with unknown diagnostic statuses. Our evaluation indicates that a diagnosis accuracy as high as 78.2 % can be achieved when information from the longitudinal scans is used-6.6 % higher than the case using only the reference time point image. In other words, information provided by the longitudinal history of the disease improves diagnosis accuracy. [ABSTRACT FROM AUTHOR]

Dynamic texture (DT) widely exists in various social video media. Therefore, DT modeling and synthesis plays an important role in social media analyzing and processing. In this paper, we propose a Bayesian-based nonlinear dynamic texture modeling method for dynamic texture synthesis. To capture the non-stationary distribution of DT, we utilize the Gaussian process latent variable model for dimensional reduction. Furthermore, we design a multi-kernel dynamic system for the latent dynamic behavior modeling. In our model, we do not make strong assumption on the nonlinear function. Instead, our model automatically constructs a suitable nonlinear kernel for dynamic modeling and therefore is capable of fitting various types of dynamics. We evaluate the effectiveness our methods on the DynTex database and compared with representative DT synthesis method. Experimental results show that our method can achieve synthesis results with higher visual quality. [ABSTRACT FROM AUTHOR]

Maximum entropy discrimination (MED) is a general framework for discriminative estimation which integrates the principles of maximum entropy and maximum margin. In this paper, we propose a novel approach named multi-kernel MED (MKMED) for multi-view learning (MVL), which takes advantage of the complementary principle for MVL. Multiple kernels encode the similarities in different views. We obtain a kernel matrix by multiple kernel combination to make use of the complementary information in different views. Based on the kernel matrix obtained by multiple kernel combination, we can proceed MVL within the MED framework. The experimental results on multiple datasets demonstrate the effectiveness of the proposed MKMED. MKMED outperforms the single-view MEDs and a competing MVL mothod named SVM-2K, and is competitive with the state-of-the-art multi-view MED (MVMED) and even sometimes exceeds it. [ABSTRACT FROM AUTHOR]

Food recognition is a key component in evaluation of everyday food intakes, and its challenge is due to intraclass variation. In this paper, we present an automatic food classification method, DietCam, which specifically addresses the variation of food appearances. DietCam consists of two major components, ingredient detection and food classification. Food ingredients are detected through a combination of a deformable part-based model and a texture verification model. From the detected ingredients, food categories are classified using a multiview multikernel SVM. In the experiment, DietCam presents reliability and outperformance in recognition of food with complex ingredients on a database including 15,262 food images of 55 food types. [ABSTRACT FROM PUBLISHER]

This paper presents a new approach to image-set-based face recognition, where each training and testing example is a set of face images captured from varying poses, illuminations, expressions, and resolutions. While a number of image set based face recognition methods have been proposed in recent years, most of them model each face image set as a single linear subspace or as the union of linear subspaces, which may lose some discriminative information for face image set representation. To address this shortcoming, we propose exploiting statistics information as feature representations for face image sets and develop a localized multikernel metric learning algorithm to effectively combine different statistics for recognition. Moreover, we propose a localized multikernel multimetric learning method to jointly learn multiple feature-specific distance metrics in the kernel spaces, one for each statistic feature, to better exploit complementary information for recognition. Our methods achieve state-of-the-art performance on four widely used video face datasets including the Honda, MoBo, YouTube Celebrities, and YouTube Face datasets. [ABSTRACT FROM AUTHOR]

Photo quality assessment using the principles of visual aesthetics has been a hot research topic in recent years. Due to the complexity of human aesthetic activities, this task is very challenging. Most existing works apply binary labels (“good” or “bad”) to represent the photo quality, and focus on constructing rule-based features under the guidance of photography knowledge. However, those features strictly imitate photography rules and suffer from low effectiveness and high computational cost. Besides, the binary quality representation is oversimplified and fails to distinguish varying quality degrees. To tackle these problems, we construct new effective and efficient features from different views and further fuse them to predict multi-level, instead of binary, photo quality. More specifically, we design a set of compact rule-based features through careful analyses on photographic rules and aesthetic attributes. We propose using Deep Convolutional Neural Network (DCNN) descriptor, which encodes the photo content thoroughly, to implicitly describe the photo quality. Experiments conducted on two large scale benchmark datasets verify the effectiveness of these two different kinds of features. Furthermore, we propose a method to combine these features for multi-level photo quality prediction. This feature fusion method has proven to be effective on a dataset that is carefully organized to support research on this new multi-level photo quality assessment problem. [ABSTRACT FROM AUTHOR]

Nowadays it is important to develop effective computational methods for accurately identifying and predicting biological activity in the virtual screening of bioassay data so as to speed up the process of drug development. Among these methods, multi-criteria optimization classifier (MCOC) is a classifier which can find a trade-off between the overlapping degree of different classes and the total distance from input points to the decision hyperplane. The former should be minimized while the latter should be maximized. Then a decision function is derived from training data and this function is subsequently used to predict the class label of an unseen instance. However, due to outliers, anomalies, highly imbalanced classes, high dimension, nonlinear separability and other uncertainties in data, MCOC and other methods often give the poor predictive performance. In this paper, we introduce a new fuzzy contribution to each input point based on class median, by defining the new row and column kernel functions the linear combination of different feature kernels to replace the single kernel function in the kernel-induced feature space and penalty factors to imbalanced classes, thus a novel multi-kernel multi-criteria optimization classifier with fuzzification and penalty factors (MK–MCOC–FP) is proposed and the effects of the aforementioned problems are significantly reduced. The experimental results of predicting active compounds in the virtual screening and comparison with linear and quadratic MCOCs, support vector machines (SVM), fuzzy SVM and neural network, the conclusions show that MK–MCOC–FP evidently increased the ability of resisting noise interference, the predictive accuracy of highly class-imbalanced bioassay data, the separation of active compounds and inactive compounds, the interpretability of importance or contributions of different features to classification, the efficiency of classification with feature selection or dimensionality reduction for high-dimensional data, and the generalization of predicting the biological activity of new compounds. [ABSTRACT FROM AUTHOR]

In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine (SVM), that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realised. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a single decision function based on an integrated kernel matrix, or, by creating an ensemble of multiple single modality classifiers and integrating their predictions. Here, we describe four integrative approaches: 1) an un-weighted sum of kernels, 2) multi-kernel learning, 3) prediction averaging, and 4) majority voting, and compare their ability to enhance classification accuracy relative to the best single-modality classification accuracy. We achieve this by integrating structural, functional and diffusion tensor magnetic resonance imaging data, in order to compare ultra-high risk (UHR; n=19), first episode psychosis (FEP; n=19) and healthy control subjects (HCs; n=19). Our results show that i) whilst integration can enhance classification accuracy by up to 13%, the frequency of such instances may be limited, ii) where classification can be enhanced, simple methods may yield greater increases relative to more computationally complex alternatives, and, iii) the potential for classification enhancement is highly influenced by the specific diagnostic comparison under consideration. In conclusion, our findings suggest that for moderately sized clinical neuroimaging datasets, combining different imaging modalities in a data-driven manner is no magic bullet for increasing classification accuracy.

Previous work on 3D action recognition has focused on using hand-designed features, either from depth videos or 2D videos. In this work, we present an effective way to combine unsupervised feature learning with discriminative feature mining. Unsupervised feature learning allows us to extract spatio-temporal features from unlabeled video data. With this, we can avoid the cumbersome process of designing feature extraction by hand. We propose an ensemble approach using a discriminative learning algorithm, where each base learner is a discriminative multi-kernel-learning classifier, trained to learn an optimal combination of joint-based features. Our evaluation includes a comparison to state-of-the-art methods on the MSRAction 3D dataset, where our method, abbreviated EnMkl, outperforms earlier methods. Furthermore, we analyze the efficiency of our approach in a 3D action recognition system. [ABSTRACT FROM AUTHOR]

Functional neuroimaging studies have found intra-regional activity and inter-regional connectivity alterations in patients with post-traumatic stress disorder (PTSD). However, the results of these studies are based on group-level statistics and therefore it is unclear whether PTSD can be discriminated at single-subject level, for instance using the machine learning approach. Here, we proposed a novel framework to identify PTSD using multi-level measures derived from resting-state functional MRI (fMRI). Specifically, three levels of measures were extracted as classification features: (1) regional amplitude of low-frequency fluctuations (univariate feature), which represents local spontaneous synchronous neural activity; (2) temporal functional connectivity (bivariate feature), which represents the extent of similarity of local activity between two regions, and (3) spatial functional connectivity (multivariate feature), which represents the extent of similarity of temporal correlation maps between two regions. Our method was evaluated on 20 PTSD patients and 20 demographically matched healthy controls. The experimental results showed that the features of each level could successfully discriminate PTSD patients from healthy controls. Furthermore, the combination of multi-level features using multi-kernel learning can further improve the classification performance. Specifically, the classification accuracy obtained by the proposed framework was 92.5 %, which was an increase of at least 5 and 17.5 % from the two-level and single-level feature based methods, respectively. Particularly, the limbic structure and prefrontal cortex provided the most discriminant features for classification, consistent with results reported in previous studies. Together, this study demonstrated for the first time that patients with PTSD can be identified at the individual level using resting-state fMRI data. The promising classification results indicated that this method may provide a complementary approach for improving the clinical diagnosis of PTSD. [ABSTRACT FROM AUTHOR]

The smart grid vision entails advanced information technology and data analytics to enhance the efficiency, sustainability, and economics of the power grid infrastructure. Aligned to this end, modern statistical learning tools are leveraged here for electricity market inference. Day-ahead price forecasting is cast as a low-rank kernel learning problem. Uniquely exploiting the market clearing process, congestion patterns are modeled as rank-one components in the matrix of spatio-temporally varying prices. Through a novel nuclear norm-based regularization, kernels across pricing nodes and hours can be systematically selected. Even though market-wide forecasting is beneficial from a learning perspective, it involves processing high-dimensional market data. The latter becomes possible after devising a block-coordinate descent algorithm for solving the non-convex optimization problem involved. The algorithm utilizes results from block-sparse vector recovery and is guaranteed to converge to a stationary point. Numerical tests on real data from the Midwest ISO (MISO) market corroborate the prediction accuracy, computational efficiency, and the interpretative merits of the developed approach over existing alternatives. [ABSTRACT FROM PUBLISHER]

Similarity learning plays a fundamental role in the problem of database retrieval and nearest classification problem. Traditional pairwise similarity measure ignores the contextual information, and the Graph Transduction (GT) has been proposed as a contextual similarity learning algorithm to utilize the contextual information, which is embedded in a nearest neighbor graph. On main shortage of this method is that it is difficult to choose the optimal graph since different graphs may focus on different aspects of the objects. Co-Transduction (CT) is lately proposed by fusing two different graphs. In this paper, we generalize this problem by using the ensemble of many candidate graphs with different models and parameters for transduction, by assuming that the optimal graph could be obtained by the weighted linear ensemble of these candidate graphs. The similarities and graph weights are modeled within one unified objective function, and optimized alternately in an iterative algorithm. The new proposed algorithm, named as Ensemble Transduction (ET), is tested on two challenging tasks and the experimental results show that it can outperform both the GT and CT. [ABSTRACT FROM AUTHOR]

In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine (SVM), that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realised. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a single decision function based on an integrated kernel matrix, or, by creating an ensemble of multiple single modality classifiers and integrating their predictions. Here, we describe four integrative approaches: 1) an un-weighted sum of kernels, 2) multi-kernel learning, 3) prediction averaging, and 4) majority voting, and compare their ability to enhance classification accuracy relative to the best single-modality classification accuracy. We achieve this by integrating structural, functional and diffusion tensor magnetic resonance imaging data, in order to compare ultra-high risk (UHR; n=19), first episode psychosis (FEP; n=19) and healthy control subjects (HCs; n=19). Our results show that i) whilst integration can enhance classification accuracy by up to 13%, the frequency of such instances may be limited, ii) where classification can be enhanced, simple methods may yield greater increases relative to more computationally complex alternatives, and, iii) the potential for classification enhancement is highly influenced by the specific diagnostic comparison under consideration. In conclusion, our findings suggest that for moderately sized clinical neuroimaging datasets, combining different imaging modalities in a data-driven manner is no "magic bullet" for increasing classification accuracy. [ABSTRACT FROM AUTHOR]

Abstract: Customer response modeling is essential for a firm to allocate the marketing resources to active customers who have potential values. With the development of social media, customer response modeling in social media plays important roles in the firms’ marketing decisions. For customer response modeling in social media, the inputs involve multiple types of data and the purposes are to identify respondents to multiple items. In this study, a multi-task multi-kernel transfer learning (MT-MKTL) method is proposed to integrate shared, task-specific and transferred features in a framework for customer response modeling in social media. A two-phase algorithm is applied to solving the MT-MKTL problem. A computational experiment is conducted on microblog data. The experimental results show that the MT-MKTL method exhibits good performance. [Copyright &y& Elsevier]

Abstract: Noises are inevitably introduced in digital image acquisition processes, and thus image denoising is still a hot research problem. Different from local methods operating on local regions of images, the non-local methods utilize non-local information (even the whole image) to accomplish image denoising. Due to their superior performance, the non-local methods have recently drawn more and more attention in the image denoising community. However, these methods generally do not work well in handling complicated noises with different levels and types. Inspired by the fact in machine learning field that multi-kernel methods are more robust and effective in tackling complex problems than single-kernel ones, we establish a general non-local denoising model based on multi-kernel-induced measures (GNLMKIM for short), which provides us a platform to analyze some existing and design new filters. With the help of GNLMKIM, we reinterpret two well-known non-local filters in the united view and extend them to their novel multi-kernel counterparts. The comprehensive experiments indicate that these novel filters achieve encouraging denoising results in both visual effect and PSNR index. [Copyright &y& Elsevier]

Abstract: Accuracy of interpolation coefficients fitting to the auto-calibrating signal data is crucial for k-space-based parallel reconstruction. Both conventional generalized autocalibrating partially parallel acquisitions (GRAPPA) reconstruction that utilizes linear interpolation function and nonlinear GRAPPA (NLGRAPPA) reconstruction with polynomial kernel function are sensitive to interpolation window and often cannot consistently produce good results for overall acceleration factors. In this study, sparse multi-kernel learning is conducted within the framework of least squares support vector regression to fit interpolation coefficients as well as to reconstruct images robustly under different subsampling patterns and coil datasets. The kernel combination weights and interpolation coefficients are adaptively determined by efficient semi-infinite linear programming techniques. Experimental results on phantom and in vivo data indicate that the proposed method can automatically achieve an optimized compromise between noise suppression and residual artifacts for various sampling schemes. Compared with NLGRAPPA, our method is significantly less sensitive to the interpolation window and kernel parameters. [Copyright &y& Elsevier]

Attention deficit/hyperactivity disorder (ADHD) is one of the most common diseases in school-age children. To date, the diagnosis of ADHD is mainly subjective and studies of objective diagnostic method are of great importance. Although many efforts have been made recently to investigate the use of structural and functional brain images for the diagnosis purpose, few of them are related to ADHD. In this paper, we introduce an automatic classification framework based on brain imaging features of ADHD patients, and present in detail the feature extraction, feature selection and classifier training methods. The effects of using different features are compared against each other. In addition, we integrate multimodal image features using multi-kernel learning (MKL). The performance of our framework has been validated in the ADHD-200 Global Competition, which is a world-wide classification contest on the ADHD-200 datasets. In this competition, our classification framework using features of resting-state functional connectivity was ranked the 6th out of 21 participants under the competition scoring policy, and performed the best in terms of sensitivity and J-statistic.

Abstract: We investigate the problem of regression from multiple reproducing kernel Hilbert spaces by means of orthogonal greedy algorithm. The greedy algorithm is appealing as it uses a small portion of candidate kernels to represent the approximation of regression function, and can greatly reduce the computational burden of traditional multi-kernel learning. Satisfied learning rates are obtained based on the Rademacher chaos complexity and data dependent hypothesis spaces. [Copyright &y& Elsevier]