Use Of Multiple Kernel Learning Research Articles

A structure-guided approach to the prediction of natural image saliency

The structure of a scene provides global contextual information in directing gaze and complements local object information in saliency prediction. In this study, we explore how visual attention can be affected by scene structures, namely openness, depth and perspective. We first build an eye tracking dataset with 2500 natural scene images and collect gaze data via both eye tracking and mouse tracking. We make observations on scene layout properties and propose a set of scene structural features relating to visual attention. The set of complementary features are then integrated for saliency prediction. Our features are independent of and can work together with many computational modules, and this work demonstrates the use of Multiple kernel learning (MKL) as an example to integrate the features at low- and high-levels. Experimental results demonstrate that our model outperforms existing methods and our scene structural features can improve the performance of other saliency models in outdoor scenes.

Transferable Representation Learning with Deep Adaptation Networks.

Domain adaptation studies learning algorithms that generalize across source domains and target domains that exhibit different distributions. Recent studies reveal that deep neural networks can learn transferable features that generalize well to similar novel tasks. However, as deep features eventually transition from general to specific along the network, feature transferability drops significantly in higher task-specific layers with increasing domain discrepancy. To formally reduce the effects of this discrepancy and enhance feature transferability in task-specific layers, we develop a novel framework for deep adaptation networks that extends deep convolutional neural networks to domain adaptation problems. The framework embeds the deep features of all task-specific layers into reproducing kernel Hilbert spaces (RKHSs) and optimally matches different domain distributions. The deep features are made more transferable by exploiting low-density separation of target-unlabeled data in very deep architectures, while the domain discrepancy is further reduced via the use of multiple kernel learning that enhances the statistical power of kernel embedding matching. The overall framework is cast in a minimax game setting. Extensive empirical evidence shows that the proposed networks yield state-of-the-art results on standard visual domain-adaptation benchmarks.

Optimizing Multiple Kernel Learning for the Classification of UAV Data

Unmanned Aerial Vehicles (UAVs) are capable of providing high-quality orthoimagery and 3D information in the form of point clouds at a relatively low cost. Their increasing popularity stresses the necessity of understanding which algorithms are especially suited for processing the data obtained from UAVs. The features that are extracted from the point cloud and imagery have different statistical characteristics and can be considered as heterogeneous, which motivates the use of Multiple Kernel Learning (MKL) for classification problems. In this paper, we illustrate the utility of applying MKL for the classification of heterogeneous features obtained from UAV data through a case study of an informal settlement in Kigali, Rwanda. Results indicate that MKL can achieve a classification accuracy of 90.6%, a 5.2% increase over a standard single-kernel Support Vector Machine (SVM). A comparison of seven MKL methods indicates that linearly-weighted kernel combinations based on simple heuristics are competitive with respect to computationally-complex, non-linear kernel combination methods. We further underline the importance of utilizing appropriate feature grouping strategies for MKL, which has not been directly addressed in the literature, and we propose a novel, automated feature grouping method that achieves a high classification accuracy for various MKL methods.

Multiple kernel support vector regression for pricing nifty option

<p>The goal of present experiments is to investigate the use of multiple kernel learning as a tool for pricing options in the context of Indian stock market for Nifty index options. In this paper, fair price of an option is predicted by Multiple Kernel Support Vector Regression (MKLSVR) using linear combinations of kernels and Single Kernel Support Vector Regression (SKSVR). Prices of option highly depend on different money market conditions like deep-in-the-money, in-the-money, at-the-money, out-of-money and deep-out-of-money condition. The experimental study attempts to identify the forecasting errors with the help of mean square error; root meant square error, and normalized root meant square error between the market option prices and the calculated option prices by model for all market conditions. The results reflect that multiple kernel support vector regression performed fairly well in comparison to support vector regression with single kernel.</p>

A pathway-based data integration framework for prediction of disease progression

Motivation: Within medical research there is an increasing trend toward deriving multiple types of data from the same individual. The most effective prognostic prediction methods should use all available data, as this maximizes the amount of information used. In this article, we consider a variety of learning strategies to boost prediction performance based on the use of all available data.Implementation: We consider data integration via the use of multiple kernel learning supervised learning methods. We propose a scheme in which feature selection by statistical score is performed separately per data type and by pathway membership. We further consider the introduction of a confidence measure for the class assignment, both to remove some ambiguously labeled datapoints from the training data and to implement a cautious classifier that only makes predictions when the associated confidence is high.Results: We use the METABRIC dataset for breast cancer, with prediction of survival at 2000 days from diagnosis. Predictive accuracy is improved by using kernels that exclusively use those genes, as features, which are known members of particular pathways. We show that yet further improvements can be made by using a range of additional kernels based on clinical covariates such as Estrogen Receptor (ER) status. Using this range of measures to improve prediction performance, we show that the test accuracy on new instances is nearly 80%, though predictions are only made on 69.2% of the patient cohort.Availability: https://github.com/jseoane/FSMKLContact: J.Seoane@bristol.ac.ukSupplementary information: Supplementary data are available at Bioinformatics online.

Automatic Diagnosis of Pathological Myopia from Heterogeneous Biomedical Data

Pathological myopia is one of the leading causes of blindness worldwide. The condition is particularly prevalent in Asia. Unlike myopia, pathological myopia is accompanied by degenerative changes in the retina, which if left untreated can lead to irrecoverable vision loss. The accurate diagnosis of pathological myopia will enable timely intervention and facilitate better disease management to slow down the progression of the disease. Current methods of assessment typically consider only one type of data, such as that from retinal imaging. However, different kinds of data, including that of genetic, demographic and clinical information, may contain different and independent information, which can provide different perspectives on the visually observable, genetic or environmental mechanisms for the disease. The combination of these potentially complementary pieces of information can enhance the understanding of the disease, providing a holistic appreciation of the multiple risks factors as well as improving the detection outcomes. In this study, we propose a computer-aided diagnosis framework for Pathological Myopia diagnosis through Biomedical and Image Informatics(PM-BMII). Through the use of multiple kernel learning (MKL) methods, PM-BMII intelligently fuses heterogeneous biomedical information to improve the accuracy of disease diagnosis. Data from 2,258 subjects of a population-based study, in which demographic and clinical information, retinal fundus imaging data and genotyping data were collected, are used to evaluate the proposed framework. The experimental results show that PM-BMII achieves an AUC of 0.888, outperforming the detection results from the use of demographic and clinical information 0.607 (increase , ), genotyping data 0.774 (increase , ) or imaging data 0.852 (increase , ) alone. The accuracy of the results obtained demonstrates the feasibility of using heterogeneous data for improved disease diagnosis through our proposed PM-BMII framework.

Calpain cleavage prediction using multiple kernel learning.

Calpain, an intracellular -dependent cysteine protease, is known to play a role in a wide range of metabolic pathways through limited proteolysis of its substrates. However, only a limited number of these substrates are currently known, with the exact mechanism of substrate recognition and cleavage by calpain still largely unknown. While previous research has successfully applied standard machine-learning algorithms to accurately predict substrate cleavage by other similar types of proteases, their approach does not extend well to calpain, possibly due to its particular mode of proteolytic action and limited amount of experimental data. Through the use of Multiple Kernel Learning, a recent extension to the classic Support Vector Machine framework, we were able to train complex models based on rich, heterogeneous feature sets, leading to significantly improved prediction quality (6% over highest AUC score produced by state-of-the-art methods). In addition to producing a stronger machine-learning model for the prediction of calpain cleavage, we were able to highlight the importance and role of each feature of substrate sequences in defining specificity: primary sequence, secondary structure and solvent accessibility. Most notably, we showed there existed significant specificity differences across calpain sub-types, despite previous assumption to the contrary. Prediction accuracy was further successfully validated using, as an unbiased test set, mutated sequences of calpastatin (endogenous inhibitor of calpain) modified to no longer block calpain's proteolytic action. An online implementation of our prediction tool is available at http://calpain.org.

Learning wind fields with multiple kernels

This paper presents multiple kernel learning (MKL) regression as an exploratory spatial data analysis and modelling tool. The MKL approach is introduced as an extension of support vector regression, where MKL uses dedicated kernels to divide a given task into sub-problems and to treat them separately in an effective way. It provides better interpretability to non-linear robust kernel regression at the cost of a more complex numerical optimization. In particular, we investigate the use of MKL as a tool that allows us to avoid using ad-hoc topographic indices as covariables in statistical models in complex terrains. Instead, MKL learns these relationships from the data in a non-parametric fashion. A study on data simulated from real terrain features confirms the ability of MKL to enhance the interpretability of data-driven models and to aid feature selection without degrading predictive performances. Here we examine the stability of the MKL algorithm with respect to the number of training data samples and to the presence of noise. The results of a real case study are also presented, where MKL is able to exploit a large set of terrain features computed at multiple spatial scales, when predicting mean wind speed in an Alpine region.