The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
While state-of-the-art kernels for graphs with discrete labels scale well to graphs with thousands of nodes, the few existing kernels for graphs with continuous attributes, unfortunately, do not scale well. To overcome this limitation, we present hash graph kernels, a general framework to derive kernels for graphs with continuous attributes from discrete ones. The idea is to iteratively turn continuous...
One of the main tasks sought after with machine learning is classification. Support vector machines are one of the widely used machine learning algorithms for data classification. SVMs are by default binary classifiers, extending them to multi-class classifiers is a challenging on-going research problem. In this paper, we propose a new approach to constructing the multi-class classification function,...
Parkinson's disease (PD) and essential tremor (ET) are two kinds of tremor disorders which always confusing doctors in clinical diagnosis. Early experiments on structural MRI have already shown that Parkinson's disease can cause pathological changes in the brain region named Caudate_R (a part of Basal ganglia) while essential tremor cannot. Although there are many research work on the classification...
Software metrics can be used as a indicator of the presence of software vulnerabilities. These metrics have been used with machine learning to predict source code prone to contain vulnerabilities. Although it is not possible to find the exact location of the flaws, the models can show which components require more attention during inspections and testing. Each new technique uses his own evaluation...
High-level understanding of image contents has been receiving much attention in the last decade. Low level processing figures as abuilding block in this framework and it also continues to play an important role in several specific tasks such as in image filtering and colorization, medical imaging, and document image processing. The design of image operators for these tasks is usually done manually...
Designing image operators is a hard task usually tackled by specialists in image processing. An alternative approach is to use machine learning to estimate local transformations, that characterize the image operators, from pairs of input-output images. The main challenge of this approach, called W-operator learning, is estimating operators over large windows without overfitting. Current techniques...
This paper presents a new flexible approach to predict the gender of the writers from their handwriting samples. Handwriting features can be extracted from different methods. Therefore, the multi-feature sets are irrelevant and redundant. The conflict of the features exists in the sets, which affects the accuracy of classification and the computing cost. This paper proposes a Mutual Information (MI)...
With the development of deep learning, many difficult recognition problems can be solved by deep learning models. For handwritten character recognition, the CNN is used the most. In order to improve the performance of CNN, many new models have been proposed and in which the relaxation CNN [35] is widely used. The relaxation CNN has more complicated structure than CNN while the recognition time is...
Sparse Matrix-Vector multiplication (SpMV) is a computational kernel widely used in many applications. There are many different implementations using different processors and algorithms for SpMV. The performances of different SpMV implementations are quite different, and it is basically difficult to choose the implementation that has the best performance for a given sparse matrix and a given platform...
Hurricanes can cause significant damages to the electric power systems and result in widespread and prolonged loss of electric services. A preventive scheduling of available resources in response to these events can be of significant importance in reducing the related undesirable aftermath. An Event-driven Security-Constrained Unit Commitment (E-SCUC), as discussed in this paper, can be used as a...
Detection algorithms for electroencephalography (EEG) data typically employ handcrafted features that take advantage of the signal's specific properties. In the field of interictal epileptic discharge (IED) detection, the feature representation that provides optimal classification performance is still an unresolved issue. In this paper, we consider deep learning for automatic feature generation from...
Quality of food and agricultural products is vital for farmers and consumers. Quality based classification of these products is being carried out manually in the industry which is tedious and expensive. Computer Vision systems can be used to automate the classification process. Automation can reduce the production cost and improve the overall quality. A computer vision system captures the image of...
The major challenge of machine learning based image steganalysis lies in obtaining powerful feature representations. Recently, Qian et al. have shown that Convolutional Neural Network (CNN) is effective for learning features automatically for steganalysis. In this paper, we follow up this new paradigm in steganalysis, and propose a framework based on transfer learning to help the training of CNN for...
Document is unavailable: This DOI was registered to an article that was not presented by the author(s) at this conference. As per section 8.2.1.B.13 of IEEE's "Publication Services and Products Board Operations Manual," IEEE has chosen to exclude this article from distribution. We regret any inconvenience.
Deep learning is well known as a method to extract hierarchical representations of data. In this paper a novel unsupervised deep learning based methodology, named Local Binary Pattern Network (LBPNet), is proposed to efficiently extract and compare high-level over-complete features in multilayer hierarchy. The LBPNet retains the same topology of Convolutional Neural Network (CNN) — one of the most...
We study a natural problem: Given a small piece of a large parent network, is it possible to identify the parent network? We approach this problem from two perspectives. First, using several “sophisticated” or “classical” network features that have been developed over decades of social network study. These features measure aggregate properties of the network and have been found to take on distinctive...
Deep learning has attracted great research interest in recent years in many signal processing application areas. However, investigation of deep learning implementations in highly resource-constrained contexts has been relatively unexplored due to the large computational requirements involved. In this paper, we investigate the implementation of a deep learning application for vehicle classification...
Automatic and accurate lumbar vertebrae detection is an essential step of image-guided minimally invasive spine surgery (IG-MISS). However, traditional methods still require human intervention due to the similarity of vertebrae, abnormal pathological conditions and uncertain imaging angle. In this paper, we present a novel convolutional neural network (CNN) model to automatically detect lumbar vertebrae...
Human action recognition is a challenging vision task due to the complex action patterns in the real-world videos. In this work, we propose a DeepAction Kernel Gaussian Process, which takes advantage of Gaussian process (GP) and deep learning, to capture the distinctive action characteristics. Specifically, we design a unified, deep and non-adjacent kernel structure within Gaussian process to classify...
Dynamic ranking learning problem is considered when the training sample is a data stream, consisting of a sequence of a series of objects characterized by a set of features and relative ranks within each series. The problem is reduced to preference learning to rank on clusters in the feature space of ranked objects, while aggregated training dataset is formed from the centers of clusters and estimates...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.