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.
Plankton image classification plays an important role in the ocean ecosystems research. Recently, a large scale database for plankton classification with over 3 million images annotated with over 100 classes was released. However, the database suffers from imbalanced class distribution in which over 90% of images belong to only 5 classes. Due to this class-imbalance problem, the existing classification...
While data-dependent dimensionality reduction has dominated in many applications of hyperspectral imagery, there is increasing interest in data-independent strategies—such as random projections—due to their promise for reduced computational complexity as well as their demonstrated ability to preserve application-important information. Such random-projection-based dimensionality reduction is investigated...
Detecting cyber-attacks in cloud infrastructures is essential for protecting cloud infrastructures from cyber-attacks. It is difficult to detect cyber-attacks in cloud infrastructures due to the complex and distributed natures of cloud infrastructures. In addition, various computing and storage devices, both mobile and stationary, are connected to cloud infrastructures to facilitate users access,...
Statistical machine translation (SMT) plays more and more important role now. The performance of the SMT is largely dependent on the size and quality of training data. But the demands for translation is rich, how to make the best of limited in-domain data to satisfy the needs of translation coming from different domains is one of the hot focus in current SMT. Domain adaption aims to obviously improve...
Terrain classification is one of the most important applications of the polarimetric SAR (PolSAR) data. Although many effective methods have been proposed, it is still a hot issue. This paper proposes a novel algorithm using deep convolutional networks (ConvNets) for PolSAR data classification. This algorithm is validated by AirSAR data over San Francisco and ALOS-PALSAR2 data over Shanghai Hengsha...
Event Driven Software (EDS) testing is a very challenging task as a large number of events can be invoked by users. So far it is difficult to test all the user inputs invoked, therefore, test case prioritization is essentially required for giving more priority to test cases which reveal higher faults comparatively. We have proposed test case prioritization for EDS: as the Event Type, Interaction of...
This paper presents a recurrent optimized heuristic Artificial Neural Network (ANN) uses Recurrent Elman Gradient Descent Adaptive Learning Rate and Momentum method with various parameter values. The values is approached by using El-Nino Southern Oscillation (ENSO) variable, which are Southern Oscillation Index (SOI), Wind, Outgoing Long Wave Radiation (OLR), and Sea Surface Temperature (SST) to forecast...
In this paper, a new online learning algorithm is proposed to learn a data sample in hybrid mode. This new algorithm is developed and referred as Growing and Pruning — Fuzzy ARTMAP-radial basis function (GAP-FAM-RBF) neural network. In this algorithm, fuzzy ARTMAP (FAM) network learns from training samples and radial basis function (RBF) network provides viable solutions. The GAP-FAM-RBF that proposed...
Wearable sensors based activity recognition is a research area where inertial measurement units based information is used to recognize human activities. While every human is different the usage of adaptive and personal models has become more attractive approach in the area. In this article, a novel solution is presented how to combine the human independent and personal models more effectively using...
To train a scene classifier with good generalization capability, a large number of human labeled training images are often needed. However, a large number of well-labeled training images may not always be available. To alleviate this problem, the web resources-aided scene classification framework was proposed. The present paper is a new development based on our previously proposed framework [1], with...
Most works covering the topic of transfer learning propose an algorithm to solve a given domain adaptation problem, then test the algorithm using real-world datasets. A test with a real-world dataset represents a single transfer learning test condition, which partially measures an algorithm's performance. Previous research has placed little emphasis on developing a comprehensive and uniform test for...
A novel fMRI classification method designed for rapid event related fMRI experiments is described and applied to the classification of loud reading of isolated words in Hebrew. Three comparisons of different grammatical complexity were performed: (i) words versus asterisks (ii) “with diacritics versus without diacritics” and (iii) “with root versus no root”. We discuss the most difficult task and,...
The paper presents an improved redial basis function network to degrade the influence of the heteroscedasticity noises in the training data. A general purpose learning algorithm is regarded as the statistical nonlinear regression model which is assumed the constant noise level. However, the heteroscedasticity noises always exist in the real data. The transformation based least trimmed squares-support...
Roadside vegetation classification has recently attracted increasing attention, due to its significance in applications such as vegetation growth management and fire hazard identification. Existing studies primarily focus on learning visible feature based classifiers or invisible feature based thresholds, which often suffer from a generalization problem to new data. This paper proposes an approach...
It is well known that feed-forward neural networks can be learnt from symbolic data although the learnt networks usually have poor performance. This paper explores the ability of a recently popular feed-forward neural network, i.e., Extreme Learning Machine (ELM) for modeling symbolic data. An experimental study is conducted to compare C4.5 (a very popular algorithm of learning from symbolic data)...
This paper proposes a novel fuzzy forecasting method for forecasting the TAIEX based on optimal partitions of intervals, optimal weights, and particle swarm optimization (PSO) techniques. First, it applies PSO techniques to find optimal intervals and optimal weighting vectors of two-factors second-order fuzzy-trend logical relationship groups (TFSTLRGs) simultaneously using the historical training...
Video-based crowd counting (VCC) is a high demanded technique in many video applications. Existing supervised VCC methods essentially learn an intrinsic mapping function between image features and corresponding crowd counts. However, imbalanced training dataset degrades the performance of VCC significantly. Encouraged by recent success in cost-sensitive learning for image classification with imbalance...
Removal of inconsistency from a data set contributes significantly in improving classification accuracy. Inconsistency occurs when attributes of objects have same value but they belong to different classes. Inconsistency is either inherent in the data set or appear during different data preprocessing steps, like discretization, dimensionality reduction and missing value prediction. The aim of the...
In this paper, we concentrate on a challenging problem — image parsing trained on images with weakly supervised information, i.e., image-level labels. Image-level labels are ambiguous and difficult for training. Typically, an affinity graph of superpixels is constructed to provide additional information about labels of the target superpixel. However, existing work constructs affinity graph in a naive...
Iris liveness detection methods have been developed to overcome the vulnerability of iris biometric systems to spoofing attacks. In the literature, it is typically assumed that a known attack modality will be perpetrated. Then liveness models are designed using labelled samples from both real/live and fake/spoof distributions, the latter derived from the assumed attack modality. In this work it is...
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.