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.
Endmember extraction is a fundamental task in spectral unmixing of remotely sensed hyperspectral images. In this work, we develop a new robust algorithm for endmember extraction which is based on a nonnegative sparse autoencoder. The proposed approach is based on two main steps. First, it uses an automatic sampler approach with local outlier factor and affinity propagation to intelligently gather...
Graph embedding, as a dimensionality reduction framework, has already drawn great attention in hyperspectral image analysis. Taking locality preserving projection (LPP) as example, LPP utilizes typical Euclidean distance in heat kernel to create an affinity matrix and projects the high-dimensional data into a lower-dimensional space. However, the Euclidean distance is not sufficiently correlated with...
This paper developed an approach to determine optimal parameters, C and s, for support vector domain description (SVDD) model to map specific land cover from integrating of training and window-based validation sets (WVS-SVDD). The validation set based on window-based approach made a tighten hypersphere because of compact constraint by the outlier pixels which were located closely to the target class...
An overview of the wind speed retrieval algorithm used to generate the first CYGNSS Level 2 wind speed products is presented. The algorithm uses two observables derived from Level 1b calibrated Delay/Doppler Maps, and constructs a geophysical model function which maps the observable value and its associated incidence angle into a wind speed value. The wind estimates from the two observables are also...
This paper presents a combination of machine learning and lexicon-based approaches for sentiment analysis of students feedback. The textual feedback, typically collected towards the end of a semester, provides useful insights into the overall teaching quality and suggests valuable ways for improving teaching methodology. The paper describes a sentiment analysis model trained using TF-IDF and lexicon-based...
Accelerating the inference of a trained DNN is a well studied subject. In this paper we switch the focus to the training of DNNs. The training phase is compute intensive, demands complicated data communication, and contains multiple levels of data dependencies and parallelism. This paper presents an algorithm/architecture space exploration of efficient accelerators to achieve better network convergence...
Content-based image retrieval technology is one of the most important research directions in modern image retrieval technology. With the development of deep learning, the effective features of image can be extracted by well-trained convolution neural networks (CNNs). Based on the extracted image features, we can measure the similarity between two images. Directly comparing image similarity on large...
Echo state network (ESN) is a powerful tool for nonlinear system modeling. However, the random setting of structure (mainly the reservoir) may degrade its estimation accuracy. To create the optimal reservoir for a given task, a novel ESN design method based on differential evolution algorithm is proposed. Firstly, the weight matrix of reservoir is constructed via the singular value decomposition (SVD)...
Image steganalysis is to discriminate innocent images and those suspected images with hidden messages. In this paper, we propose a unified Convolutional Neural Network (CNN) model for this task. In order to reliably detect modern steganographic algorithms, we design the proposed model from two aspects. For the first, different from existing CNN based steganalytic algorithms that use a predefined highpass...
This paper presents a novel nonlinear adaptive filter method, namely, Hammerstein adaptive filter with single feedback under minimum mean square error (HAF-SF-MMSE). A single delayed output is incorporated into the estimation of the current output based on minimum mean square error criterion, and therefore the history information of output is considered. Moreover, hybrid learning rates and adaptive...
Prolonged and sustained warming of the sea, acidification of surface water and rising of sea levels, creates significant habitat losses, resulting in the proliferation and spread of invasive species which immigrate to foreign regions seeking colder climate conditions. This is happening either because their natural habitat does not satisfy the temperature range in which they can survive, or because...
In order to solve the problem of the lack of prior knowledge in intrusion detection, as an unsupervised learning algorithm, the clustering algorithm is applied to intrusion detection. Aiming at the shortcomings of intrusion detection algorithm based on traditional hierarchical clustering, such as high time complexity and high false positive rate, a new clustering algorithm for intrusion detection...
Independent Component Analysis (ICA) is a dimensionality reduction technique that can boost efficiency of machine learning models that deal with probability density functions, e.g. Bayesian neural networks. Algorithms that implement adaptive ICA converge slower than their nonadaptive counterparts, however, they are capable of tracking changes in underlying distributions of input features. This intrinsically...
Implementing higher voltages in vehicles like 48V mild hybrid or full-hybrid enables CO2 reduction and weight savings. However, the increase in the voltage demands an accurate and robust protection system again potential fault conditions. Series arc is one of the fault conditions which needs to be detected and addressed before the benefits of using higher voltages in vehicle can be fully realized...
In daily life it is necessary to learn skills that can be applied in different tasks and different contexts. Usually these skills are acquired by observation or by direct physical training with another expert person. The critical point is to know which is the best possible way to achieve this knowledge acquisition. In this work we have proposed a collaborative environment where subjects with different...
The purpose of data mining is to explore, find and hence analyze relevant data from a massive data source using various technical means. This paper introduces the development of data mining to date, its functions, tasks and algorithms, as well as the process of data mining. The application and problems of data mining are also presented and finally the potential future development of data mining technology...
While there is a large amount of text data on the Internet, people need to organize the text data with experienced category. However, the flat structure of categories could not satisfy the modern information management. To solve this problem, we propose a hierarchical classification process with a strategy, called candidates, used to relieve the blocking problems. Besides, we establish the description...
Electric power SDH network is a comprehensive communication network, which takes advantages of SDH technology, and is a widely used technology. How to protect the network more effectively is the concern of the operators. So the main purpose of this paper is to find a way to analysis risk in advance and enhance reliability of electric power SDH network. Firstly, we set up an evaluation index system...
Scaling CMOS integrated circuit technology leads to decrease the chip price and increase processing performance in complex applications with re-configurability. Thus, VLSI architecture is a promising candidate in implementing neural network models nowadays. Backpropagation algorithm is used for training multilayer perceptron with high degree of parallel processing. Parallel computing implementation...
This paper develops a distributed stochastic subgrandient-based support vector machine algorithm when training data to train support vector machines are distributed in the network. In this situation, all the data are decentralized stored and unavailable to all agents and each agent has to make its own update based on its computation and communication with neighbors. With mild connectivity conditions,...
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.