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.
In this paper, we demonstrate nonlinear features extracted by deep neural network have better results in the task of dictionary learning. A nonlinear dictionary learning model is constructed and the optimization algorithm is developed. In the learning algorithm, we use the deep neural network to convey raw samples to feature space and learn a nonlinear dictionary. The extensive experimental results...
The real-time information on the Web changes dynamically and surge quickly, which cause considerable difficulty in access to interested information. How to mine hot events, how to analyze the correlation of events and how to organize information structurally are challenging tasks. In this paper, to address these problems, we propose STeller, an approach to mine context-aware story — a series of correlated...
In this paper, we present CLUE, a system event analytics tool for black-box performance diagnosis in production Cloud Computing systems. CLUE provides an unified and extensible means of profiling service transactional behaviors, and builds structured data called event sketches. CLUE further offers a set of analytic tools for summarizing and analyzing event sketches by integrating data mining and statistical...
To diagnose performance problems in production systems, many OS kernel-level monitoring and analysis tools have been proposed. Using low level kernel events provides benefits in efficiency and transparency to monitor application software. On the other hand, such approaches miss application-specific semantic information which can be effective to differentiate the trace patterns from distinct application...
Unified tracing is the process of collecting trace logs across the boundary of kernel and user spaces, and has been used to understand the in-depth correspondence between low level events and application program context for diagnosing system failures and performance problems. Crossing the boundary from the kernel space to a user space to collect trace events from dual spaces imposes challenges compared...
In the field of computer vision, image matching is very important in many applications, such as the object recognition, 3D reconstruction, stereo vision, motion tracking and augmented reality. A method of improving the Opensurf algorithm used in AR for decreasing matching points and mismatch and increasing the calculation speed is proposed.
Aircraft icing can seriously affect the safety of aircraft, and different types of aircraft icing have an effect on the aircraft safety to various extents. A SVM (Support Vector Machine) model for aircraft icing type prediction is presented to classify aircraft icing types. The input variables of icing type are analyzed, and then based on the analysis, the appropriate forecast methods are chosen and...
Consider the moment consistency and strong consistency of the weighted kernel estimator of unknown function under regression model. By the moment inequality, Cr inequality, Borel-Cantelli lemma, we get new moment consistency and strong consistency theorems of weighted kernel estimators of nonparametric regression functions for ANA sequences errors under some suitable conditions. The results obtained...
In this paper we describe a non iterative approach to evaluate and compensate the phase errors of radar subsurface image, and implement the approach to the images based on the MARSIS (Mars Advance Radar for Subsurface and Ionosphere Sounding) data. The main idea of the approach is to build the relationship by phase error vector between the unknown perfect image and a given phase-corrupted image, use...
Feature representation and classification are two key steps for face recognition. A novel method for face recognition was presented based on combination of PCA (principal component analysis), LDA (linear discriminate analysis) and SVM (support vector machine). PCA and LDA combination was used for feature extraction and SVM were used for classification. The normalization had been done to eliminate...
Organizations and people have been looking for a secure data storage method for years, but with the rapidly progressed data recovering and analyzing technology, itpsilas seemed to be futureless. Noticed that conventional ways of disk encryption or hiding always expose many clues that could be utilized by adversaries to recover the data. This paper suggests a new method of disguising which would deduce...
Kernel-mode security enhancement technologies are widely used to improve the efficiency of data processing and the security of data and operating systems in recent years. However, the security modules have been implemented without consolidated standards, in kernel-mode which make them hard to be compared, selected and reused. In this paper, a kernel-mode security module evaluation framework (KSEF)...
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.