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.
Stochastic principal component analysis (SPCA) has become a popular dimensionality reduction strategy for large, high-dimensional datasets. We derive a simplified algorithm, called Lazy SPCA, which has reduced computational complexity and is better suited for large-scale distributed computation. We prove that SPCA and Lazy SPCA find the same approximations to the principal subspace, and that the pairwise...
Contrast patterns are itemsets that frequently occur in one dataset while not in another. These patterns have been successfully applied to many data mining domains, such as prediction, classification and clustering. However, none of the previous studies has considered extracting contrast patterns from different types of datasets. In this paper, we introduce a new type of contrast pattern, Conditional...
App repackaging is a common threat in the Android ecosystem. To face this threat, the literature now includes a large body of work proposing approaches for identifying repackaged apps. Unfortunately, although most research involves pairwise similarity comparison to distinguish repackaged apps from their "original" counterparts, no work has considered the threat to validity of not being able...
Cognitive radio (CR) is a promising technology to improve spectrum utilization. However, spectrum availability is uncertain which mainly depends on primary user's (PU's) behaviors. Broadcast is the most basic way to disseminate data from one source node to all the others in multi-channel cognitive radio networks (CRNs), and the retransmission can be a vital factor for improving broadcast performance...
Accurate and real-time traffic flow prediction is important in Intelligent Transportation System (ITS), especially for traffic control. Existing models such as ARMA, ARIMA are mainly linear models and cannot describe the stochastic and nonlinear nature of traffic flow. In recent years, deep-learning-based methods have been applied as novel alternatives for traffic flow prediction. However, which kind...
The stability analysis and control design problem of Takagi-Sugeno (T-S) fuzzy time-delay systems under mismached premise membership functions are investigated in this paper. A membership function dependent stability criterion is derived first based on Lyapunov stability analysis method. As the information of the membership functions is included in the derived criterion, it is less conservtive than...
This work focuses on stability analysis and stabilization synthesis problem for a class of Takagi-Sugeno (T-S) polynominal fuzzy-model-based time-delay systems based on the sum-of-squares (SOS) approach. Firstly, a novel stability criterion is proposed based on Lyapunov stability theorey, which is less conservative as the information of the membership functions is included in the stability conditions...
The ecological environment of the Loess Plateau in China is the most vulnerable area, and also one of most serious soil erosion areas. Medium-resolution and multi-spectral remote sensing image, such as Landsat Imagery, plays an important role in the study of the ecological environment monitoring and soil erosion, especially for medium and large scale or watershed level. However, how to improve the...
Recommender systems become extremely popular and widely applied in recent years. Researchers have done many work to developing recommender systems in social network. However, recommendation algorithm is still a challenging problem in practice. In this paper, we address the problem of recommending both friends and product simultaneously in the social network. Recommendation system are widely researched...
Recently, researches on microgrids have attracted more and more attention all over the world. Numerous studies and experiments about microgrid converters have been done. This paper presents a method to improve the power quality by controlling the real and reactive power flow between the main grid and the microgrid through the grid-interfaced inverter. Firstly, the desired values of Id and Iq can be...
Support vector machine(SVM) means that structural risk minimization principle is used to substitute Empirical risk minimization principle. SVM has shown the excellent performance in pattern recognition. The kernel function is the core of SVM, with which SVM can help to resolve many kinds of non-linear classification problems. Different kernel models and parameters have different result in the performance...
This paper investigates the issue of stability for stochastic genetic networks with both Markovian jumping parameters and mixed time delays. The jumping parameters are modelled as a continuous-time discrete-state Markovian chain. By constructing Lyapunov functional and using linear matrix inequality (LMI) techniques, sufficient conditions for genetic regulatory networks to be asymptotically stable...
For the shortage of K-Means algorithm, a clustering algorithm based on trust value called TrustCluster is proposed, The algorithm does not need to pre-specify the number of clusters, and clustering results do not depend on the selection of the initial values, clusters of nonspherical shape can be found and the outliers can be identified effectively . TrustCluster clustering algorithm was verified...
Chinese Research Universities have done many efforts for underground students to enhance innovation capabilities. But the effect is not so ideal for many reasons. The authors discuss the three questions, innovation team building, innovation capability cultivating and research methods directing, based on the experience on it in the past years.
In order to eliminate the inefficiency of the conventional bus based architecture, network-on-chip (NoC) has been suggested as a novel approach for several years. Considering the trend that hundreds or even thousands of IP blocks will be integrated on a chip, the concept of multi-cluster NoC is proposed. It usually adopts the hybrid architecture mixed with bus based local system and mesh based global...
In order to realize accurate and fast tracking moving human, a moving human tracking algorithm based on partial Hausdorff distance is presented. This algorithm adopts Gaussian mixture distribution to model background of each pixel and background subtraction to detect moving regions. Shadow elimination and aftertreatment of moving regions provide moving human regions. Kalman filter is used to predict...
With the rapid development of information technology, the scale of a database increasingly grows. The problem, how to translate the large number data in a database into useful information and knowledge, is concerned by the academies and industries. At this point, data mining emerges and receives great concerns from the information industry and the whole society. In this paper, we firstly describe...
Trust is a key constraining factor in the development of electronic commerce. The parties must establish a certain trust model between each other before the beginning of transaction. This paper analyses the advantages and deficiencies of existing models, and presents a trust model for E-commerce based on Bayesian network. The model is based on Bayesian network and conditional probability formula,...
Many improvements are developed for echo hiding system, but there is not an intensive study on the hiding capacity of echo hiding. Based on the speech signals with various sampling rate and single echo hiding scheme, this work explores the regular pattern of recovery accuracy and fragment length, and presents that the hiding capacity of speech clip is 55bit/s, and the capacity is not related to the...
Particle swarm optimization (PSO) is one of the most famous nature-inspired algorithms, which has shown good performance on many optimization problems. To enhance the performance of PSO, this paper presents some modifications of PSO. The proposed approach is called MPSO, which employs a novel local search technique to obtain better candidate solutions. In order to verify the performance of the MPSO,...
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.