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 deep neural networks, inputs in each layer are affected by all previous parameters of input layers, so even small changes in input distributions to the network are delivered to internal layers, for leading to differences between source domain and target domain, which is known as covariate shift. Batch Normalization(BN) is designed to address the issue, and makes normalization for each training...
Block-sparse reconstruction, which arises from the reconstruction of block-sparse signals in structured compressed sensing, is generally considered to be difficult due to the mixed-norm structure. In this paper, we propose efficient algorithms based on split Bregman iteration to solve the block-sparse reconstruction problems, including the constrained form and unconstrained form. Numerical results...
This paper discusses cryptographic algorithm and operation mode at wireless sensor network, and introduces the selection of candidate algorithm. The candidate algorithm cost is evaluated by using better performance indicators including computation time, storage space, energy cost, and algorithm choice of security framework is given.
In this paper, we propose a computationally efficient approach for unsupervised audio stream segmentation via the Bayesian Information Criterion (BIC). Based on traditional BIC and DISTBIC, a novel multi-stage framework is presented. A statistic mean Euclidean distance based segmentation algorithm is used to pre-select candidate segmentation boundaries, and then delta-BIC integrating energy-based...
Aiming at the increasing diversity and real-time requirements of applications, the state-of-art web service composition approaches are facing more and more serious bottlenecks of effectiveness and stability, since new Web service chain must be generated from "scratch" for each application. To break these bottlenecks, this paper presents a min-conflict heuristic-based Web services chain reconfiguration...
The moving objects are what attract most attention in the video surveillance system, and also the key part for study. Currently, the video surveillance system relies much on the subjective initiative of the observers while having the real-time surveillance. In this study, applying the mixture Gaussian model algorithm, the profile image of the moving objects in the picture got from the video surveillance...
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.