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.
Subspace clustering is a common modeling paradigm used to identify constituent modes of variation in data with locally linear structure. These structures are common to many problems in computer vision, including modeling time series of complex human motion. However classical subspace clustering algorithms learn the relationships within a set of data without considering the temporal dependency and...
Expectation-Maximization (EM) is typically used to compute maximum likelihood estimates given incomplete samples and estimated the parameters. We proposed a new algorithm for generating an extension Dynamic Topic Model (exDTM)-in a time-based manner and based on the distribution of documents topics on Spark. The proposed algorithm can be applied in clustering documents from data streams for threat...
Latent Dirichlet Allocation (LDA) has been widely applied to text mining. LDA is a probabilistic topic model which processes documents as the probability distribution of topics. One challenging issue in application of LDA is to select the optimal number of topics in LDA model. This paper presents a topic selection method which considers the density of each topic and computes the most unstable topic...
The effectiveness of cluster-based distributed sensor networks depends to a large extent on the coverage provided by the sensor deployment. We propose probabilistic based approach for detection of objects using wireless sensor networks. We also propose of selecting a cluster head after detection of objects based on the energy and location of sensor nodes. The selection of cluster head is based on...
Methods developed for image annotation usually make use of region clustering algorithms. Visual codebooks generated for region clusters, using low level features are matched with words in various ways. In this work, we ensured that clustering is more meaningful by using words in associated text in addition to image data in clustering of image regions to generate a codebook. We first compute topic...
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.