Patents by Inventor Cheng-Fa Tsai
Cheng-Fa Tsai has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 8666986Abstract: A grid-based data clustering method is disclosed. A parameter setting step sets a grid parameter and a threshold parameter. A diving step divides a space having a plurality of data points according to the grid parameter. A categorizing step determines whether a number of the data points contained in each grid is larger than or equal to a value of the threshold parameter. The grid is categorized as a valid grid if the number of the data points contained therein is larger than or equal to the value of the threshold parameter, and the grid is categorized as an invalid grid if the number of the data points contained therein is smaller than the value of the threshold parameter. The clustering step retrieves one of the valid grids. If the retrieved valid grid is not yet clustered, the clustering step performs horizontal and vertical searching/merging operations on the valid grid.Type: GrantFiled: April 23, 2012Date of Patent: March 4, 2014Assignee: National Pingtung University of Science & TechnologyInventors: Cheng-Fa Tsai, Yung-Ching Hu
-
Patent number: 8661040Abstract: A grid-based data clustering method performed by a computer system includes a setup step, a dividing step, a categorizing step and an expanding/clustering step. The setup step sets a grid quantity and a threshold value. The dividing step divides a space containing a data set having a plurality of data points into a two-dimensional matrix. The matrix has a plurality of grids G(i,j) comprising a plurality of target sequences and a plurality of non-target sequences interlaced with the plurality of target sequences. The indices “i” and “j” of each grid G(i,j) represents the coordinate thereof. The categorizing step determines whether each of the grids is valid based on the threshold value. The expanding/clustering step respectively retrieves each of the grids of the target sequences, performs an expansion operation on each of the grids retrieved and clusters the plurality grids G(i,j).Type: GrantFiled: May 10, 2012Date of Patent: February 25, 2014Assignee: National Pingtung University of Science & TechnologyInventors: Cheng-Fa Tsai, Chun-Hao Chang
-
Patent number: 8429166Abstract: A density-based data clustering method executed by a computer system is disclosed. The method includes a setup step, a clustering step, an expansion step and a termination step. The setup step sets a radius and a threshold value. The clustering step defines a single cluster on a plurality of data points of a data set, and provides and adds a plurality of first boundary marks to a seed list as seeds. The expansion step expands the cluster from each seed of the seed list, and provides and adds at least one second boundary mark to the seed list as seeds. The termination step determines whether each of the data points is clustered, wherein the clustering step is re-performed if the determination is negative.Type: GrantFiled: May 2, 2012Date of Patent: April 23, 2013Assignee: National Pingtung University of Science & TechnologyInventors: Cheng-Fa Tsai, Tang-Wei Huang
-
Patent number: 8407168Abstract: A codebook generating method includes a dividing and transforming step dividing an original image into original blocks and transforming the original blocks into original vectors; a dividing step grouping the original vectors to obtain centroids; a first layer neuron training step selecting a portion of the centroids as first-level neurons; a grouping step assigning each of the original vectors to a closest first-level neuron so as to obtain groups; a second layer neuron assigning step assigning a number of second-level neurons in each of the groups, and selecting a portion of the original vectors in each of the groups as the second-level neurons; and a second layer neuron training step defining the original vectors in each of the groups as samples, training the second-level neurons in each of the groups to obtain final neurons, and storing vectors corresponding to the final neurons in a codebook.Type: GrantFiled: July 1, 2010Date of Patent: March 26, 2013Assignee: National Pingtung University of Science & TechnologyInventors: Cheng-Fa Tsai, Yu-Chun Lin
-
Patent number: 8352578Abstract: A data-transmitting method for wireless sensor network includes: constructing a wireless sensor network having a plurality of nodes for information sensing and a sink for quest raising and data collecting; clustering the nodes to form a plurality of groups, with one of the nodes in each group being identified as a kernel; identifying one of all the nodes as a summit dissemination node and the kernels in all the groups as first level dissemination nodes; and transmitting data between the quest-raising sink and one of the first level dissemination nodes or summit dissemination node to collect information sensed by a source that is one of the nodes.Type: GrantFiled: August 6, 2008Date of Patent: January 8, 2013Assignee: National Pingtung University of Science & TechnologyInventors: Cheng-Fa Tsai, Shih-Yuan Chao
-
Publication number: 20120296904Abstract: A grid-based data clustering method is disclosed. A parameter setting step sets a grid parameter and a threshold parameter. A diving step divides a space having a plurality of data points according to the grid parameter. A categorizing step determines whether a number of the data points contained in each grid is larger than or equal to a value of the threshold parameter. The grid is categorized as a valid grid if the number of the data points contained therein is larger than or equal to the value of the threshold parameter, and the grid is categorized as an invalid grid if the number of the data points contained therein is smaller than the value of the threshold parameter. The clustering step retrieves one of the valid grids. If the retrieved valid grid is not yet clustered, the clustering step performs horizontal and vertical searching/merging operations on the valid grid.Type: ApplicationFiled: April 23, 2012Publication date: November 22, 2012Inventors: Cheng-Fa Tsai, Yung-Ching Hu
-
Publication number: 20120296906Abstract: A grid-based data clustering method performed by a computer system includes a setup step, a dividing step, a categorizing step and an expanding/clustering step. The setup step sets a grid quantity and a threshold value. The dividing step divides a space containing a data set having a plurality of data points into a two-dimensional matrix. The matrix has a plurality of grids G(i,j) comprising a plurality of target sequences and a plurality of non-target sequences interlaced with the plurality of target sequences. The indices “i” and “j” of each grid G(i,j) represents the coordinate thereof. The categorizing step determines whether each of the grids is valid based on the threshold value. The expanding/clustering step respectively retrieves each of the grids of the target sequences, performs an expansion operation on each of the grids retrieved and clusters the plurality grids G(i,j).Type: ApplicationFiled: May 10, 2012Publication date: November 22, 2012Inventors: Cheng-Fa TSAI, Chun-Hao CHANG
-
Publication number: 20120296905Abstract: A density-based data clustering method executed by a computer system is disclosed. The method includes a setup step, a clustering step, an expansion step and a termination step. The setup step sets a radius and a threshold value. The clustering step defines a single cluster on a plurality of data points of a data set, and provides and adds a plurality of first boundary marks to a seed list as seeds. The expansion step expands the cluster from each seed of the seed list, and provides and adds at least one second boundary mark to the seed list as seeds. The termination step determines whether each of the data points is clustered, wherein the clustering step is re-performed if the determination is negative.Type: ApplicationFiled: May 2, 2012Publication date: November 22, 2012Inventors: Cheng-Fa TSAI, Tang-Wei Huang
-
Patent number: 8285053Abstract: A codebook generating method comprises a dividing and transforming step dividing an original image into original blocks and transforming each of the original blocks into an original vector; a parameter setting step setting a distortion tolerance and a predetermined number of representative blocks; a single group setting step setting the original vectors as a group; a preliminary grouping step grouping all the original vectors in a group currently having largest distortion into two groups using a grouping algorithm, wherein the preliminary grouping step is repeated until the number of groups is equal to the predetermined number of representative blocks; and a grouping step grouping all the original vectors based on a plurality of initial centroids to obtain final centroids, and storing vectors corresponding to the final centroids in a codebook, wherein the centroids of the groups are treated as the initial centroids.Type: GrantFiled: July 1, 2010Date of Patent: October 9, 2012Assignee: National Pingtung University of Science & TechnologyInventors: Cheng-Fa Tsai, Jiun-Huang Ju
-
Patent number: 8195662Abstract: A density-based data clustering method, comprising a parameter-setting step, a first retrieving step, a first determination step, a second determination step, a second retrieving step, a third determination step and first and second termination determination steps. The parameter-setting step sets parameters. The first retrieving step retrieves one data point and defines neighboring points. The first determination step determines whether the number of the data points exceeds the minimum threshold value. The second determination step arranges a plurality of first border symbols. The second retrieving step retrieves one seed data point from the seed list, arranges a plurality of second border symbols and defines seed neighboring points. The third determination step determines whether a data point density of searching ranges of the seed neighboring points is the same. The first termination determination step determines whether the clustering is finished.Type: GrantFiled: January 6, 2010Date of Patent: June 5, 2012Assignee: National Pingtung University Of Science & TechnologyInventors: Cheng-Fa Tsai, Yi-Ching Huang
-
Patent number: 8171025Abstract: A density-based data clustering method, comprising a parameter-setting step for setting a scanning radius and a minimum threshold value, a dividing step for dividing a space of a plurality of data points according to the scanning radius, a data-retrieving step for retrieving one data point out of the plurality of data points as a core data point, a searching step for calculating a distance between the core data point and each of the query points, a grouping determination step for determining whether a number of the neighboring points is smaller than the minimum threshold value.Type: GrantFiled: January 6, 2010Date of Patent: May 1, 2012Assignee: National Pingtung University Of Science & TechnologyInventors: Cheng-Fa Tsai, Chien-Tsung Wu
-
Patent number: 8166035Abstract: A grid-based data clustering method comprises: a parameter setting step, a partition step, a searching step, a seed-classifying step, an extension step, and a termination step. Through the above-mentioned steps, data in a data set are disposed in a plurality of grids, and the grids are classified into dense grids and uncrowded grids for a cluster to extend from one of the dense grid to gradually combine data in other dense grids nearby. Consequently, convenience in parameter setting, efficiency and accuracy in data clustering, and performance in noise filtering are achieved.Type: GrantFiled: January 6, 2010Date of Patent: April 24, 2012Assignee: National Pingtung University of Science & TechnologyInventors: Cheng-Fa Tsai, Chien-Sheng Chiu
-
Patent number: 8037533Abstract: A detecting method for network intrusion includes: selecting a plurality of features contained within plural statistical data by a data-transforming module; normalizing a plurality of feature values of the selected features into the same scale to obtain a plurality of normalized feature data; creating at least one feature model by a data clustering technique incorporated with density-based and grid-based algorithms through a model-creating module; evaluating the at least one feature model through a model-identifying module to select a detecting model; and detecting whether a new packet datum belongs to an intrusion instance or not by a detecting module.Type: GrantFiled: January 29, 2008Date of Patent: October 11, 2011Assignee: National Pingtung University of Science and TechnologyInventors: Cheng-Fa Tsai, Chia-Chen Yen
-
Publication number: 20110072016Abstract: A density-based data clustering method, comprising a parameter-setting step, a first retrieving step, a first determination step, a second determination step, a second retrieving step, a third determination step and first and second termination determination steps. The parameter-setting step sets parameters. The first retrieving step retrieves one data point and defines neighboring points. The first determination step determines whether the number of the data points exceeds the minimum threshold value. The second determination step arranges a plurality of first border symbols. The second retrieving step retrieves one seed data point from the seed list, arranges a plurality of second border symbols and defines seed neighboring points. The third determination step determines whether a data point density of searching ranges of the seed neighboring points is the same. The first termination determination step determines whether the clustering is finished.Type: ApplicationFiled: January 6, 2010Publication date: March 24, 2011Inventors: Cheng-Fa TSAI, Yi-Ching Huang
-
Publication number: 20110066580Abstract: A codebook generating method comprises a dividing and transforming step dividing an original image into original blocks and transforming the original blocks into original vectors; a dividing step grouping the original vectors to obtain centroids; a first layer neuron training step selecting a portion of the centroids as first-level neurons; a grouping step assigning each of the original vectors to a closest first-level neuron so as to obtain groups; a second layer neuron assigning step assigning a number of second-level neurons in each of the groups, and selecting a portion of the original vectors in each of the groups as the second-level neurons; and a second layer neuron training step defining the original vectors in each of the groups as samples, training the second-level neurons in each of the groups to obtain final neurons, and storing vectors corresponding to the final neurons in a codebook.Type: ApplicationFiled: July 1, 2010Publication date: March 17, 2011Inventors: Cheng-Fa Tsai, Yu-Chun Lin
-
Publication number: 20110055212Abstract: A density-based data clustering method, comprising a parameter-setting step for setting a scanning radius and a minimum threshold value, a dividing step for dividing a space of a plurality of data points according to the scanning radius, a data-retrieving step for retrieving one data point out of the plurality of data points as a core data point, a searching step for calculating a distance between the core data point and each of the query points, a grouping determination step for determining whether a number of the neighboring points is smaller than the minimum threshold value.Type: ApplicationFiled: January 6, 2010Publication date: March 3, 2011Inventors: Cheng-Fa TSAI, Chien-Tsung Wu
-
Publication number: 20110040758Abstract: A grid-based data clustering method comprises: a parameter setting step, a partition step, a searching step, a seed-classifying step, an extension step, and a termination step. Through the above-mentioned steps, data in a data set are disposed in a plurality of grids, and the grids are classified into dense grids and uncrowded grids for a cluster to extend from one of the dense grid to gradually combine data in other dense grids nearby. Consequently, convenience in parameter setting, efficiency and accuracy in data clustering, and performance in noise filtering are achieved.Type: ApplicationFiled: January 6, 2010Publication date: February 17, 2011Inventors: Cheng-Fa TSAI, Chien-Sheng Chiu
-
Publication number: 20110026830Abstract: A codebook generating method comprises a dividing and transforming step dividing an original image into original blocks and transforming each of the original blocks into an original vector; a parameter setting step setting a distortion tolerance and a predetermined number of representative blocks; a single group setting step setting the original vectors as a group; a preliminary grouping step grouping all the original vectors in a group currently having largest distortion into two groups using a grouping algorithm, wherein the preliminary grouping step is repeated until the number of groups is equal to the predetermined number of representative blocks; and a grouping step grouping all the original vectors based on a plurality of initial centroids to obtain final centroids, and storing vectors corresponding to the final centroids in a codebook, wherein the centroids of the groups are treated as the initial centroids.Type: ApplicationFiled: July 1, 2010Publication date: February 3, 2011Inventors: Cheng-Fa TSAI, Jiun-Huang Ju
-
Patent number: 7853542Abstract: A method for grid-based data clustering comprises: creating a feature space having a plurality of cubes by a computer and showing the feature space by an interface of the computer, disposing a plurality of data stored in a database into the cubes, and then defining a plurality of the cubes as populated cubes; identifying whether the data within each of the populated cubes being evenly distributed or not to define each populated cube as a major cube or minor cube; combining border data of the minor cubes with the data in the major cubes; and designating all the data combined with each other as in the same cluster and recursively processing the above procedures to cluster all the data stored in the database.Type: GrantFiled: December 18, 2007Date of Patent: December 14, 2010Assignee: National Pingtung University of Science and TechnologyInventors: Cheng-Fa Tsai, Chia-Chen Yen
-
Publication number: 20090046630Abstract: A data-transmitting method for wireless sensor network comprises: constructing a wireless sensor network having a plurality of nodes for information sensing and a sink for quest raising and data collecting; clustering the nodes to form a plurality of groups, with one of the nodes in each group being identified as a kernel; identifying one of all the nodes as a summit dissemination node and the kernels in all the groups as first level dissemination nodes; and transmitting data between the quest-raising sink and one of the first level dissemination nodes or summit dissemination node to collect information sensed by a source that is one of the nodes.Type: ApplicationFiled: August 6, 2008Publication date: February 19, 2009Inventors: Cheng-Fa Tsai, Shih-Yuan Chao