SVM-BTA UPDATING APPARATUS AND METHOD FOR LARGE SCALE DATASET

A method for updating a binary tree structure of a support vector machine (SVM) for classifying large scale data comprises the following steps: receiving an input data set including at least one input data set; detecting at least one leaf node among a plurality of SVM nodes composed of a binary tree...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: JANG, SU INN, NOH, BYEONG JOON, PARK, DAI HEE, OH, SEUNG GEUN
Format: Patent
Sprache:eng ; kor
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator JANG, SU INN
NOH, BYEONG JOON
PARK, DAI HEE
OH, SEUNG GEUN
description A method for updating a binary tree structure of a support vector machine (SVM) for classifying large scale data comprises the following steps: receiving an input data set including at least one input data set; detecting at least one leaf node among a plurality of SVM nodes composed of a binary tree structure; and updating the binary tree structure by generating a new SVM node to receive the input data set branched from any one among the detected leaf nodes. A weighting coefficient is calculated based on the class size and the depth in the binary tree structure for each of the SVM nodes, and a leaf node to be branched is selected among the leaf nodes detected based on the weighting coefficient. 대규모 데이터 분류를 위한 서포트 벡터 머신의 이진 트리 구조 갱신 시, 적어도 하나의 입력 데이터를 포함하는 입력 데이터 셋(set)을 수신하고, 이진 트리 구조(Binary Tree Architecture)로 구성된 복수의 SVM(Support Vector Machine) 노드 중 적어도 하나의 잎 노드(Leaf node)를 검출하고, 검출된 잎 노드 중 어느 하나에서 분기된 상기 입력 데이터를 할당할 새로운 SVM 노드를 생성하여 상기 이진 트리 구조를 갱신하되, 복수의 SVM 노드 별로 이진 트리 구조에서의 깊이 및 클래스 크기에 기초하여 가중 계수를 산출하고, 가중 계수에 기초하여 검출된 잎 노드 중 분기할 잎 노드를 선택한다.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_KR20150133027A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>KR20150133027A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_KR20150133027A3</originalsourceid><addsrcrecordid>eNrjZLANDvPVdQpxVAgNcHEM8fRzV3AMCHAMcgwJDVZw9HNR8HUN8fB3UXDzD1LwcQxyd1UIdnb0cVUAqnUMdg3hYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXx3kFGBoamBobGxgZG5o7GxKkCAK25Kks</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>SVM-BTA UPDATING APPARATUS AND METHOD FOR LARGE SCALE DATASET</title><source>esp@cenet</source><creator>JANG, SU INN ; NOH, BYEONG JOON ; PARK, DAI HEE ; OH, SEUNG GEUN</creator><creatorcontrib>JANG, SU INN ; NOH, BYEONG JOON ; PARK, DAI HEE ; OH, SEUNG GEUN</creatorcontrib><description>A method for updating a binary tree structure of a support vector machine (SVM) for classifying large scale data comprises the following steps: receiving an input data set including at least one input data set; detecting at least one leaf node among a plurality of SVM nodes composed of a binary tree structure; and updating the binary tree structure by generating a new SVM node to receive the input data set branched from any one among the detected leaf nodes. A weighting coefficient is calculated based on the class size and the depth in the binary tree structure for each of the SVM nodes, and a leaf node to be branched is selected among the leaf nodes detected based on the weighting coefficient. 대규모 데이터 분류를 위한 서포트 벡터 머신의 이진 트리 구조 갱신 시, 적어도 하나의 입력 데이터를 포함하는 입력 데이터 셋(set)을 수신하고, 이진 트리 구조(Binary Tree Architecture)로 구성된 복수의 SVM(Support Vector Machine) 노드 중 적어도 하나의 잎 노드(Leaf node)를 검출하고, 검출된 잎 노드 중 어느 하나에서 분기된 상기 입력 데이터를 할당할 새로운 SVM 노드를 생성하여 상기 이진 트리 구조를 갱신하되, 복수의 SVM 노드 별로 이진 트리 구조에서의 깊이 및 클래스 크기에 기초하여 가중 계수를 산출하고, 가중 계수에 기초하여 검출된 잎 노드 중 분기할 잎 노드를 선택한다.</description><language>eng ; kor</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2015</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20151127&amp;DB=EPODOC&amp;CC=KR&amp;NR=20150133027A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20151127&amp;DB=EPODOC&amp;CC=KR&amp;NR=20150133027A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>JANG, SU INN</creatorcontrib><creatorcontrib>NOH, BYEONG JOON</creatorcontrib><creatorcontrib>PARK, DAI HEE</creatorcontrib><creatorcontrib>OH, SEUNG GEUN</creatorcontrib><title>SVM-BTA UPDATING APPARATUS AND METHOD FOR LARGE SCALE DATASET</title><description>A method for updating a binary tree structure of a support vector machine (SVM) for classifying large scale data comprises the following steps: receiving an input data set including at least one input data set; detecting at least one leaf node among a plurality of SVM nodes composed of a binary tree structure; and updating the binary tree structure by generating a new SVM node to receive the input data set branched from any one among the detected leaf nodes. A weighting coefficient is calculated based on the class size and the depth in the binary tree structure for each of the SVM nodes, and a leaf node to be branched is selected among the leaf nodes detected based on the weighting coefficient. 대규모 데이터 분류를 위한 서포트 벡터 머신의 이진 트리 구조 갱신 시, 적어도 하나의 입력 데이터를 포함하는 입력 데이터 셋(set)을 수신하고, 이진 트리 구조(Binary Tree Architecture)로 구성된 복수의 SVM(Support Vector Machine) 노드 중 적어도 하나의 잎 노드(Leaf node)를 검출하고, 검출된 잎 노드 중 어느 하나에서 분기된 상기 입력 데이터를 할당할 새로운 SVM 노드를 생성하여 상기 이진 트리 구조를 갱신하되, 복수의 SVM 노드 별로 이진 트리 구조에서의 깊이 및 클래스 크기에 기초하여 가중 계수를 산출하고, 가중 계수에 기초하여 검출된 잎 노드 중 분기할 잎 노드를 선택한다.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2015</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZLANDvPVdQpxVAgNcHEM8fRzV3AMCHAMcgwJDVZw9HNR8HUN8fB3UXDzD1LwcQxyd1UIdnb0cVUAqnUMdg3hYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXx3kFGBoamBobGxgZG5o7GxKkCAK25Kks</recordid><startdate>20151127</startdate><enddate>20151127</enddate><creator>JANG, SU INN</creator><creator>NOH, BYEONG JOON</creator><creator>PARK, DAI HEE</creator><creator>OH, SEUNG GEUN</creator><scope>EVB</scope></search><sort><creationdate>20151127</creationdate><title>SVM-BTA UPDATING APPARATUS AND METHOD FOR LARGE SCALE DATASET</title><author>JANG, SU INN ; NOH, BYEONG JOON ; PARK, DAI HEE ; OH, SEUNG GEUN</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_KR20150133027A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; kor</language><creationdate>2015</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>JANG, SU INN</creatorcontrib><creatorcontrib>NOH, BYEONG JOON</creatorcontrib><creatorcontrib>PARK, DAI HEE</creatorcontrib><creatorcontrib>OH, SEUNG GEUN</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>JANG, SU INN</au><au>NOH, BYEONG JOON</au><au>PARK, DAI HEE</au><au>OH, SEUNG GEUN</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>SVM-BTA UPDATING APPARATUS AND METHOD FOR LARGE SCALE DATASET</title><date>2015-11-27</date><risdate>2015</risdate><abstract>A method for updating a binary tree structure of a support vector machine (SVM) for classifying large scale data comprises the following steps: receiving an input data set including at least one input data set; detecting at least one leaf node among a plurality of SVM nodes composed of a binary tree structure; and updating the binary tree structure by generating a new SVM node to receive the input data set branched from any one among the detected leaf nodes. A weighting coefficient is calculated based on the class size and the depth in the binary tree structure for each of the SVM nodes, and a leaf node to be branched is selected among the leaf nodes detected based on the weighting coefficient. 대규모 데이터 분류를 위한 서포트 벡터 머신의 이진 트리 구조 갱신 시, 적어도 하나의 입력 데이터를 포함하는 입력 데이터 셋(set)을 수신하고, 이진 트리 구조(Binary Tree Architecture)로 구성된 복수의 SVM(Support Vector Machine) 노드 중 적어도 하나의 잎 노드(Leaf node)를 검출하고, 검출된 잎 노드 중 어느 하나에서 분기된 상기 입력 데이터를 할당할 새로운 SVM 노드를 생성하여 상기 이진 트리 구조를 갱신하되, 복수의 SVM 노드 별로 이진 트리 구조에서의 깊이 및 클래스 크기에 기초하여 가중 계수를 산출하고, 가중 계수에 기초하여 검출된 잎 노드 중 분기할 잎 노드를 선택한다.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng ; kor
recordid cdi_epo_espacenet_KR20150133027A
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title SVM-BTA UPDATING APPARATUS AND METHOD FOR LARGE SCALE DATASET
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-10T06%3A36%3A40IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=JANG,%20SU%20INN&rft.date=2015-11-27&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EKR20150133027A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true