A Multimodel Fusion Engine for Filtering Webpages
Fusing multiple existing models for filtering webpages can mitigate the shortcomings of individual filtering models. To provide an engine for such fusion, we propose a multimodel fusion engine for filtering webpages for the extraction of target webpages. This engine can handle large datasets of webp...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8528301/ |
id |
doaj-d3b791e2564f4be0bfb4efb866824d9f |
---|---|
record_format |
Article |
spelling |
doaj-d3b791e2564f4be0bfb4efb866824d9f2021-03-29T20:28:28ZengIEEEIEEE Access2169-35362018-01-016660626607110.1109/ACCESS.2018.28788978528301A Multimodel Fusion Engine for Filtering WebpagesZiyun Deng0https://orcid.org/0000-0003-1276-5222Tingqin He1https://orcid.org/0000-0001-7890-7567Weiping Ding2https://orcid.org/0000-0002-3180-7347Zehong Cao3https://orcid.org/0000-0003-3656-0328College of Economics and Trade, Changsha Commerce and Tourism College, Changsha, ChinaNational Supercomputing Center in Changsha, Hunan University, Changsha, ChinaSchool of Computer Science and Technology, Nantong University, Nantong, ChinaCentre for Artificial Intelligence, Faculty of Engineering and Information Technologies, University of Technology Sydney, Ultimo, NSW, AustraliaFusing multiple existing models for filtering webpages can mitigate the shortcomings of individual filtering models. To provide an engine for such fusion, we propose a multimodel fusion engine for filtering webpages for the extraction of target webpages. This engine can handle large datasets of webpages crawled from websites and supports five individual filtering models and the fusion of any two of them. There are two possible fusion methods: one is to simultaneously satisfy the conditions of both individual models, and the other is to satisfy the conditions of one of the two individual models. We present the functions, architecture, and software design of the proposed engine. We use recall ratio (RR) and precision ratio (PR) as the evaluation indices of the filtering models and propose rules describing how PR and RR change when individual models are fused. We use 200 000 webpages collected by crawling the popular online shopping website “<uri>http://www.jd.com</uri>” as the experimental dataset to verify these rules. The experimental results show that two-model fusion can improve either PR or RR. Thus, the proposed engine has good practical value for engineering applications.https://ieeexplore.ieee.org/document/8528301/Multimodelfusionengine designwebpage filtering |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Ziyun Deng Tingqin He Weiping Ding Zehong Cao |
spellingShingle |
Ziyun Deng Tingqin He Weiping Ding Zehong Cao A Multimodel Fusion Engine for Filtering Webpages IEEE Access Multimodel fusion engine design webpage filtering |
author_facet |
Ziyun Deng Tingqin He Weiping Ding Zehong Cao |
author_sort |
Ziyun Deng |
title |
A Multimodel Fusion Engine for Filtering Webpages |
title_short |
A Multimodel Fusion Engine for Filtering Webpages |
title_full |
A Multimodel Fusion Engine for Filtering Webpages |
title_fullStr |
A Multimodel Fusion Engine for Filtering Webpages |
title_full_unstemmed |
A Multimodel Fusion Engine for Filtering Webpages |
title_sort |
multimodel fusion engine for filtering webpages |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
Fusing multiple existing models for filtering webpages can mitigate the shortcomings of individual filtering models. To provide an engine for such fusion, we propose a multimodel fusion engine for filtering webpages for the extraction of target webpages. This engine can handle large datasets of webpages crawled from websites and supports five individual filtering models and the fusion of any two of them. There are two possible fusion methods: one is to simultaneously satisfy the conditions of both individual models, and the other is to satisfy the conditions of one of the two individual models. We present the functions, architecture, and software design of the proposed engine. We use recall ratio (RR) and precision ratio (PR) as the evaluation indices of the filtering models and propose rules describing how PR and RR change when individual models are fused. We use 200 000 webpages collected by crawling the popular online shopping website “<uri>http://www.jd.com</uri>” as the experimental dataset to verify these rules. The experimental results show that two-model fusion can improve either PR or RR. Thus, the proposed engine has good practical value for engineering applications. |
topic |
Multimodel fusion engine design webpage filtering |
url |
https://ieeexplore.ieee.org/document/8528301/ |
work_keys_str_mv |
AT ziyundeng amultimodelfusionengineforfilteringwebpages AT tingqinhe amultimodelfusionengineforfilteringwebpages AT weipingding amultimodelfusionengineforfilteringwebpages AT zehongcao amultimodelfusionengineforfilteringwebpages AT ziyundeng multimodelfusionengineforfilteringwebpages AT tingqinhe multimodelfusionengineforfilteringwebpages AT weipingding multimodelfusionengineforfilteringwebpages AT zehongcao multimodelfusionengineforfilteringwebpages |
_version_ |
1724194830650703872 |