Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/15017
Title: | Evolvable Media Repositories: An Evolutionary System to Retrieve and Ever-Renovate Related Media Web Content |
Authors: | Koutsomichalis, Marinos Gambäck, Björn |
Major Field of Science: | Engineering and Technology |
Field Category: | Computer and Information Sciences |
Keywords: | Genetic algorithms;Database management;Multimedia information systems;Natural language processing |
Issue Date: | Jul-2019 |
Source: | Intelligent Computing Proceedings of the 2019 Computing Conference, Volume 1: 2019, pp. 76-92 |
Abstract: | The paper tackles the question of evolvable media reposito- ries, i.e., local pools of media files that are retrieved over the Internet and that are ever-renovated with new, related files in an evolutionary fash- ion. The herein proposed method encodes genotypic space by virtue of simple undirected graphs of natural language tokens that represent web queries without employing fitness functions or other evaluation/selection schemata. Once a first population is seeded, a series of modular crawlers query the particular World Wide Web repositories of interest for both media content and assorted meta-data. Then, a series of attached intelli- gent comprehenders analyse the retrieved content in order to eventually generate new genetic representations, and the cycle is repeated. Such a method is generic, scalable and modular, and can be made fit the pur- poses of a wide array of applications in all sorts of disparate contextual and functional scenarios. The paper features a formal description of the method, gives implementation guidelines, and presents example usages. |
URI: | https://hdl.handle.net/20.500.14279/15017 |
ISBN: | 978-3-030-22868-2 |
DOI: | 10.1007/978-3-030-22868-2_6 |
Rights: | © Springer Nature Switzerland AG 2019 |
Type: | Book Chapter |
Affiliation : | Cyprus University of Technology Norwegian University of Science and Technology |
Publication Type: | Peer Reviewed |
Appears in Collections: | Κεφάλαια βιβλίων/Book chapters |
CORE Recommender
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.