An Efficient Deep Learning based Information Retrieval and Classification Model with Query Execution using Ontology

dc.contributor.guideHussain, Syed
dc.coverage.spatial
dc.creator.researcherEswaraiah, Poluru
dc.date.accessioned2024-11-07T06:47:51Z
dc.date.available2024-11-07T06:47:51Z
dc.date.awarded2024
dc.date.completed2024
dc.date.registered2021
dc.description.abstractInformation Retrieval (IR) is a method for locating relevant documents inside large newlinedatasets. Providing high-quality search results has become more of a challenge, and traditional information retrieval methods are struggling to keep up with the provider s demands and the growing number of queries. In response to these difficulties, researchers newlinehave focused on improving the functionality between information and search queries, newlineas well as interactive query formation through ontologies, with the goal of producing result sets that are more in line with users research needs. Multiple real-world computer vision applications make use of multimedia data, which includes textual information. newlineEvery day, news and social media sites add over a million new records and the written newlineinformation within them is getting more complicated by the day. It may be difficult newlinefor computer vision researchers to find a relevant text record in an archive. Query text and metadata, which are based on language, are still the go-to methods for most image searches. Although content-based text retrieval and analysis has made great strides inthe previous 20 years, there are still many unanswered questions. newlineMany people fail to recognize feature extraction s significance in search engines. newlineCommon applications that make use of these characteristics include question-answering, newlineproduct and web-based search engines, and recommendation systems. Many free and newlineopen-source programs struggle with the task of extracting high-quality machine learning newlinefeatures from massive text volumes. Deep learning analyzes new actual feature newlinedemos from training data, saving a lot of time compared to manually creating an effective feature set. The area of Natural Language Processing (NLP) has made extensive newlineuse of text classification, which is becoming an increasingly pressing concern for companies dealing with large amounts of data produced online. Users must be able to sort newlinetexts into distinct categories in order to remember and use vital information. By using newlinea deep learni
dc.description.note
dc.format.accompanyingmaterialDVD
dc.format.dimensions29x19
dc.format.extentxiii,128
dc.identifier.urihttp://hdl.handle.net/10603/599784
dc.languageEnglish
dc.publisher.institutionDepartment of Computer Science and Engineering
dc.publisher.placeAmaravati
dc.publisher.universityVellore Institute of Technology (VIT-AP)
dc.relation
dc.rightsuniversity
dc.source.universityUniversity
dc.subject.keywordContent Extraction
dc.subject.keywordInformation Retrieval
dc.subject.keywordKnowledge Discovery
dc.titleAn Efficient Deep Learning based Information Retrieval and Classification Model with Query Execution using Ontology
dc.title.alternative
dc.type.degreePh.D.

Files

Original bundle

Now showing 1 - 5 of 11
Loading...
Thumbnail Image
Name:
01_title.pdf
Size:
74.06 KB
Format:
Adobe Portable Document Format
Description:
Attached File
Loading...
Thumbnail Image
Name:
02_prelim pages.pdf
Size:
176.84 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
03_contents.pdf
Size:
47.38 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
04_abstract.pdf
Size:
61.76 KB
Format:
Adobe Portable Document Format
Loading...
Thumbnail Image
Name:
05_chapter-1.pdf
Size:
337.14 KB
Format:
Adobe Portable Document Format

License bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
license.txt
Size:
1.79 KB
Format:
Plain Text
Description: