View in EDS

Design of a modified large language model for semantic communication in sixth-generation wireless networks.

Saved in:
Bibliographic Details
Title: Design of a modified large language model for semantic communication in sixth-generation wireless networks.
Authors: Mathur, Samiksha1 (AUTHOR) smkmthr@gmail.com, Kumar, Dharmender1 (AUTHOR), Noliya, Amandeep1 (AUTHOR)
Source: Engineering Applications of Artificial Intelligence. Jan2026:Part 4, Vol. 163, pN.PAG-N.PAG. 1p.
Subjects: 6G networks, Artificial intelligence, Gaussian distribution, Data transmission systems, Wireless communications, Language models
Abstract: As the demand for sophisticated communication systems intensifies particularly with the advent of sixth-generation wireless networks there is a growing need for advanced artificial intelligence models capable of enhancing semantic communication. This paper presents the design of a modified large language model, specifically developed for semantic communication in 6G networks and integrated with a Multiple Input Multiple Output Long Term Evolution framework. The proposed model leverages the capabilities of artificial intelligence through a modified architecture based on the Bidirectional and Auto-Regressive Transformer, a type of natural language processing model. Enhancements include novel attention mechanisms and contextual embeddings that improve the generation and interpretation of semantically rich and contextually accurate messages. Furthermore, a novel semi–Cumulative Distribution Function based on the Gaussian distribution is introduced as an activation function to improve data handling capacity and transmission efficiency. This approach effectively addresses core challenges in semantic communication, such as preserving context, enhancing message relevance, and reducing ambiguity in high-speed, low-latency environments. In comparative evaluations on datasets of 10,000 words, the modified model achieved a semantic communication score of 0.606 significantly outperforming other large language models including the Text-To-Text Transfer Transformer (score: 0.548), the Pre-training with Extracted Gap-sentences for Abstractive Summarization model (score: 0.417), and the conventional Bidirectional and Auto-Regressive Transformer (score: 0.518). The findings highlight the potential of artificial intelligence -based natural language generation in optimizing communication efficiency and accuracy for future sixth-generation applications. • Designed a modified large language model for semantic communication in 6G networks. • Integrated semantic AI with MIMO-LTE to enhance communication efficiency and context. • Introduced a novel Gaussian-based semi-CDF activation for better data transmission. [ABSTRACT FROM AUTHOR]
Copyright of Engineering Applications of Artificial Intelligence is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
FullText Text:
  Availability: 0
Header DbId: egs
DbLabel: Engineering Source
An: 189342341
AccessLevel: 6
PubType: Academic Journal
PubTypeId: academicJournal
PreciseRelevancyScore: 0
IllustrationInfo
Items – Name: Title
  Label: Title
  Group: Ti
  Data: Design of a modified large language model for semantic communication in sixth-generation wireless networks.
– Name: Author
  Label: Authors
  Group: Au
  Data: <searchLink fieldCode="AR" term="%22Mathur%2C+Samiksha%22">Mathur, Samiksha</searchLink><relatesTo>1</relatesTo> (AUTHOR)<i> smkmthr@gmail.com</i><br /><searchLink fieldCode="AR" term="%22Kumar%2C+Dharmender%22">Kumar, Dharmender</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Noliya%2C+Amandeep%22">Noliya, Amandeep</searchLink><relatesTo>1</relatesTo> (AUTHOR)
– Name: TitleSource
  Label: Source
  Group: Src
  Data: <searchLink fieldCode="JN" term="%22Engineering+Applications+of+Artificial+Intelligence%22">Engineering Applications of Artificial Intelligence</searchLink>. Jan2026:Part 4, Vol. 163, pN.PAG-N.PAG. 1p.
– Name: Subject
  Label: Subjects
  Group: Su
  Data: <searchLink fieldCode="DE" term="%226G+networks%22">6G networks</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22Gaussian+distribution%22">Gaussian distribution</searchLink><br /><searchLink fieldCode="DE" term="%22Data+transmission+systems%22">Data transmission systems</searchLink><br /><searchLink fieldCode="DE" term="%22Wireless+communications%22">Wireless communications</searchLink><br /><searchLink fieldCode="DE" term="%22Language+models%22">Language models</searchLink>
– Name: Abstract
  Label: Abstract
  Group: Ab
  Data: As the demand for sophisticated communication systems intensifies particularly with the advent of sixth-generation wireless networks there is a growing need for advanced artificial intelligence models capable of enhancing semantic communication. This paper presents the design of a modified large language model, specifically developed for semantic communication in 6G networks and integrated with a Multiple Input Multiple Output Long Term Evolution framework. The proposed model leverages the capabilities of artificial intelligence through a modified architecture based on the Bidirectional and Auto-Regressive Transformer, a type of natural language processing model. Enhancements include novel attention mechanisms and contextual embeddings that improve the generation and interpretation of semantically rich and contextually accurate messages. Furthermore, a novel semi–Cumulative Distribution Function based on the Gaussian distribution is introduced as an activation function to improve data handling capacity and transmission efficiency. This approach effectively addresses core challenges in semantic communication, such as preserving context, enhancing message relevance, and reducing ambiguity in high-speed, low-latency environments. In comparative evaluations on datasets of 10,000 words, the modified model achieved a semantic communication score of 0.606 significantly outperforming other large language models including the Text-To-Text Transfer Transformer (score: 0.548), the Pre-training with Extracted Gap-sentences for Abstractive Summarization model (score: 0.417), and the conventional Bidirectional and Auto-Regressive Transformer (score: 0.518). The findings highlight the potential of artificial intelligence -based natural language generation in optimizing communication efficiency and accuracy for future sixth-generation applications. • Designed a modified large language model for semantic communication in 6G networks. • Integrated semantic AI with MIMO-LTE to enhance communication efficiency and context. • Introduced a novel Gaussian-based semi-CDF activation for better data transmission. [ABSTRACT FROM AUTHOR]
– Name: AbstractSuppliedCopyright
  Label:
  Group: Ab
  Data: <i>Copyright of Engineering Applications of Artificial Intelligence is the property of Pergamon Press - An Imprint of Elsevier Science and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.)
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=189342341
RecordInfo BibRecord:
  BibEntity:
    Identifiers:
      – Type: doi
        Value: 10.1016/j.engappai.2025.113043
    Languages:
      – Code: eng
        Text: English
    PhysicalDescription:
      Pagination:
        PageCount: 1
        StartPage: N.PAG
    Subjects:
      – SubjectFull: 6G networks
        Type: general
      – SubjectFull: Artificial intelligence
        Type: general
      – SubjectFull: Gaussian distribution
        Type: general
      – SubjectFull: Data transmission systems
        Type: general
      – SubjectFull: Wireless communications
        Type: general
      – SubjectFull: Language models
        Type: general
    Titles:
      – TitleFull: Design of a modified large language model for semantic communication in sixth-generation wireless networks.
        Type: main
  BibRelationships:
    HasContributorRelationships:
      – PersonEntity:
          Name:
            NameFull: Mathur, Samiksha
      – PersonEntity:
          Name:
            NameFull: Kumar, Dharmender
      – PersonEntity:
          Name:
            NameFull: Noliya, Amandeep
    IsPartOfRelationships:
      – BibEntity:
          Dates:
            – D: 20
              M: 01
              Text: Jan2026:Part 4
              Type: published
              Y: 2026
          Identifiers:
            – Type: issn-print
              Value: 09521976
          Numbering:
            – Type: volume
              Value: 163
          Titles:
            – TitleFull: Engineering Applications of Artificial Intelligence
              Type: main
ResultId 1