A Model for Quantifying the Degree of Understanding in Cross-Domain M2M Semantic Communications

This paper addresses the problem of semantic communications (SemComs) in intelligent machine-to-machine (M2M) applications. Although M2M applications may employ other languages as the communication medium, natural languages are commonly used as the medium between machines and robots. One favorable c...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2024, Vol.12, p.84515-84536
Main Authors: Hou, Ricky Yuen-Tan, Liu, Gang, Fong, Jefferson, Zhang, Hui, Jeong, Seon-Phil
Format: Article
Language:English
Subjects:
Communication
Cross-domain interpretation
degree of understanding
Exact solutions
Intelligent systems
Knowledge bases (artificial intelligence)
Languages
machine-to-machine
Machine-to-machine communications
Natural languages
Numerical models
Receivers
Robots
semantic communications
Semantics
two-stage validation
Vectors
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper addresses the problem of semantic communications (SemComs) in intelligent machine-to-machine (M2M) applications. Although M2M applications may employ other languages as the communication medium, natural languages are commonly used as the medium between machines and robots. One favorable characteristic of using natural languages is that it allows humans to inspect communication contents easily, which caters to the needs of security and quality of service for M2M communication. Currently, no exact solutions are available for quantifying and measuring the understanding of M2M communication. This paper identifies three specific challenges in the field: inconsistent knowledge base (KB), cross-domain interpretation, and a measure for understanding the meaning of messages. We propose a model to address these challenges in two steps. First, we propose an evidence-based shared-KB communication model for cross-domain meaning interpretation using Dewey Decimal Classification. Second, we propose a measure to quantify the understanding level through a two-stage validation between the sender and receiver. Real-life datasets and numerical experiments are used to evaluate the model's performance. The results show that the degree of understanding (DoU) can be successfully measured by observing the performance of the sender and receiver under the same conditions. The proposed method can effectively improve mutual understanding between the two machines.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3412929