• Home
  • Search
  • The self supervised multimodal semantic transmission mechanism for complex network environments
  • Cite Icon5
  • https://doi.org/10.1038/s41598-025-15162-xCopy DOI Icon

The self supervised multimodal semantic transmission mechanism for complex network environments

Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

With the rapid development of intelligent transportation systems, the challenge of achieving efficient and accurate multimodal traffic data transmission and collaborative processing in complex network environments with bandwidth limitations, signal interference, and high concurrency has become a key issue that needs to be addressed. This paper proposes a Self-supervised Multi-modal and Reinforcement learning-based Traffic data semantic collaboration Transmission mechanism (SMART), aiming to optimize the transmission efficiency and robustness of multimodal data through a combination of self-supervised learning and reinforcement learning. The sending end employs a self-supervised conditional variational autoencoder and Transformer-DRL-based dynamic semantic compression strategy to intelligently filter and transmit the most core semantic information from video, radar, and LiDAR data. The receiving end combines Transformer and graph neural networks for deep decoding and feature fusion of multimodal data, while also using reinforcement learning self-supervised multi-task optimization engine to collaboratively enhance multiple task scenarios (such as traffic accident detection and vehicle behavior recognition). Experimental results show that SMART significantly outperforms traditional methods in low signal-to-noise ratio, high packet loss rate, and large-scale concurrency environments, excelling in key indicators such as semantic similarity, transmission efficiency, robustness, and end-to-end latency, demonstrating its effectiveness and innovation in smart transportation scenarios.

Similar Papers
  • PDF
  • Research Article
  • Citations50

A Kriging based spatiotemporal approach for traffic volume data imputation.

  • Apr 17, 2018
  • PLOS ONE
  • Hongtai Yang +6
  • Research Article

Research on Key Technologies and Development Trends in Intelligent Vehicle Path Planning

  • Oct 23, 2025
  • Frontiers in Science and Engineering
  • Tingxuan Yuan
  • Research Article
  • Citations1

Special issue: emerging technologies for intelligent transportation

  • Feb 09, 2015
  • Journal of Advanced Transportation
  • William H K Lam
  • Research Article
  • Citations5

STAP: A Spatio-Temporal Correlative Estimating Model for Improving Quality of Traffic Data

  • Oct 06, 2020
  • IEEE Transactions on Intelligent Transportation Systems
  • Yingjie Xia +2
  • Research Article
  • Citations3

An adaptive k nearest neighbour method for imputation of missing traffic data based on two similarity

  • Jun 30, 2020
  • Archives of Transport
  • Yang Wang +3
  • Research Article
  • Citations7

Privacy-Preserving Distributed Transfer Learning and Its Application in Intelligent Transportation

  • Mar 01, 2024
  • IEEE Transactions on Intelligent Transportation Systems
  • Zhi Li +6
  • Preprint Article

Graph Neural Networks for Hourly 1 km Urban CO2 Emissions Estimation Using Real-World Data

  • May 21, 2025
  • Yeonsu Lee +3
  • PDF
  • Research Article
  • Citations1

Product Design Method Based on Data Fusion and Transmission Based on Multimode Sensor

  • Jul 30, 2022
  • Mobile Information Systems
  • Jun Hu
  • Research Article
  • Citations23

Hybrid deep learning model with VMD-BiLSTM-GRU networks for short-term traffic flow prediction

  • Sep 01, 2025
  • Data Science and Management
  • Changxi Ma +2
  • Research Article
  • Citations21

Development of Intelligent Transportation System and Its Applications for an Urban Corridor During COVID-19

  • Jan 01, 2021
  • Journal of The Institution of Engineers (India): Series B
  • Sourabh Jain +1
  • Research Article

Electric Vehicle Routing Optimization Oriented to Intelligent Transportation Systems: A Review and Future Trends

  • Jan 27, 2026
  • International Journal of Global Economics and Management
  • Shiqi Zhang
  • Research Article

A Large Language Model for Traffic Flow Prediction Based on Stationary Wavelet Transform and Graph Convolutional Networks

  • Apr 11, 2026
  • ISPRS International Journal of Geo-Information
  • Xin Wang +4
  • Research Article
  • Citations12

Intelligent transportation system in China: The optimal evaluation period of transportation’s application performance

  • May 06, 2020
  • Journal of Intelligent & Fuzzy Systems
  • Li Mingwei +1
  • Dissertation

Visual Sensing for Comprehensive Granular Traffic Data Collection in Support of Intelligent Transportation Applications

  • Jan 01, 2023
  • Linjun Lu
  • Conference Article
  • Citations1

Traffic Flow Forecasting Model Based on Data Mining

  • Jan 01, 2016
  • Xin Guo
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.