Task-Oriented Mulsemedia Communication using Unified Perceiver and Conformal Prediction in 6G Wireless Systems

TL;DR

This paper presents MuSeCo, a task-oriented mulsemedia communication system using unified Perceiver models and Conformal Prediction, enabling efficient sensory data fusion and communication in 6G systems for immersive experiences.

Contribution

Introduces MuSeCo, a novel multi-task mulsemedia communication framework that leverages unified Perceiver models and Conformal Prediction for adaptable, efficient sensory data processing in 6G networks.

Findings

Effective sensory modality fusion demonstrated in simulations.

Significant reduction in communication latency and energy consumption.

High accuracy maintained in communication-constrained environments.

Abstract

The growing prominence of eXtended Reality (XR), holographic-type communications, and metaverse demands truly immersive user experiences by using many sensory modalities, including sight, hearing, touch, smell, taste, etc. Additionally, the widespread deployment of sensors in areas such as agriculture, manufacturing, and smart homes is generating diverse sensory data. A new media format known as multisensory media (mulsemedia) has emerged, which incorporates many sensory modalities beyond the traditional visual and auditory media. 6G wireless systems are envisioned to support the Internet of Senses, making it crucial to explore effective data fusion and communication strategies for mulsemedia. In this paper, we introduce a task-oriented multi-task mulsemedia communication system named MuSeCo, which is developed using unified Perceiver models and Conformal Prediction. This unified model can accept any sensory input and efficiently extract latent semantic features, making it adaptable for deployment across various Artificial Intelligence of Things (AIoT) devices. Conformal Prediction is employed for modality selection and combination, enhancing task accuracy while minimizing data communication overhead. The model is trained using six sensory modalities across four classification tasks. Simulations and experiments demonstrate that it can effectively fuse sensory modalities, significantly reduce end-to-end communication latency and energy consumption, and maintain high accuracy in communication-constrained systems.