Prion-ViT: Prions-Inspired Vision Transformers for Temperature prediction with Specklegrams

TL;DR

This paper introduces Prion-ViT, a prion-inspired Vision Transformer model that enhances temperature prediction accuracy from fiber specklegram data by modeling long-term dependencies and providing explainability insights.

Contribution

The study presents a novel prion-inspired Vision Transformer architecture with persistent memory for improved temperature prediction from specklegram data, outperforming existing models.

Findings

Prion-ViT achieves MAE of 0.71°C, surpassing ResNet and other models.

The model effectively captures long-term dependencies in specklegram data.

Explainable AI techniques reveal key regions influencing predictions.

Abstract

Fiber Specklegram Sensors (FSS) are vital for environmental monitoring due to their high temperature sensitivity, but their complex data poses challenges for predictive models. This study introduces Prion-ViT, a prion-inspired Vision Transformer model, inspired by biological prion memory mechanisms, to improve long-term dependency modeling and temperature prediction accuracy using FSS data. Prion-ViT leverages a persistent memory state to retain and propagate key features across layers, reducing mean absolute error (MAE) to 0.71$^\circ$C and outperforming models like ResNet, Inception Net V2, and Standard Vision Transformers. This paper also discusses Explainable AI (XAI) techniques, providing a perspective on specklegrams through attention and saliency maps, which highlight key regions contributing to predictions