Saved in:
Bibliographic Details
Main Authors: Wang, Shiao, Wang, Yifeng, Ma, Qingchuan, Wang, Xiao, Yan, Ning, Yang, Qingquan, Xu, Guosheng, Tang, Jin
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.08879
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913541976489984
author Wang, Shiao
Wang, Yifeng
Ma, Qingchuan
Wang, Xiao
Yan, Ning
Yang, Qingquan
Xu, Guosheng
Tang, Jin
author_facet Wang, Shiao
Wang, Yifeng
Ma, Qingchuan
Wang, Xiao
Yan, Ning
Yang, Qingquan
Xu, Guosheng
Tang, Jin
contents Q-distribution prediction is a crucial research direction in controlled nuclear fusion, with deep learning emerging as a key approach to solving prediction challenges. In this paper, we leverage deep learning techniques to tackle the complexities of Q-distribution prediction. Specifically, we explore multimodal fusion methods in computer vision, integrating 2D line image data with the original 1D data to form a bimodal input. Additionally, we employ the Transformer's attention mechanism for feature extraction and the interactive fusion of bimodal information. Extensive experiments validate the effectiveness of our approach, significantly reducing prediction errors in Q-distribution.
format Preprint
id arxiv_https___arxiv_org_abs_2410_08879
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multi-modal Fusion based Q-distribution Prediction for Controlled Nuclear Fusion
Wang, Shiao
Wang, Yifeng
Ma, Qingchuan
Wang, Xiao
Yan, Ning
Yang, Qingquan
Xu, Guosheng
Tang, Jin
Computer Vision and Pattern Recognition
Q-distribution prediction is a crucial research direction in controlled nuclear fusion, with deep learning emerging as a key approach to solving prediction challenges. In this paper, we leverage deep learning techniques to tackle the complexities of Q-distribution prediction. Specifically, we explore multimodal fusion methods in computer vision, integrating 2D line image data with the original 1D data to form a bimodal input. Additionally, we employ the Transformer's attention mechanism for feature extraction and the interactive fusion of bimodal information. Extensive experiments validate the effectiveness of our approach, significantly reducing prediction errors in Q-distribution.
title Multi-modal Fusion based Q-distribution Prediction for Controlled Nuclear Fusion
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.08879