.png){kind=icon}
返回
AWED: Asymmetric Wavelet Encoder-Decoder Framework for Simultaneous Gas Distribution Mapping and Gas Source Localization
.png){kind=icon}
PRE
AI
DOI：10.1109/TIM.2024.3472798.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Gas distribution mapping (GDM) and gas source localization (GSL) are two crucial research areas in gas monitoring. However, due to the time-varying and nonuniform nature of gas distribution and the limitations of gas sensors, the accurate and rapid estimation of gas distribution from sparse sensor data is a challenging task. This article proposes an end-to-end model called asymmetric wavelet encoder-decoder (AWED) to address GDM and GSL from ultrasparse sensor data. The model uses a simplified encoder and an enhanced decoder, incorporating a wavelet reconstruction module (WRM) to decode from both spatial and frequency domains. In addition, a wavelet L1 loss is introduced to promote frequency-domain similarity between predicted and real images. The proposed method achieves a 32x super-resolution of gas distribution maps from 7x7 sensor data to 224x224 resolution images and achieves a GSL accuracy of 0.265 m within a 10x10 m area. The model also exhibits fewer parameters, faster prediction speed, and better real-time performance compared to existing methods. Experiments demonstrate that the proposed method outperforms traditional interpolation and state-of-the-art (SOTA) deep learning-based methods in reconstructing gas distribution maps and localizing gas sources from ultrasparse sensor data.
Keyword:
Superresolution
Gas detectors
Sensors
Image reconstruction
Wavelet transforms
Decoding
Location awareness
Image sensors
Accuracy
Image restoration
Gas distribution mapping (GDM)
gas source localization (GSL)
image super-resolution
wavelet transform
期刊
IF:
5.9
论文数:
2.0W
被引数:
5.8W
机构
引用论文
Red, green, and blue electrochromism in ambipolar poly(amine–amide–imide)s based on electroactive tetraphenyl‐p‐phenylenediamine units基于电活性四苯基 p-苯二胺单元的双极性聚 (胺-酰胺-酰亚胺) 中的红色，绿色和蓝色电致变色
PREAI
分享收藏分享收藏Conformational studies of parathyroid hormone (PTH)/PTH-related protein (PTHrP) point-mutated hybrids.png)
Biopolymers
BiopolymersIF0
PREAI
分享收藏Fast estimation of airflow distribution in an urban model using generative adversarial networks with limited sensing data使用具有有限感知数据的生成对抗网络快速估计城市模型中的气流分布
PREAI
分享收藏
查看更多内容