Search

Your search keyword '"Dai, MengYun"' showing total 5 results
Start Over Author "Dai, MengYun"
5 results on '"Dai, MengYun"'

4. MS3A-Net: multi-scale and spectral-spatial attention network for hyperspectral image classification.

Author

Dai, Mengyun, Sun, Qi, Dai, Luanyan, Lin, Yaohai, Wei, Lifang, Yang, Changcai, and Chen, Riqing

Subjects
*FEATURE extraction, *MULTISPECTRAL imaging, *CLASSIFICATION, *ATTENTION
Abstract

Hyperspectral image (HSI) classification methods usually combine spatial information and rich spectral information effectively to reflect the delicate features of ground objects, improve classification accuracy, and lay a foundation for further analysis of ground objects. However, the current research on HSI classification mainly focuses on the joint extraction of spectral-spatial features and does not fully consider the difference in the size of ground objects corresponding to feature extraction. To alleviate the problem, we propose a new multi-scale and spectral-spatial attention network (MS3A-Net), which contains a proposed multi-scale attention feature extraction (MAFE) block and a spectral-spatial cooperative attention (SSCA) block in the front end of the network. The proposed MAFE block can extract the features of ground objects at different scales and minimize the interference of different sizes of ground objects. The proposed MS3A-Net can increase the influence of effective pixels in both spatial and spectral dimensions and suppress the effect of invalid or even disturbing pixels. A large number of quantitative and qualitative experimental results on Indian Pines, Salinas Valley, and University of Pavias data sets show the performance of our proposed network. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

5. Energy saving based lighting system optimization and smart control solutions for rail transportation: Evidence from China

Author

Raufdeen Rameezdeen, MengYun Dai, XiaoDong Lai, Lai, XiaoDong, Dai, MengYun, and Rameezdeen, Raufdeen

Subjects
Scheme (programming language), business.industry, Computer science, lcsh:T, energy management system, Control (management), General Engineering, Intelligent lighting, influence factors, Energy consumption, lcsh:Technology, Automotive engineering, Energy management system, Software, Control system, lighting system, business, computer, Energy (signal processing), artificial intelligent control technology, computer.programming_language
Abstract

As the natural resources are becoming exhausted, energy consumption by metro systems dominates internal transportation resources in urban areas. The comprehensive exploration of energy improvements in lighting system energy is necessary. To evaluate the energy-saving potential and identify the efficiency improvement opportunities for lighting operations in metro systems, an intelligent energy management system for metro stations is examined through a case study in Nanchang city of China. First, the study explores the main factors influencing the lighting energy consumption of metro systems and analyses the lighting distribution in different station regions. Second, DIALux software is employed to optimize and monitor the best illuminating effect for hall lighting in the selected station. Third, an intelligent model is proposed for the lighting system based on the energy-saving scheme and solution using BECH energy analysis software combined with DIALux software. A thermal model is proposed to verify the energy and load performances. Results show that (1) the proper layout by means of DIALux software, can not only meet the functional demands of lighting but also reduce energy consumption; (2) intelligent lighting control system can improve the lighting energy-saving design, and the lighting control framework is capable of refined control; and (3) based on the performance analyses, the solution with the adopted DALI digital light adjustment is helpful for increasing passengers' comfort and realizing the goals reduction.The novelty is to integrate the lighting energy saving solution with software within an intelligent management and verified its valuable application, it is practical for construction emission control. Keywords: Lighting system, Influence factors, Artificial intelligent control technology, Energy management system

Published
2020

Catalog

Books, media, physical & digital resources
See catalog results