Search results
1 – 4 of 4Qingchen Qiu, Xuelian Wu, Zhi Liu, Bo Tang, Yuefeng Zhao, Xinyi Wu, Hongliang Zhu and Yang Xin
This paper aims to provide a framework of the supervised hyperspectral classification, to study the traditional flowchart of hyperspectral image (HIS) analysis and processing. HSI…
Abstract
Purpose
This paper aims to provide a framework of the supervised hyperspectral classification, to study the traditional flowchart of hyperspectral image (HIS) analysis and processing. HSI technology has been proposed for many years, and the applications of this technology were promoted by technical advancements.
Design/methodology/approach
First, the properties and current situation of hyperspectral technology are summarized. Then, this paper introduces a series of common classification approaches. In addition, a comparison of different classification approaches on real hyperspectral data is conducted. Finally, this survey presents a discussion on the classification results and points out the classification development tendency.
Findings
The core of this survey is to review of the state of the art of the classification for hyperspectral images, to study the performance and efficiency of certain implementation measures and to point out the challenges still exist.
Originality value
The study categorized the supervised classification for hyperspectral images, demonstrated the comparisons among these methods and pointed out the challenges that still exist.
Details
Keywords
Zhao Wang, Yuefeng Li, Jun Zou, Bobo Yang and Mingming Shi
The purpose of this paper is to investigate the effect of different soldering temperatures on the performance of chip-on-board (COB) light sources during vacuum reflow soldering.
Abstract
Purpose
The purpose of this paper is to investigate the effect of different soldering temperatures on the performance of chip-on-board (COB) light sources during vacuum reflow soldering.
Design/methodology/approach
First, the influence of the void ratio of the COB light source on the steady-state voltage, luminous flux, luminous efficiency and junction temperature has been explored at soldering temperatures of 250°C, 260°C, 270°C, 280°C and 290°C. The COB chip has also been tested for practical application and aging.
Findings
The results show that when the soldering temperature is 270°C, the void ratio of the soldering layer is only 5.1%, the junction temperature of the chip is only 76.52°C, and the luminous flux and luminous efficiency are the highest, and it has been observed that the luminous efficiency and average junction temperature of the chip are 107 lm/W and 72.3°C, respectively, which meets the requirements of street lights. After aging for 1,080 h, the light attenuation is 84.64% of the initial value, which indicates that it has higher reliability and longer life.
Originality/value
It can provide reference data for readers and people in this field and can be directly applied to practical engineering.
Details
Keywords
Yuefeng Cen, Minglu Wang, Gang Cen, Yongping Cai, Cheng Zhao and Zhigang Cheng
The stock indexes are an important issue for investors, and in this paper good trading strategies will be aimed to be adopted according to the accurate prediction of the stock…
Abstract
Purpose
The stock indexes are an important issue for investors, and in this paper good trading strategies will be aimed to be adopted according to the accurate prediction of the stock indexes to chase high returns.
Design/methodology/approach
To avoid the problem of insufficient financial data for daily stock indexes prediction during modeling, a data augmentation method based on time scale transformation (DATT) was introduced. After that, a new deep learning model which combined DATT and NGRU (DATT-nested gated recurrent units (NGRU)) was proposed for stock indexes prediction. The proposed models and their competitive models were used to test the stock indexes prediction and simulated trading in five stock markets of China and the United States.
Findings
The experimental results demonstrated that both NGRU and DATT-NGRU outperformed the other recurrent neural network (RNN) models in the daily stock indexes prediction.
Originality/value
A novel RNN with NGRU and data augmentation is proposed. It uses the nested structure to increase the depth of the deep learning model.
Details
Keywords
Xuliang Yao, Xiao Han, Yuefeng Liao and Jingfang Wang
This paper aims to better design the resonant tank parameters for LLC resonant converter. And, it is found that under heavy load, the voltage gain is affected by junction…
Abstract
Purpose
This paper aims to better design the resonant tank parameters for LLC resonant converter. And, it is found that under heavy load, the voltage gain is affected by junction capacitors of the primary side switching and the parasitic parameters of the secondary side diodes converted to the primary side, which will cause the voltage gain decreased when the switching frequency decreased.
Design/methodology/approach
This paper proposes an optimization parameters design method to solve this problem, which was based on impedance model considering the parasitic parameters of switching devices and diodes.
Findings
The effectiveness of the proposed method is verified by impedance Bode plots and experimental results.
Originality/value
From the perspective of impedance modeling, this paper finds the reasons for the insufficient voltage regulation capability of LLC resonant converters under heavy load and finds solutions through analysis.
Details