Yujun Zhang

Dr. Yujun Zhang

Anhui Institute of Optics and Fine Mechanics, Chinese Academy of Sciences, Hefei 230031, China

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
13 August 2019 in Sensors
Verified
Journal Article
Open access
PDF file
HXHao Xie
Hao Xie
YZYujun Zhang
Yujun Zhang
YHYing He
Ying He
KYKun You
Kun You
BFBoqiang Fan
Boqiang Fan
MLMengqi Li
Mengqi Li
Optical remote sensing systems (RSSs) for monitoring vehicle emissions can be installed on any road and provide non-contact on-road measurements, that allow law enforcement departments to monitor emissions of a large number of on-road vehicles. Although many studies in different research fields have been performed using RSSs, there has been little research on the automatic recognition of on-road high-emitting vehicles. In general, high-emitting vehicles and low-emitting vehicles are classified by fixed emission concentration cut-points, that lack a strict scientific basis, and the actual cut-points are sensitive to environmental factors, such as wind speed and direction, outdoor temperature, relative humidity, atmospheric pressure, and so on. Besides this issue, single instantaneous monitoring results from RSSs are easily affected by systematic and random errors, leading to unreliable results. This paper proposes a method to solve the above problems. The automatic and fast-recognition method for on-road high-emitting vehicles (AFR-OHV) is the first application of machine learning, combined with big data analysis for remote sensing monitoring of on-road high-emitting vehicles. The method constructs adaptively updates a clustering database using real-time collections of emission datasets from an RSS. Then, new vehicles, that pass through the RSS, are recognized rapidly by the nearest neighbor classifier, which is guided by a real-time updated clustering database. Experimental results, based on real data, including the Davies-Bouldin Index (DBI) and Dunn Validity Index (DVI), show that AFR-OHV provides faster convergence speed and better performance. Furthermore, it is not easily disturbed by outliers. Our classifier obtains high scores for Precision (PRE), Recall (REC), the Receiver Operator Characteristic (ROC), and the Area Under the Curve (AUC). The rates of different classifications of excessive emissions and self-adaptive cut-points are calculated automatically in order to provide references for law enforcement departments to establish evaluation criterion for on-road high-emitting vehicles, detected by the RSS.

1 April 2014 in Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy
Verified
Journal Article
Closed access
XYXiaoya Yu
Xiaoya Yu
YZYujun Zhang
Yujun Zhang
GYGaofang Yin
Gaofang Yin
NZNanjing Zhao
Nanjing Zhao
XXXue Xiao
Xue Xiao
WZWei Zhang
Wei Zhang

26 September 2011 in Journal of Chemometrics
Verified
Journal Article
Closed access
PDF file
SYShaohui Yu
Shaohui Yu
YZYujun Zhang
Yujun Zhang
WLWenqing Liu
Wenqing Liu
NZNanjing Zhao
Nanjing Zhao
XXXue Xiao
Xue Xiao
GYGaofang Yin
Gaofang Yin

12 February 2018 in Optics Express
Verified
Journal Article
Closed access
PDF file
TQTang Qi-Xing
Tang Qi-Xing
YZYujun Zhang
Yujun Zhang
CDChen Dong
Chen Dong
ZKZhang Kai
Zhang Kai
HYHe Ying
He Ying
YDYu Dong-Qi
Yu Dong-Qi
In the detection process of atmospheric laser absorption spectroscopy in open space, the transmitted beam is inevitably affected by atmospheric turbulence, resulting in superimposed fluctuation noise in the received optical signal. First, the correction method of atmospheric turbulence is theoretically analyzed. In order to reduce the error influence factors and the error transfer coefficient, a new method of spectral data processing based on co-frequency and dual-wave has been proposed. By modifying scintillation noise and background noise, the influence of atmospheric turbulence noise in open space is reduced. An atmospheric detection system in open space based on co-frequency and dual-wave has been established. The experimental results show that the maximum fluctuation of the spectral signal processed by the method of spectrum data processing based on the co-frequency and dual-wave is reduced from 12.854% to 4.635%, and the single-intensity absorbance is fitted by Voigt with its correlation coefficient of 0.9525. The mean of the standard deviation of the algorithm is 0.1370, while the mean value of the standard deviation of the existing algorithm in a short time is 0.6928. And, through the comparative experiment, the standard deviation of the existing data processing techniques of two-wavelength differential absorption is 0.2974, while the standard deviation of the method of spectrum data processing based on the co-frequency and dual-wave is 0.1038. It can be concluded that the co-frequency and dual-wave method can effectively reduce the influence of atmospheric turbulence noise and laser flashing to improve the stability of concentration measurement, which has practical engineering value.

1 January 2019 in Chinese Optics Letters
Verified
Journal Article
Closed access
CSChao Shen
Chao Shen
NZNanjing Zhao
Nanjing Zhao
JPJaka Pribošek
Jaka Pribošek
MMMingjun Ma
Mingjun Ma
LFLi Fang
Li Fang
YZYujun Zhang
Yujun Zhang
The CLP Publishing collects CLP journals and partnered optics and photonics journals, and provides readers an optical publishing platform with global influence. SPIE, OSA, CUP. Chinese Laser Press (CLP), established by Shanghai Institute of Optics and Fine Mechanics (SIOM), Chinese Academy of Sciences (CAS) and Chinese Optical Society (COS) in 2009, nowadays publishes eight journals and manages three online platforms.

1 April 2011 in Applied Spectroscopy
Verified
Journal Article
Closed access
PDF file
SYShaohui Yu
Shaohui Yu
XXXue Xiao
Xue Xiao
ZWZhigang Wang
Zhigang Wang
KZKai Zhang
Kai Zhang
GYGaofang Yin
Gaofang Yin
WLWenqing Liu
Wenqing Liu
Component recognition is a very important issue in the analysis of mixed three-dimensional fluorescence spectra and it can be realized by calculating the similarity index between the reference spectra and the computed spectra from the trilinear decomposition of the three-dimensional data arrays. However, the most popular similarity index available in the literature for processing three-dimensional fluorescence spectra takes advantage of only part of the information from the trilinear decomposition. It works well when there are clear differences between the component spectra, but it may fail when the spectra are severely overlapped. In order to overcome the shortcomings and to adapt to the rapid development of online monitoring, we propose a type of integrated similarity index (ISI) that is particularly superior for component recognition in mixtures with severely overlapped spectra. The ISI makes full use of as much information of the three-dimensional fluorescence spectra as possible, namely, of both the waveform and the characteristic peak wavelength, as well as both the emission spectra and the excitation spectra. With the ISI, the recognition process can be accomplished automatically and more accurately in extreme cases than the traditionally defined similarity indices that are based on only one specific feature. The feasibility of the ISI is demonstrated by experiments with mixtures of phenol, cresol, and thymol.