Zhenjie Hong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zhenjie Hong has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Xijin Tang
Chinese Academy of Sciences
2 shared publications - Zhenpeng Li
Taizhou University
2 shared publications - Baolong Liu
Zhejiang Gongshang University & Zhejiang Key Lab of E-Commerce, Hangzhou, China
1 shared publication - Chuang Yu
Mechanical and Electrical Engineering, China University of Mining and Technology, Xuzhou, Jiangsu, 221000, PR China
1 shared publication - Fan Ye
City College of Wenzhou University
1 shared publication - Insha Ullah
Research School of Finance, Actuarial Studies & Statistics, ANU College of Business & Economics The Australian National University Canberra Australian Capital Territory Australia
1 shared publication
Latest Publications
- 28 December 2022
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 35 (6) , 2319-2335
Opinion Dynamics Induced by Agents with Particular Goal
- 28 December 2022
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 35 (6) , 2319-2335
Opinion Dynamics Induced by Agents with Particular Goal
- 18 August 2022
- Published by Springer Nature in The European Physical Journal B
- Vol. 95 (8) , 1-11
Collective attention dynamic induced by novelty decay
- 18 August 2022
- Published by Springer Nature in The European Physical Journal B
- Vol. 95 (8) , 1-11
Collective attention dynamic induced by novelty decay
- Open Access
- 20 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 71106-71116
A Novel Active Learning Algorithm for Robust Image Classification
Training samples need to be labeled before being used to train classification model, which usually takes too much labor and material resources. Recently, this problem has attracted widespread attention. In order to reduce the workload of labeling samples, we propose a novel active learning methodology, which uses locally linear reconstruction coefficients to construct semi-supervised data manifold adaptive kernel space. Comparing the new method with other sampling approaches on several real-world image datasets, experimental results indicate that the novel algorithm has preferable classification ability. Especially, it can show higher classification accuracy under the condition that only a few samples are selected to train the classifier model.
- 20 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 71106-71116
Open AccessA Novel Active Learning Algorithm for Robust Image Classification
Training samples need to be labeled before being used to train classification model, which usually takes too much labor and material resources. Recently, this problem has attracted widespread attention. In order to reduce the workload of labeling samples, we propose a novel active learning methodology, which uses locally linear reconstruction coefficients to construct semi-supervised data manifold adaptive kernel space. Comparing the new method with other sampling approaches on several real-world image datasets, experimental results indicate that the novel algorithm has preferable classification ability. Especially, it can show higher classification accuracy under the condition that only a few samples are selected to train the classifier model.
- Open Access
- 16 May 2019
- Published by MDPI AG in Remote Sensing
- Vol. 11 (10) , 1172
The Two-Parts Step-by-Step Ionospheric Assimilation Based on Ground-Based/Spaceborne Observations and Its Verification
This study introduced a Kalman filtering assimilation model that considers the DCB errors of GPS/LEO satellites and GNSS stations. The assimilation results and reliability were verified by various types of data, such as ionMap, ionosonde, ISR, and the EDP of ionPrf from COSMIC. The following analyses were carried out. Assimilating the measured ground-based/spaceborne ionospheric observation data from DOY 010, 2008 and DOY 089, 2012 revealed that the introduction of GPS/LEO satellite and GPS station DCB errors can effectively suppress the STEC observation errors caused by the single-layer hypothesis. Furthermore, the top of the ionosphere contributes 2.8 TECU (approximately 10–20% of the STEC) of electrons during the ionospheric quiet period, greatly influencing the ionospheric assimilation at altitudes of 100–800 km. The assimilation results also show that, after subtracting the influence of the top of the ionosphere, the ionospheric deviation during the quiet period improved from 1.645 TECU to 1.464 TECU; when the ionosphere was active, the standard deviation was improved from 4.408 TECU to 3.536 TECU. The IRI-Imp model introduced by Wu et al. and the IRI (2007) model were used as background fields to compare the effects of COSMIC occultation observation data on the ionospheric assimilation process. Upon comparison, the occultation data introduced by the improved model showed the greatest improvement in the vertical structure of the ionosphere; additionally, the assimilation process reused the horizontal structure information of the occultation data, and the assimilation result (IRI-Imp-Assi) was the most ideal. Due to the lack of an occultation data correction, the IRI2007 model was relatively more prone to errors. With the strategy of the IRI-Imp-Assi model, the introduction of occultation data caused a more significant reduction in the error between the assimilation model with the IRI model as the background field and the ionMap.
- 16 May 2019
- Published by MDPI AG in Remote Sensing
- Vol. 11 (10) , 1172
Open AccessThe Two-Parts Step-by-Step Ionospheric Assimilation Based on Ground-Based/Spaceborne Observations and Its Verification
This study introduced a Kalman filtering assimilation model that considers the DCB errors of GPS/LEO satellites and GNSS stations. The assimilation results and reliability were verified by various types of data, such as ionMap, ionosonde, ISR, and the EDP of ionPrf from COSMIC. The following analyses were carried out. Assimilating the measured ground-based/spaceborne ionospheric observation data from DOY 010, 2008 and DOY 089, 2012 revealed that the introduction of GPS/LEO satellite and GPS station DCB errors can effectively suppress the STEC observation errors caused by the single-layer hypothesis. Furthermore, the top of the ionosphere contributes 2.8 TECU (approximately 10–20% of the STEC) of electrons during the ionospheric quiet period, greatly influencing the ionospheric assimilation at altitudes of 100–800 km. The assimilation results also show that, after subtracting the influence of the top of the ionosphere, the ionospheric deviation during the quiet period improved from 1.645 TECU to 1.464 TECU; when the ionosphere was active, the standard deviation was improved from 4.408 TECU to 3.536 TECU. The IRI-Imp model introduced by Wu et al. and the IRI (2007) model were used as background fields to compare the effects of COSMIC occultation observation data on the ionospheric assimilation process. Upon comparison, the occultation data introduced by the improved model showed the greatest improvement in the vertical structure of the ionosphere; additionally, the assimilation process reused the horizontal structure information of the occultation data, and the assimilation result (IRI-Imp-Assi) was the most ideal. Due to the lack of an occultation data correction, the IRI2007 model was relatively more prone to errors. With the strategy of the IRI-Imp-Assi model, the introduction of occultation data caused a more significant reduction in the error between the assimilation model with the IRI model as the background field and the ionMap.
- 15 March 2019
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 35 (20) , 3996-4003
Significance tests for analyzing gene expression data with small sample sizes
Motivation: Under two biologically different conditions, we are often interested in identifying differentially expressed genes. It is usually the case that the assumption of equal variances on the two groups is violated for many genes where a large number of them are required to be filtered or ranked. In these cases, exact tests are unavailable and the Welch’s approximate test is most reliable one. The Welch’s test involves two layers of approximations: approximating the distribution of the statistic by a t-distribution, which in turn depends on approximate degrees of freedom. This study attempts to improve upon Welch’s approximate test by avoiding one layer of approximation.Results: We introduce a new distribution that generalizes the t-distribution and propose a Monte Carlo based test that uses only one layer of approximation for statistical inferences. Experimental results based on extensive simulation studies show that the Monte Carol based tests enhance the statistical power and performs better than Welch’s t-approximation, especially when the equal variance assumption is not met and the sample size of the sample with a larger variance is smaller. We analyzed two gene-expression datasets, namely the childhood acute lymphoblastic leukemia gene-expression dataset with 22 283 genes and Golden Spike dataset produced by a controlled experiment with 13 966 genes. The new test identified additional genes of interest in both datasets. Some of these genes have been proven to play important roles in medical literature.Availability and implementation: R scripts and the R package mcBFtest is available in CRAN and to reproduce all reported results are available at the GitHub repository, https://github.com/iullah1980/MCTcodes.Supplementary information: Supplementary data is available at Bioinformatics online.
- 15 March 2019
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 35 (20) , 3996-4003
Significance tests for analyzing gene expression data with small sample sizes
Motivation: Under two biologically different conditions, we are often interested in identifying differentially expressed genes. It is usually the case that the assumption of equal variances on the two groups is violated for many genes where a large number of them are required to be filtered or ranked. In these cases, exact tests are unavailable and the Welch’s approximate test is most reliable one. The Welch’s test involves two layers of approximations: approximating the distribution of the statistic by a t-distribution, which in turn depends on approximate degrees of freedom. This study attempts to improve upon Welch’s approximate test by avoiding one layer of approximation.Results: We introduce a new distribution that generalizes the t-distribution and propose a Monte Carlo based test that uses only one layer of approximation for statistical inferences. Experimental results based on extensive simulation studies show that the Monte Carol based tests enhance the statistical power and performs better than Welch’s t-approximation, especially when the equal variance assumption is not met and the sample size of the sample with a larger variance is smaller. We analyzed two gene-expression datasets, namely the childhood acute lymphoblastic leukemia gene-expression dataset with 22 283 genes and Golden Spike dataset produced by a controlled experiment with 13 966 genes. The new test identified additional genes of interest in both datasets. Some of these genes have been proven to play important roles in medical literature.Availability and implementation: R scripts and the R package mcBFtest is available in CRAN and to reproduce all reported results are available at the GitHub repository, https://github.com/iullah1980/MCTcodes.Supplementary information: Supplementary data is available at Bioinformatics online.
- 25 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 9 (4) , 102-117
Locating Various Ship License Numbers in the Wild: An Effective Approach
Ship License Numbers (SLNs) play a significant role in intelligent waterway transportation systems. However, there is a dearth of published papers concerning the location of SLNs. In this paper, we present an effective coarse-to-fine approach for locating various SLNs. The proposed method contains four main steps. First, for ships in the wild, the coarse problem of locating SLNs is posed as the detection of specific text groups. In this phase, the proximity and similarity laws of Gestalt Theory are collaboratively used to create text-group hypotheses and detect the meaningful region groups that may contain text in input images. In the second step, four SLN prior features are first summarized. An SLN prior-based fine location process is then conducted to determine the locations of text candidates that actually contain characters and text, i.e., the candidate SLNs. Two connected component classification and merging algorithms are proposed based on height continuity and vertical/horizontal projection analysis. Third, a connected-component scatter-based fake-SLN elimination algorithm is developed. The accurate positions of the SLNs in the input image are obtained in this stage. Finally, partially located SLNs are compensated by a method that characterizes the color and brightness similarity features of characters in the same SLN. The proposed approach is then applied to two collected datasets. The approach is proved to be effective with an overall ship-level location accuracy of 70.38% and a SLN-level F-measure of 0.642 on 950 images with 1374 labeled SLNs.
- 25 October 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Intelligent Transportation Systems Magazine
- Vol. 9 (4) , 102-117
Locating Various Ship License Numbers in the Wild: An Effective Approach
Ship License Numbers (SLNs) play a significant role in intelligent waterway transportation systems. However, there is a dearth of published papers concerning the location of SLNs. In this paper, we present an effective coarse-to-fine approach for locating various SLNs. The proposed method contains four main steps. First, for ships in the wild, the coarse problem of locating SLNs is posed as the detection of specific text groups. In this phase, the proximity and similarity laws of Gestalt Theory are collaboratively used to create text-group hypotheses and detect the meaningful region groups that may contain text in input images. In the second step, four SLN prior features are first summarized. An SLN prior-based fine location process is then conducted to determine the locations of text candidates that actually contain characters and text, i.e., the candidate SLNs. Two connected component classification and merging algorithms are proposed based on height continuity and vertical/horizontal projection analysis. Third, a connected-component scatter-based fake-SLN elimination algorithm is developed. The accurate positions of the SLNs in the input image are obtained in this stage. Finally, partially located SLNs are compensated by a method that characterizes the color and brightness similarity features of characters in the same SLN. The proposed approach is then applied to two collected datasets. The approach is proved to be effective with an overall ship-level location accuracy of 70.38% and a SLN-level F-measure of 0.642 on 950 images with 1374 labeled SLNs.
- 18 October 2012
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 25 (5) , 942-949
The sufficient and necessary condition of the major stochastic preference rule in group decision making
- 18 October 2012
- Published by Springer Nature in Journal of Systems Science and Complexity
- Vol. 25 (5) , 942-949
The sufficient and necessary condition of the major stochastic preference rule in group decision making
- Open Access
- 1 July 2010
- Published by Wiley in Chinese Journal of Geophysics
- Vol. 53 (4) , 639-645
Simulation of Atmospheric Refractive Profile Retrieving from Low‐Elevation Ground‐Based GPS Observations
A new retrieval algorithm of atmospheric refractive profile from ground‐based GPS signal bending and delays is developed. A more reasonable power system of the value function is proposed in optimizing the value function. Based on variational assimilation technique and a four‐parameter refractivity model, the atmospheric profile is inversed. The simulation results show fairly good agreement between the retrieved atmospheric refractive profiles with the input true values. The new method can also be applied to detecting the atmospheric duct layer in the planetary boundary layer.
- 1 July 2010
- Published by Wiley in Chinese Journal of Geophysics
- Vol. 53 (4) , 639-645
Open AccessSimulation of Atmospheric Refractive Profile Retrieving from Low‐Elevation Ground‐Based GPS Observations
A new retrieval algorithm of atmospheric refractive profile from ground‐based GPS signal bending and delays is developed. A more reasonable power system of the value function is proposed in optimizing the value function. Based on variational assimilation technique and a four‐parameter refractivity model, the atmospheric profile is inversed. The simulation results show fairly good agreement between the retrieved atmospheric refractive profiles with the input true values. The new method can also be applied to detecting the atmospheric duct layer in the planetary boundary layer.