Zhongjie Wang

Prof. Dr. Zhongjie Wang


Research Focus & Metrics

Academic Career Length

19Years (2008-Present)

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

Representative Publications

View All Publications
25 October 2022 in Pattern Recognition
Verified
Journal Article
Closed access
JFJinfu Fan
Jinfu Fan
YYYang Yu
Yang Yu
LHLinqing Huang
Linqing Huang
ZWZhongjie Wang
Zhongjie Wang

7 June 2018 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
YYYang Yu
Yang Yu
ZWZhongjie Wang
Zhongjie Wang
CLChengchao Lu
Chengchao Lu
Accurate power system state estimation facilitates power system control, optimization, and security analysis. In this paper, a joint filter approach is proposed to estimate both the static states (voltage magnitude and phase angle of bus) and the dynamic states (rotor angle, rotor speed, and transient voltages of generator) utilizing the measurements of phasor measurement unit. First, due to the complexity and dynamics of power system, the power system model is usually not known accurately. The uncertainties include both model uncertainty and noise statistics uncertainty. Therefore, H∞ filter is applied to reliable estimation of the static states. As a link between the static state estimation and the dynamic state estimation, the estimated static states are fed to dynamic state estimation. Next, to deal with the nonlinearity of synchronous generator model, an extended Kalman particle filter is employed to accurately estimate the dynamic states. The numerical tests on IEEE 30-bus system show that the proposed method is into both the static state estimation and the dynamic state estimation.

9 January 2024 in IEEE Transactions on Neural Networks and Learning Systems
Verified
Journal Article
Closed access
JFJinfu Fan
Jinfu Fan
LHLinqing Huang
Linqing Huang
Chaoyu GongChaoyu Gong
Chaoyu Gong
YYYang You
Yang You
MGMin Gan
Min Gan
ZWZhongjie Wang
Zhongjie Wang
Partial label learning (PLL) studies the problem of learning instance classification with a set of candidate labels and only one is correct. While recent works have demonstrated that the Vision Transformer (ViT) has achieved good results when training from clean data, its applications to PLL remain limited and challenging. To address this issue, we rethink the relationship between instances and object queries to propose K-means cross-attention transformer for PLL (KMT-PLL), which can continuously learn cluster centers and be used for downstream disambiguation tasks. More specifically, K-means cross-attention as a clustering process can effectively learn the cluster centers to represent label classes. The purpose of this operation is to make the similarity between instances and labels measurable, which can effectively detect noise labels. Furthermore, we propose a new corrected cross entropy formulation, which can assign weights to candidate labels according to the instance-to-label relevance to guide the training of the instance classifier. As the training goes on, the ground-truth label is progressively identified, and the refined labels and cluster centers in turn help to improve the classifier. Simulation results demonstrate the advantage of the KMT-PLL and its suitability for PLL.

31 December 2021 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
JFJinfu Fan
Jinfu Fan
YYYang Yu
Yang Yu
ZWZhongjie Wang
Zhongjie Wang
JGJinyi Gu
Jinyi Gu
Partial Label Learning (PLL) is a weakly supervised learning framework where each training instance is associated with more than one candidate label. This learning method is dedicated to finding out the true label for each training instance. Most of the current PLL algorithms directly disambiguate the candidate labels without correcting the disambiguated results, making the algorithms vulnerable to the influence of instances easily misjudged. In this paper, GraphDCN, an innovative disambiguation correction net with inductive graph representation learning model is proposed. GraphDCN consists of a disambiguation model and a correction model. For a given instance, the disambiguation model tries to fit its underlying ground-truth label through the candidate label distribution of the instances connected with the given one, while the correction model tries to maximize the distance between the disambiguated labels and non-candidate labels, and uses the label probability thresholds to correct the disambiguated labels that may be wrong. As the training goes on, both the disambiguation and correction models alternately and iteratively boost their performance. Moreover, when considering the implementation of the disambiguation model, a partial cross entropy formulation is proposed to estimate the ground-truth label loss by updating the ambiguity confidence matrix, which can be proved satisfying convergence in PLL. Simulation results reveal the overwhelming performance of GraphDCN.

23 November 2019 in Advances in Manufacturing
Verified
Journal Article
Closed access
PDF file
ZLZhao-Hui Liu
Zhao-Hui Liu
ZWZhongjie Wang
Zhongjie Wang
CYChen Yang
Chen Yang

18 April 2018 in IET Generation, Transmission & Distribution
Verified
Journal Article
Open access
PDF file
CLChengchao Lu
Chengchao Lu
ZWZhongjie Wang
Zhongjie Wang
YYYang Yu
Yang Yu
This study proposes a novel optimal phasor measurement unit (PMU) placement method for dynamic vulnerability assessment with minimum number of PMUs. PMU measurements should reflect the change of power system status as earlier as possible when a contingency occurs. Therefore, those buses which are sensitive to the change of power system status have to be equipped with PMUs to monitor the fragile areas of power systems. First, a large power system is partitioned into several coherent clusters. Next, a probabilistic vulnerability index defined as the objective function and a binary quadratic programming model are proposed for this purpose. Finally, the proposed method is tested on IEEE 9‐, 39‐, and 145‐bus systems. Results show that this method results in a PMU configuration with minimum number of devices and high vulnerability index. Such a PMU placement is able to estimate the vulnerability of power systems.