Jiangmei Zhang

Prof. Jiangmei Zhang


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
1 February 2022 in Neurocomputing
Verified
Journal Article
Closed access
ZQZhang xiao qian
Zhang xiao qian
JWJing Wang
Jing Wang
XXXuqian Xue
Xuqian Xue
HSHuaijiang Sun
Huaijiang Sun
JZJiangmei Zhang
Jiangmei Zhang

10 January 2024 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Guoqing ZhangGuoqing Zhang
Guoqing Zhang
WZWang Zhun
Wang Zhun
JZJiangmei Zhang
Jiangmei Zhang
ZLZhiyuan Luo
Zhiyuan Luo
ZZZhihao Zhao
Zhihao Zhao
Cross-Resolution Person Re-Identification (re-ID) aims to match images with disparate resolutions arising from variations in camera hardware and shooting distances. Most conventional works utilize Super-Resolution (SR) models to recover Low Resolution (LR) images to High Resolution (HR) images. However, because the SR models cannot completely compensate for the missing information in the LR images, there is still a large gap between the HR image recovered from the LR images and the real HR images. To tackle this challenge, we propose a novel Multi-Scale Image- and Feature-Level Alignment (MSIFLA) framework to align the images on multiple resolution scales at both the image and feature level. Specifically, (i) we design a Cascaded Multi-Scale Resolution Reconstruction (CMSR2) module, which is composed of three cascaded Image Reconstruction (IR) networks, and can continuously reconstruct multiple variables of different resolution scales from low to high for each image, regardless of image resolution. The reconstructed images with specific resolution scales are of similar distribution; therefore, the images are aligned on multiple resolution scales at the image level. (ii) We propose a Multi-Resolution Representation Learning (MR2L) module which consists of three-person re-ID networks to encourage the IR models to preserve the ID-discriminative information during training separately. Each re-ID network focuses on mining discriminative information from a specific scale without the disturbance from various resolutions. By matching the extracted features on three resolution scales, the images with different resolutions are also aligned at the feature-level. We conduct extensive experiments on multiple public cross-resolution person re-ID datasets to demonstrate the superiority of the proposed method. In addition, the generalization of MSIFLA in handling cross-resolution retrieval tasks is verified on the UAV vehicle dataset.

19 February 2024 in Water
Verified
Journal Article
Open access
PDF file
YZYangxin Zhang
Yangxin Zhang
JZJiangmei Zhang
Jiangmei Zhang
TLTuantuan Liu
Tuantuan Liu
XFXinghua Feng
Xinghua Feng
TXTengxiang Xie
Tengxiang Xie
HLHaolin Liu
Haolin Liu
Many nuclear power plants have been built along China’s coasts, and the migration and diffusion of radioactive nuclides in coastal harbours is very concerning. In this study, considering the decay and free diffusion of radioactive nuclides, a local hydrodynamic model based on the FVCOM was built to investigate the migration and diffusion of the radioactive nuclide tritium in Haizhou Bay, China. This model was calibrated according to the observed tidal level and flow velocity and direction, which provide an accurate background. This study aimed to evaluate the impact of tides and monsoons on the migration path and concentration variations in tritium over time. The results demonstrated that the simulated flow field can reflect real-life receiving waters. The distribution of the tritium concentration is affected by the flow field, which is related to the tides. Moreover, more severe radioactive contamination was exhibited in winter than in summer because monsoons may have hindered the migration and diffusion of tritium within the harbour. Given the poor hydrodynamic conditions and slow water exchange in the open ocean in Haizhou Bay, the diffusion rate of radioactive nuclides outside the bay area was higher than that within it.

1 November 2021 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
SZSiyi Zhou
Siyi Zhou
JZJiangmei Zhang
Jiangmei Zhang
XFXinghua Feng
Xinghua Feng
CZCaolin Zhang
Caolin Zhang
In the real energy spectrum attenuation environment, many traditional nuclide identification methods for nuclear robot systems have problems such as using only part of the energy spectrum curve, being susceptible to noise, and having low recognition accuracy. Proposes an energy spectrum nuclide recognition method based on S-transform (ST) and Mahalanobis distance-based support vector machine (MSVM). Regarding the energy spectrum curve as a non-stationary signal, combined with the widely used S transformation method in signal transformation, the energy spectrum data is two-dimensional, Then use two-dimensional principal component analysis(2D-PCA) to reduce the dimension of the two-dimensional energy spectrum data for feature extraction, and design a support vector machine (SVM) classifier based on Mahalanobis distance to realize the identification of energy spectrum nuclides. Finally, experiments are carried out with simulated nuclide energy spectrum data based on Geant4. The experimental results show that this method effectively improves the accuracy of energy spectrum nuclide recognition by using full spectrum information. At the same time, experiments are carried out on the nuclide energy spectrum data of different detection distances obtained by the NaI detector in the real environment, and it is verified that the algorithm proposed in this paper also has a good recognition performance for the nuclide energy spectrum collected in the real environment.

5 October 2025 in Electronics
Verified
Journal Article
Open access
PDF file
YLYongzhuo LIU
Yongzhuo LIU
JZJiangmei Zhang
Jiangmei Zhang
HLHaolin Liu
Haolin Liu
YZYangxin Zhang
Yangxin Zhang
This paper presents a dual-structured convolutional neural network (CNN) for image classification, which integrates two parallel branches: CNN-A with spatial attention and CNN-B with channel attention. The spatial attention module in CNN-A dynamically emphasizes discriminative regions by aggregating channel-wise information, while the channel attention mechanism in CNN-B adaptively recalibrates feature channel importance. The extracted features from both branches are fused through concatenation, enhancing the model’s representational capacity by capturing complementary spatial and channel-wise dependencies. Extensive experiments on a 12-class image dataset demonstrate the superiority of the proposed model over state-of-the-art methods, achieving 98.06% accuracy, 96.00% precision, and 98.01% F1-score. Despite a marginally longer training time, the model exhibits robust convergence and generalization, as evidenced by stable loss curves and high per-class recognition rates (>90%). The results validate the efficacy of dual attention mechanisms in improving feature discrimination for complex image classification tasks.

23 December 2022 in Symmetry
Verified
Journal Article
Open access
PDF file
XFXinghua Feng
Xinghua Feng
KWKunpeng Wang
Kunpeng Wang
JZJiangmei Zhang
Jiangmei Zhang
JGJiayue Guan
Jiayue Guan
In this paper, we propose a new consistency measurement for classification rule sets that is based on the similarity of their classification abilities. The similarity of the classification abilities of the two rule sets is evaluated though the similarity of the corresponding partitions of the feature space using the different rule sets. The proposed consistency measure can be used to measure the equivalent symmetry of subsystems decomposed from a large, complex cyber–physical system (CPS). It can be used to verify whether the same knowledge is obtained by the sensing data in the different subsystems. In the experiments, five decision tree algorithms and eighteen datasets from the UCI machine learning repository are employed to extract the classification rules, and the consistency between the corresponding rule sets is investigated. The classification rule sets extracted from the use of the C4.5 algorithm on the electrical grid stability dataset have a consistency of 0.88, which implies that the different subsystems contain almost equivalent knowledge about the network stability.