Weibao ZOU

Dr. Weibao ZOU


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 July 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
JXJiangbo Xi
Jiangbo Xi
MCMing Cong
Ming Cong
PBPurdue Bookstore
Purdue Bookstore
WZWeibao ZOU
Weibao ZOU
Chaoying ZhaoChaoying Zhao
Chaoying Zhao
TWTianjun Wu
Tianjun Wu
Recently, deep learning has been successfully and widely used in hyperspectral image (HSI) classification. Considering the difficulty of acquiring HSIs, there are usually a small number of pixels used as the training instances. Therefore, it is hard to fully use the advantages of deep learning networks; for example, the very deep layers with a large number of parameters lead to overfitting. This paper proposed a dynamic wide and deep neural network (DWDNN) for HSI classification, which includes multiple efficient wide sliding window and subsampling (EWSWS) networks and can grow dynamically according to the complexity of the problems. The EWSWS network in the DWDNN was designed both in the wide and deep direction with transform kernels as hidden units. These multiple layers of kernels can extract features from the low to high level, and because they are extended in the wide direction, they can learn features more steadily and smoothly. The sliding windows with the stride and subsampling were designed to reduce the dimension of the features for each layer; therefore, the computational load was reduced. Finally, all the weights were only from the fully connected layer, and the iterative least squares method was used to compute them easily. The proposed DWDNN was tested with several HSI data including the Botswana, Pavia University, and Salinas remote sensing datasets with different numbers of instances (from small to big). The experimental results showed that the proposed method had the highest test accuracies compared to both the typical machine learning methods such as support vector machine (SVM), multilayer perceptron (MLP), radial basis function (RBF), and the recently proposed deep learning methods including the 2D convolutional neural network (CNN) and the 3D CNN designed for HSI classification.

8 June 2026 in Measurement Science and Technology
Verified
Journal Article
Closed access
YCYongjie Chen
Yongjie Chen
WZWeibao ZOU
Weibao ZOU
Geomagnetic navigation offers advantages such as all weather capability, strong autonomy, and no accumulated error, making it a reliable alternative in satellite navigation denied scenarios, with wide applications in multiple fields. This paper focuses on four core aspects: geomagnetic field models, airborne geomagnetic navigation sensors, geomagnetic data denoising algorithms, and navigation algorithms, to review and summarize the research achievements and recent progress. It primarily introduces the characteristics and local accuracy issues of three mainstream geomagnetic field models: the International Geomagnetic Reference Field (IGRF), the World Magnetic Model (WMM), and the Enhanced Magnetic Model (EMM). It further analyzes advances in performance optimization of various geomagnetic sensors and the effectiveness of denoising algorithms. In addition, it summarizes the research progress and directions for improvement of mainstream traditional and intelligent geomagnetic navigation algorithms, including the Iterative Closest Contour Point (ICCP) algorithm, the Mean Absolute Difference (MAD) algorithm, the Magnetic Contour Matching (MAGCOM) algorithm, and various filtering algorithms. Finally, the current pressing issues in geomagnetic navigation technology are summarized, and future development prospects are outlined in areas such as intelligent data fusion, quantum sensing, and deep learning driven approaches.