Jingyu Wang

Title: Innovations of Jingyu Wang in Data Dimension Reduction

Introduction

Jingyu Wang is an accomplished inventor based in Xi'an, China. He has made significant contributions to the field of data dimension reduction, particularly in the context of image classification and pattern recognition. His innovative approach addresses key challenges in traditional linear discriminant analysis.

Latest Patents

Jingyu Wang holds a patent for a "Data dimension reduction method based on maximizing ratio sum for linear discriminant analysis." This invention focuses on constructing a data matrix, a label vector, and a label matrix. It involves calculating a within-class covariance matrix and a between-class covariance matrix. The optimization problem is constructed based on maximizing the ratio sum for linear discriminant analysis. The method utilizes the alternating direction method of multipliers to obtain a projection matrix that maximizes the objective function. This invention effectively avoids the pitfalls of traditional linear discriminant analysis, which often selects features with small variances and weak discriminating ability. By doing so, it enhances the selection of features that are more conducive to classification. Additionally, this method does not rely on the calculation of the inverse matrix of the within-class covariance matrix and does not require data preprocessing, thereby improving its adaptability to original data features.

Career Highlights

Jingyu Wang is affiliated with Northwestern Polytechnical University, where he continues to advance his research and innovations in data analysis. His work has garnered attention for its practical applications in various fields.

Collaborations

Jingyu Wang collaborates with notable colleagues, including Hongmei Wang and Feiping Nie, who contribute to his research endeavors.

Conclusion

Jingyu Wang's innovative methods in data dimension reduction represent a significant advancement in the field of image classification and pattern recognition. His contributions are poised to influence future research and applications in data analysis.