Yu-Ping Gu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yu-Ping Gu has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Haoyue Xu1 shared publication
Li-Jiao Xu
School of Automotive and Rail Transit, Nanjing Institute of Technology
1 shared publicationLong-Sheng Cheng
School of Economics and Management, Nanjing University of Science and Technology
1 shared publication- Wenhe Chen
Anhui Normal University
1 shared publication Xiang-Lai Chen
School of Business, Hunan University of Technology
1 shared publication- Zhipeng Chang
School of Business Anhui University of Technology Ma'anshan China
1 shared publication
Latest Publications
- Open Access
- 17 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 20428-20438
Mahalanobis-Taguchi System for Symbolic Interval Data Based on Kernel Mahalanobis Distance
Mahalanobis-Taguchi System (MTS), as a pattern recognition method by constructing a continuous measurement scale, has a very good performance on classification and feature selection for real-valued data. However, the record of symbolic interval data has become a common practice with the recent advances in database technologies. Kernel methods not only are powerful statistical nonlinear learning methods, but also can be defined over objects as diverse as graphs, sets, strings, and text documents. In this paper, we derive kernel Mahalanobis distance (KMD) to extend MTS to symbolic interval data. To evaluate the proposed method, four experiments with synthetic symbolic interval data sets and seven experiments with real symbolic interval data sets are performed and we have compared our method with MTS based on interval Mahalanobis distance (IMD). The experimental results show our method has a better classification performance than MTS based on IMD on Accuracy, Specificity, Sensitivity, and G-means. However, MTS based on IMD has a stronger dimension reduction rate than our method.
- 17 January 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 20428-20438
Open AccessMahalanobis-Taguchi System for Symbolic Interval Data Based on Kernel Mahalanobis Distance
Mahalanobis-Taguchi System (MTS), as a pattern recognition method by constructing a continuous measurement scale, has a very good performance on classification and feature selection for real-valued data. However, the record of symbolic interval data has become a common practice with the recent advances in database technologies. Kernel methods not only are powerful statistical nonlinear learning methods, but also can be defined over objects as diverse as graphs, sets, strings, and text documents. In this paper, we derive kernel Mahalanobis distance (KMD) to extend MTS to symbolic interval data. To evaluate the proposed method, four experiments with synthetic symbolic interval data sets and seven experiments with real symbolic interval data sets are performed and we have compared our method with MTS based on interval Mahalanobis distance (IMD). The experimental results show our method has a better classification performance than MTS based on IMD on Accuracy, Specificity, Sensitivity, and G-means. However, MTS based on IMD has a stronger dimension reduction rate than our method.
- 4 July 2019
- Published by Taylor & Francis in Journal of Industrial and Production Engineering
- Vol. 36 (5) , 271-275
Optimization of cable insulation eccentricity by Taguchi robust design
Reduction of the cable insulation eccentricity is an important proposition in the cable industry. In this paper, firstly a strong negative correlation between the insulation eccentricity and the signal-to-noise ratio of insulation thickness in nominal-the-best characteristics is obtained by correlation and regression analysis. Secondly, the methods of fault tree and risk priority number are used to determine three key factors. Finally, Taguchi robust design is used to optimize process parameters. Experimental results showed that the average thickness of insulation can be reduced from 4.52 mm to 4.31 mm and the average eccentricity of insulation can be reduced from 6.12% to 3.09%. Taguchi robust design can not only improve the product quality, but also save product costs and achieve significant economic benefits.
- 4 July 2019
- Published by Taylor & Francis in Journal of Industrial and Production Engineering
- Vol. 36 (5) , 271-275
Optimization of cable insulation eccentricity by Taguchi robust design
Reduction of the cable insulation eccentricity is an important proposition in the cable industry. In this paper, firstly a strong negative correlation between the insulation eccentricity and the signal-to-noise ratio of insulation thickness in nominal-the-best characteristics is obtained by correlation and regression analysis. Secondly, the methods of fault tree and risk priority number are used to determine three key factors. Finally, Taguchi robust design is used to optimize process parameters. Experimental results showed that the average thickness of insulation can be reduced from 4.52 mm to 4.31 mm and the average eccentricity of insulation can be reduced from 6.12% to 3.09%. Taguchi robust design can not only improve the product quality, but also save product costs and achieve significant economic benefits.