Qualitative Analysis of Pesticide Residues on Chinese Cabbage Based on GK Improved Possibilistic C-Means Clustering

Yang TAN; Xiao-hong WU; Bin WU; Yan-jun SHEN; Jin-mao LIU

doi:10.3964/j.issn.1000-0593(2022)05-1465-06

Journals >Spectroscopy and Spectral Analysis >Volume 42 >Issue 5 >Page 1465 > Article

Spectroscopy and Spectral Analysis
Vol. 42, Issue 5, 1465 (2022)

Qualitative Analysis of Pesticide Residues on Chinese Cabbage Based on GK Improved Possibilistic C-Means Clustering

Yang TAN^1、1;, Xiao-hong WU^{2、2; 3; *;}, Bin WU^4、4;, Yan-jun SHEN^1、1;, and Jin-mao LIU^1、1;

Author Affiliations

¹1. Institute of Talented Engineering Students, Jiangsu University, Zhenjiang 212013, China

²2. School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China

⁴4. Department of Information Engineering, Chuzhou Polytechnic, Chuzhou 239000, China

show less

DOI: 10.3964/j.issn.1000-0593(2022)05-1465-06 Cite this Article

Yang TAN, Xiao-hong WU, Bin WU, Yan-jun SHEN, Jin-mao LIU. Qualitative Analysis of Pesticide Residues on Chinese Cabbage Based on GK Improved Possibilistic C-Means Clustering[J]. Spectroscopy and Spectral Analysis, 2022, 42(5): 1465 Copy Citation Text

show less

Fig. 1. Raw FT-MIR spectral data

Download full size | View in the Article

Fig. 2. FT-MIR spectral data processed by MSC

Download full size | View in the Article

Fig. 3. The average FT-MIR spectral data processed by MSC

Download full size | View in the Article

Fig. 4. Scores plot of LDA algorithm

Download full size | View in the Article

Fig. 5. Typical value of GKIPCM

Download full size | View in the Article

m	GK聚类	GKIPCM聚类	IPCM聚类
2.0	63.89%	97.22%	91.67%
2.4	90.28%	97.22%	91.67%
2.8	94.44%	95.83%	91.67%
3.2	94.44%	95.83%	94.44%
3.6	94.44%	94.44%	94.44%
4.0	94.44%	95.83%	94.44%
4.4	94.44%	95.83%	95.83%
4.8	94.44%	97.22%	87.50%
5.2	95.83%	97.22%	86.11%
5.6	95.83%	97.22%	87.50%
6.0	97.22%	93.06%	90.28%

Table 1. Clustering accuracies of GK, GKIPCM, IPCM with different values of m

View in the Article

主成分个数	GK聚类	GKIPCM聚类	IPCM聚类
11	56.94%	51.39%	59.72%
13	56.94%	87.50%	54.17%
15	88.89%	87.50%	83.33%
17	86.11%	87.50%	86.11%
19	86.11%	94.44%	88.89%
21	47.22%	95.83%	91.67%
23	63.89%	97.22%	91.67%
25	88.89%	94.44%	91.67%
27	93.06%	94.44%	94.44%
29	86.11%	95.83%	95.83%
31	94.44%	95.83%	95.83%
33	93.06%	95.83%	91.67%
35	81.94%	93.06%	91.67%
37	93.06%	94.44%	90.28%
39	94.44%	93.06%	90.28%

Table 2. Clustering accuracies of GK, GKIPCM, IPCM with different numbers of principal components

Download Citation

Save the article for my favorites

Paper Information