Extraction of Chemical Parameter Characterizing the Upper, Middle and Lower Stream by Principal Component Analysis and Neural Network
- The Case of Tamagawa River, Tokyo, Japan -

Junko KAMBEa, Tomoko FUKUDAb, c, Umpei NAGASHIMAd* and Tomoo AOYAMAe

aFaculty of Foreign Language, Daito Bunka University
1-9-1 Takashimadaira, Itabashi, Tokyo 175-8571, Japan
bDepartment of Life Arts, Faculty of Home Economics, Japan Women's University
2-8-1 Mejirodai, Bunkyo-ku, Tokyo 112-8681, Japan
cBestsystems Co. Ltd.
4-15-2-1-204 Matsushiro, Tsukuba, Ibaraki 305-0035, Japan
dTsukuba Advanced Computing Center, National Institute for Advanced Industrial Science and Technology
1-1 Higashi, Tsukuba, Ibaraki 305-8565 Japan
eFaculty of Technology, Miyazaki University
Gakuenkihanadai Nishi, Miyazaki 889-2192 Japan
*e-mail:

(Received: February 28, 2001; Accepted for publication: October 10, 2001; Published on Web: December 7, 2001)

We attempted to extract chemical parameter characterizing the upper, middle and lower stream by the principal component and the analysis of differential coefficients of input parameter for perceptron type neural network with three layers. The analysis of differential coefficients of input parameter for perceptron type neural network was developed by Aoyama [2] and was newly equipped into a neural network simulator Neco. The data used are 12 chemical parameters at 17 points along the main stream of the Tamagawa river in Tokyo, Japan, for 1997-1999 [3].
The K-L plot of the first and second principal components (Figure 4) well divides 17 points into three groups corresponding to the three regions: upper, middle and lower streams, respectively. From results of the analysis of differential coefficients of input parameter for perceptron type neural network, Cl-, COND and NH4-N have relatively large differential coefficients and divide middle and lower streams. DO and pH are large in upper stream of Tamagawa river (Figure 5). The first principal component classifies well two groups: upper and middle-lower streams on the K-L plots. This result suggests that the water contamination is more drastic in the midstream of Tamagawa river than downstream. The water contamination in midstream should be decreased for keeping Tamagawa river clean.

Keywords: Water Contamination, Principal Component Analysis, Differential Coefficients Analysis of Input Parameter for Neural Network, Upper Stream, Middle Stream, Lower Stream


Abstract in Japanese

Text in Japanese

PDF file(210kB)


Author Index
Keyword Index
Return