Using unsupervised method to classify the space of river pollution in the image of the satellites

• Main Authors: Ke-Han Yan, 顏可翰
• Other Authors: Wei-Chin Chang
• Format: Others
• Language: zh-TW
• Published: 2008
• Online Access: http://ndltd.ncl.edu.tw/handle/zd24ta

碩士 === 國立雲林科技大學 === 防災與環境工程研究所 === 96 === The rivers are important resources in the natural environment. With the development of industries and urban cities, environment and water resource are being exploited. This makes the quality of life influenced. So how to offer accurate and changing the pollution of river in the large range, it is a main purpose of this research. This story uses a two unsupervised fuzzy and probabilistic clustering method in order to research how predict the space of rivers is polluted. The river pollution includes many kinds of different water quality. But it is to need to possess various and representative study sample to utilize the supervised type to classify. Unsupervised method does not needing to study samples, but need local value as monitoring and classifying the basis finally. This method improves many traditional unsupervised methods that have been set up the number of clusters, and the automatic optimization classification. It is classing the pollution of river in the image of the satellites. In addition improve the accuracy predicted to the pollution of river, input the best variable association that is screened, in order to set up the prediction system that the space of river pollution in the image of the satellites. The method tests the known database, the variable is screened again, is electing 8 variables of inputting in the water pollution classification of rivers. Match up the existing river pollution index in order to imitate the space distribution concept picture of the water pollution. Make method input many optimization variable as in the water pollution classification of rivers have as primitive band. And the rate of accuracy of this method also has better rate of accuracy than traditional unsupervised method (ISODATA). Test that examines River Pollution Index that stands on hand, classify the rate of accuracy of the river pollution that more than 75%. Though is longer in the operation time of method, but still in the time range with applicable reality. Reveal the feasibility of this way is imitating the pollution of rivers to classify and monitor.