Search

To recognize an underwater target precisely is always a more difficult task for the navy compared to the air force due to the complicated watery environment which is very different from the aerial circumstance. Part of the reason is that there is much more interference under the sea. Sonar is the most efficient way to detect items in the underwater world at the present time. In this paper, a genetic-based classifier system is designed which recognizes targets by sonar fingerprints. This method will, to a certain degree, relieve the sonar man of some of his work. Experiments show that the system gains acceptable speed and accuracy in the classifying operation. The proposed underwater target classifier system is highly automatic, with quite finite hardware requirements for operation. [ABSTRACT FROM AUTHOR]

This paper aims at discovering useful knowledge from a large collection of satellite cloud images and rainfall data using image mining. The paper illustrates how important the data conversion is in building an accurate data mining architecture. Most of data about image features and rainfall data are values or vectors, which are not fit for mining directly. We present two approaches to implement the conversion of data: a clustering algorithm and a fuzzy clustering method (FCM). The clustering algorithm is used to map the numerical value to categorical value. The FCM implements the conversion of feature vector. Finally, the association rules are determined using the Apriori algorithm. The experiment results show that the acquired association rules are consistent with the fact and the results are satisfying. Keywords: Association rules mining, satellite cloud image, clustering partition. [ABSTRACT FROM AUTHOR]