As the most widely used clustering algorithm nowadays, the K-means algorithm has been applied in diverse fields. It is characterized with a fast calculation speed and a simple algorithm. It is, however, nonetheless beset by a number of problems. One difficulty is that choosing the starting center at random will have a negative influence on the clustering result. Second, outliers are susceptible to the K-means algorithm. Third, such an algorithm still has a significant time cost. To address these concerns, this work introduces the AGK Adaptive-GK method, which takes use of the grid clustering technique's benefits. Our AGK can accurately identify an initial center, increase the accuracy of the standard K-means method, and lower the algorithm's computation complexity. We did a thorough study of our AGK on a variety of data sets, and the findings show that it is accurate and efficient.
KEYWORDS: Feature extraction, Principal component analysis, Data fusion, Data analysis, Mining, Image segmentation, Data modeling, Software development, Algorithm development, Sun
The redundant information contained in feature can be reduced and the accuracy of data analysis is improved via extracting the features from the data set. The existing methods to extract the feature ignoring the information contained in the data vector of feature. In this paper, the similarity between data features is firstly calculated via multiple methods to form the similarity vector of feature. Then the adaptive weighted clustering ensemble is proposed to cluster the similarity vector of feature to partitioning the feature subspaces. Secondly, utilizing the characteristics of the data vector of feature, the weights of the features in the subspace are calculated, and then the effective features are extracted using the linear weighted method. In the experiments, the result shows that the proposed method can significantly improve the accuracy of the data analysis.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.