A literature study on clustering the uncertainty data
Journal Title: Indian Journal of Computer Science and Engineering - Year 2016, Vol 7, Issue 3
Abstract
Clustering is one of the important topics in data mining. The purpose of clustering is to group the similar data items. Clustering the uncertainty data is not an easy task but an essential task in data mining. Uncertain data represents the unexpected outcome. It is mostly found in the area of sensor networks. The uncertain data may have numerical and categorical data. For numerical clustering, the distance measure is based on geometric concepts such as Euclidean distance or Manhattan distance. Since the categorical data contains nominal values like [good, bad], [low, medium, high],the geometric distance measures are not applicable for categorical or nominal data. We used the numerical data (i.e.) Gas sensor data. From the literature in this field, it is noticed that very few attempts had been made for clustering gas sensor dataset using few methods and discuss the same in this paper.
Authors and Affiliations
S. SATHAPPAN , Dr. D. C. TOMAR
Keywords
Related Articles
- EP ID EP112545
- DOI -
- Views 178
- Downloads 0
Microcontroller Based Data Acquisition System For Electrical Motor Vibrations using VB software.
The electrical machine parameters under various operating conditions play a vital role in the considerations for the performance, efficiency, reliability and life of machine. Vibration signals measured at the external su...
A SURVEY OF SKYLINE PROCESSING IN VARIOUS ENVIRONMENT
Skyline queries which received an interesting attention to the database and data mining field and its main advantage is it is used for multi-criteria decision making. Advanced query operators, such as skyline queries are...
ENHANCING TRUST BELIEFS IN E-COMMERCE THROUGH WHITELIST WEBSITE SECURITY PARADIGM
In the emerging global economy, E-commerce has increasingly become a strong catalyst for economic development. Based on the observation of the E-commerce management practices in India it is felt that there is a need to i...
COMPARISON AND EVALUATION ON METRICS BASED APPROACH FOR DETECTING CODE CLONE
Many techniques were proposed for detecting code clone. In this paper we have compared the metrics based on speed, quality and their cost as these are the most that affects due to code clone. The strength and weakness of...
PERFORMANCE EVALUATION OF CONTENT BASED IMAGE RETRIEVAL FOR MEDICAL IMAGES
Content-based image retrieval (CBIR) technology benefits not only large image collections management, but also helps clinical care, biomedical research, and education. Digital images are found in X-Rays, MRI, CT which ar...