Stream data mining: techniques, issues and challenges

Type :

Term papers

Pages :

5 pages

Format :

.pdf

Published date :

10/09/2009

Category :

Science & technology

Sub category :

Computer science

Oboulo.com selection criteria

$ 10.95 Add to cart

Summary :

Abstract
Introduction
Theoretical foundations
1. Data based techniques
2. Sampling
3. Load shedding
4. Sketching
5. Synopsis data structures
6. Aggregation
7. Task based techniques
8. Approximation algorithms
9. Sliding window
10. Algorithm output granularity
Mining techniques
1. Clustering dynamic and evolving data system
2. Stream classification
3. Stream frequent pattern analysis
4. Time series analysis
Streaming analysis systems
Research issues
Conclusion
References

Abstract

data stream mining is the process of extracting knowledge structures from continuous, rapid data records. Examples of data streams include computer network traffic, phone conversations, ATM transactions, web searches and sensor data. data mining is the interdisciplinary field of study that can extract models and patterns from large amounts of information stored in data repositories. data mining is increasingly recognized as a key technique to analyzing and understanding the flood of digital data in many organizations. data can grow without limit at a high rate of millions of data items per day. Domains with these continuous data streams include credit fraud detection, mining e-commerce data, web mining, stock analysis, network intrusion detection, telecommunication data mining, and counter terrorism data mining. mining data streams brings unique opportunities but also new challenges. The intelligent data analysis has passed through a number of stages. Each stage addresses novel research issues that have arisen.