Loading...
Please wait, while we are loading the content...
Similar Documents
Data Stream Mining for Big Data
| Content Provider | Scilit |
|---|---|
| Author | Maurya, Chandresh Kumar |
| Copyright Year | 2020 |
| Description | Today's era is one where data is present in abundance. The massive use of technologies has given rise to what is called big data. For example, Facebook alone generates 4 PBs of data per day. The data is usually characterized by its nature, such as high volume, velocity, and variety. Mining such data for knowledge discovery means that decision making is a challenging task. In this chapter, the author focuses on streaming data which has a particular characterization. For example, data is so huge that it cannot be stored in main memory; it is also transient and fast-moving. However, the goal is to process such data in a machine that has low processing power, no access to Graphical Processing Units, or has hundreds of GBs of main memory. Streaming data exhibits non-stationary behavior (also known as concept drift in the data mining community). Besides, only one pass (sometimes two or three passes) over data is allowed. All of these issues thwart the use of traditional machine-learning algorithms for various tasks such as classification, clustering, and frequent pattern mining. In this chapter, the author presents efficient algorithms for handling streaming data. Book Name: Applied Intelligent Decision Making in Machine Learning |
| Related Links | https://content.taylorfrancis.com/books/download?dac=C2019-0-07903-0&isbn=9781003049548&doi=10.1201/9781003049548-1&format=pdf |
| DOI | 10.1201/9781003049548-1 |
| Language | English |
| Publisher | Informa UK Limited |
| Publisher Date | 2020-11-18 |
| Access Restriction | Open |
| Subject Keyword | Book Name: Applied Intelligent Decision Making in Machine Learning Computation Theory and Mathematics Decision Making Streaming Data |
| Content Type | Text |
| Resource Type | Chapter |
