Data Mining - Mehmed Kantardzic [205]
12.4 DISTRIBUTED DATA MINING (DDM)
The emergence of tremendous data sets creates a growing need for analyzing them across geographical lines using distributed systems. These developments have created unprecedented opportunities for a large-scale data-driven knowledge discovery, as well as the potential for fundamental gains in scientific and business understanding. Implementations of data-mining techniques on high-performance distributed computing platforms are moving away from centralized computing models for both technical and organizational reasons. In some cases, centralization is hard because it requires these multi-terabyte data sets to be transmitted over very long distances. In others, centralization violates privacy legislation, exposes business secrets, or poses other social challenges. Common examples of such challenges arise in medicine, where relevant data might be spread among multiple parties, in commercial organizations such as drug companies or hospitals, government bodies such as the U.S. Food and Drug Administration, and nongovernment organizations such as charities and public-health organizations. Each organization is bound by regulatory restrictions, such as privacy legislation, or corporate requirements on proprietary information that could give competitors a commercial advantage. Consequently, a need exists for developing algorithms, tools, services, and infrastructure that let us mine data distributed across organizations while preserving privacy.
This shift toward intrinsically distributed, complex environments has prompted a range of new data-mining challenges. The added dimension of distributed data significantly increases the complexity of the data-mining process. Advances in computing and communication over wired and wireless networks have resulted in many pervasive distributed computing environments. Many of these environments deal with different distributed sources of voluminous data, multiple compute nodes, and distributed user community. Analyzing and monitoring these distributed data sources require a new data-mining technology designed for distributed applications. The field of DDM deals with these problems—mining distributed data by paying careful attention to the distributed resources. In addition to data being distributed, the advent of the Internet has led to increasingly complex data, including natural-language text, images, time series, sensor data, and multi-relational and object data types. To further complicate matters, systems with distributed streaming data need incremental or online mining tools that require a complete process whenever a change is made to the underlying data. Data-mining techniques involved in such a complex environment must encounter great dynamics due to changes in the system, and it can affect the overall performance of the system. Providing support for all these features in DDM systems requires novel solutions.
The Web architecture, with layered protocols and services, provides a sound framework for supporting DDM. The new framework embraces the growing trend of merging computation with communication. DDM accepts the fact that data may be inherently distributed among different loosely coupled sites, often with heterogeneous data, and connected by a network. It offers techniques to discover new knowledge through distributed data analysis and modeling using minimal communication of data. Also, interactions in a distributed system need to be implemented in a reliable, stable, and scalable way. Ultimately, systems must be able to hide this technological complexity from users.
Today, the goods