Thursday, 24 January 2013

Data in Knowledge Discovery

Discuss various kinds of data in knowledge discovery process??

Data Stream Mining
            Data Stream Mining is the process of extracting knowledge structures from continuous, rapid data records. A data stream is an ordered sequence of instances that in many applications of data stream mining can be read only once or a small number of times using limited computing and storage capabilities.
 Examples of data streams include computer network traffic, phone conversations, ATM transactions, web searches, and sensor data. 

Sensor data:
            Sensor data is information captured at an instance in time that represents the condition, or state, of one or more databases. The data can be used for later analysis and policy evaluation. The sensor data is stored in the Sensor Data repository as a group (or a set) of records made up of data elements

Time series data:
            Traditional database systems bring rows of data into L1/L2 cache for processing. But time series data – such as trades and quotes – are naturally columnar, and are better handled by a time series database approach that fetches such records into CPU cache as columns, thereby avoiding flooding the cache with unwanted data.

Temporal Databases

            Temporal data stored in a temporal database is  a time period attached to the data expresses when it was valid or stored in the database.

Heterogeneous database system 
            A Heterogeneous database system is an automated (or semi-automated) system for the integration of heterogeneous, disparate database management systems to present a user with a single, unified query interface.
            Heterogeneous database systems (HDBs) are computational models and software implementations that provide heterogeneous database integration.

legacy databases
            In a more specific context, it can refer to a database system that was inherited by a team from previous project owners.