Machine Learning & Data Mining Methods in Diabetes Research
How It Works
In reality, the organizations often have the great quantity of data stored in the databases. The large size of data in terms of the number of attributes and objects make the analysis process becomes very difficult as the data are complex. In order to overcome this problem, the use of sufficient number of attributes and objects will contribute to get the best solution. There are many techniques which can be employed to reduce the number of attributes in the dataset. In this project, two core techniques, namely Rough Set theory and Case-Based Reasoning were applied to the medical dataset. These algorithms were the core algorithm used for developing the system and the system was fully developed using VB.NET programming language and SQL server CE2000.