Data Structure
Networking
RDBMS
Operating System
Java
MS Excel
iOS
HTML
CSS
Android
Python
C Programming
C++
C#
MongoDB
MySQL
Javascript
PHP
Physics
Chemistry
Biology
Mathematics
English
Economics
Psychology
Social Studies
Fashion Studies
Legal Studies
- Selected Reading
- UPSC IAS Exams Notes
- Developer's Best Practices
- Questions and Answers
- Effective Resume Writing
- HR Interview Questions
- Computer Glossary
- Who is Who
What is CBR?
CBR stands for Case-based reasoning. CBR classifiers need a database of problem solutions to clarify new problems. Unlike nearest-neighbor classifiers, which save training tuples as points in Euclidean space, CBR saves the tuples or “cases” for problem solving as difficult symbolic representation.
There are various business applications of CBR include problem resolution for customer service help desks, where cases describe product-related diagnostic problems. CBR has been used to areas including engineering and law, where cases are technical designs or legal rulings, accordingly.
Medical education is an application for CBR, where patient case histories and treatments are used to support diagnose and consider new patients. When given a new case to define, a case-based reasoner will tests if an identical training case continue. If one is discovered, then the accompanying solution to that case is restored.
If no interchangeable case is discovered, then the case-based reasoner will search for training cases having elements that are same to those of the new case. These training cases can be treated as neighbors of the new case.
If cases are defined as graphs, this contains searching for subgraphs that are same to subgraphs inside the new case. The case-based reasoner tries to set the solutions of the neighboring training cases to suggest a solution for the new case. If incompatibilities increase with the single solutions, therefore backtracking to search for different solutions can be important.
The case-based reasoner can use background knowledge and problem-solving methods to propose a possible combined solution. There are several challenges in case-based reasoning include discovering a best similarity metric (e.g., for connecting subgraphs) and suitable methods for combining solutions.
There are other challenges include the selection of salient features for indexing training cases and the development of efficient indexing techniques. A trade-off between accuracy and efficiency evolves as the number of stored cases becomes very large.
There are two approaches in CBR are as follows −
Data Mining is only one element of the KDD process which can include accessing multiple files, cleaning data, and executing results. The data mining search can also be time-consuming. The data about the search results and the entire KDD process can be stored in a case so that more time will not be spent on mining the same data more than once.
CBR can be used in supporting some background knowledge about nature in a database, for example, the weight of features for a classifier can be understand from the CBR tool. In a Bayesian network, the mechanism of the network can be set up by the CBR tool (model construction), utilizing its "expert knowledge" and the parameters understand using DM algorithms.
283 Views
To Continue Learning Please Login