Download presentation
Presentation is loading. Please wait.
Published byKathleen Kennedy Modified over 9 years ago
1
Programming Project (Last updated: August 31 st /2010) Updates: - All details of project given - Deadline: Part I: September 29 TH 2010 (in class) Part II: November 15 th 2010 (in class) Part III: December 6 th 2010 (in class)
2
Overview What: We are going to implement a IDSS for a diagnosis task (e.g., help-desk system) using Interactive CBR Representation: attribute-value pairs that vary from case to case Idea: attribute values will be asked to the user to dynamically determine which case(s) are more similar to the current situation Requirement: Should run in this classroom Part II will be presented in class: December 6 th, Part III
3
Idea IDSS’s Known Facts interaction … Alternative cases (ranked according to their similarity to the current problem) selects case We perform interactive situation elicitation User problem
4
Input The system will read two text files: one containing the list of cases and one containing the list of known facts Format of the cases (XML): text value 1 value 2 … value text
5
Input (Cont’d) Format of the types: attribute integer/real/text attribute symbol name 1 … name m
6
Input (Cont’d) Format of the file with the cases: … …
7
Input (Cont’d) Format of the facts (cont’d): value Format of the facts file: …
8
Part I Due Date: September 29 TH 2010 You should have decided the programming language that you want to use for implementing your project You should have a data structure for: Case Type List of types List of cases Fact List of facts You should have a parser working that is capable of parsing the two files (you may make your own parser, or find and use an existing one) Output: print in standard output the cases/facts read
9
Part II Due date: November 15 nd 2010 System should be capable of displaying: Attributes (distinguish those that the value is already known -i.e., facts- and those that not) Attribute weights parameter to give more weight to matches/mismatches Alternative cases Details of cases Please use windowed GUI for the interface
10
Part II The system should let users be able to: assign/change values to attributes read cases and facts files Choose to see a case in detail Select a case (any case!) as the solution Enter weights for attributes and assign other weights automatically so they add to 1 Enter parameter for matches/mismatches Due date: November 15 th 2010 (in class)
11
Part II The system should be able to: Display attributes in descending order according to: To their information gain Display cases in descending order according to their Weighted Hamming Distance and the parameter
12
Components System Interface Settings Window Facts window Cases window | Change parameter Default is set to 0.5 Change attribute weights Automatically recalculate so weights add to 1. User may set weight for 2 out of n attributes, the system will set equal weight to the remaining n-2, so that all weights add to 1 User can select to read facts and case base files | Sorted by Information gain formula Resulting values must be displayed in interface Test it on Restaurant domain (compare against slides/book for the correct numeric value) Allows changing values of attributes Sorted by (inverse) of Hamming distance Resulting values must be displayed in interface As facts are changed, the similarities must change User can view the actual case
13
Part II You should hand out a document describing: 1.Description of the project 2.The interface: components, functionality, etc 3.Formulas: Information gain/mixed formula ordering attributes Weighted Hamming distance with parameter 4. Limitations of the system/Possible extensions 5. Conclusions Due date: November 15 th 2010 (in class)
14
Part III Due date: December 6th 2010 (noon) Create a knowledge base in a domain of your choice Case base consists
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.