KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Subject: search.filters.subject.Case-Based Reasoning

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An ELECTRE III Based CBR Approach to Combinatorial Portfolio Selection
    (2019-06-01)
    Chanvarasuth, Pisit
    ;
    Boongasame, Laor
    ;
    Boonjing, Veera
    Investors generally learn from historical data and use it to improve future investment decisions. However, existing portfolio selection research rarely considers such a concept. This paper proposes a novel approach to the combinatorial portfolio selection problem. Our solution employs the Case-Based Reasoning (CBR) approach with ELECTRE III, based on the Industry Classification Benchmark standards. The target stocks are ranked based on their similarities to a reference case, allowing specified selection criteria. Similarities are calculated based on selected ELECTRE III metrics. Experimental results with the Stock Exchange of Thailand data show that our CBR approach with ELECTRE III outperforms the traditional method.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Online Thai medical diagnostic system using case-based reasoning
    (2014-01-01)
    Muangprathub, Jirapond
    ;
    Boonjing, Veera
    The paper proposes a case-based medical diagnostic system supporting queries in Thai language. The system is intended to reduce both expense and time required by doctor's visits by giving a preliminary diagnosis. It is a web based application established with PHP language and a MySQL database. MySQL is used in our system for storing previous diagnoses of cases entered by doctors. The users can query by inputting their symptoms in Thai. The inputs are used to select the best matches among prior cases in the database. We evaluated our proposed system with 33 queries for each of 50 diseases. The result showed a 67.87% accuracy of diagnoses, with a 99% confidence interval from 53.98 to 81.74%.