선택한 단어 수는 입니다.
최소 단어 이상 선택하여야 합니다.
최소 단어 이상 선택하여야 합니다.
선택한 단어 수는 30입니다.
최대 10 단어까지만 선택 가능합니다.
최대 10 단어까지만 선택 가능합니다.
제안 방법
- SOM was proven to be an effective tool for semantic correspondence, but it was tested with clean data. In our study, we used a more complex database, the customer database, to test the robustness of SOM in clustering a different kind of data.
- We extracted 14 data patterns by computing the summary of statistics of the instances or records of customer database. We compute for the count of missing values, count of distinct values, average length, standard deviation of length, min and max of length, average number of digits and average number of characters, min and max of percentage of digits in the records of each attribute, average of percentage of digits in the record of each attribute, standard deviation of the percentage of digits in the record of each attribute, min and max of percentage of character in the records of each attribute, average of percentage of character in the record of each attribute, standard deviation of the percentage of character in the record of each attribute.
이론/모형
- We extracted 45 features using naming similarity, where each attribute from the two customer database are compared using 1-edit distance[8] algorithm to compute for the similarity of two attributes.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.