25 November 2020 in Psychiatry Investigation
Objective The primary objective of this study was to predict subgroups of autism spectrum disorder (ASD) based on the Diagnostic Statistical Manual for Mental Disorders-IV Text Revision (DSM-IV-TR) by machine learning (ML). The secondary objective was to set up a ranking of Autism Diagnostic Interview-Revised (ADI-R) diagnostic algorithm items based on ML, and to confirm whether ML can sufficiently predict the diagnosis with these minimum items.Methods In the first experiment, a multiclass decision forest algorithm was applied, and the diagnostic algorithm score value of 1,269 Korean ADI-R test data was used for prediction. In the second experiment, we used 539 Korean ADI-R case data (over 48 months with verbal language) to apply mutual information to rank items used in the ADI diagnostic algorithm.Results In the first experiment, the results of predicting in the case of pervasive developmental disorder not otherwise specified as “ASD” were almost three times higher than predicting it as “No diagnosis.” In the second experiment, the top 10 ranking items of ADI-R were mainly related to the quality abnormality of communication.Conclusion In conclusion, we verified the applicability of ML in diagnosis and found that the application of artificial intelligence for rapid diagnosis or screening of ASD patients may be useful.
31 March 2017 in The International Journal of Advanced Culture Technology
29 August 2018 in International Journal of Engineering & Technology
KONEPS is the National Comprehensive Electronic Procurement System of the Public Procurement Service. If KONEPS can know the bidding possibility and trend before bidding, it will be more efficient for companies to bid. In this paper, we used in the experiment was the data of "Progress Bidding Classification" of the Procurement Information Open Portal. And preprocessing process was performed to facilitate prediction model learning. Prior to learning, preprocessed 1,158 data sets were normalized to match the range of data or to make the distribution similar. After normalization we select the number of cluster. As a result of K-Means Clustering, Biddropping is 77 ~ 80%, Budget Allocated is about 2 billion Won(₩), Biddropping is 83 ~ 87%, Budget Allocated is about 1 billion won, bid dropping is 87 ~ 90% Budget Allocated is distributed around 500 million won. And can be confirmed that the cluster is divided based on the number of enterprise 58. Through the results, it is possible to study the tendering trends through the community by learning the prediction models of the bidder companies, the number of bidders, and the tendency of the bidding business, and it will help KONEPS to develop the next generation ISP.