ÀΰøÁö´ÉÀ» Àû¿ëÇÑ ½Ã·Âµ¥ÀÌÅÍ ºÐ¼® : ±â°èÇнÀ ¸ðµ¨°£ ºñ±³ ¹× ÃÖÀû¸ðµ¨Á¦½Ã
Analysis of Vision Acuity (V.A.) using Artificial Intelligence (A.I.): Comparison of Machine Learning Models and Proposition of an Optimized Model

´ëÇѽðúÇÐȸÁö 2020³â 22±Ç 3È£ p.229 ~ p.236

À¯Çü¼®(Ryu Hyeong-Suk) - Korea University Department of Brain and Cognitive Engineering
·ùȸ¼º(Ryu Hoe-Sung) - Korea University Department of Artificial Intelligence
(Wallraven Christian) - Korea University Department of Brain and Cognitive Engineering

Abstract

¸ñÀû : ÀΰøÁö´ÉÀÇ ±â°èÇнÀ ¶Ç´Â ½ÉÃþÇнÀÀ» ÀÌ¿ëÇÑ ¿¬±¸°¡ ´Ù¾çÇÑ ºÐ¾ß¿¡¼­ ½ÃµµµÇ°í ÀÖ´Ù. º» ¿¬±¸´Â °ø°ø½Ã·Âµ¥ÀÌÅ͸¦ ÀÚµ¿È­ ¼öÁýÇÏ°í, ¼öÁýÇÑ µ¥ÀÌÅ͸¦ ±â°èÇнÀ¿¡ Àû¿ë ¹× ¿¹ÃøÇÏ¿´´Ù. ´Ù¾çÇÑ ÇнÀ¸ðµ¨°£ ¼º´ÉÀ» ºñ±³ÇÔÀ¸·Î½á, ½Ã°úÇко߿¡¼­ Àû¿ë °¡´ÉÇÑ ±â°èÇнÀ ÃÖÀûÈ­¸ðµ¨À» Á¦½ÃÇÔ¿¡ ÀÖ´Ù.

¹æ¹ý : ±¹¹Î°Ç°­º¸Çè(NHISS) ¹× Åë°èÆ÷ÅÐ(KOSIS)¿¡ ¹ßÇ¥µÈ ±¹¹Î ½Ã·ÂºÐÆ÷ ÇöȲ°ü·Ã ÀڷḦ ƯÁ¤ »öÀÎÀ» Æ÷ÇÔÇÏ´Â ÀÚ·á°Ë»ö±â¹ýÀÎ Å©·Ñ¸µ(crawling)À» »ç¿ëÇÏ¿© °Ë»ö ¹× ¼öÁýÀ» ÀÚµ¿È­ÇÏ¿´´Ù. 2011³âºÎÅÍ 2018³â±îÁö º¸°íµÈ ¸ðµç ÀڷḦ ¼öÁýÇÏ¿´À¸¸ç, µ¥ÀÌÅÍ ÇнÀÀ» À§ÇØ Linear Regression, LASSO, Ridge, Elastic Net, Huber Regression, LASSO/LARS, Passive Aggressive Regressor ±×¸®°í Pansacregressor ÃÑ 8°³ ¸ðµ¨À» »ç¿ëÇÏ¿© °¢°¢ µ¥ÀÌÅÍ ÇнÀÇÏ¿´´Ù.

°á°ú : ¼öÁýÇÑ µ¥ÀÌÅ͸¦ ±â¹ÝÀ¸·Î ±â°èÇнÀ ¸ðµ¨À» ÅëÇØ 2018³âÀ» ¿¹ÃøÇÏ¿´´Ù. °¢ ¸ðµ¨°£ 2018³âµµ ½ÇÁ¦-¿¹Ãøµ¥ÀÌÅÍ Â÷À̸¦ MAE(Mean Absolute Error)¿Í RMSE(Root Mean Square Error) Á¡¼ö·Î °¢°¢ ³ªÅ¸³Â´Ù. ÇнÀ¸ðµ¨ º° Â÷ÀÌ Áß MAE Æò°¡°á°ú ¸ðµ¨°£ ¿ì/Á Linear Regression(0.22/0.22), LASSO(0.83/0.81), RIDGE(0.31/0.31), Elastic Net(0.86/0.84), Huber Regression(0.14/0.07), LASSO/LARS(0.15/0.14), Passive Aggressive Regressor (0.29/0.18) ±×¸®°í RANSA Regressor(0.22/0.22)¸¦ º¸¿´´Ù. RMSE¿¡¼­ Linear Regression(0.40/0.40), LASSO (1.08/1.06), Ridge(0.54/0.54), Elastic Net(1.19/1.17), Huber Regression(0.20/0.20), LASSO/LARS(0.24/0.23), Passive Aggressive Regressor(0.21/0.58) ±×¸®°í RANSA Regressor(0.40/0.40) °¢°¢ ³ªÅ¸³Â´Ù.

°á·Ð : º» ¿¬±¸´Â ÀÚµ¿È­ ÀÚ·á°Ë»ö ¹× ¼öÁýÀ» À§ÇÑ Å©·Ñ¸µ ±â¹ýÀ» ÀÌ¿ëÇÏ¿© µ¥ÀÌÅ͸¦ ¼öÁýÇÏ¿´´Ù. À̸¦ ±â¹ÝÀ¸·Î °íÀü ¼±Çü¸ðµ¨À» ±â°èÇнÀ¿¡ Àû¿ëÇÒ ¼ö ÀÖµµ·Ï ÇÏ°í, µ¥ÀÌÅÍ ÇнÀÀ» À§ÇÑ 8°³ ÇнÀ¸ðµ¨µé °£ ¼º´ÉÀ» ºñ±³ÇÏ¿´´Ù.
Purpose : Recently, the use of AI in research has shown widespread investigation in various fields.In this study, we performed an automated collection of vision acuity (V.A.) data, and trained mechanical learning models for prediction. By comparing performance between eight different learning models, we present a machine learning optimization model applicable in the field of vision science.

Methods : Automated search and collection of data related to the national vision distribution status published in the National Health Insurance Sharing Service (NHISS) and the Korean Statistical Information Service (KOSIS) were performed through crawling, a data retrieval technique that includes specific indexes. Reported data from 2011 to 2018 were collected, and were studied using all of eight different models for data analysis such as Linear Region, LASSO, Ridge, Elastic Net, Huber Region, LASSO Lars, Passive Aggregation and Pansacrerestor.

Results : V.A. of the 2018 portion of the dataset was predicted in the test session. The difference between ground truth and prediction from each model was expressed as MAE (Mean Absolute Error) and RMSE (Root Mean Square Error) scores, respectively. MAE evaluation results for model difference in Right/Left were as the following: Linear Region(0.22/0.22), LASSO(0.83/0.81), Ridge(0.31/0.31), Elastic Net(0.86/0.84), HUBER Region(0.14/0.07), LASSO/LARS(0.15/0.14), Passive Aggressive Regressior(0.29/0.18), and RANSA Regressor(0.22/0.22). In RMSE, it also shows Linear Region(0.40/0.40), LASSO(1.08/1.06), Ridge(0.54/0.54), Elastic Net(1.19/1.17), Huber Region(0.20/0.20), LASSO/LARS(0.24/0.23), Passive Aggregation Regressor(0.21/0.58), and RANSA Regressor (0.40/0.40).

Conclusion : In this study, we collected data using crawling techniques for automatic data retrieval and collection. Based on the data, classical linear machine learning models were applied for prediction, and performance of the eight machine learning models was compared for performance.

Å°¿öµå

ÀΰøÁö´É, µ¥ÀÌÅÍÇнÀ, ±â°èÇнÀ
Artificial intelligence, Data Learning, Machine Learning
¿ø¹® ¹× ¸µÅ©¾Æ¿ô Á¤º¸
µîÀçÀú³Î Á¤º¸
ÇмúÁøÈïÀç´Ü(KCI) 
ÁÖÁ¦ÄÚµå
ÁÖÁ¦¸í(Target field)
¿¬±¸´ë»ó(Population)
¿¬±¸Âü¿©(Sample size)
´ë»ó¼ºº°(Gender)
Áúº´Æ¯¼º(Condition Category)
¿¬±¸È¯°æ(Setting)
¿¬±¸¼³°è(Study Design)
¿¬±¸±â°£(Period)
ÁßÀç¹æ¹ý(Intervention Type)
ÁßÀç¸íĪ(Intervention Name)
Å°¿öµå(Keyword)
À¯È¿¼º°á°ú(Recomendation)
Based on the data, classical linear machine learning models were applied for prediction, and performance of the eight machine learning models was compared for performance.
¿¬±¸ºñÁö¿ø(Fund Source)
±Ù°Å¼öÁØÆò°¡(Evidence Hierarchy)
ÃâÆdz⵵(Year)
Âü¿©ÀúÀÚ¼ö(Authors)
´ëÇ¥ÀúÀÚ
KCDÄÚµå
ICD 03
°Ç°­º¸ÇèÄÚµå