Trans. Korean Soc. Noise Vib. Eng., 29(5) : 577~583, 2019 한국소음진동공학회논문집 제29 권 제5 호, pp. 577~583, 2019 https://doi.org/10.5050/KSNVE.2019.29.5.577 ISSN 1598-2785(Print), ISSN 2287-5476(Online) Trans. Korean Soc. Noise Vib. Eng., 29(5) : 577~583, 2019 ┃ 577 1) 1. 서 론 도심 지역 도로통 소 및 대기오염 물질 주된 발생 , 도시 거주민 주거 환 신 체적 정신적 건강 협하 다. 도로는 도시가 지되기 해 필수적 사회적 기반시설로, 를 축 소 또는 제거하여 소 및 대기오염 물질 저감 하 는 것 현실적로 불가능하다. 따라서 도로에서 방 출되는 소 전달로 상 흡, 반사 및 회절 등  려하는 도로통소 예측식 용하여 예측 모델 축, 도시 현재 또는 미래 통량 적용 하여 성한 소지도로 도로통소 리하  다. 러한 도로통소 예측 정 상용 소지도 성 소프트어를 기반로 수행된다. 는 소 발생 및 전달 정 수학적로 산하는 것로 규 모가 큰 역도시를 대상로 수행하는  많 시 간 비용 소요된다. 따라서 시간, 비용 등 절약 하여 간단하게 도심 지역 도로통소 예측하는 통적 도로통소 예측 방법 연가 필요하다. † Corresponding Author ; Member, School of Environmental Engine- ering, University of Seoul E-mail : schang@uos.ac.kr * Member, Department of Energy and Environmental System Engineering, University of Seoul ** Member, Korean Educational Environments Protection Agency *** Department of Statistics, University of Seoul # A part of this paper was presented at the KSNVE 2018 Annual Autumn Conference ‡ Recommended by Editor Jong Kwan Ryu The Korean Society for Noise and Vibration Engineering 도로통소 도시성요소  분석 한 신망 모형 Artificial Neural Network Model Development based on Road-traffic Noise and Urban Form Indicators 김 필 립 * · 류 훈 재 ** · 전 종 준 *** ·  서  † Phillip Kim * , Hunjae Ryu ** , Jong June Jeon *** and Seo Il Chang † (Received May 9, 2019 ; Revised August 19, 2019 ; Accepted August 19, 2019) Key Words : Artificial Neural Network(신망), Ordinary Least Squares Model(통상최소승 모형), Road-traffic Noise(도로통소), Urban Form Indicator(도시 성 요소) ABSTRACT Road-traffic noise is a critical factor that affects the life and health environments of urban inhabitants. In Korea, noise maps of cities created by commercial noise mapping software are used to manage road-traffic noise. This makes the management of noisy environments easy, but in the case of metropolitan cities, the creation of noise maps is time-consuming and costly. In this study, the relationship between road-traffic noise and urban form indicators (i.e., population, roads, build- ings, and land use), showing the characteristics of a city, were analyzed to predict the road-traffic noise level using a statistical model. The road-traffic noise level predicted by the artificial neural network method was compared to that using the ordinary least squares method: The adjusted co- efficient of determination (R 2 ) of the former method was 0.5, while that of the latter model was 0.44. Furthermore, the floor space index was used as the urban form indicator, which has the largest effect on the road-traffic noise level.