• Journal of Korean Society of Transportation
• /
• v.22 no.3 s.74
• /
• pp.127-135
• /
• 2004

교차로 안전성 진단과 관련된 기존의 연구는 교차로 상에서 발생한 사고 자료에 기초하여 교차로 기하구조 요소, 교통량 및 신호운영방법 등과 관련된 요인을 변수로 사용하여 교통사고건수 예측모형 개발에 관한 연구가 대부분이다. 그러나, 분석하고자 하는 대상 교차로의 사고건수 예측모형을 개발하기 위해 필요한 교통사고 자료의 경우 단 기일에 걸쳐 획득되지 않으며 몇 년간의 사고 자료를 요구할 수도 있다. 이러한 자료를 이용하더라도 사고 발생 기간동안 교차로 사고에 영향을 미치는 요인(교차로 운영방법, 기하구조 등)이 변화될 수도 있다는 문제점을 지닌다. 이와 같은 이유로 교차로 안전성을 진단하는데 있어 기존 교통사고 자료는 언제나 절대적인 자료가 될 수 없다. 이에 대한 보완책으로, 3일에서 5일정도의 조사 자료만으로도 안전성 진단이 가능한 상충자료를 이용하여 교차로 안전성 진단을 할 수 있다. 본 연구는 기존사고 자료를 이용하여 사고 발생에 기인하는 여러 변수들을 교통사고심각도와의 상관관계를 분석하고, 상관관계가 높은 변수를 이용하여 신경망 사고심각도 예측모형을 개발하였으며, 모형 검증을 위해 다중회귀사고심각도 예측모형을 개발하여 비교 평가한 결과 신경망 사고심각도 예측모형의 예측력이 우수한 것으로 나타났다. 현장에서 조사된 상충자료를 신경망 사고심각도 예측모형에 적용하여 상충이 사고로 연결 될 경우 사고심각도를 예측하였으며, 예측된 사고심각도에 가중치를 부여하여 대상 교차로 위험우선순위를 결정한 결과 사고비용에 기초한 위험우선순위 결정법과 같은 순위의 결과를 도출하였다.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.9
• /
• pp.339-348
• /
• 2021

In recent software defect prediction research, defect prediction between cross projects and cross-version projects are actively studied. Cross-version defect prediction studies assume WP(Within-Project) so far. However, in the CV(Cross-Version) environment, the previous work does not consider the distribution difference between project versions is important. In this study, we propose an automated Bayesian optimization framework that considers distribution differences between different versions. Through this, it automatically selects whether to perform transfer learning according to the difference in distribution. This framework is a technique that optimizes the distribution difference between versions, transfer learning, and hyper-parameters of the classifier. We confirmed that the method of automatically selecting whether to perform transfer learning based on the distribution difference is effective through experiments. Moreover, we can see that using our optimization framework is effective in improving performance and, as a result, can reduce software inspection effort. This is expected to support practical quality assurance activities for new version projects in a cross-version project environment.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.4 no.2
• /
• pp.1-11
• /
• 1984

This aims of this study is to analyse the correlationship between traffic accident s and traffic characteristic variables in at-grade intersections of urban area, to build up an accident forecasting model and to propose an evaluation method of hazardous at-grade intersections. The accident forecasting model is formulated by the use of residual indexes that is selected by principal component analysis and its statistical significance is tested by step-wise regression analysis. Effective countermeasures for safety can be established on the basis of identifying high accident intersections, because the validity of this model was examined and found to coincide with real world situations.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.370-370
• /
• 2021

태풍으로 인한 피해를 줄이기 위해 경로, 강도 및 폭풍해일의 사전 예측은 매우 중요하다. 이중, 태풍의 경로와는 달리 강도 및 폭풍해일의 예측에 있어서 바람장은 수치 모델의 초기 입력값으로 요구되기 때문에 정확한 바람장 정보는 필수적이다. 대기 바람장 예측 방법은 크게 해석적 모델링, 라디오존데 측정과 위성 사진을 통한 산출로 구분할 수 있다. Holland의 해석적 모델링은 비교적 적은 입력값이 필요하지만 정확도가 낮고, 라디오존데 측정은 정확도가 높지만 점 측정에 가깝기 때문에 이차원 바람장을 산출하기에 한계가 있다. 위성 사진을 통한 바람장 산출은 위성기술의 고도화로 관측 채널 수 및 시공간 해상도가 크게 증가하고 있기 때문에 다양한 기법들이 개발되고 있다. 본 연구에서는 생성적 적대 신경망 (Generative Adversarial Network, GAN)을 통해 일련의 연속된 과거 적외 채널 위성 사진 흐름의 패턴을 학습시켜 미래 위성 사진을 예측하고, 예측된 연속적인 위성 사진들의 교차상관 (cross-correlation)을 통해 바람장을 산출하였다. GAN을 적용함에 있어 2011년부터 2019년까지 한반도 근방에 접근했던 태풍 중에 4등급 이상인 68개의 태풍의 한 시간 간격으로 촬영된 총 15,683개의 위성 사진을 학습시켜 생성된 이미지들은 실측 위성 사진들과 매우 유사한 것으로 나타났다. 또한, 생성된 이미지들의 교차상관으로 얻어진 바람장 벡터들의 풍향, 풍속, 벡터 일관성 및 수치 모델과의 비교를 통해 각각의 벡터들의 품질 계수를 구하고 정확도가 높은 벡터들만 결과에 포함하였다. 마지막으로 국내 6개의 라디오존데 관측점에서의 실측 벡터와의 비교를 통해 본 연구 결과의 실효성을 검증하였다. 본 연구에서 확장하여, 이와 같이 AI 기법과 이미지 교차상관 기법을 사용하여 얻어진 바람장으로부터 태풍 강도예측에 필요한 요소인 태풍의 눈의 위치, 최고 속도와 태풍 반경을 직접적으로 산출할 수 있고. 이러한 위성 사진을 기반으로 한 바람장은 단순화된 해석적 바람장을 대체하여 폭풍 해일 모델링의 예측 성능 개선에 기여할 것으로 보여진다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.6
• /
• pp.1-16
• /
• 2023

Accurate traffic information prediction is considered to be one of the most important aspects of intelligent transport systems(ITS), as it can be used to guide users of transportation facilities to avoid congested routes. Various deep learning models have been developed for accurate traffic prediction. Recently, ensemble techniques have been utilized to combine the strengths and weaknesses of various models in various ways to improve prediction accuracy and stability. Therefore, in this study, we developed and evaluated a traffic information prediction model using various deep learning models, and evaluated the performance of the developed deep learning models as a stacking ensemble. The individual models showed error rates within 10% for traffic volume prediction and 3% for speed prediction. The ensemble model showed higher accuracy compared to other models when no cross-validation was performed, and when cross-validation was performed, it showed a uniform error rate in long-term forecasting.

• The Journal of Bigdata
• /
• v.7 no.2
• /
• pp.195-204
• /
• 2022

The tourism industry is facing a crisis due to the recent COVID-19 pandemic, and it is vital to improving profitability to overcome it. In situations such as COVID-19, it would be more efficient to sell additional products other than guest rooms to customers who have visited to increase the unit price rather than adopting an aggressive sales strategy to increase room occupancy to increase profits. Previous tourism studies have used machine learning techniques for demand forecasting, but there have been few studies on cross-selling forecasting. Also, in a broader sense, a resort is the same accommodation industry as a hotel. However, there is no study specialized in the resort industry, which is operated based on a membership system and has facilities suitable for lodging and cooking. Therefore, in this study, we propose a cross-selling prediction model using various machine learning techniques with an actual resort company's accommodation data. In addition, by applying the explainable artificial intelligence XAI(eXplainable AI) technique, we intend to interpret what factors affect cross-selling and confirm how they affect cross-selling through empirical analysis.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.39 no.1
• /
• pp.73-80
• /
• 2019

Traffic Safety and efficient Road Traffic Policy of Traffic management came into effect over the certain size of the road like main road. Comparatively, Safety for Living street is deteriorated. Especially, Vehicle are usually priority to the life-zone street, even though Safety for the Passengers are essential to the life-zone street in the residential area. Improvement for the Living street has not been achieved In this study, To suggest Intersection Notifications standard of installation in Living Street, We execute on-site survey in priority to Gwangju Metropolitan City. Furthermore, After We suggest experimental value for the Intersection Notifications' standard of installation Prediction model in the Living street, Intersection Notifications compare & veritfy experimental value to the installation point's value to suggest the standard of installation in the living street. As a result, We can prevent frequent traffic accident in the Living Street. Furthermore, We are judged by installation of intersection Notifications considering stability and convenience to the passengers who are using the living street.

• Korean Chemical Engineering Research
• /
• v.59 no.4
• /
• pp.532-541
• /
• 2021

Recently, research on the application of artificial intelligence in the chemical process has been increasing rapidly. However, overfitting is a significant problem that prevents the model from being generalized well to predict unseen data on test data, as well as observed training data. Cross validation is one of the ways to solve the overfitting problem. In this study, the time-series cross validation method was applied to optimize the number of batch and epoch in the hyperparameters of the prediction model for the 2,3-BDO distillation process, and it compared with K-fold cross validation generally used. As a result, the RMSE of the model with time-series cross validation was lower by 9.06%, and the MAPE was higher by 0.61% than the model with K-fold cross validation. Also, the calculation time was 198.29 sec less than the K-fold cross validation method.

• Journal of Korean Society of Transportation
• /
• v.27 no.3
• /
• pp.91-102
• /
• 2009

A traffic accident prediction model developed using various design variables(road design variables, geometric variables, and traffic environmental variables) is one of the most important factors to safety design evaluation system for roads. However, statistical accident models have a crucial problem not applicable for all intersections. To make up this problem, this study developed AMFs(Accident Modification Factors) through statistical modeling methods, historical accident databases, judgment from traffic experts, and literature review by considering design variable's characteristics, traffic accident rates, and traffic accident frequency. AMFs developed in this study include exclusive left-turn lane, exclusive right-turn lane, sight distance, and intersection angle. Predictabilities of the developed AMFs and the existing accident prediction models are compared with real accident historical data. The results showed that performances of the developed AMFs are superior to the existing statistical accident prediction models. These findings show that AMFs should be considered as a important process to develop safety design evaluation algorithms. Additionally, AMFs could be used as an index that can judge the impact of corresponding design variables on accidents in rural intersections.

• The Journal of the Acoustical Society of Korea
• /
• v.32 no.3
• /
• pp.227-236
• /
• 2013

In this paper, we present a vocal suppression algorithm that can enhance the quality of music signal coded using Spatial Audio Object Coding (SAOC) in Karaoke mode. The residual vocal component in the coded music signal is estimated by using a cross prediction method in which the music signal coded in Karaoke mode is used as the primary input and the vocal signal coded in Solo mode is used as a reference. However, the signals are extracted from the same downmix signal and highly correlated, so that the music signal can be severely damaged by the cross prediction. To prevent this, a psycho-acoustic disturbance rule is proposed, in which the level of disturbance to the reference input of the cross prediction filter is adapted according to the auditory masking property. Objective and subjective test were performed and the results confirm that the proposed algorithm offers improved quality.