• 대한교통학회지
• /
• 제23권3호
• /
• pp.125-136
• /
• 2005

현재 도로사업의 타당성 조사 시 사용하는 교통사고 감소편익 산정시 도로등급별로 사고율을 일률적으로 적용하고 있고, 도로특성 및 V/C에 따른 특성이 고려되고 있지 못하고 있다. 이와 같은 문제점을 해결하기 위해 본 논문에서는 도로유형별 V/C 및 교통 특성을 반영하여 사고를 예측할 수 있는 모형을 개발하여 도로의 신설 및 개량에서 그 도로의 안전성을 평가할 수 있는 방법론을 제시하였다. 본 연구에서는 초기 단계로서 도시지역 도로를 대상으로 하여 모형을 개발하였다. 우선 도로유형별로 사고에 영향을 미치는 요인을 선정하였다. 이 때 선정 기준은 도로설계단계에서 획득할 수 있는 자료를 위주로 선정하였으며. 교통량, 중앙분리대의 유 무, 교차점수. 연결로수, 횡단신호등수 그리고 차로수를 선정하였다. 각 요인과 사고와의 관계를 분석해 본 결과 모두 통계적으로 유의한 수준에서 상관성이 있는 것으로 나타났다. 본 연구에서는 도로의 등급 및 V/C에 따라 4가지 유형으로 분류하고, 각각에 대하여 포아송 선형회귀식을 통하여 사고예측모형을 도출하였으며, 실제 자료를 이용하여 검증하였다. 검증결과 모형식의 결과가 실제 사고 자료에 대해 비교적 양호하게 추정력을 보이는 것으로 나타났다. 본 연구에서는 V/C에 따른 도로유형별 사고예측모형을 개발함으로써 도로의 물리적인 특성으로 인한 교통사고예측이 가능하고, 이 결과를 도로의 신설 및 개량에 대한 타당성 조사시 사고비용을 추정하는데 활용할 수 있을 것이라 판단된다. 본 연구에서 이용한 자료가 전라북도 한 지역으로 한정되어있어 전국적인 대표성을 지니는 데에는 한계가 있을 수 있다는 사실을 밝히고자한다.

• International Journal of Control, Automation, and Systems
• /
• 제3권4호
• /
• pp.509-523
• /
• 2005

We are developing a novel framework, PRIDE (PRediction In Dynamic Environments), to perform moving object prediction (MOP) for autonomous ground vehicles. The underlying concept is based upon a multi-resolutional, hierarchical approach which incorporates multiple prediction algorithms into a single, unifying framework. The lower levels of the framework utilize estimation-theoretic short-term predictions while the upper levels utilize a probabilistic prediction approach based on situation recognition with an underlying cost model. The estimation-theoretic short-term prediction is via an extended Kalman filter-based algorithm using sensor data to predict the future location of moving objects with an associated confidence measure. The proposed estimation-theoretic approach does not incorporate a priori knowledge such as road networks and traffic signage and assumes uninfluenced constant trajectory and is thus suited for short-term prediction in both on-road and off-road driving. In this article, we analyze the complementary role played by vehicle kinematic models in such short-term prediction of moving objects. In particular, the importance of vehicle process models and their effect on predicting the positions and orientations of moving objects for autonomous ground vehicle navigation are examined. We present results using field data obtained from different autonomous ground vehicles operating in outdoor environments.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권2호
• /
• pp.907-923
• /
• 2020

For the severe haze situation in the Beijing-Tianjin-Hebei region, conventional fine particulate matter (PM2.5) concentration prediction methods based on pollutant data face problems such as incomplete data, which may lead to poor prediction performance. Therefore, this paper proposes a method of predicting the PM2.5 concentration based on image analysis technology that combines image data, which can reflect the original weather conditions, with currently popular machine learning methods. First, based on local parameter estimation, autoregressive (AR) model analysis and local estimation of the increase in image blur, we extract features from the weather images using an approach inspired by free energy and a no-reference robust metric model. Next, we compare the coefficient energy and contrast difference of each pixel in the AR model and then use the percentages to calculate the image sharpness to derive the overall mass fraction. Furthermore, the results are compared. The relationship between residual value and PM2.5 concentration is fitted by generalized Gauss distribution (GGD) model. Finally, nonlinear mapping is performed via the wavelet neural network (WNN) method to obtain the PM2.5 concentration. Experimental results obtained on real data show that the proposed method offers an improved prediction accuracy and lower root mean square error (RMSE).

• 한국경영정보학회:학술대회논문집
• /
• 한국경영정보학회 2007년도 International Conference
• /
• pp.509-514
• /
• 2007

Most of the IS continuance research has assumed that IS use is activated by an intention to use, which in turn is determined by the evaluation of IS usage. Perceived usefulness is one of the evaluation variables most widely used. Typically, the past studies adopt this perceived usefulness because it views continuance as an extension of acceptance behavior. However, the literature on interpersonal relationships suggests that individuals are motivated to maintain relationships either because they genuinely want to or they believe they have no other option. The former is referred to as dedication-based relationship maintenance and the latter as constraint-based relationship maintenance. The IS continuance can be considered as the relationship maintenance situation with the existing IS that the user is currently using. The belief constructs previously used in IS continuance researches fall into the category of dedication-based ones. Additional constraint-based belief constructs are needed to explain the IS continuance behavior. In this regard, switching cost represents an important avenue for better understanding and predicting customer retention in that it can be regarded as the constraint-based motivation for relationship maintenance or IS use continuance. For an empirical exploration, 275 samples were collected from the users of a web portal site. Data analysis using Structural Equation Modeling (SEM) shows that perceived usefulness shows a significant direct effect on continuance intention while perceived switching cost significantly affects continuance usage.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2007년도 춘계종합학술대회
• /
• pp.917-920
• /
• 2007

본 연구에서는 태풍 "매미" 당시 해일로 인해 가장 큰 피해를 입었던 마산만 지역을 중심으로 태풍모형을 재현하여 이때 발생하는 최고극조위를 계산한 후 실제 최고극조위와의 비교분석을 실시하고 또한 최고극조위에 따른 최대범람구역을 산정하여 실제 범람구역과 비교분석함으로 태풍모형의 정확도를 분석하여 향후 태풍모형에 따른 조위 변화등을 예측함으로써 안정적인 항만구조물설계가 이루어 질 수 있도록 필요한 기초 자료를 제공하는데 연구목적이 있다.

• 정보처리학회논문지B
• /
• 제9B권4호
• /
• pp.421-428
• /
• 2002

지금까지 삽입(Embedding)백터를 이용한 국소적예측방법은 고차미분방정식으로부터 생성된 카오스 시계열을 예측할 때, 파라메타 $\tau$의 추정이 정확하지 않으면 예측성능은 떨어졌다. 지금까지 지연시간 ($\tau$)의 값을 추정하는 방법은 많이 제안되어있지만 실제로 고차원미분방정식부터 생성되어진 수많은 시계열에 모두 적용 가능한 방법은 아직 없다. 이것을 기울기 백터를 이용한 기울기 선형모델을 도입하는 것에 의해 정확한 지연시간 ($\tau$)의 값을 추정하지 않아도 예측성능에 만족할 수 있는 결과를 표시했다. 이것을 이론뿐이 아니고 경제시계열에도 적용해서 종래의 예측방법과 비교해서 그 유효성을 표시했다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2143-2147
• /
• 2005

Human-Robot interaction (HRI) has recently become one of the most important issues in the field of robotics. Understanding and predicting the intentions of human users is a major difficulty for robotic programs. In this paper we suggest an interaction method allows the robot to execute the human user's desires in an intelligent room-based domain, even when the user does not give a specific command for the action. To achieve this, we constructed a full system architecture of an intelligent room so that the following were present and sequentially interconnected: decision-making based on the Bayesian belief network, responding to human commands, and generating queries to remove ambiguities. The robot obtained all the necessary information from analyzing the user's condition and the environmental state of the room. This information is then used to evaluate the probabilities of the results coming from the output nodes of the Bayesian belief network, which is composed of the nodes that includes several states, and the causal relationships between them. Our study shows that the suggested system and proposed method would improve a robot's ability to understand human commands, intuit human desires, and predict human intentions resulting in a comfortable intelligent room for the human user.

• KIEAE Journal
• /
• 제10권2호
• /
• pp.25-30
• /
• 2010

The daylited space can improve visual comfort and occupant's well-being. However discomfort glare from the daylight is a common problem in indoor environments and in general, the window is the main glare sources. Some formulas have been proposed for predicting glare from the daylight, however, they do not consider the effect on glare of the view through a window and some studies proved that they are inadequate in real daylight situation. This research aims to identify the relationship between view and discomfort glare considering the subjective impressions. As a preliminary experiment, this paper sets up the experimental protocol to reveal relationships between views from a window and visual perception in a controlled laboratory experiment. $1.2m{\times}1.2m$ artificial window was developed and $0.9m{\times}0.9m$ view image was placed on the window. Discomfort glare and impression evaluation was carried out under four different views and one blank view as a reference condition. The results showed that the subjects evaluated discomfort glare differently with the views even under the same luminance conditions and tended to feel less glare with distance views compared to near views.

• Journal of Information Technology Applications and Management
• /
• 제23권2호
• /
• pp.263-277
• /
• 2016

Recently, 3D printing technology has been considered as a core applicable technology because it brings many improvements such as the development of medical technology, medical customization, and reducing production cost and shortening treatment period. This research suggests a market prediction framework for medical 3D printing business. As an immature market situation, it is important to control some uncertainty for market prediction such as a customers' conversion rate. So we adopt decision making tree (DMT) model which used to choose an optimal decision making among diverse pathway. Among medical industries this paper just focuses on dentistry business. For predicting a 5 year period trend expected market size, we identified some replaceable denture procedure by 3D printing, collected related data, controlled uncertain variables. The result shows that medical 3D printing business could be a market of 28.2 billion won at 1st year and in the end of fifth year it could become on a scale of 61.1 billion won market.

• 한국실내디자인학회논문집
• /
• 제41호
• /
• pp.137-145
• /
• 2003

This research analyzed the space scheme in connection with complexity, one of the new changes in the discount stores, and has a goal of predicting the direction of space scheme in the upcoming complexity era. The research was conducted in the following way. Firstly, this researcher tried to grasp what kinds of changes were required in the overall distribution industry socially and economically. Secondly, the characteristic and situation of discount stores were scrutinized. Thirdly, the domestic stores' complexity status was classified and types of those were elicited. Fourthly, the time-series change and use were analyzed. The result of this analysis reveals that the types of complexity can be divided by location and adjustment to environmental changes. The time-series analysis shows that total operating area, the number of parked cars and the tenant ratio have increased dramatically in 2000 and 2003. And, according to the correlation analysis between factors, the tenant ratio has, a strong correlation with other two factors. Self-complexity takes the basic form of living facilities and complexity with other facilities is combined with other cultural, sales, educational and administrative ones. Mass-complexity is merged with the stadiums, parks or station sites. As you've seen, the concept of complex shopping mall for the realization of one stop shopping and convenience will continue in the days to come. It is desirable that the study on the large-scale shopping spaces will be conducted continually for the preparedness of future life style.