• Journal of Korean Society of Transportation
• /
• v.23 no.3 s.81
• /
• pp.125-136
• /
• 2005

The current traffic accident reduction procedure in economic feasibility study does not consider the characteristics of road and V/C ratio. For solving this problem, this paper suggests methods to be able to evaluate safety of each road in construction and improvement through developing accident Prediction model in reflecting V/C ratio Per road types and traffic characters. In this paper as primary process, model is made by tke object of urban roads. Most of all, factor effecting on accident relying on road types is selected. At this point, selecting criteria chooses data obtained from road planning procedure, traffic volume, existence or non-existence of median barrier, and the number of crossing point, of connecting road. and of traffic signals. As a result of analyzing between each factor and accident. all appear to have relatives at a significant level of statistics. In this research, models are classified as 4-categorized classes according to roads and V/C ratio and each of models draws accident predicting model through Poisson regression along with verifying real situation data. The results of verifying models come out relatively satisfactory estimation against real traffic data. In this paper, traffic accident prediction is possible caused by road's physical characters by developing accident predicting model per road types resulted in V/C ratio and this result is inferred to be used on predicting accident cost when road construction and improvement are performed. Because data using this paper are limited in only province of Jeollabuk-Do, this paper has a limitation of revealing standards of all regions (nation).

• International Journal of Control, Automation, and Systems
• /
• v.3 no.4
• /
• 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)
• /
• v.14 no.2
• /
• 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
• /
• 2007.06a
• /
• 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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.917-920
• /
• 2007

In this research, a typhoon model has been reproduced on the Masan area which had a great damage caused by a tidal wave of the typhoon "MAEMI" at that time. In addition, after calculating the highest level of a tide that happens in the case, it can be compared with one in a real situation, and the accuracy of the typhoon model could be analyzed as well by comparing the actual overflow area with the greatest overflow area computed by the data of the highest level of a tide. This research is to provide some fundamental and primary materials for the design of stable harbor structure by predicting such as tidal changes that follow some typhoon matrixes hereafter.

• The KIPS Transactions:PartB
• /
• v.9B no.4
• /
• pp.421-428
• /
• 2002

The local prediction method utilizing embedding vector loses the prediction power when the parameter r estimation is not exact for predicting the chaos time series induced from the high order differential equation. In spite of the fact that there have been a lot of suggestions regarding how to estimate the delay time ($\tau$), no specific method is proposed to apply to any time series. The inclinded linear model, which utilizes inclinded netter, yields satisfying degree of prediction power without estimating exact delay time ($\tau$). The usefulness of this approach has been indicated not only theoretically but also in practical situation when the method w8s applied to economical time series analysis.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• 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
• /
• v.10 no.2
• /
• 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
• /
• v.23 no.2
• /
• 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.

• Korean Institute of Interior Design Journal
• /
• no.41
• /
• 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.