• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.79-89
• /
• 2017

Current intersection with collectors allow entry and exit in the relevant sections just as defined by the pertinent design criteria without considering driving behavior of the vehicles coming in and out of the intersection. This study analyzed the roads in the weaving sections to review driving behavior. As a result, vehicles entering a main line are found to try to change a driving lane at a section 50~55m away from a nose part, while those entering a ramp from a main line try to change it at 35~40m from a nose part. Accordingly vehicles exiting to a connecting road from a main line were found to take prior action to change a lane earlier than those entering a main line. Conflict took place intensively at 35~40m section from the nose part entering a main line. Consequently, such conflict at an weaving section may be controlled by adjusting the length of driving lane making use of a double line (solid and dotted line) that can control changing a lane. Outcome of this study may be used as a basic data for operating and maintaining an weaving section of a intersection of a road and improving traffic safety.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.1
• /
• pp.85-93
• /
• 2015

Previous studies have estimated crash prediction models with the fixed effect model which assumes the fixed value of coefficients without considering characteristics of each intersections. However the fixed effect model would estimate under estimation of the standard error resulted in over estimation of t-value. In order to overcome these shortcomings, the random effect model can be used with considering heterogeneity of AADT, geometric information and unobserved factors. In this study, data collections from 89 intersections in Daejeon and estimates of crash prediction models were conducted using the random and fixed effect negative binomial regression model for comparison and analysis of two models. As a result of model estimates, AADT, speed limits, number of lanes, exclusive right turn pockets and front traffic signal were found to be significant. For comparing statistical significance of two models, the random effect model could be better statistical significance with -1537.802 of log-likelihood at convergence comparing with -1691.327 for the fixed effect model. Also likelihood ration value was computed as 0.279 for the random effect model and 0.207 for the fixed effect model. This mean that the random effect model can be improved for statistical significance of models comparing with the fixed effect model.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.14 no.1
• /
• pp.22-30
• /
• 2015

Recently ITS have been increasingly applied on the roads to resolve traffic problems. Especially, Variable Message Sign (VMS), which is the one of ITS for traffic management and traffic safety, can be used for providing information about road conditions, climate conditions. In this study, data acquisition and statistical analysis were conducted for estimating safety impacts of providing traffic information through VMS. As a result of analyzing traffic characteristics before and after providing traffic information through VMS, average travel speed was decreased and vehicles tended to drive on centerline of lanes in 1st and 2nd lane after providing traffic information through VMS. Also, in order to analyze safety impacts of provided VMS traffic information, traffic safety hazard zone was established in each lane and probability distributions of passing traffic on the study area was estimated through Anderson-Darling Test. As a result of this, safety impacts of VMS traffic information in 1st lane could, on average, increase in left and right side of the lane by 0.69% and 7.07%, respectively. In case of 2nd lane, safety impacts could, on average, increase in left and right side of the lane by 2.71% and 0.02%, respectively.

• Korean Chemical Engineering Research
• /
• v.57 no.6
• /
• pp.781-789
• /
• 2019

There are frequent accidents by chemicals during laboratory experiments and pilot plant and reactor operations. It is necessary to find and comprehend relevant information to prevent accidents before starting synthesis experiments. In the process design stage, reaction information is also necessary to prevent runaway reactions. Although there are various sources available for synthesis information, including the Internet, it takes long time to search and is difficult to choose the right path because the substances used in each synthesis method are different. In order to solve these problems, we propose an intelligent synthetic path search system to help researchers shorten the search time for synthetic paths and identify hazardous intermediates that may exist on paths. The system proposed in this study automatically updates the database by collecting information existing on the Internet through Web scraping and crawling using Selenium, a Python package. Based on the depth-first search, the path search performs searches based on the target substance, distinguishes hazardous chemical grades and yields, etc., and suggests all synthetic paths within a defined limit of path steps. For the benefit of each research institution, researchers can register their private data and expand the database according to the format type. The system is being released as open source for free use. The system is expected to find a safer way and help prevent accidents by supporting researchers referring to the suggested paths.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.3
• /
• pp.14-33
• /
• 2019

MaaS, which provides all-in-one service for comfort mobility for customers, has been popularly researched and developed mainly in Europe. Even in Korea, the research on MaaS is also carried out which is fit to the mobility environment and needs of Korea. Korea Land & Housing Corporation(LH) also carries out research on MaaS called 'Integrated Mobility' for the residents living in LH public apartments. This study categorised the around 800 public apartments into 12 groups based on 3 key characteristics, then analysed the preference on shared-transport services by the residents of representing apartments for the each group using C&RT method. The results show that the preference on shared-transport services such as car-sharing and ride-sharing (carpool) were higher in the apartments which are located in medium or small cities or lived by the more handicapped resident groups in mobility such as the elderly. The study suggests the method to analysis the relationship between residents' preference on shared transport services and bounded ertain areas such as apartments or districts and then to introduce shared transport service fit to target areas.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.1
• /
• pp.1-13
• /
• 2019

With commercial apps popular in EU, MaaS has been emerging around the globe as a new approach to worsening urban traffic problems. In contrast, it is still mainstay in Korea simply discussing the concept and necessities of MaaS, rather than seeking for real-world solutions for the commercialization. The purpose of this research is to analyze the demand-side i1mpacts of travel time and cost changes according to MaaS adoption, and to see its commercial feasibility in Korea. The 2010 KTDB traveler's nationwide OD data is used to estimate the level of fare discount for balancing the mode shift and fare revenue changes followed by MaaS implementation. The analysis results show that MaaS leads to the increase of public transport ridership as a result of the diminishing travel cost and time, and that the time saving works more positively for ridership increase. Also, the optimum level of fare discount is estimated 2.56% without damaging the revenue. This finding reveals that MaaS impact is superior to the other single-sided public transport inventive measures since it can affect both travel cost and time reduction at the same time.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.155-170
• /
• 2018

Predicting a company's financial bankruptcy is traditionally one of the most crucial forecasting problems in business analytics. In previous studies, prediction models have been proposed by applying or combining statistical and machine learning-based techniques. In this paper, we propose a novel intelligent prediction model based on the simulated annealing which is one of the well-known optimization techniques. The simulated annealing is known to have comparable optimization performance to the genetic algorithms. Nevertheless, since there has been little research on the prediction and classification of business decision-making problems using the simulated annealing, it is meaningful to confirm the usefulness of the proposed model in business analytics. In this study, we use the combined model of simulated annealing and machine learning to select the input features of the bankruptcy prediction model. Typical types of combining optimization and machine learning techniques are feature selection, feature weighting, and instance selection. This study proposes a combining model for feature selection, which has been studied the most. In order to confirm the superiority of the proposed model in this study, we apply the real-world financial data of the Korean companies and analyze the results. The results show that the predictive accuracy of the proposed model is better than that of the naïve model. Notably, the performance is significantly improved as compared with the traditional decision tree, random forests, artificial neural network, SVM, and logistic regression analysis.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.5
• /
• pp.18-34
• /
• 2021

Pedestrian deaths in Korea due to traffic accidents are 40 percent of the fatalities in traffic accidents, which is about twice the average of OECD member countries. To reduce severe pedestrian accidents, it is necessary to apply the accident reduction measures to high-risk drivers (novice, elderly, and commercial vehicle drivers) who are more likely to cause traffic accidents than general drivers. Therefore, this study analyzed the effect of safe driving education on high-risk drivers' behavior. Here, the safe driving education is chosen as the measure to reduce traffic accidents. As part of the study, sudden pedestrian crossing situations were implemented in the driving simulator, and the vehicle trajectory data were collected to compare the driving behavior before and after the education. Most surrogate safety measures showed no improvement in the driving behavior of novice and elderly drivers, and the effect of safe driving education was found to be significant only in the group of commercial vehicle drivers. The results implied that additional measures such as pedestrian safety infrastructure and driver assistance systems, apart from the safe driving education, may be needed for novice and elderly drivers to reduce pedestrian accidents caused by them. With the findings mentioned above, this study is expected to provide a foundation to establish a plan to reduce pedestrian accidents caused by high-risk drivers.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.3
• /
• pp.20-33
• /
• 2021

Modern society is steadily implementing policies to encourage public transportation to cope with the growing traffic demand on limited roads. The expectation is rising for transit signal priority to ensure the speed of buses as the installation of the bus rapid transit(BRT) expands nationwide to secure the competitiveness of buses. On the other hand, the form of BRT stops without considering some aspects of bus operation may increase the number of stops on the bus, thereby reducing the effectiveness of bus signal priority applications. This study suggests the type of bus stop to increase the operation efficiency of buses by analyzing the bus signal priority effect according to the BRT station type using Hannuri-daero, Sejong. The bus signal priority is used to maximize the two-way bandwidth of passenger cars and buses. As a result of the application, the effectiveness of the bus signal priority at the stop causing the double stop of the bus was reduced drastically, and the efficiency of the bus signal priority was increased significantly after improvement. These results are expected to be used as basic data in the form of proper bus stops considering the aspects of traffic operation when designing BRT stops in new towns in the future.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.117-132
• /
• 2021

Due to the terrain in Korea, there are many road sections passing through mountainous areas. During the winter, there is a higher risk of traffic accidents, due to black ice caused by the lack of sunlight. Despite domestic road freezing safety measures, accidents caused by road freezing results in severe traffic accidents. Under these considerations, this study analyzed whether traffic safety signs that change in response to the external temperature help drivers recognize frozen road segments. The study was conducted through analysis of the effect of the signs on a driver's perspective. For the signs under development, out of the signs designed by experts, the sign design which received the highest visibility and effectiveness evaluation ratings from the general public was selected. The sign was implemented through Virtual Reality (VR) and installed on the right side of the road to analyze the effect on gazing and driving behavior. As a result of analyzing the driver's driving behavior, a speed reduction of about 7km/h or more was found in the sign section. Therefore, It was found that the existence of the sign had a strong relationship with the rate of the drivers' speed reduction.