• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.1
• /
• pp.73-80
• /
• 2018

In motorway traffic flow control, the conventional way based on real-time response has been changed into advanced way based on proactive response. Future traffic conditions over multiple time intervals are crucial input data for advanced motorway traffic flow control. It is necessary to overcome the uncertainty of the future state in order for forecasting multiple-period traffic volumes, as the number of uncertainty concurrently increase when the forecasting horizon expands. In this vein, multi-interval forecasting of traffic volumes requires a viable approach to conquer future uncertainties successfully. In this paper, a forecasting model is proposed which effectively addresses the uncertainties of future state based on the behaviors of temporal evolution of traffic volume states that intrinsically exits in the big past data. The model selects the past states from the big past data based on the state evolution of current traffic volumes, and then the selected past states are employed for estimating future states. The model was also designed to be suitable for data management systems in practice. Test results demonstrated that the model can effectively overcome the uncertainties over multiple time periods and can generate very reliable predictions in term of prediction accuracy. Hence, it is indicated that the model can be mounted and utilized on advanced data management systems.

• Journal of Wetlands Research
• /
• v.21 no.2
• /
• pp.157-162
• /
• 2019

Recently, the occurrence of unusual heavy snow and cold are increasing due to the unusual global climate change. In particular, the temperature dropped to minus 69 degrees Celsius in the United States on January 8, 2018. In Korea, on February 17, 2014, the auditorium building in Gyeongju Mauna Resort was collapsed due to the heavy snowfall. Because of the tragic accident many studies on the reduction of snow damage is being conducted, but it is difficult to predict the exact damage due to the lack of historical damage data, and uncertainty of meteorological data due to the long distance between the damaged area and the observatory. Therefore, in this study, available data were collected from factors that are thought to be corresponding to snow damage, and the amount of snow damage was estimated categorically using a random forest. At present, the prediction accuracy was not sufficient due to lack of historical damage data and changes of the design code for green houses. However, if accurate weather data are obtained in the affected areas. the accuracy of estimates would increase enough for being used for be the degree preparedness of disaster management.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.53-67
• /
• 2020

This study employees a supervised learning prediction model to detect nonconformity in advance of processed food manufacturing and processing businesses. The study was conducted according to the standard procedure of machine learning, such as definition of objective function, data preprocessing and feature engineering and model selection and evaluation. The dependent variable was set as the number of supervised inspection detections over the past five years from 2014 to 2018, and the objective function was to maximize the probability of detecting the nonconforming companies. The data was preprocessed by reflecting not only basic attributes such as revenues, operating duration, number of employees, but also the inspections track records and extraneous climate data. After applying the feature variable extraction method, the machine learning algorithm was applied to the data by deriving the company's risk, item risk, environmental risk, and past violation history as feature variables that affect the determination of nonconformity. The f1-score of the decision tree, one of ensemble models, was much higher than those of other models. Based on the results of this study, it is expected that the official food control for food safety management will be enhanced and geared into the data-evidence based management as well as scientific administrative system.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.1
• /
• pp.28-38
• /
• 2016

Cooperative-Intelligent Transport Systems (c-ITS) has emphasized a real-time traffic safety service in urgent situations among highway infrastructure and four-wheeled vehicles, while two-wheeled vehicles, e.g. bicycles and motorcycle, sharing highway space and endangering highway safety, have yet been out of its interest. This paper delivers the results of a study conducted to analyze the patterns of two-wheeled-vehicle traffic accidents experienced in the past, the last three years (2011~2013), and to propose the types of service enhancing the safety of the riders of those. It was found from the analysis of historical accident data that the side collision on a link section should be taken care of for further safety treatment, while the old female drivers need additional care to decrease their fatality rate. By combining the services proposed for bicycles and motorcycles, this paper proposes (1) eight different bicycle-to-everything (B2X) services which can be eventually provided in c-ITS and (2) three of those that would be available in the near future with the current communication technologies.

• Journal of the Korean Geotechnical Society
• /
• v.33 no.10
• /
• pp.5-14
• /
• 2017

The hazard maps for predicting collapse on natural slopes consist of a combination of topographic, hydrological, and geological factors. Topographic factors are extracted from DEM, including aspect, slope, curvature, and topographic index. Hydrological factors, such as soil drainage, stream-power index, and wetness index are most important factors for slope instability. However, most of the urban areas are located on the plains and it is difficult to apply the hazard map using the topography and hydrological factors. In order to evaluate the risk of subsidence of flat and low slope areas, soil depth and groundwater level data were collected and used as a factor for interpretation. In addition, the reliability of the hazard map was compared with the disaster history of the study area (Gangnam-gu and Yeouido district). In the disaster map of the disaster prevention agency, the urban area was mostly classified as the stable area and did not reflect the collapse history. Soil depth, drainage conditions and groundwater level obtained from boreholes were added as input data of hazard map, and disaster vulnerability increased at the location where the actual subsidence points. In the study area where damage occurred, the moderate and low grades of the vulnerability of previous hazard map were 12% and 88%, respectively. While, the improved map showed 2% high grade, moderate grade 29%, low grade 66% and very low grade 2%. These results were similar to actual damage.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.6
• /
• pp.1-14
• /
• 2012

Traffic management centers (TMC) collect real-time traffic data from the field and have powerful databases for analysing, recording, and archiving the data. Recent advanced sensor and communication technologies have been widely applied to intelligent transportation systems (ITS). Regarding sensors, various in-vehicle sensors, in addition to global positioning system (GPS) receiver, are capable of providing high resolution data representing vehicle maneuverings. Regarding communication technologies, advanced wireless communication technologies including vehicle-to-vehicle (V2V) and vehicle-to-vehicle infrastructure (V2I), which are generally referred to as V2X, have been widely used for traffic information and operations (references). The V2X environment considers the transportation system as a network in which each element, such as the vehicles, infrastructure, and drivers, communicates and reacts systematically to acquire information without any time and/or place restrictions. This study is motivated by needs of exploiting aforementioned cutting-edge technologies for developing smarter transportation services. The proposed system has been implemented in the field and discussed in this study. The proposed system is expected to be used effectively to support the development of various traffic information control strategies for the purpose of enhancing traffic safety on highways.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.1
• /
• pp.11-20
• /
• 1999

Because conventional spatial databases process the spatial information that is valid at current time, it is difficult to manage historical information efficiently which has been changed from the past to current. Recently, there are rapid increasing of interest to solve this problem so that makes databases to support historical information as well as spatial management at the same time. It can be eventually used in a various application areas. The formal semantics in a database is used to represent database structures and operations in order to prove the correctiveness of them in terms or mathematics. It also plays an important role in database to design a database and database management system. So in this paper, we suggest spatiotemporal domain, object, data, and spatiotemporal geometric/topological operations. And we not only formalize relational algebra/calculus using formal semantics for a spatiotemporal data model, but also show the example of real orld with them.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.354-354
• /
• 2021

2020년은 장마기간이 49일간 지속됨에 따라 침수, 산사태 등 많은 홍수피해가 발생하였다. 특히 서울에서는 한강 본류의 수위가 급격하게 증가함에 따라 둔치 및 도로 침수 피해가 발생하였다. 이처럼 하천의 수위증가로 인한 홍수피해에 대응하기 위해 홍수통제소 및 기초지자체에서는 홍수특보를 발령한다. 이 홍수특보는 수위관측소 지점별 계획홍수량의 50 %, 70 % 이상의 홍수량이 발생할 경우 홍수주의보와 홍수경보가 발령되며, 이 기준은 각 권역별로 동일하다. 하지만 2017년 의정부시에서는 중랑천 수위증가로 인해 주변 지역에 침수피해가 발생하였지만, 이때 홍수량은 계획홍수량 대비 약 30 %에 불과하였다. 이처럼 한강권역 내 하천수위 증가로 인한 홍수피해는 계획홍수량의 50 % 이내에서 발생하기도 한다. 이에 본 연구에서는 한강권역을 대상으로 현재 2단계로 발령되는 홍수특보를 3단계로 세분화하고자 하였다. 단계별 홍수량 위험기준을 산정하기 위해 과거 홍수피해 발생 이력이 있는 한강권역 내 43개의 수위관측소 지점을 선정하였으며, 지점별 홍수기 동안의 홍수량 및 피해액 자료를 수집하였다. 각 단계별 홍수량 기준을 산정하기 위해서는 로지스틱 회귀분석 방법을 활용하여 피해발생 확률을 산정하였다. 1단계 기준은 계획홍수량 대비 홍수량 비율과 홍수피해 발생여부를 고려한 이항 로지스틱 회귀분석 모델을 구축한 후 3계 도함수에 적용하여 홍수피해 발생확률이 급격하게 증가하는 특이점을 산정하였다. 2단계와 3단계 기준은 다항 로지스틱 회귀분석 중 계층형 로지스틱 회귀분석을 활용하여 지점별 피해액 비율이 60 ~ 80 %, 80 ~ 100 % 구간에 속할 확률을 산정하고, 1단계와 동일한 방법으로 특이점을 산정하였다. 그 결과 지점별로 기존 제공되고 있는 홍수특보 기준을 과거 발생한 홍수피해를 고려하여 세분화할 수 있었으며, 이 결과는 지역별 홍수피해 저감대책에 활용될 수 있을 것으로 판단된다.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2007.06a
• /
• pp.177-182
• /
• 2007

최근 텔레매틱스 분야에서 GPS 수신기를 장착한 probe car를 통해 교통 정보를 수집하는 방법에 대한 연구가 활발히 진행되고 있다. 이 방법은 기존에 교통 정보를 수집하기 위해 활용되고 있던 고정식 검지기들에 비해 수집되는 정보가 높은 신뢰성을 가지고, 도로 환경에 민감하지 않으며, 낮은 유지비용으로 운용할 수 있다는 장점을 가지고 있다. 하지만, probe car는 자신의 위치 정보를 교통 정보 센터로 전송해 주어야 하기 때문에 프라이버시가 노출될 수 있고, 주차되어 있는 시간에는 통행 정보를 보내줄 수가 없다. 이런 이유로 대중 교통차량이나 상업용 차량이 주로 probe car로 활용되어지게 되는데, 그 수가 많지 않을뿐더러 운행 구간이 고르게 분포되지 않아 probe car가 지나지 않는 구간, 즉 교통 정보 누락 구간이 존재할 수 있는 문제점을 가지고 있다. 본 논문에서는 교통 정보 누락 구간의 처리를 위해 과거의 이력 정보로 대체하는 방법, 주변 도로의 구간 정보로 예측하는 방법, 회귀 분석을 통한 예측 방법 등을 기술하고 실제 probe car들로 수집된 서울시 강남대로 구간의 자료로 각 방법에 대한 실험을 실시하여 각각의 방법에 대한 결과를 비교 분석한다.

• Journal of the Korean Society of Hazard Mitigation
• /
• v.8 no.2
• /
• pp.65-73
• /
• 2008

Since the damages caused by disasters increase every year associated with wrenching climatic changes and the diversification of the social structure, the efficient management system is required to reduce damages and an assessment of the vulnerable disaster areas is necessary to prevent and mitigate the damages. In this paper, we have estimated the vulnerable disaster areas based on the records of the past damage histories and performed the risk assessment of the social infrastructures in Busan city to provide the fundamental information for the real-time monitoring system and the systematic approach for disaster prevention system to build V-City model. These results are illustrated by using Geographical Information System (GIS) and the order of vulnerable disaster areas are also estimated.