• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2016.11a
• /
• pp.261-262
• /
• 2016

교통사고의 발생요인에는 다양한 원인들이 있지만 본 연구에서는 공간적으로 접근하여 사고유형별 분포특성을 도출하기 위해 공간적 자기상관성 분석을 수행하였다. 논문에서는 2012년부터 2014년까지 울산광역시에서 발생된 교통사고를 대상으로 분석을 수행하였다. 그 결과 울산시 전체 교통사고 약 53%는 안전운전불이행이며 다음으로는 안전거리미확보, 신호위반 순으로 나타났다. 밀도분석 결과는 사고유형별로 분포가 차이가 있었으며 안전운전불이행의 경우 가장 큰 군집은 중심시가지인 달동과 삼산동 중심에 나타났으며 중앙선침범은 도시의 중심부 보다는 면지역에 넓게 퍼져서 발생되었으며 산업단지가 있는 동구지역에 군집이 크게 나타났다. 따라서 읍면동별 공간적 특성을 파악하기 위해 Moran's I분석과 LISA분석을 수행한 결과 안전운전불이행, 안전거리미확보, 신호위반, 교차로운행방해 모두 중심시가지인 신정동, 달동, 삼산동이 공간적 자기상관성이 높았으며 중앙선침범의 경우 밀도분석 결과와 마찬가지로 중심시가지 이외에 읍면 지역도 자기상관성이 더 높게 나타났다. 이를 통해 사고유형별 공간의존성 및 이질성을 파악하여 교통사고 다발지역을 도출하고 이를 토대로 지역특성에 맞는 저감 대책 마련에 활용되고자 한다.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2015.11a
• /
• pp.193-194
• /
• 2015

본 연구는 요인분석을 통해 노인 보행자 사고 유형을 대표할 수 있는 성분 값을 계산하고 군집분석을 실시하여 노인 보행자 사고 취약 지역을 선정하는 모델을 확인하였다. 기존 노인보행자 사고에 관한 연구는 보행 환경 분석 및 노인보행자 사고 특성을 확인한 뒤, 제도적, 물리적 환경 개선 등에 대한 정책 제언의 형식으로 진행되었다. 이러한 연구는 실질적으로 노인 보행자 특성을 분석하여 사고를 감소시키는 연구가 아닌, 일반적으로 알려진 사실이나 해외 사례를 들어 노인 보행자 사고의 현 실태에 대해 어느 정도 환기만 시켜주는 역할로 그쳤다. 이러한 점에서 군집분석을 통한 노인 보행자 사고 취약지역 선정은 노인 보행자 사고 특성의 비교를 명확하게 할 수 있도록 새로운 기준을 제시하였다. 이에 기존의 방법론에서 벗어나 실질적으로 노인 보행자 사고 방지 대책이 시급한 지역을 선정하였고, 노인 보행자 사고에 관해 활발히 연구 시킬 것이라 예상한다. 군집분석을 사용하는 핵심은 사망자 수와 사망률이 상대적으로 동시에 높은 군집을 선정할 수 있고 지역 특성 비교를 통해 향후 노인 보행자 사고에 관한 추가 연구가 가능할 것으로 기대한다.

• Journal of Industrial Convergence
• /
• v.18 no.3
• /
• pp.1-6
• /
• 2020

The purpose of this study is to theoretically understand hope theory suggested by Snyder and confirm its utility in the school settings. We analyzed the survey data responded by general high school students to find clustering types of hope and mean difference of learning strategies by each type through ANOVA. Results are as follows. First, hope by cluster analysis resulted in four types. Second, hope and learning strategy showed statistically positive correlation. Especially two sub-variables of hope and meta-cognition had highest correlation. Researchers suggested the direction of a future study to investigate structural relation among hope profile, student achievement, adjustment, and etc.

• Journal of the Korean Geographical Society
• /
• v.39 no.3
• /
• pp.457-472
• /
• 2004

The purpose of this study is to analyze spatial patterns of traffic accidents and to investigate spatial relations among neighboring spatial objects by applying GIS and spatial data mining methods. This study investigated traffic accident data in Kangnam-gu, Seoul, as a case study. As a result, four clusters were emerged based on individual attributes of traffic accidents. Each cluster showed distinctive properties. In spatial associations between individual attributes of traffic accidents and neighboring spatial objects, there were many rules according to concept hierarchy and definition of spatial relations. Although all rules were not be interesting and significant, they could be a clue to investigate more.

• Journal of Industrial Convergence
• /
• v.19 no.4
• /
• pp.9-15
• /
• 2021

The purpose of the study is to find out the difference between high school students' hopes and the school happiness of each cluster of grits. Method: 282 high students' responses were analyzed through correlation analysis and cluster analysis. Results: First, There is a positive correlation between hope and grit and school happiness. Second, Hope and Grit appeared in four clusters. School happiness had the highest "high psychological capital" group and the lowest "low psychological capital. Conclusion: It was discussed that the agency thinking and effort perseverance of grit should be reflected in the curriculum of general high schools. In addition, we propose to develop questionnaires for practical measurements.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.6
• /
• pp.132-145
• /
• 2022

This study was based on the black box images of traffic accidents on highways, cluster analysis and prediction model comparisons were carried out. As analysis data, vehicle driving behavior and road surface conditions that can grasp road and traffic conditions just before the accident were used as explanatory variables. Considering that traffic accident data is affected by many factors, cluster analysis reflecting data heterogeneity is used. Each cluster classified by cluster analysis was divided based on the ratio of the severity level of the accident, and then an accident prediction evaluation was performed. As a result of applying the Logit model, the accident prediction model showed excellent predictive ability when classifying groups by cluster analysis and predicting them rather than analyzing the entire data. It is judged that it is more effective to predict accidents by reflecting the characteristics of accidents by group and the severity of accidents. In addition, it was found that a collision accident during stopping such as a secondary accident and a side collision accident during lane change act as important driving behavior variables.

• Journal of the Economic Geographical Society of Korea
• /
• v.10 no.2
• /
• pp.137-152
• /
• 2007

This paper aims to clarify the types of cities by automobile traffic accidents and to search the characteristics of automobile traffic accidents for each type. Cities by automobile traffic accidents are classified into 4 types. Seoul city belongs to Type A in which 'automobile use and accident type' is closely related. Osan city belongs to Type B where the number of automobile traffic accidents is the greatest. And many satellite cities of Seoul city and metropolitan cities, and cities distributed in Southeastern industrial region belongs to Type C in which automobile accidents are fewer than the national average. Other 57 cities belongs to Type D which there are more automobile accidents than the national average. The cause of traffic accidents for each city type are as follows. In Seoul city the major causes of accidents are no security of safety distance, road patterns of other region, and injury of pedestrians. In Osan city, many single lane road accidents, central line invasion, and traffic accidents of children of under 14 years. And in satellite cities of Seoul city and metropolitan cities, and cities distributed in Southeastern industrial region, the major causes are traffic regulation violation, of under 6m in crossroad accidents, accident of children of under 14 years, and injury of pedestrians. Lastly, in other 57 cities chief causes are traffic regulation violation, wrong methods of passing crossroads, injury of children of under 14 and elderly of over 61 years, and injury of pedestrians.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.19 no.2
• /
• pp.122-134
• /
• 2020

To improve traffic congestion, reduce fuel consumption, and improve the stability of truck operations, truck platooning, in which several trucks are organized in a single platoon, is being actively researched globally. Compared to the operation of a single truck, the operation of a truck platoon requires more caution before the actual operation because an accident of one vehicle in the platoon can lead to an accident with all the vehicles in the platoon. Therefore, this study examined the types of trucks and cargo suitable for truck platooning to prevent safety accidents. The review showed that a closed-van-type truck is appropriate for truck platooning to prevent falling objects during driving. In the case of cargo types, it is necessary to exclude liquids and dangerous goods defined in related laws from truck platooning.

• Journal of the Society of Disaster Information
• /
• v.20 no.2
• /
• pp.379-389
• /
• 2024

Purpose and Method: Crowed Events can lead to sudden accidents caused by unpredictable variables. Therefore, focusing on the '10.29 Itaewon accident' among the representative cases, we examined the accident as the process of occurrence. In addition, improvement measures were suggested through analysis of related legal systems. Result: In the Itaewon accident, a "colony wave phenomenon" occurred due to "ultra-high-density cluster stay". In addition, cluster destruction occurred from a weak location in the cluster due to clusters and pressures in different directions to avoid this. Looking at the laws related to the safety management of Crowed Events, the laws and regulations differ depending on the location and type. Due to the complementary nature of the approach to the legal blind spot, the legal system that uses similar terms of the same concept and is not systematic is causing uncertainty in the application and interpretation of the law. Conclusion: Crowd control and on-site management should be carried out for events when the cluster density is expected to reach 8 people/m² or reached. Consistency should be maintained through the unified application of legislation to related legislation.

• Journal of the Korea Institute of Building Construction
• /
• v.19 no.4
• /
• pp.341-350
• /
• 2019

Construction industry is one of the most dangerous industry. As the construction accidents occur due to the repeated factors found in each accidents, there is a limitation in analyzing all types of occupational accidents by the existing descriptive analysis and statistical test. In this study, we classified safety accidents caused by falling objects among the accident types occurring at construction sites into fatal and nonfatal accidents and deduced the factors. In addition, we deduced the association rules among the safety accidents factors caused by falling objects through the association rule analysis method among the machine learning techniques. Therefore, considering the association rules for fatal and nonfatal accidents proposed in this study, it would be possible to prevent accidents by searching for countermeasures against safety accidents caused by falling objects.