• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.3
• /
• pp.581-590
• /
• 2024

This study aims to extract key topics through text mining of incident records (incident history, post-incident measures, preventive measures) from construction safety accident case data available on the public data portal. It also seeks to provide fundamental insights contributing to the establishment of manuals for disaster prevention by identifying correlations between these topics. After pre-processing the input data, we used the LDA-based topic modeling technique to derive the main topics. Consequently, we obtained five topics related to incident history, and four topics each related to post-incident measures and preventive measures. Although no dominant patterns emerged from the topic pattern analysis, the study holds significance as it provides quantitative information on the follow-up actions related to the incident history, thereby suggesting practical implications for the establishment of a preventive decision-making system through the linkage between accident history and subsequent measures for reccurrence prevention.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.268-271
• /
• 1998

this paper presents the potential application of fuzzy logic to the automatic incident detection system. While the conventional incident detection algorithms are based on a binary decision process, the algorithm using fuzzy logic can incorporate ambiguity which occurs in determining incidents. Since collecting good amount of data to construct data base for incidents is pretty expensive, a traffic simulator called FRESIM is used to simulate traffic condition in a freeway. Incident data are obtained by changing input parameters of the simulator and the fuzzy algorithm generates fuzzy rule for determining normal and incident traffic conditions. In this paper, various steps are described to test the algorithm and its results are summarized.

• Journal of the Society of Disaster Information
• /
• v.18 no.3
• /
• pp.609-621
• /
• 2022

Purpose: Natural Disaster has well formed framework more than social disaster, because natural disaster is controlled by one department, such as MOIS, but social disaster is distributed. This study is on the design of the integrated service platform for the social diaster data. and then, apply to the local governments. Method: Firstly, we design DB templates for the incident cases considering the incident investigation reports. For the risk management, life-damage oriented social disaster risk assessment is defined. In case of the real-time incident data from NDMS, AI system provides the prediction information in the life damage and the cause of the incident. Result: We design the structured and unstructured incident data management system, and design the integrated social disaster and safety incident management system. Conclusion: The integrated social disaster and safety incident management system may be used in the local governments

• International conference on construction engineering and project management
• /
• 2011.02a
• /
• pp.234-240
• /
• 2011

Preventing incidents occurred in construction process is important for safe implementation of construction projects. Due to the complexity and magnitude of the project and moreover, poor safe planning and management, construction incidents in Korea have been increasing. Reducing construction incidents effectively, appropriate safety management program in consideration of the incident rate of each facility is to be adapted. This study analyzes incident frequency and severity rate of each facility based on the data of construction sites(about 1,560 thousand cases) recorded by Korea Occupational Safety & Health Agency for 3 years from 2007 to 2009, and the incident related data (about 40 thousand cases) of Korea Workers' Compensation & Welfare Service. The results of this study revealed that construction incident rates of 'cold refrigeration storage facilities' are the highest among building types, followed by traditional building religious building, arcade department store and shopping center. In case of other facilities, the incident rate and the rate of intensity of 'pipelining project' are the highest, followed by 'tunneling project'. These results would be used in providing safety programs beneficial for preventing construction incidents.

• Journal of Korean Society of Transportation
• /
• v.33 no.5
• /
• pp.497-507
• /
• 2015

Nonrecurrent congestion of freeway was primarily caused by incident. The main cause of incident was known as a traffic accident. Therefore, accurate prediction of traffic incident clearance time is very important in accident management. Traffic accident data on freeway during year 2008 to year 2014 period were analyzed for this study. KNN(K-Nearest Neighbor) algorithm was hired for developing incident clearance time prediction model with the historical traffic accident data. Analysis result of accident data explains the level of accident significantly affect on the incident clearance time. For this reason, incident clearance time was categorized by accident level. Data were sorted by classification of traffic volume, number of lanes and time periods to consider traffic conditions and roadway geometry. Factors affecting incident clearance time were analyzed from the extracted data for identifying similar types of accident. Lastly, weight of detail factors was calculated in order to measure distance metric. Weight was calculated with applying standard method of normal distribution, then incident clearance time was predicted. Prediction result of model showed a lower prediction error(MAPE) than models of previous studies. The improve model developed in this study is expected to contribute to the efficient highway operation management when incident occurs.

• Journal of Distribution Science
• /
• v.14 no.12
• /
• pp.61-69
• /
• 2016

Purpose - This study investigates the determinants that affect the number of IT Incident tickets of an IT Service Provider ("ITSP") to logistics industry in order to improve its management process by reducing the incident tickets. Research design, data, and Methodology - This study uses weekly data of IT incident tickets from September 2012 to June 2015. Correlation and regression analyses are conducted. Six identified determinants i.e., IT Change, User Errors, Shipment Volume, Network, Hardware and Software Issues are used as the explanatory variables. Results - Our findings show as following. First, our analysis indicates that IT Change is not a significant determinant as opposed to what commonly believed by many as the most important factor. Second, Software issue is the highest contributor to the Major IT incident tickets, followed by User Error, Network and Hardware issues. Third, it seems there is lead-lag relationship between IT Change and Major IT Incidents tickets as indicated by earlier studies. Fourth, the relationship between IT Change and Major IT tickets is also affected by shipment volume. Conclusions - As policy recommendation, all identified determinants should be treated according to priority. In addition, improving the way IT Changes are implemented will definitely reduce the IT incident tickets.

• Journal of Communications and Networks
• /
• v.12 no.4
• /
• pp.382-394
• /
• 2010

Cross-domain event information sharing is a topic of great interest in the area of event based network management. In this work we use data sets which represent actual attacks in the operational Internet. We analyze the data sets to understand the dynamics of the attacks and then go onto show the effectiveness of sharing incident related information to contain these attacks. We describe universal data acquisition system for event based management (UniDAS), a novel system for secure and automated cross-domain event information sharing. The system uses a generic, structured data format based on a standardized incident object description and exchange format (IODEF). IODEF is an XML-based extensible data format for security incident information exchange. We propose a simple and effective security model for IODEF and apply it to the secure and automated generic event information sharing system UniDAS. We present the system we have developed and evaluate its effectiveness.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.24 no.3
• /
• pp.523-533
• /
• 2014

It has been spent too much time to figure out the incident route when we are facing computer security incident. The incident often recurs moreover the damage is expanded because critical clues are lost while we are wasting time with hesitation. This paper suggests to build a Digital Evidence Map (DEM) in order to find out the incident cause speedy and accurately. The DEM is consist of the log chain which is a mesh relationship between machine data. And the DEM should be managed constantly because the log chain is vulnerable to various external facts. It could help handle the incident quickly and cost-effectively by acquainting it before incident. Thus we can prevent recurrence of incident by removing the root cause of it. Since the DEM has adopted artifacts in data as well as log, we could make effective response to APT attack and Anti-Forensic.

• Proceedings of the KOR-KST Conference
• /
• 1995.12a
• /
• pp.77-107
• /
• 1995

This paper documents the development of a fuzzy logic based incident detection model for urban diamond interchanges. Research in incident detection for intersections and arterials is at a very initial stage. Existing algorithms are still far from being robust in dealing with the difficulties related with data availability and the multi-dimensional nature of the incident detection problem. The purpose of this study is to develop a new real-time incident detection model for urban diamond interchanges. The development of the algorithm is based on fuzzy logic. The incident detection model developed through this research is capable of detecting lane¬blocking incidents when their effects are manifested by certain patterns of deterioration in traffic conditions and, thereby, adjustments in signal control strategies are required. The model overcomes the boundary condition problem inherent in conventional threshold-based concepts. The model captures system-wide incident effects utilizing multiple measures for more accurate and reliable detection, and serves as a component module of a real-time traffic adaptive diamond interchange control system. The model is designed to be readily scalable and expandable for larger systems of arterial streets. The prototype incident detection model was applied to an actual diamond interchange to investigate its performance. A simulation study was performed to evaluate the model's performance in terms of detection rate, false alarm rate, and mean time to detect. The model's performance was encouraging, and the fuzzy logic based approach to incident detection is promising.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.4
• /
• pp.95-102
• /
• 2016

Computer security incident such as confidential information leak and data destruction are constantly growing and it becomes threat to information in digital devices. To respond against the incident, digital forensic techniques are also developing to help digital incident investigation. With the development of digital forensic technology, a variety of forensic artifact has been developed to trace the behavior of users. Also, a diversity of forensic tool has been developed to extract information from forensic artifact. However, there is a issue that information from forensic tools has its own forms. To solve this problem, it needs to process data when it is output from forensic tools. Then it needs to compare and analyze processed data to identify how data is related each other and interpret the implications. To reach this, it calls for effective method to store and output data in the course of data processing. This paper aims to propose DFIOC (Digital Forensic Indicators Of Compromise) that is capable of transcribing a variety of forensic artifact information effectively during incident analysis and response. DFIOC, which is XML based format, provides "Evidence" to represent various forensic artifacts in the incident investigation. Furthermore, It provides "Forensic Analysis" to report forensic analysis result and also gives "Indicator" to investigate the trace of incidence quickly. By logging data into one sheet in DFIOC format for forensic analysis process, it is capable of avoiding unnecessary data processing. Lastly, since collected information is recorded in a normalized format, data input and output becomes much easier as well as it will be convenient to use for identification of collected information and analysis of data relationship.