• Journal of the Korean Society of Safety
• /
• v.33 no.3
• /
• pp.58-64
• /
• 2018

Recently, a lot of accident report documents have accumulated in almost all of industries, including critical information of accidents. Accordingly, text data contained in accident report documents are considered useful information for understanding accident processes. However, there has been a lack of systematic approaches to analyzing accident report documents. In this respect, this paper aims at proposing text analytics approach to extracting critical information on accident processes. To be specific, major causes of the accident occurrence are classified based on text information contained in accident report documents by using both textmining and latent Dirichlet allocation (LDA) algorithms. The textmining algorithm is used to structure the document-term matrix and the LDA algorithm is applied to extract latent topics included in a lot of accident report documents. We extract ten topics of accidents as accident types and related keywords of accidents with respect to each accident type. The cause-and-effect diagram is then depicted as a tool for navigating processes of the accident occurrence by structuring causes extracted from LDA. Further, the trends of accidents are identified to explore patterns of accident occurrence in each of types. Three patterns of increasing to decreasing, decreasing to increasing, or only increasing are presented in the case of a chemical plant. The proposed approach helps safety managers systematically supervise the causes and processes of accidents through analysis of text information contained in accident report documents.

• Journal of the Korean Society of Safety
• /
• v.15 no.1
• /
• pp.53-58
• /
• 2000

In a car accident in Kyongju, each of the two occupants insisted that he was not driving the car. The accident was investigated to determine who the driver is through careful review of the collision report, the statements of accident and witness, photographs taken at the scene, and the expert report of the National Institute of Scientific Investigation. The accident was reconstructed based on the physical principles, injuries of occupants, damages of the involved vehicles and their final stops. A mistake was found in the expert report.

• Journal of the Korean Society of Safety
• /
• v.33 no.6
• /
• pp.77-84
• /
• 2018

Report documents of industrial and occupational accidents have continuously been accumulated in private and public institutes. Amongst others, information on narrative-texts of accidents such as accident processes and risk factors contained in disaster report documents is gaining the useful value for accident analysis. Despite this increasingly potential value of analysis of text information, scientific and algorithmic text analytics for safety management has not been carried out yet. Thus, this study aims to develop data processing and visualization techniques that provide a systematic and structural view of text information contained in a disaster report document so that safety managers can effectively analyze accident risk factors. To this end, the risk factor map using text mining and self-organizing map is developed. Text mining is firstly used to extract risk keywords from disaster report documents and then, the Self-Organizing Map (SOM) algorithm is conducted to visualize the risk factor map based on the similarity of disaster report documents. As a result, it is expected that fruitful text information buried in a myriad of disaster report documents is analyzed, providing risk factors to safety managers.

• Journal of Auto-vehicle Safety Association
• /
• v.12 no.3
• /
• pp.52-60
• /
• 2020

Usage of EDR(Event Data Recorder) report for traffic accident analysis is currently increasing due to government regulation of EDR data release. Nevertheless, a lot of investigators simply adopt by comparing the number of ignition cycles(crash) at event to the number of ignition cycles(download) without an exact judgment whether event data occurred by this accident or not. In the EDR report, besides ignition cycles, there are many factors such as event record type, algorithm active(rear/rollover/side/frontal), time between events, event severity status(rollover/rear/right side/reft side/frontal), belt switch circuit status, driver/passenger pretensioner/air-bag deployment, PDOF(Principal Direction of Force) by ΔV to be able to decide whether or not to adopt. also the event data is considered enough to vehicle damaged state, accident situation at the scene of the accident. and there is described in "all data should be examined in conjunction with other available physical evidence from the vehicle and scene" in the CDR(Crash Data Retrieval) report. Therefore many investigators have to decide whether or not to adopt after they consider sufficiently to above factors when they are the traffic accident analysis and investigate the causes of a accident on the adopted event data. In this paper, we report to traffic accident investigators notable points and analysis methods on the basis of thousands of cases and the results of one's own experiment in NFS(National Forensic Service).

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.2
• /
• pp.167-182
• /
• 2022

The accident data attributes of the traffic accident report are used not only in traditional traffic safety-related research to identify the cause of traffic accidents, but also as basis data for the development of the automated vehicle driving performance verification scenarios. However, since the data attributes of the traffic accident report are limited for the purpose of reconstructing the traffic situation and developing scenarios, this study aims to provide the directions for improvement of traffic accident report, ultimately for its expanded usability for the automated vehicle test scenarios. The directions for improvement of the traffic accident report are provided by categorizing the traffic situation before the accident (pre-crash), the situation immediately before or during the accident (on-crash), and the situation after the accident (post-crash), respectively. Additional data items or data processing methods are presented. Furthermore, data elements that can be extracted from the traffic accident process data in the unstructured narrative form are explored and provided.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.28 no.1
• /
• pp.106-114
• /
• 2020

The Lion Air JT610 accident in Indonesia in October 2018, along with the Ethiopian Airline ET302 accident in March 2019, is an significant aircraft accident that detects defects of the B737MAX aircraft. Shortly after the accident, the FAA prohibited operation of the aircraft. This action has affected the market environment of airlines and aircraft manufacturers around the world. In October 2019, Indonesian Traffic Safety Committee released an accident investigation report for Lion Air JT610, which concluded that the causes of the accident were MCAS design defects, lack of education and training, and errors in the repair process. This paper summarizes the flight control system of the B737MAX aircraft, the causes of the accident based on the final accident investigation report, and provides considerations for aircraft design and retrofit.

• The Journal of Korean Obstetrics and Gynecology
• /
• v.23 no.4
• /
• pp.187-195
• /
• 2010

Purpose: The purpose of this report is to report the clinical application and safety of oriental treatment to pain and symptoms caused by traffic accident during early pregnancy. Methods: The three patients who suffered from several pain and symptoms caused by traffic accident during early pregnancy were treated with herbal medicine, acupuncture, moxibustion, cupping therapy and physical treatment during their admission. And we followed up by phone call after their delivery. Results: Patients' pain and symptoms of this case were improved with oriental treatment during their admission. And serious side effects were not found on the patients and infants after treatment. Conclusion: This report shows that oriental treatment can be effective for those who suffering from several pain and symptoms caused by traffic accident during early pregnancy.

• Journal of the Korean Society of Safety
• /
• v.36 no.1
• /
• pp.56-63
• /
• 2021

The narrative texts of industrial accident reports help to identify accident risk factors. They relate the accident triggers to the sequence of events and the outcomes of an accident. Particularly, a set of related keywords in the context of the narrative can represent how the accident proceeded. Previous studies on text analytics for structuring accident reports have been limited to extracting individual keywords without context. We proposed a context-based analysis using a Natural Language Processing (NLP) algorithm to remedy this shortcoming. This study aims to apply Word2Vec of the NLP algorithm to extract adjacent keywords, known as word embedding, conducted by the neural network algorithm based on supervised learning. During processing, Word2Vec is conducted by adjacent keywords in narrative texts as inputs to achieve its supervised learning; keyword weights emerge as the vectors representing the degree of neighboring among keywords. Similar keyword weights mean that the keywords are closely arranged within sentences in the narrative text. Consequently, a set of keywords that have similar weights presents similar accidents. We extracted ten accident processes containing related keywords and used them to understand the risk factors determining how an accident proceeds. This information helps identify how a checklist for an accident report should be structured.

• Proceedings of KOSOMES biannual meeting
• /
• 2017.11a
• /
• pp.123-123
• /
• 2017

• Journal of Radiation Protection and Research
• /
• v.21 no.3
• /
• pp.217-253
• /
• 1996

Following after the Chernobyl accident. the response to the large scale nuclear accidents became a clear example to show how these accidents affect the public information that strongly depend on political, economical, and social factors. Futhermore, in present day although we live in the era of various information, as far as the problem of nuclear is concerned, the acceptance of the source of Information is always apt to limited. Therefore, in this investigations, as a case study, an attempt is to make the method of minimizing and a preparation to cope with the grope of countermeasure for psychologically unsettled and disordered problems that accepted from both of the unconfirmed and of the exaggerated circumstantial report of mass media as well as a clue to the probability under the condition of existence of major and minor nuclear accidents. In the present paper, it also intends to establish the terminology that covered all the part of nuclear field use in a writing guideline to the scientific column of nuclear accident as shown in the table. and several methodology in relation to the report tendency of mass communication in nuclear accident and the standpoint of public acceptance from a intrinsic point of view are discussed.