• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.4
• /
• pp.68-80
• /
• 2016

This study proposes the traffic prediction and optimal traffic control system based on cell transmission model and genetic algorithm in cloud environment. The proposed prediction and control system consists of four parts. 1) Data preprocessing module detects and imputes the corrupted data and missing data points. 2) Data-driven traffic prediction module predicts the future traffic state using Multi-level K-Nearest Neighbor (MK-NN) Algorithm with stored historical data in SQL database. 3) Online traffic simulation module simulates the future traffic state in various situations including accident, road work, and extreme weather condition with predicted traffic data by MK-NN. 4) Optimal road control module produces the control strategy for large road network with cell transmission model and genetic algorithm. The results show that proposed system can effectively reduce the Vehicle Hours Traveled upto 60%.

• The Journal of Information Systems
• /
• v.8 no.2
• /
• pp.145-168
• /
• 1999

There are still occurring aviation accidents in spite of great preventing efforts all over the world. This paper contains some methods to prevent aircrafts deficiencies and accidents. First part of this paper refers to the background of those aviation deficiencies on mechanical, human and environment structures which influence directly to the air accidents and general survey on various theories of the aircraft's systems. On the way we discussed the general situations of the air tool's deficiencies which cause tragic accidents to the human lives and assets. After analysis on the situations we suggest the new systems which would forecast more detail accuracies concerned air elements for the safety flying. Then we introduce the following new systems resulting from the forecasting which can solve problems on aircraft deficiencies and complex interrelationships among air accidental factors. To simplify the complex systems, we needed to build the mechanical and organizational database for maintaining the procedures of the past troubleshooting on the major parts preventing deficiencies of those mechanical units. These suggested systems will contribute a great deal of aids, the maintenance credibility and air safety for the air operations and all customers in the world. Avoiding the past troubleshooting from just by using simple systems which can forecast main causes of the units and parts of the crafts, this system will be able to provide excellent management tools for the promoting aviational industries. The comfortable and convenient air operations are very valuable works, and the scientific method and detail maintenance will improve our daily air life by minimizing accidents. Adapting these developing systems, for the forecasting aircraft deficiencies and accidents can be integrated with the other aircraft management systems to promote more air safety in the world. This study is focused to eliminating aircraft accidents through forecasting deficiency symptom procedures by relational coordinations among all of the systems. Futhermore we need continuously detailed analysis and study for eliminating air accidents all together those who work in those fields.

• Journal of Biomedical Engineering Research
• /
• v.26 no.6
• /
• pp.399-406
• /
• 2005

In these days, HIS(Hospital Information System) raise the quality of medical services by effective management of medical records. As computing environment was developed, it is possible to search information quickly. But, standard medical data exchange is not completed between medical clinic and another organ so far. In case of patient transfer, past medical record was not efficiently transmitted. It be feasible treatment delay or medical accident. It is trouble that medical records is transferred by a person and communicate with each other. Extensible Markup Language (XML) is a simple, very flexible text format derived from SGML. Originally designed to meet the challenges of large-scale electronic publishing, XML is also playing an increasingly important role in the exchange of a wide variety of data on the Web and elsewhere. Form in system of company product, relative organs that handle bio-signal data is each other dissimilar and integration and to transmit to supplement bottleneck this research uses XML. In this study, it is discussed about sharing of medical data using XML web technology to standard medical record between hospital and relative organization The data structure model was designed to manage bio-signal data and patient record. We experimented about data transmission and all-in-one between different systems (one make use of MS-SQL database system and the other manage existent bio-signal data in itself form in file in this research). In order to search and refer medical record, the web-based system was implemented. The system that can be shared medical data was tested to estimate the merits of XML. Implemented XML schema confirms data transmission between different data system and integration result.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.22 no.3
• /
• pp.52-58
• /
• 2008

The importance of. identifying the causes of electrical faults cannot be overstated because of the accidents caused by over-current that take place at the home, the office and electrical facilities due to misuse, poor products and system faults. It is necessary to gather objective, scientific data pertaining to electrical fault investigation in a product liability(PL) environment. To date, no database(DB) has been built concerning the accurate cause analysis of faultyfacilities. In this paper, accident hazard and arc scattering when over-current flows in copper wire was investigated. It was found that when over-current flows in a copper wire, the copper wire became heated and bent and beads were scattered around the wire with a flash. It was determinedthat the fusing current and time was related to the current rise per second. For example, when the current rise per second was largethe fusing current was higher than when the current rise per second was small, and the beads dispersed along a wide area. Fusing time, however, was shorter. The possibility of electrical fault became highest when the fusing current was higher. As the current rise per second is short, the dendrite structure is distributed in the surface of the copper wire. These experimental results can be utilized for a fault process DB system in the investigation and the prevention of electrical faults.

• Journal of the Society of Disaster Information
• /
• v.9 no.3
• /
• pp.266-275
• /
• 2013

New paradigm to the advancement of disaster management is required for building resilient and safe society. In these circumstances, the importance of local government disaster management capacity has been emphasized through experiencing a series of accidents including 2012 september Gumi fluorosilicic acid diffusion accident. The increase of people's disaster awareness has emerged the public demands on disaster management information of local area. In this study, the disaster management capacity analysis program is developed for self-assessment of local government. The program is designed for disaster managers to database the categorized index of disaster management capacity and recognize the capacity level. For the public announcement of disaster management capacity, the analysis results are shown for citizens in the understandable format. It is expected that the enhancement of emergency management capacity of local society can be achieved by the efforts of local government analyzing and improving the vulnerability as well as the participation of local society.

• Korean Journal of Remote Sensing
• /
• v.24 no.2
• /
• pp.153-164
• /
• 2008

According to the economic growth, many highways are constructed for increasing need of better life style. Especially roads and roadside facilities are used for accident prevention and offering mobility for drivers. For these purpose, roads and roadside facilities should be well maintained and managed. Now, many roads and roadside facilities are constructed in many areas. Because of traditional surveying method requires much time and surveying efforts, we designed and developed mobile mapping system for highway maintenance and management purpose using multi sensors. We tested our mobile mapping system and data management process. Using developed database, road managers can easily check the information of facility conditions, positions, and attributes. We are expecting low cost and efficient road maintenance process by using our system.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.47 no.5
• /
• pp.365-372
• /
• 2021

Objectives: Mandibular fractures vary significantly with respect to epidemiological and demographic parameters among populations. To date, no study has evaluated these aspects of mandibular fractures in Nuh, Mewat, Haryana, India. To retrospectively analyze the incidence, age and sex distributions, etiology, anatomic distribution, occlusal status, treatment modality provided, and their correlation in patients who suffered isolated mandibular fractures. Materials and Methods: The records of maxillofacial injury patients who reported to the Department of Dentistry, SHKM Government Medical College from January 2013 to December 2019, were retrieved from our database, and necessary information was collected. The data collected were analyzed statistically using IBM SPSS ver. 21. Results: Totals of 146 patients and 211 fractures were analyzed. There were 127 males and 19 females with an age range of 3-70 years (mean age, 26 years). Road traffic accident (RTA) was the most common cause of fracture (64.4%), followed by fall (19.9%), assault (15.1%), and sports injury (0.7%). Of all patients, 42.5% had bilateral fractures, 31.5% had left side fracture, 21.2% had right side fracture, 3.4% sustained midline symphyseal fracture, and 1.4% had symphyseal fracture along one side of the mandible. Site distribution was as follows: parasymphysis (34.6%), angle (23.7%), condyle (20.4%), body (12.8%), symphysis (4.3%), ramus 2.4%, and dentoalveolar 1.9%. The most common facture combination was angle with parasymphysis (17.8%). Occlusion was disrupted in 69.2% patients. Closed reduction was the predominant treatment modality. Conclusion: The data obtained from retrospective analyses of maxillofacial trauma increase the understanding of variables and their outcomes among populations. The results of the present study are comparable to those of the literature in some aspects and different in others.

• Journal of Trauma and Injury
• /
• v.34 no.3
• /
• pp.147-154
• /
• 2021

Purpose: We analyzed the characteristics and outcomes of patients with bicycle-related injuries at a regional trauma center in northern Gyeonggi Province as a first step toward the development of improved prevention measures and treatments. Methods: The records of 239 patients who were injured in different types of bicycle-related accidents and transported to a single regional trauma center between January 2017 and December 2018 were examined. This retrospective single-center study used data from the Korea Trauma Database. Results: In total, 239 patients experienced bicycle-related accidents, most of whom were males (204, 85.4%), and 46.9% of the accidents were on roads for automobiles. Forty patients (16.7%) had an Injury Severity Score (ISS) of 16 or more. There were 125 patients (52.3%) with head/neck/face injuries, 97 patients (40.6%) with injuries to the extremities, 59 patients (24.7%) with chest injuries, and 21 patients (8.8%) with abdominal injuries. Patients who had head/neck/face injuries and an Abbreviated Injury Score (AIS) ≥3 were more likely to experience severe trauma (ISS ≥16). In addition, only 13 of 125 patients (10.4%) with head/neck/face injuries were wearing helmets, and patients with injuries in this region who were not wearing helmets had a 3.9-fold increased odds ratio of severe injury (AIS ≥2). Conclusions: We suggest that comprehensive accident prevention measures, including safety training and expansion of safety facilities, should be implemented at the governmental level, and that helmet wearing should be more strictly enforced to prevent injuries to the head, neck, and face.

• Database Research
• /
• v.34 no.3
• /
• pp.45-57
• /
• 2018

The drowsiness that occurs in the driving is a very dangerous driver condition that can be directly linked to a major accident. In order to prevent drowsiness, there are traditional drowsiness detection methods to grasp the driver's condition, but there is a limit to the generalized driver's condition recognition that reflects the individual characteristics of drivers. In recent years, deep learning based state recognition studies have been proposed to recognize drivers' condition. Deep learning has the advantage of extracting features from a non-human machine and deriving a more generalized recognition model. In this study, we propose a more accurate state recognition model than the existing deep learning method by learning image and PPG at the same time to grasp driver's condition. This paper confirms the effect of driver's image and PPG data on drowsiness detection and experiment to see if it improves the performance of learning model when used together. We confirmed the accuracy improvement of around 3% when using image and PPG together than using image alone. In addition, the multimodal deep learning based model that classifies the driver's condition into three categories showed a classification accuracy of 96%.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.119-127
• /
• 2022

Most of the construction works are conducted outdoors, so the construction workers are affected by weather conditions such as temperature, humidity, and wind velocity which can be evaluated the thermal comfort as environmental factors. In our previous researches, it was found that construction accidents are usually occurred in the discomfort ranges. The safety management, therefore, should be planned in consideration of the thermal comfort and measured by a specialized simulation tool. However, it is very complex, time-consuming, and difficult to model. To address this issue, this study is aimed to develop a framework of a prediction model for improving the prediction accuracy about outdoor thermal comfort considering environmental factors using machine learning algorithms with hyperparameter tuning. This study is done in four steps: i) Establishment of database, ii) Selection of variables to develop prediction model, iii) Development of prediction model; iv) Conducting of hyperparameter tuning. The tree type algorithm is used to develop the prediction model. The results of this study are as follows. First, considering three variables related to environmental factor, the prediction accuracy was 85.74%. Second, the prediction accuracy was 86.55% when considering four environmental factors. Third, after conducting hyperparameter tuning, the prediction accuracy was increased up to 87.28%. This study has several contributions. First, using this prediction model, the thermal comfort can be calculated easily and quickly. Second, using this prediction model, the safety management can be utilized to manage the construction accident considering weather conditions.