• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.33 no.5
• /
• pp.535-542
• /
• 2007

Ameloblastoma, a benign tumor of odontogenic type, represents 10% of all tumors of the jaw. It is localized in the mandible(80%) and in the maxilla(20%). In every case, the selection of the surgical treatment must consider some fundamental elements, including the age and general state of health the clinicopathological variant, and the localization and extent of the tumor. This study was invested the clinicopathological findings of 23 patients with ameloblastoma which had been diagnosed by biopsy during the period of 1987 to 2005 at Chonnam National University Hospital. And it contained the statistical analysis according to the treatment methods and the clinicopathological findings such as sex, age, location, chief complaints, duration, radiographic findings, histologic findings, treatment methods. The results obtained are were follows. The age of patient ranged from 10 to 91 years(means, 35.9 years) at biopsy. Thirteen(57%) of the 23 subjects were males, and 10(43%) were females. Twenty(87%) of the 23 ameloblastomas were located in the mandible. Swelling was the most common symptom and was experienced by 20(87%) patients. Radiographically, 11(48%) of the 23 tumors were unilocular with a well-demarcated border and 12(52%) were multilocular. The most common histologic pattern was plexiform and acanthomatous rather then follicular. Conservative treatment was performed 7 cases(30%), radical treatment 11 cases(48%), and combined treatment 5 cases(22%). Follow-up period ranged from 2.1 years to 22 years(mean 5.1 years). Based on the above results, surgical excision after marsupialization was found to be useful as a preliminary treatment of the large cystic ameloblastoma in children and adolescents. On the contrary, the lesion with a soap bubble appearance, the one with ineffective marsupialization was subjected to extensive excision of the tumor with a wide margin of normal bone.

• Journal of the Korean Society of Radiology
• /
• v.12 no.7
• /
• pp.861-868
• /
• 2018

As the research about supplementary education of radiological technologist who works in medical clinics, this study was conducted to draw the improvements by analyzing the satisfaction level and problems of the supplementary education. During November 01, 2016 to April 30, 2017, after we distributed a total of 150 questionnaires for the survey to radiological technologists working at medical clinics located in Changwon-si, Gyoungsangnam province, 106 questionnaires suitable for research were analysis by using SPSS 18.0 statistical analysis software. As the sociodemographic characteristics, the age, gender, working period, level of education, and working department were used. And As the welfare factors, working environment, financial support, educational opportunity, medical support, working culture, etc. were used. As the satisfaction factors, 21 items such as system, subject, help, appropriateness of lecturer selection, professionalism were used. And as the problem factors, 18 items such as place, transportation, diversity, administrative treatment, education promotion, proceed method were used. Consequentially, the satisfaction level(3.02 point) of the supplementary education were confirmed as normal level. And the problems(3.18 point) of the supplementary education was analyzed a little higher. The supplementary education is the mandatory education that any health and medical service personnel must complete every three years for license re-issuance. There were many opinions that the supplementary education for radiologists working in various medical institutions did not meet the education level of radiologists working in the medical clinics. In order to improve the satisfaction of the supplementary education of medical clinic's radiological technologist, it should be improved the quality of education through a practical education program that reflects various opinions and improvements on conservative education.

• The Journal of Bigdata
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2018

The study is based on machine learning techniques to increase the accuracy of the forest fire predictive model. It used 14 years of data from 2003 to 2016 in Gang-won-do where forest fire were the most frequent. To reduce weather data errors, Gang-won-do was divided into nine areas and weather data from each region was used. However, dividing the forest fire forecast model into nine zones would make a large difference between the date of occurrence and the date of not occurring. Imbalance issues can degrade model performance. To address this, several sampling methods were applied. To increase the accuracy of the model, five indices in the Canadian Frost Fire Weather Index (FWI) were used as derived variable. The modeling method used statistical methods for logistic regression and machine learning methods for random forest and xgboost. The selection criteria for each zone's final model were set in consideration of accuracy, sensitivity and specificity, and the prediction of the nine zones resulted in 80 of the 104 fires that occurred, and 7426 of the 9758 non-fires. Overall accuracy was 76.1%.

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.309-327
• /
• 2021

Dynamic treatment regimes (DTRs) are decision-making rules designed to provide personalized treatment to individuals in multi-stage randomized trials. Unlike classical methods, in which all individuals are prescribed the same type of treatment, DTRs prescribe patient-tailored treatments which take into account individual characteristics that may change over time. The Q-learning method, one of regression-based algorithms to figure out optimal treatment rules, becomes more popular as it can be easily implemented. However, the performance of the Q-learning algorithm heavily relies on the correct specification of the Q-function for response, especially in observational studies. In this article, we examine a number of double-robust weighted least-squares estimating methods for Q-learning in high-dimensional settings, where treatment models for propensity score and penalization for sparse estimation are also investigated. We further consider flexible ensemble machine learning methods for the treatment model to achieve double-robustness, so that optimal decision rule can be correctly estimated as long as at least one of the outcome model or treatment model is correct. Extensive simulation studies show that the proposed methods work well with practical sample sizes. The practical utility of the proposed methods is proven with real data example.

• Journal of the Society of Disaster Information
• /
• v.17 no.4
• /
• pp.848-863
• /
• 2021

Purpose: On August 16, 2021, the Taliban established the Taliban regime after conquering capital Kabul of the Afghan by using the strong alliance of international terrorist organizations. The Taliban carried out terrorism targeting the Korean people, including the kidnapping of Kim Seon-il in 2004, the abduction of a member of the Saemmul Church in 2007, and the attack on Korean Provincial Reconstruction Team in 2009. Therefore, this research has shown the possibility of Taliban terrorism in Korea. Method: Based on the statistical data on terrorism that occurred in Afghanistan, Taliban's various terrorist activities such as tactics, strategies, and weapons are examined. Consequently, the target facilities and the type of terrorist attacks are analyzed. Result: The Taliban are targeting the Afghan government as their main target of attack, and IS and the Taliban differ in their selection of targets for terrorism. Conclusion: From the result of this research, we recommend Korea need to reinforce the counter terrorism system in soft targets. Because If the Taliban, which has seized control of Afghanistan, and IS, which has established a worldwide terrorism network, cooperate to threaten domestic multi-use facilities with bombing, the Republic of Korea may face a terrorist crisis with insufficient resources and counter-terrorism related countermeasures.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.5
• /
• pp.19-32
• /
• 2023

The fragmentation of habitats resulting from human activities leads to the isolation of wildlife and it also causes wildlife-vehicle collisions (i.e. Road-kill). In that sense, it is important to predict potential habitats of specific wildlife that causes wildlife-vehicle collisions by considering geographic, environmental and transportation variables. Road-kill, especially by large mammals, threatens human safety as well as financial losses. Therefore, we conducted this study on roe deer (Capreolus pygargus tianschanicus), a large mammal that causes frequently Road-kill in Jeju Island. So, to predict potential wildlife habitats by considering geographic, environmental, and transportation variables for a specific species this study was conducted to identify high-priority restoration sites with both characteristics of potential habitats and road-kill hotspot. we identified high-priority restoration sites that is likely to be potential habitats, and also identified the known location of a Road-kill records. For this purpose, first, we defined the environmental variables and collect the occurrence records of roe deer. After that, the potential habitat map was generated by using Random Forest model. Second, to analyze roadkill hotspots, a kernel density estimation was used to generate a hotspot map. Third, to define high-priority restoration sites, each map was normalized and overlaid. As a result, three northern regions roads and two southern regions roads of Jeju Island were defined as high-priority restoration sites. Regarding Random Forest modeling, in the case of environmental variables, The importace was found to be a lot in the order of distance from the Oreum, elevation, distance from forest edge(outside) and distance from waterbody. The AUC(Area under the curve) value, which means discrimination capacity, was found to be 0.973 and support the statistical accuracy of prediction result. As a result of predicting the habitat of C. pygargus, it was found to be mainly distributed in forests, agricultural lands, and grasslands, indicating that it supported the results of previous studies.

• Journal of Internet Computing and Services
• /
• v.24 no.5
• /
• pp.17-27
• /
• 2023

Today, as AI (Artificial Intelligence) technology develops and its practicality increases, it is widely used in various application fields in real life. At this time, the AI model is basically learned based on various statistical properties of the learning data and then distributed to the system, but unexpected changes in the data in a rapidly changing data situation cause a decrease in the model's performance. In particular, as it becomes important to find drift signals of deployed models in order to respond to new and unknown attacks that are constantly created in the security field, the need for lifecycle management of the entire model is gradually emerging. In general, it can be detected through performance changes in the model's accuracy and error rate (loss), but there are limitations in the usage environment in that an actual label for the model prediction result is required, and the detection of the point where the actual drift occurs is uncertain. there is. This is because the model's error rate is greatly influenced by various external environmental factors, model selection and parameter settings, and new input data, so it is necessary to precisely determine when actual drift in the data occurs based only on the corresponding value. There are limits to this. Therefore, this paper proposes a method to detect when actual drift occurs through an Anomaly analysis technique based on XAI (eXplainable Artificial Intelligence). As a result of testing a classification model that detects DGA (Domain Generation Algorithm), anomaly scores were extracted through the SHAP(Shapley Additive exPlanations) Value of the data after distribution, and as a result, it was confirmed that efficient drift point detection was possible.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.2
• /
• pp.15-31
• /
• 2024

The characteristics of elderly traffic accidents were identified by reflecting the situation of the elderly population in Korea, which is entering an ultra-aging society, and the relationship between independent and dependent variables was analyzed by classifying traffic accidents of serious or higher and traffic accidents of minor or lower in elderly pedestrian traffic accidents using binomial variables. Data collection, processing, and variable selection were performed by acquiring data from the elderly pedestrian traffic accident analysis system (TAAS) for the past 10 years (from 13 to 22 years), and basic statistics and analysis by accident factors were performed. A total of 15 influencing variables were derived by applying the logistic regression model, and the influencing variables that have the greatest influence on the probability of a traffic accident involving severe or higher elderly pedestrians were derived. After that, statistical tests were performed to analyze the suitability of the logistic model, and a method for predicting the probability of a traffic accident according to the construction of a prediction model was presented.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.1
• /
• pp.63-73
• /
• 2024

Autonomous vehicles at Levels 3 to 5, currently under global research and development, seek to replace the driver's perception, judgment, and control processes with various sensors integrated into the vehicle. This integration enables artificial intelligence to autonomously perform the majority of driving tasks. However, autonomous vehicles currently obtain temporary driving permits, allowing them to operate on roads if they meet minimum criteria for autonomous judgment abilities set by individual countries. When autonomous vehicles become more widespread in the future, it is anticipated that buyers may not have high confidence in the ability of these vehicles to avoid hazardous situations due to the limitations of temporary driving permits. In this study, we propose a method for grading the judgment abilities of autonomous vehicles based on a driving simulator experiment comparing and evaluating drivers' abilities to avoid hazardous situations. The goal is to derive evaluation criteria that allow for grading based on specific scenarios and to propose a framework for grading autonomous vehicles. Thirty adults (25 males and 5 females) participated in the driving simulator experiment. The analysis of the experimental results involved K-means cluster analysis and independent sample t-tests, confirming the possibility of classifying the judgment abilities of autonomous vehicles and the statistical significance of such classifications. Enhancing confidence in the risk-avoidance capabilities of autonomous vehicles in future hazardous situations could be a significant contribution of this research.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.30 no.4
• /
• pp.340-347
• /
• 2024

In this study, an expert survey was conducted using the Delphi technique to select items and indicators for evaluation before installing educational facilities in the marine fisheries safety field, in which the educational infrastructure gap between regions is wide. Seven indicators were selected as geographic, social, and administrative factors. In order to objectively evaluate each indicator, evaluation indicators that could be evaluated using public data such as the "Comprehensive National Balanced Development Information System" and "National Statistical Portal" were developed. The Analytic Hierarchy Process (AHP) method was applied to select the weight for each indicator, resulting in 10 most important influencing factors on the selection of the location of educational facilities of the Marine Fisheries Safety Education Facilities: the distribution of marine officers, access to high-speed railways, the number of small ships less than 5 tons, access to highways interchange, the distribution of fishing boats, the close relationship of related industries, the planned new port, the distribution of commercial ports, the number of marine leisure riders, and the availability of long-term land leases in local government councils. The location evaluation index of marine and fishery safety education facilities developed in this study can be used to evaluate each region using national public data, and has the advantage of enabling objective evaluation. Therefore, it is judged that this evaluation index can be used to verify the feasibility of installing marine fisheries safety education facilities as well as other marine-related facilities.