• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.347-348
• /
• 2019

컴퓨터 프로그래밍 수업에서 학습자들의 평소 학습 이해도를 파악하는 방법으로 형성평가가 보편적으로 많이 이용되고 있다. 교수자에게 형성평가는 학습자들의 이해도를 파악하는 방법이지만, 평가 결과를 성적에 반영할 때 학습자들에게는 학습 동기를 향상시킬 수 있는 요소임을 선행 연구를 통해 알 수 있었다. 본 연구에서는 수년간 컴퓨터 프로그래밍 수업에 적용해온 형성평가의 문제 난이도를 조절하여 난이도가 학습자들의 학습 동기 부여에 얼마나 영향을 미치는 요소인지를 살펴보고자 한다. 특히 형성 평가에 출제한 문제의 난이도 정도가 형성평가 다음에 이어지는 중간고사나 기말고사 등의 큰 평가에서 얼마나 긍정적인 영향을 미치는지를 통해 학습 동기 부여 정도를 분석하고자 한다.

• Annual Conference on Human and Language Technology
• /
• 2023.10a
• /
• pp.113-118
• /
• 2023

딥러닝을 이용한 언어 모델은 다양한 분야에서 사용되고 있는데, 그 중 교육 분야에선 꾸준히 시험 문항을 자동으로 생성하려는 요구가 존재해 왔다. 그러나 빈칸 추론 문항, 그 중에서도 어구 단위 빈칸 추론 문항은 학습 및 평가 목적으로 널리 쓰이고 있지만, 이를 자동 생성하려는 연구는 상대적으로 드물다. 이에 본 연구에선 masked language modeling (MLM)을 이용한 난이도 조절이 가능한 어구 단위 빈칸 추론 문항 생성 시스템을 제안한다. 본 시스템은 정답 생성 모델의 attention 정보에 따라 지문 내 중요한 어구를 삭제해 오답을 생성하고, 동시에 어구의 삭제 비율을 조절함으로써 더 쉽거나 더 어려운 오답을 만들어낼 수 있다. 평가 결과, 제안한 시스템은 기존 접근법보다 정답과의 유사도가 최고 28.3% 낮았고, 또한 난이도 설정에 따라 쉬운 오답이 어려운 오답에 비해 유사도가 15.1% 낮아, 더 정답과 먼 뜻의 오답을 생성해내었다.

• Journal of the Korean School Mathematics Society
• /
• v.13 no.2
• /
• pp.323-343
• /
• 2010

The purpose of the study was to analyze difficulty analyzed through a quantitative method examining rate of correct answerers to each questions in the side of difficulty that students solving questions felt by finding variables to predict difficulty of questions in an objective way, not in an intuitive way, and examining what variables difficulty that each student solving questions felt depended on. The study divided 6 students in the 3rd grade of a high school into a two-person group or a three-person group and observed their question-solving process the total 11times for three months from March, to May. The study an alyzed what variables difficulty that each student felt depended on through semi-structuralized interview. As a result, the study could see that difficulty of questions depended on contents, strangeness of material, behavioral range, type of questions and complexity of questions.

• Journal of the Korean School Mathematics Society
• /
• v.10 no.1
• /
• pp.113-127
• /
• 2007

This study explored the possibility of building a statistical model predicting difficulty of mathematics test items through the analysis of nation-wide scholastic ability test results for the past 5 years. Multiple linear regression analysis was conducted in predicting difficulty of mathematics test items. We adopted three major areas for independent variables: the content area, the behavior area, and the test item format area, each of which was categorized into more detailed sub-areas. For the dependent variable, the proportion of correct answer was used to represent the item difficulty. Statistically significant independent variables were included in the regression model based on the stepwise selection method. Several important factors affecting difficulty of mathematics test items for each area were identified. R-squares for the final regression model were fairly high, implying that the regression equation can be used to predict difficulty of test items at an acceptable level. Lastly, the regression model was cross-validated using independently collected data. We believe that this study will provide basic but very critical information for predicting the proportion of correct answer by showing the factors that should be considered for developing mathematics test items for the college entrance examination or high school classroom test.

• Journal of Korea Game Society
• /
• v.15 no.4
• /
• pp.169-178
• /
• 2015

Providing various levels of difficulty of game play is one of important considerations in game development. In this paper, we propose a method for obtaining the challenges that will be placed on the track of an one-player car driving game. Herein challenges denote obstacles on the track, and the level of difficulty is represented by an estimated time needed for driving one lap of the track. In the proposed method, the problem for finding challenge placement is modeled as an IP(Integer Programming) one, and then LP relaxation and Simultaneous Annealing are employed to find a solution. To the experiment with the proposed method, we can obtain challenge placements to approximately meet given target driving times. Also, after practically driving on the track where those obtained challenges are being placed, it is seen that the average driving times approximate the target driving times of those challenge placements. Our method can allow game play with various levels of difficulty so that the users' interest and the level of immerse are expected to be raised.

• Journal of the Korea Convergence Society
• /
• v.11 no.3
• /
• pp.67-75
• /
• 2020

The 'level of difficulty' is one of the major factors for learners when selecting learning contents. However, the criteria for the difficulty level is mostly defined by the contents providers. This approach does not support the personalized education which should consider the abilities and environments of various learners. In this research, the knowledge of the learners and contents were formalized and generalized to resolve the issue, and object models, including a metric for personalized difficulty level, were designed in order to be applied for experiments. And then, based on 100 contents for music education and 20 learners, we performed simulations with an implemented tool to validate our approach. The experimental results showed that our method can calculate the personalized difficulty levels considering the similarities between the knowledges from the learning state and the contents. Our approach can be effectively applied to the on-line learning management system which contains easy access to the learning state and contents data.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.1
• /
• pp.225-234
• /
• 2019

Bitcoin is a cryptocurrency with characteristics such as de-centralization and distributed ledger, and these features are maintained through a mining system called "proof of work". In the mining system, mining difficulty is adjusted to keep the block generation time constant. However, Bitcoin's current method to update mining difficulty does not reflect the future hash power, so the block generation time can not be kept constant and the error occurs between designed time and real time. This increases the inconsistency between block generation and real world and causes problems such as not meeting deadlines of transaction and exposing the vulnerability to coin-hopping attack. Previous studies to keep the block generation time constant still have the error. In this paper, we propose a machine-learning based method to reduce the error. By training with the previous hash power, we predict the future hash power and adjust the mining difficulty. Our experimental result shows that the error rate can be reduced by about 36% compared with the current method.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.214-227
• /
• 2021

The purpose of this study is to find the driving difficulty of automated vehicles in terms of road infrastructure operation. It was judged out of this study that the level of automated driving would be enhanced if the road situation recognition ability was advanced through the presentation of infrastructure information during the difficult driving situations. The difficulty evaluation index was divided into three stages, and a survey of experts and an AHP were conducted. The result of the AHP showed that the driving difficulty of the interrupted flow was much higher than that of the uninterrupted flow. The AHP results also showed that and the driving difficulty of unsignalized intersections and roundabouts under an interrupted flow was evaluated as the highest. The top six driving situations with high difficulty were also evaluated to occur under unsignalized intersections and roundabouts.

• Korean Journal of Environment and Ecology
• /
• v.29 no.4
• /
• pp.626-635
• /
• 2015

Recently, the number of trail users in Korea has risen tremendously. Consequently, the cost of safety measures related to hiking is sharply increasing. Despite the safety cost input, the number of heart-related adverse events has been not decreasing. Therefore, this research aims to suggest the use of objective and quantitative trail use information in terms of course difficulty. The study site is Jirisan Dullegil (Jirisan Forest Trail). The currently available trail difficulty information either provides the difficulty rating in terms of 3 to 5 levels according to several empirical difficulty factors reported by staff who maintain the forest or simply states the distance of each trail. Thus, many trail visitors feel a great gap between the given information and actual difficulties they experience. In this study, we tried to assess the degree of difficulty by actual energy consumption. Calculating the volumetric oxygen consumption (VOC) by the distance and gradient not only makes possible an absolute rating but a comparison among the trails as well. Also, it is highly effective to simply describe the exercise intensity of a certain trail. Further, it is easy to check the VOCs' changes by switching the start-end points of the same trail. Providing the trail information of VOCs by sections and directions, we expect to prevent heart-related accidents.

• The korean journal of orthodontics
• /
• v.35 no.1 s.108
• /
• pp.69-81
• /
• 2005

As one of the variations in growth and development of the craniofacial complex. malocclusion shows lack of concordance In the recognition and severity of malocclusion for dentists as well as the acceptance and need of orthodontic treatment for the patient The purposes of this study were 1) to examine the relationships between objective malocclusion severity aid subjective treatment difficulty. 2) to evaluate the effect of malocclusion components to the subjective perceived difficulty of treatment. 3) to establish the weighted values of malocclusion components to reflect the treatment difficulty 100 pairs of dental casts with the general characteristics of malocclusion. were selected from the orthodontic departments of Kyunghee University and Samsuug Medical Center. The severity of malocclusion was evaluated by the author with the PAR index The perceived treatment difficulty and the estimated treatment duration on these dental models were evaluated by 8 experienced orthodontists. The relationships between the objective malocclusion severity and the subjective treatment difficulty were statistically evaluated. and the weighted values of malocclusion components to reflect treatment difficulty were statistically formulated. There were significant relationships between objective malocclusion severity and subjective treatment difficulty The malocclusion components which significantly affected the treatment difficulty and their weighted values in parentheses were as follows upper anterior alignment(1). overbite (2). buccal occlusion (3) middline (4), and overjet (5). This study Provides the fundamental principle to evaluate the objective malocclusion severity which is reflected by the subjective treatment difficulty of Korean orthodontists.