• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.529-534
• /
• 2021

Computing thinking is regarded as one of the important skills required in the 21st century, and many countries have introduced and implemented computing thinking training courses. Among computational thinking education methods, educational game-based methods increase student participation and motivation, and increase access to computational thinking. Autothinking is an educational game developed for the purpose of providing computational thinking education to learners. It is an adaptive system that dynamically provides feedback to learners and automatically adjusts the difficulty according to the learner's computational thinking ability. However, because the game was designed based on rules, it cannot intelligently consider the computational thinking of learners or give feedback. In this study, game data collected through Autothikning is introduced, and game score prediction that reflects computational thinking is performed in order to increase the adaptability of the game by using it. To solve this problem, a comparative study was conducted on linear regression, decision tree, random forest, and support vector machine algorithms, which are most commonly used in regression problems. As a result of the study, the linear regression method showed the best performance in predicting game scores.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.667-671
• /
• 2024

Professional job training for government officers emphasizes establishing desirable values as public officials and improving professionalism in public service. To provide customized education, some studies are analyzed factors affecting education satisfaction. However, there is a lack of research predicting education satisfaction with educational contents. Therefore, we propose a deep learning-based regression model that predicts government officer education satisfaction with educational contents. We use education information data for government officer. We use one-hot encoding to categorize variables collected in text format, such as education targets, education classifications, and education types. We quantify the education contents stored in text format as TF-IDF. We train our deep learning-based regression model and validate model performance with 10-Fold Cross Validation. Our proposed model showed 99.87% accuracy on test sets. We expect that customized education recommendations based on our model will help provide and improve optimized education content.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.61-68
• /
• 2010

The objective of this study was to test the estimation possibility of driver's stress degrees with the HRV analysis. For this, first, HRV analysis was applied to the 5 driver's ECG signals which were acquired in 7 different stress situations. From this, the facts that HRV trend was different from that in long-distance driving and 6 parameters - meanRR, sdRR, HF, LF/HF, LFnorm, HFnorm were useful for the stress estimation in stress varying driving situation. Next, we designed 5 personalized linear regression models in which 6 HRV parameters were input and the outcomes were 7 different stress degrees. Finally, we tested each model for 5min-long 16 segments individually. Consequently, the models could not hit the stress degrees exactly in some segments but the correlation coefficients between original stress pattern and estimated stress pattern during entire driving showed reasonably high.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.1A
• /
• pp.142-155
• /
• 2000

In this paper, we propose an efficient policing mechanism for Markov model-based traffic descriptors of VBR MPEG video traffic. A VBR video sequence is described by a set of traffic descriptors using a scene-basedMarkov model to the network for the effective resource allocation and accurate QoS prediction. The networkmonitors the input traffic from the source using a proposed new policing method. for policing the steady statetransition probability of scene states, we define two representative monitoring parameters (mean holding andrecurrence time) for each state. For frame level cell rate policing of each scene state, accumulated average cellrates for the frame types are compared with the model parameters. We propose an exponential bounding functionto accommodate dynanic behaviors during the transient period. Our simulation results show that the proposedpolicing mechanism for Markovian traffic descriptors monitors the sophisticated traffic such as MPEG videoeffectively and well protects network resources from the nalicious or misbehaved traffic.

• Annual Conference of KIPS
• /
• 2024.05a
• /
• pp.419-422
• /
• 2024

최근 인공지능 기술의 발전과 함께 기계학습과 빅데이터를 융합한 서비스가 증가하게 되었고, 무분별한 데이터 수집과 학습으로 인한 개인정보 유출 위험도가 커졌다. 따라서 프라이버시를 보호하면서 기계학습을 수행할 수 있는 기술이 중요해졌다. 동형암호 기술은 정보 주체자의 개인정보 기밀성을 유지하면서 기계학습을 할 수 있는 방법 중 하나이다. 그러나 평문 크기에 비례하여 암호문 크기와 연산 결과의 노이즈가 커지는 동형암호의 특징으로 인해 기계학습 모델의 예측 정확도가 감소하고 학습 시간이 오래 소요되는 문제가 발생한다. 본 논문에서는 부분 동형암호화된 데이터셋으로 로지스틱 회귀 모델을 학습할 수 있는 기법을 제안한다. 실험 결과에 따르면 제안하는 기법이 종래 기법보다 예측 정확도를 59.4% 향상시킬 수 있었고, 학습 소요 시간을 63.6% 개선할 수 있었다.

• Journal of Power System Engineering
• /
• v.13 no.5
• /
• pp.76-81
• /
• 2009

The fatalities of pedestrian account for about 21.2% of all fatalities at 2007 year in Korea. To reconstruct exactly the accident, it is important to calculate the throw distance of pedestrian in car to pedestrian accident. The frontal shape of SUV vehicle is dissimilar to passenger car and bus, so the trajectory and throw distance of pedestrian by SUV vehicle is not the same of passenger car and bus. The influencing on it can be classified into the factors of vehicle and pedestrian, and road factor. It was analyzed by PC-CRASH for simulation, and SPSS s/w was used for regression analysis. From the simulation results, the maximum impact energy of multi-body of pedestrian was occurred to that of torso body at the same time. And the throw distance increased with the increasing of impact velocity, and decreased with the increasing of impact offset. Also it decreased with the increasing of velocity of pedestrian at accident, and the throw distance of wet road was longer than that of dry road. Finally, the regression analysis model of SUV(Nissan Pathfinder type)vehicle in car to pedestrian accident was as follows; $$disti_i=-0.87-0.11offseti_i+0.69speed_i-4.27height_i+0.004walk_i+0.63wet_i+{\epsilon}_i$$.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.20-28
• /
• 2004

Estimation of software project cost, effort, and duration in the early stage of software development cycle is a difficult and key problem in software engineering. Most of development effort and duration estimation models presented by regression model of simple relation function point vs. effort and effort vs. duration instead of considering developer's productivity. But different project have need for different effort according to developer's productivity if the projects are same software size. Also, different duration takes according to developer's productivity if the projects require the same effort. Therefore, models that take into account of productivity have a limited application in actual development project. This paper presents models that can be estimate the duration according to productivity in order to compensate a shortcoming of the previous models. Propose model that could presume development period by various methods based on productivity and compared models' performance. As a result of performance comparison, an estimating model of development period from software size got simple and most good result. The model gives decision-making information of development duration to project management in the early stage of software life cycle.

• The Journal of Information Systems
• /
• v.16 no.1
• /
• pp.1-21
• /
• 2007

신용평점을 위한 부도예측의 분류 문제를 다루는데 있어서 통계적 판별분석 및 인공신경망 및 유전자알고리즘 등을 이용한 데이터 마이닝의 방법들이 일반적으로 고려되어왔다. 이 연구에서는 수리계획법을 응용하여 classification gap을 고려한 이단계 수리계획 접근방법을 신용평가에 적용하는 방법론을 제안하여 수리계획법을 통한 신용평가모형 구축의 가능성을 제시한다. 1단계에서는 선형계획법을 이용해서 대출 신청자에게 대출을 허가할 것 인지의 여부를 결정하게 되는 대출 심사 filtering으로의 적용단계이고, 2단계에서는 정수계획법을 이용하여 오분류 비용이 최소가 되도록 하는 판별점수를 찾는 과정으로 모형을 구성한다. 개인 대출 신청자의 데이터(German Credit Data)에 대하여 피셔의 선형 판별함수, 로지스틱 회귀모형 및 기존의 수리계획 기법들과의 비교를 통해서 제안된 모델의 성능을 평가한다. 이단계 수리계획 접근법의 평가 결과를 통하여 신용평가모형에의 적용가능성을 기존 통계적인 접근방법 및 수리계획 접근법과 비교하여 제시하고 있다.

• Journal of the Korea Institute of Building Construction
• /
• v.12 no.1
• /
• pp.122-132
• /
• 2012

Establishing a success model of a specific information system is critical to understanding the mechanism of IS success, the various dimensions of IS performance, and the factors and their causal relations in IS success. As one of the key IT applications, the project management information system (PMIS), particularly the web-based PMIS (Web-PMIS), has played a significant role in construction management processes in Korea. However, there have been few research attempts made to construct a Web-PMIS success model. This study primarily aims to propose a Web-PMIS success model based on DeLone and McLean's IS success model, and to discuss whether or not the D&M IS success model can be applied to the construction Web-PMIS. A questionnaire was sent out to Web-PMIS users (construction managers and constructors), and 253 completed questionnaires were received. Through multi-regression analysis, it was confirmed that it is statistically acceptable to apply the D&M IS success model to the Web-PMIS. However, the explanatory power of the model is not sufficient, and some of the model factors are not statistically significant enough. Relying on the statistical analysis results, this study also discusses the development direction for the Web-PMIS success model.

• Journal of the Korea Society for Simulation
• /
• v.16 no.2
• /
• pp.45-54
• /
• 2007

In this article, we propose a different modeling approach, which aims at the simulation optimization so as to meet the design specification. Generally, Multi objective optimization problem is formulated by dependent factors as objective functions and independent factors as constraints. However, this paper presents the critical(dependent) factors as objective function and design(independent) factors as constraints for the selection of design factors directly. The objective function is normalized far the generalization of design factors while the constraints are composed of the simulation-based regression metamodels fer the critical factors and design factor's domain. Then the effective and fast solution procedure based on the pareto optimal solution set is proposed. This paper provides a comprehensive framework for the system design using the simulation and metamodels. Therefore, the method developed for this research can be adopted for other enhancements in different but comparable situations.