• Journal of The Korean Association For Science Education
• /
• v.26 no.2
• /
• pp.246-257
• /
• 2006

TIMSS (Trends in International Mathematics and Science Study) aims to produce reliable and internationally comparable indicators of student achievement. The TIMSS science achievement scale summarizes student performance on test items designed to measure a wide range of student knowledge and proficiency. This study analyzed Korean middle school students' science achievement at the advanced and high international benchmarks of the four benchmark levels of the benchmarks classified in TIMSS 2003 in light of science content areas (physics, chemistry, biology, earth science, and environmental science) and item characteristics. The average percent correct on items at the advanced benchmark by Korean students was highest in physics followed by earth science, biology, chemistry, and environmental science, whereas internationally the order was earth science, chemistry, biology, physics and lastly environmental science. Korean students performed relatively better in physics yet somewhat worse in chemistry than other top-performing countries. According to item analysis, Korean students reaching the advanced international benchmark understood some fundamentals of scientific investigation, but demonstrated weakness in written explanations of scientific principles, abstract science concept comprehension, and application of scientific concepts to solve quantitative problems. In addition, Korean students reaching the high international benchmark demonstrated relative weak conceptual understanding of ecology compared with other countries.

• Journal of KIISE:Computing Practices and Letters
• /
• v.7 no.6
• /
• pp.684-695
• /
• 2001

Recent recommender system uses a method of combining collaborative filtering system and content based filtering system in order to solve sparsity and first rater problem in collaborative filtering system. Collaborative filtering systems use a database about user preferences to predict additional topics. Content based filtering systems provide recommendations by matching user interests with topic attributes. In this paper, we describe a method for discovery of user preference through combining two techniques for recommendation that allows the application of machine learning algorithm. The proposed collaborative filtering method clusters user using genetic algorithm based on items categorized by Naive Bayes classifier and the content based filtering method builds user profile through extracting user interest using relevance feedback. We evaluate our method on a large database of user ratings for web document and it significantly outperforms previously proposed methods.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1161-1170
• /
• 2019

In this study, we propose a model for predicting Cochlodinium polykrikoides red tide occurrence using deep neural networks. A deep neural network with eight hidden layers was constructed to predict red tide occurrence. The 59 marine and meteorological factors were extracted and used for neural network model training using satellite reanalysis data and meteorological model data. The red tide occurred in the entire dataset is very small compared to the case of no red tide, resulting in an unbalanced data problem. In this study, we applied over sampling with adding noise based data augmentation to solve this problem. As a result of evaluating the accuracy of the model using test data, the accuracy was about 97%.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.1
• /
• pp.1-6
• /
• 2020

Patella surgery of small animal is an important veterinary surgery that the veterinarian should saw and drill the dislocated patella in order to fix the corrected position. However, the animal protection laws restrict the veterinarian students' chances for the practice and training of the patella surgery. This paper proposed a haptic based patella surgery simulator for veterinarian students. We modelled force feedback methods in order to provide best similar haptic feedbacks to the real drilling feedbacks in the patella surgery. The proposed patella drilling simulator provides haptic interface as a drill and a workbench in order to provide best surgery experiences. We conducted the performance evaluations in order to prove usability of the proposed patella surgery interface.

• Convergence Security Journal
• /
• v.18 no.5_1
• /
• pp.59-66
• /
• 2018

The performance of a network intrusion detection system using the machine learning method depends heavily on the composition and the size of the feature set. The detection accuracy, such as the detection rate or the false positive rate, of the system relies on the feature composition. And the time it takes to train and detect depends on the size of the feature set. Therefore, in order to enable the system to detect intrusions in real-time, the feature set to beused should have a small size as well as an appropriate composition. In this paper, we show that the size of the feature set can be further reduced without decreasing the detection rate through using Pearson correlation coefficient between features along with the multi-objective genetic algorithm which was used to shorten the size of the feature set in previous work. For the evaluation of the proposed method, the experiments to classify 10 kinds of attacks and benign traffic are performed against NSL_KDD data set.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.9-17
• /
• 2021

With the advancement of big data analysis, artificial intelligence, machine learning, etc., data analytics technology has developed to help with optimal decision-making. However, in certain areas, the lack of data restricts the use of these techniques. For example, real estate related data often have a long release cycle because of its recent release or being a non-liquid asset. In order to overcome these limitations, we studied the scalability of the existing time series through the TimeGAN model. A total of 45 time series related to weekly real estate data were collected within the period of 2012 to 2021, and a total of 15 final time series were selected by considering the correlation between the time series. As a result of data expansion through the TimeGAN model for the 15 time series, it was found that the statistical distribution between the real data and the extended data was similar through the PCA and t-SNE visualization algorithms.

• 대한공업교육학회지
• /
• v.42 no.1
• /
• pp.106-124
• /
• 2017

This study used the secondary Delphi method for experts, in order to propse a proper formation plan for the goal and curriculum of elementary and secondary invention/intellection property education. Its results are as following; First, the key objective of invention/intellectual property education for each school level is evaluated as appropriate. With regard to the key objective, elementary schools are aiming at 'fostering awareness and attitude for invention'(M=4.5), middle schools, 'understanding of invention process and method'(M=4.2), general high schools, 'application and evaluation of invention method'(M=4.1), and specialized high schools, 'understanding and application of Employee Invention'(M=4.6). The objective and goal of education for each school level are also evaluated as appropriate. Second, although the proper formation plans for a key learning element of elementary and secondary invention/intellectual property education were almost identical to an actual formation of preceding literature, overall change is required for the formation balance of each learning element, according to the objective and goal of school-leveled invention/intellectual property education. An appropriate formation shall be focusing on basic learning elements (A, B, C, D, E, and F) for elementary and middle schools(73.2%, 65.1%), lowering somewhat the former elements and increasing expanded learning elements for high schools(51.0%), which are connected to the invention, course(H), and patent application(K). Third, elementary and secondary invention/intellectual property education system should be oriented to its objective and goal. In order to reach this, an appropriate formation plan should be made for each school level, based on the principle of Tyler's learning organization, such as continuity, sequence and integration, which are key learning element. Specialized high schools, in particular, need to be differentiated from general ones, as well as elementary and middle schools. Additionally, for understanding and applying an employee invention, invention/intellectual property education system needs to be established in the phase of secondary occupational education.

• The Journal of Bigdata
• /
• v.5 no.1
• /
• pp.1-9
• /
• 2020

The study was conducted with funding from the government (Ministry of Agriculture, Food and Rural Affairs) in 2018 with support from the Agricultural, Food, and Rural Affairs Agency, 318069-03-HD040, and in based on artificial intelligence-based HPAI spread analysis and patterning. The model that is actively used in time series and text mining recently is LSTM (Long Short-Term Memory Models) model utilizing deep learning model structure. The LSTM model is a model that emerged to resolve the Long-Term Dependency Problem that occurs during the Backpropagation Through Time (BPTT) process of RNN. LSTM models have resolved the problem of forecasting very well using variable sequence data, and are still widely used.In this paper study, we used the data of the Call Detailed Record (CDR) provided by KT to identify the migration path of people who are expected to be closely related to the virus. Introduce the results of predicting the path of movement by learning the LSTM model using the path of the person concerned. The results of this study could be used to predict the route of HPAI propagation and to select routes or areas to focus on quarantine and to reduce HPAI spread.

• Ecology and Resilient Infrastructure
• /
• v.7 no.2
• /
• pp.114-125
• /
• 2020

Despite the various artificial neural networks that have been developed, most of the discharge models in previous studies have been developed using deep neural networks. This study aimed to develop a discharge model using a convolution neural network (CNN), which was used to solve classification problems. Furthermore, the applicability of CNN was evaluated. The photographs (pictures or images) for input data to CNN could not clearly show the characteristics of the study area as well as precipitation. Hence, the model employed in this study had to use numerical images. To solve the problem, the CN of NRCS was used to generate images as input data for the model. The generated images showed a good possibility of applicability as input data. Moreover, a new application of CN, which had been used only for discharge prediction, was proposed in this study. As a result of CNN training, the model was trained and generalized stably. Comparison between the actual and predicted values had an R² of 0.79, which was relatively high. The model showed good performance in terms of the Pearson correlation coefficient (0.84), the Nash-Sutcliffe efficiency (NSE) (0.63), and the root mean square error (24.54 ㎥/s).

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2008.10a
• /
• pp.431-435
• /
• 2008

2006년 11월 이후 신 차량 번호판 등장 후, 신 차량 번호판과 구 차량 번호판이 혼합되어 있다. 이에 따라 속도위반, 신호위반 단속, 무인 주차관리 시스템, 범죄 및 도주 차량 검거, 고속도로 톨게이트에서 통행료 지불로 인한 교통 체증현상을 해소하기 위한 자동 요금 징수와 같은 다양한 경우에서 자동차 번호판의 특징에 맞는 인식 시스템이 요구되고 있다. 따라서 본 논문에서는 이러한 문제를 해결하기 위해 형태학적 특징 및 차 연산과 ART2 알고리즘을 이용한 차량 번호판 인식 방법을 제안한다. 무인 카메라에서 획득된 차량 번호판 영상에서 차 연산을 이용하여 에지를 추출한 후에 블록 이진화를 한다. 이진화 된 차량 영상에서 신 구 차량 번호판의 형태학적 특성을 8방향 윤곽선 추적 알고리즘에 적용하여 잡음 영역을 제거하고, 차량의 번호판 영역을 추출한다 추출된 번호판 영역에 대하여 평균 이진화와 최대 최소 이진화를 적용하여 번호판의 개별 영역에 대한 형태학적 특성을 고려하여 잡음을 제거하고, Labeling 알고리즘을 적용하여 개별 문자를 추출한 후에 결합한다. 이렇게 분류된 개별 문자 및 숫자 코드를 ART2 알고리즘에 적용하여 학습 및 인식을 한다. 제안된 차량 번호판 추출 및 인식 방법의 성능을 평가하기 위해 녹색 번호판과 흰색 번호판 이미지 각각 100장을 대상으로 실험한 결과, 제시 된 차량 번호판 추출 및 인식 방법이 실험을 통해서 효율적인 것을 확인하였다.