• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.7
• /
• pp.211-218
• /
• 1994

Stochastic computation employs random pulse streams to represent numbers. In this paper, we study a new method to implement the number system which uses the ratio of the numbers of ones and zeros in the pulse streams. In this number system. if P is the probability that a pulse is one in a pulse stream then the number X represented by the pulse stream is defined as P/(1-P). We propose circuits to implement the basic operations such as addition multiplication and sigmoid function with this number system and examine the error characteristics of such operations in stochastic computation. We also propose a neuron model and derive a learning algorithm based on backpropagation for the 3-layered feedforward neural networks. We apply this learning algorithm to a digit recognition problem. To analyze the results, we discuss the errors due to the variance of the random pulse streams and the quantization noise of finite length register.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.11
• /
• pp.610-616
• /
• 2000

This paper presents an active noise control algorithm via Walsh transform domain controller learned by genetic algorithm. Typical active noise control algorithms such as the filtered-x lms algorithm are based on the gradient algorithm. Gradient algorithm have two major problems; local minima and eigenvalue ratio. To solve these problems, we propose a combined algorithm which consist of genetic learning algorithm and discrete Walsh transform called Walsh Transform Domain Genetic Algorithm(WTDGA). Analyses and computer simulations on the effect of Walsh transform to the genetic algorithm are performed. The results show that WTDGA increase convergence speed and reduce steady state errors.

• Journal of dental hygiene science
• /
• v.22 no.2
• /
• pp.115-125
• /
• 2022

Background: In the dental hygiene curriculum, efforts are being made to introduce an integrated curriculum based on the competency of a dental hygienist. Because there is a connection and overlap in learning contents between Dental Nutrition and Oral Biochemistry, which are basic dental hygiene subjects, it is possible to integrate these two subjects. This study aims to derive Nutritional Biochemistry as an integrated curriculum for Dental Nutrition and Oral Biochemistry, and to develop learning goals and competencies for Dental Nutritional Biochemistry. Methods: The learning contents of the integrated curriculum were composed by referring to the contents of the Dental Nutrition and Oral Biochemistry textbooks, and learning goals were derived from the learning contents. Moreover, competency was developed by analyzing the duties of a dental hygienist that can be performed through the learning goals. The Delphi survey was conducted twice to verify the content validity ratio (CVR) of the competence and the learning goal of the integrated curriculum. Results: In the first Delphi survey, the CVR for two competencies was 0.56 or higher. Moreover, it was revised based on expert's opinions, and as a result of the second Delphi survey after the revision, the CVR was either increased or maintained. Eighty-five learning goals were derived by referring to the textbook. According to CVR and expert opinions, after the first Delphi survey, the number of learning goals was reduced to 69. After the second Delphi survey, 68 learning goals were finally derived. Conclusion: The development process of the integrated curriculum conducted in this study can be utilized for integration between subjects in basic dental hygiene.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.9 no.3
• /
• pp.20-33
• /
• 2010

The purpose of this research is to investigate and analyze the recognition of students and teachers towards an influence of a subject classroom system to teacher's learning activities and student's learning attitude. The study was subjected to students and teachers at a school that has innovatively operated subject classroom system from before 2009. The results of the research are as follows. First, the result of investigation shows that the quality of class has been improved. The formats of managing class and class materials have become various. Second, there is an affirmative exchange in student's learning attitude, such as student's active participation, concentration, preparation and interest toward a class. Third, the fifty percent of teachers answered it that a block time system and intensive study system is required to manage an efficient subject classroom system. Lastly, the investigation shows that teachers and students are generally satisfied with running the subject classroom system. However, the satisfaction ratio of students is lower than the one of teachers.

• Journal of Korean Association for Spatial Structures
• /
• v.24 no.2
• /
• pp.83-90
• /
• 2024

Machine learning is widely applied to various engineering fields. In structural engineering area, machine learning is generally used to predict structural responses of building structures. The aging deterioration of reinforced concrete structure affects its structural behavior. Therefore, the aging deterioration of R.C. structure should be consider to exactly predict seismic responses of the structure. In this study, the machine learning based seismic response prediction model was developed. To this end, four machine learning algorithms were employed and prediction performance of each algorithm was compared. A 3-story coupled shear wall structure was selected as an example structure for numerical simulation. Artificial ground motions were generated based on domestic site characteristics. Elastic modulus, damping ratio and density were changed to considering concrete degradation due to chloride penetration and carbonation, etc. Various intensity measures were used input parameters of the training database. Performance evaluation was performed using metrics like root mean square error, mean square error, mean absolute error, and coefficient of determination. The optimization of hyperparameters was achieved through k-fold cross-validation and grid search techniques. The analysis results show that neural networks and extreme gradient boosting algorithms present good prediction performance.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.27 no.2
• /
• pp.147-155
• /
• 2024

Based on the recently developed deep learning technology, many studies have been conducted on deep learning networks that simultaneously detect and classify targets of interest in synthetic aperture radar(SAR) images. Although numerous research results have been derived mainly with the open SAR ship datasets, there is a lack of work carried out on the deep learning network aimed at detecting and classifying SAR ground targets and trained with the synthetic dataset generated from electromagnetic scattering simulations. In this respect, this paper presents the deep learning network trained with the synthetic dataset and applies it to detecting and classifying real SAR ground targets. With experiment results, this paper also analyzes the network performance according to the composition ratio between the real measured data and the synthetic data involved in network training. Finally, the summary and limitations are discussed to give information on the future research direction.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.37-41
• /
• 2020

본 논문에서는 Joint CTC/Attention 모델에 CTC ratio scheduling을 이용한 end-to-end 한국어 음성인식을 연구하였다. Joint CTC/Attention은 CTC와 attention의 장점을 결합한 모델로서 attention, CTC 단일 모델보다 좋은 성능을 보여주지만, 학습이 진행될수록 CTC가 attention의 학습을 저해하는 요인이 된다. 본 논문에서는 이러한 문제를 해결하기 위해, 학습 진행에 따라 CTC의 비율(ratio)를 줄여나가는 CTC ratio scheduling 방법을 제안한다. CTC ratio scheduling를 이용하여 학습한 결과물은 기존 Joint CTC/Attention, 단일 attention 모델 대비 좋은 성능을 보여주는 것을 확인하였다.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2004.04a
• /
• pp.231-234
• /
• 2004

Ratio that robot occupies is low level worldwide fairly in suspension wire, electricity electron and neutralization learning industry and domestic industry of this is staring in average love. Can speak that grafting of robotic machine and neutralization learning industry is high in terms of side of creation of the added value or progress of technology rightly hereupon. This research raises or designed multi-function handling robot that can make welding, assembly conveniently catching large size work water

• Journal of Biomedical Engineering Research
• /
• v.12 no.3
• /
• pp.191-202
• /
• 1991

This paper describes ECG data compression algorithm using neural network. As a learning method, we use back error propagation algorithm. ECG data compression is performed using learning ability of neural network. CSE database, which is sampled 12bit digitized at 500samp1e/sec, is selected as a input signal. In order to reduce unit number of input layer, we modify sampling ratio 250samples/sec in QRS complex, 125samples/sec in P & T wave respectively. hs a input pattern of neural network, from 35 points backward to 45 points forward sample Points of R peak are used.

• Journal of Satellite, Information and Communications
• /
• v.9 no.3
• /
• pp.5-8
• /
• 2014

Recently, smart devices can be used with a variety of programs. Because of these characteristics, suitable lectures are provided to mobile device in Korea educational facilities. However, it is possible to reduce the learning efficiency from taking courses. because of many smart devices are using in a small display. Therefore, we need effectively in a small display content layout for overcome these problems. In this paper, we proposed content layer format for smart devices by Illustrated Programs based on Golden Ratio.