• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10b
• /
• pp.395-400
• /
• 1993

This paper presents an application of back propagation neural network to the tracking control of line of sight stabilization system. We design a neuro-control system having two neural networks one for learning system dynamics and the other for control. We use a learning method which adjusts learning rate and momentem as a function of plant output error and error change.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.555-556
• /
• 2021

We propose a novel method based on a deep learning model with an optimized dynamic decay learning rate and improved model structure to achieve fast and accurate classification of fashion clothing images.

• Journal of dental hygiene science
• /
• v.20 no.4
• /
• pp.206-212
• /
• 2020

Background: A Teachable Machine is a kind of machine learning web-based tool for general persons. In this paper, the feasibility of Google's Teachable Machine (ver. 2.0) was studied in the diagnosis of the tooth-marked tongue. Methods: For machine learning of tooth-marked tongue diagnosis, a total of 1,250 tongue images were used on Kaggle's web site. Ninety percent of the images were used for the training data set, and the remaining 10% were used for the test data set. Using Google's Teachable Machine (ver. 2.0), machine learning was performed using separated images. To optimize the machine learning parameters, I measured the diagnosis accuracies according to the value of epoch, batch size, and learning rate. After hyper-parameter tuning, the ROC (receiver operating characteristic) analysis method determined the sensitivity (true positive rate, TPR) and specificity (false positive rate, FPR) of the machine learning model to diagnose the tooth-marked tongue. Results: To evaluate the usefulness of the Teachable Machine in clinical application, I used 634 tooth-marked tongue images and 491 no-marked tongue images for machine learning. When the epoch, batch size, and learning rate as hyper-parameters were 75, 0.0001, and 128, respectively, the accuracy of the tooth-marked tongue's diagnosis was best. The accuracies for the tooth-marked tongue and the no-marked tongue were 92.1% and 72.6%, respectively. And, the sensitivity (TPR) and specificity (FPR) were 0.92 and 0.28, respectively. Conclusion: These results are more accurate than Li's experimental results calculated with convolution neural network. Google's Teachable Machines show good performance by hyper-parameters tuning in the diagnosis of the tooth-marked tongue. We confirmed that the tool is useful for several clinical applications.

• 전기의세계
• /
• v.17 no.1
• /
• pp.48-50
• /
• 1968

The convergence rate of Bayes' learning process is investigated for a binomial random variable. A measure of the rate of convergence is proposed and it is found that such a measure can be approximated by an exponential function of the number of observations.

• The Journal of the Korea Contents Association
• /
• v.18 no.4
• /
• pp.128-137
• /
• 2018

This study aims to investigate how learning materials are used in an outstanding English class and to analyze learning materials and their use in primary English classroom activities. To this end, An Analytic Scheme of Learning Materials Use (ASLMU) is used to quantify utilization patterns of learning materials. The findings are: Learning materials are most actively used in the development period, followed by introduction and consolidation. The teacher's rate of using learning materials is much higher than student's, and the rate of using materials for whole students is higher than the rate of using materials for an individual or groups. It requires developing learning materials toward more a student-centered class because the teacher's occupancy of the learning materials is fourfold compared to the student's occupancy. Also, non-language materials are used more than language materials, and English materials are used more than Korean materials. Most of the materials are used to present a question and explain. The findings of the study are expected to suggest features of learning materials in an outstanding English class and application method of learning materials to primary English teachers.

• Education of Primary School Mathematics
• /
• v.18 no.1
• /
• pp.31-44
• /
• 2015

This study aims to test effect of transfer learning program rather than students' transfer ability. For these purpose, firstly this study design transfer learning program to apply from 'rate concept' in learning math class to 'velocity concept' in science class. Subsequently, this study is to analyze whether this program affect on 'the rate concept understanding' and 'the mathematics learning attitude'. Followings are the findings from this study. First, transfer learning program affect on improving students' rate concept understanding. Moreover, 17 among 35 students' who stay in 'ratio level' move to 'internalized ratio level'. Second, besides transfer learning program is not only cause to change students' learning attitude, this program impact on changing their learning attitude positively. The study has an important implications in that it designed new learning program that students experience transfer and test its effect.

• Education of Primary School Mathematics
• /
• v.24 no.4
• /
• pp.217-231
• /
• 2021

The purpose of this study was to investigate the effects of flipped learning through EBSmath on Students' 'rate and ratio' learning. By increasing demands for change in education, an innovative teaching and learning paradigm, 'Flipped Learning', has been presented and drawing attentions. In South Korea, Flipped Learning is also highly recognized for its effectiveness by many scholars and various media. However, this innovative learning model has limitations in application and expansion due to the excessive burden of class preparation of teachers. As remote learning becomes more active, it would be possible to overcome the limitations of Filliped learning by using the platform provided by the Korea Educational Broadcasting System (EBS). EBSmath is an online learning module that is designed to assist students' self-directed learning. Thus, EBSmath would reduce teachers' burden to prepare mathematics classes for the application of Flipped Learning; and led to students' better understanding of mathematical concepts and problem solving. In this study, the effect of Flipped Learning through EBSmath on learning 'rate and ratio' was investigated. In order to scrutinize the effects of flipped learning, students' achievement and mathematical disposition were examined and analyzed. Students' achievement, specifically, was divided into two subcategories: concept understanding and problem solving. As a result, Flipped learning through EBSmath had a positive effect on students' 'rate and ratio' problem solving. In addition, a statistically significant change was identified in the 'willingness', which is subdomain of students' mathematical disposition.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.3
• /
• pp.522-532
• /
• 1995

Multilayer neural networks with backpropagation learning algorithm are widely used for pattern classification problems. For many real applications, it is more important to reduce the misclassification rate than to increase the rate of successful classification. But multilayer perceptrons(MLP's) have drawbacks of slow learning speed and false convergence to local minima. In this paper, we propose a new method for character recognition problems with a single-layer network and double rejection mechanisms, which guarantees a very low misclassification rate. Comparing to the MLP's, it yields fast learning and requires a simple hardware architecture. We also introduce a new coding scheme to reduce the misclassification rate. We have prepared two databases: one with 135,000 digit patterns and the other with 117,000 letter patterns, and have applied the proposed method for printed character recognition, which shows that the method reduces the misclassification rate significantly without sacrificing the correct recognition rate.

• International journal of advanced smart convergence
• /
• v.8 no.4
• /
• pp.68-74
• /
• 2019

Along with the deeper architecture in the deep learning approaches, the need for the data becomes very big. In the real problem, to get huge data in some disciplines is very costly. Therefore, learning on limited data in the recent years turns to be a very appealing area. Meta-learning offers a new perspective to learn a model with this limitation. A state-of-the-art model that is made using a meta-learning framework, Meta-SGD, is proposed with a key idea of learning a hyperparameter or a learning rate of the fast adaptation stage in the outer update. However, this learning rate usually is set to be very small. In consequence, the objective function of SGD will give a little improvement to our weight parameters. In other words, the prior is being a key value of getting a good adaptation. As a goal of meta-learning approaches, learning using a single gradient step in the inner update may lead to a bad performance. Especially if the prior that we use is far from the expected one, or it works in the opposite way that it is very effective to adapt the model. By this reason, we propose to add a weight term to decrease, or increase in some conditions, the effect of this prior. The experiment on few-shot learning shows that emphasizing or weakening the prior can give better performance than using its original value.

• KIEAE Journal
• /
• v.17 no.5
• /
• pp.95-100
• /
• 2017

Purpose: The purpose of this study is to investigate the prior art based on deep learning to objectively calculate the metabolic rate which is the subjective factor for the PMV optimum control and to make a plan for future research based on this study. Methods: For this purpose, the theoretical and technical review and applicability analysis were conducted through various documents and data both in domestic and foreign. Results: As a result of the prior art research, the machine learning model of artificial neural network and deep learning has been used in various fields such as speech recognition, scene recognition, and image restoration. As a representative case, OpenCV Background Subtraction is a technique to separate backgrounds from objects or people. PASCAL VOC and ILSVRC are surveyed as representative technologies that can recognize people, objects, and backgrounds. Based on the results of previous researches on deep learning based on metabolic rate for occupational metabolic rate, it was found out that basic technology applicable to occupational metabolic rate calculation technology to be developed in future researches. It is considered that the study on the development of the activity quantity calculation model with high accuracy will be done.