• Journal of Sensor Science and Technology
• /
• v.30 no.4
• /
• pp.261-266
• /
• 2021

A simple memristor model is proposed for the neuromorphic system in the Simulation Program for Integrated Circuits Emphasis (SPICE). The memristive I-V characteristics with different voltage and frequencies were analyzed. And with the model, we configured a learning and inference system with 4 by 4 memristor array to show the practical use of the model. We examined the applicability by configuring the simplest neuromorphic circuit. The total simulation time for the proposed model was 18% lesser than that for the one-memristor model. When compared with more memristor models in a circuit, the time became even shorter.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2008.05a
• /
• pp.296-299
• /
• 2008

E-Learning 환경에서 학습자에게 보다 정확한 맞춤형 교육 시스템을 제공하기 위하여 평가 문항 및 학습 문항의 난이도, 변별도 등과 같은 문항 정보 활용이 필요하다. 본 논문에서는 문항 난이도, 변별도의 수치를 메타데이터에 저장하고, 평가 문항 및 학습 문항을 저작할 수 있는 템플릿(Templates) 및 GUI(Graphical User Interface) 기반의 SMIL(Synchronized Multimedia Integration Language) 저작도구를 설계 구현 하였다. 구현한 시스템은 SMIL 문법을 모르는 교수자가 문항 난이도, 변별도를 메타데이터에 저장하고, 학습 문항을 쉽게 저작하는데 효율적이다. 또한 저작된 문항은 XML(Extensible Markup Language) 기반 메타데이터를 활용함으로서 다른 플랫폼과의 통합 관리 및 재사용에 용이하다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.137-140
• /
• 2000

We provide an useful method to design codebooks with better performance than conventional methods. In the proposed method, new codevectors obtained by learning iterations are not the centroid vectors which is the representatives of partitions, but the vectors manipulated by the distance between new codevectors and old codevectors in the early stages of learning iteration. Experimental results show that the codevectors in the obtained by the proposed method converge to a better locally optimal codebook.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.307-309
• /
• 2023

본 논문에서는 LSTM Autoencoder를 활용한 전동기의 Anomaly Detection을 제안한다. 전동기의 Anomaly Detection를 통해 전동킥보드의 고장을 예방하여 이용자의 안전을 보장한다. 전동기로부터 얻은 시계열 진동 데이터와 시계열 데이터 분석에 유의미한 LSTM을 활용한 Autoencoder를 통해 Anomaly Detection을 구현했다. 그 결과 99.9%의 정확도를 기록하였다.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.49 no.6
• /
• pp.39-47
• /
• 2012

As a scheme to efficiently reduce the effects of multipath fading in next generation wireless communication systems, cooperative communication systems have recently come into the spotlight. Since these cooperative communication systems use cooperative relays with diverse fading coefficients to transmit information, having all relays participate in cooperative communication may result in unnecessary waste of resources, and thus relay selection schemes are required to efficiently use wireless resources. In this paper, we propose an efficient relay selection scheme through self-learning in cooperative wireless networks using Q-learning algorithm. In this scheme, we define states, actions and two rewards to achieve good SER (Symbol Error Rate) performance, while selecting a small number of cooperative relays. When these parameters are well-defined, we can obtain good performance. For demonstrating the superiority of the proposed Q-learning, We compared the proposed scheme with Q-learning and a relay selection scheme with a mathematical analysis. The simulation results show that, compared to a scheme that obtains optimum relays through a mathematical analysis, the proposed scheme uses resources efficiently by using smaller numbers of relays with comparable SER performance. According to these simulation results, the proposed scheme can be considered as a good attempt for future wireless communication.

• 전자공학회논문지 IE
• /
• v.48 no.2
• /
• pp.71-78
• /
• 2011

The purpose of the present study is to examine the causal relationship among self-regulated learning, social presence, learning flow and satisfaction in cyber education utilizing electronic media. For this study, 304 students at W cyber university in Korea completed surveys in the fall semester of 2010. The result of this study indicated that there was a meaningful effect of self-regulated learning on learning flow and satisfaction. In addition, we founded learning flow has an intermediating effect between self-regulated learning and satisfaction. Based on these results, this study propose strategies to raise satisfaction by improving students' leading role in their learning.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.05a
• /
• pp.136-138
• /
• 2013

In this paper, we investigate on overall trends and movements in e-learning performance at University. And system developed a e-learning platform consisting of smart phone portal, learning management system(LMS), and learning content management system(LCMS). Throughout the experiment, each of the components of the e-learning were implemented.

• KIISE Transactions on Computing Practices
• /
• v.22 no.2
• /
• pp.107-112
• /
• 2016

The Sejong Electronic(machine-readable) Dictionary, developed by the 21st century Sejong Plan, contains systematically organized information on Korean words. It helps to solve problems encountered in the electronic formatting of the still-commonly-used hard-copy dictionary. The Sejong Electronic Dictionary, however has a limitation relate to sentence structure and selection-restricted nouns. This paper discuses the limitations of word-sense disambiguation(WSD) that uses subcategorization information suggested by the Sejong Electronic Dictionary and generalized selection-restricted nouns from the Korean Lexico-semantic network. An alternative method that utilized semi-supervised learning, the chi-square test and some other means to make WSD decisions is presented herein.

• Journal of the Korean Society of Radiology
• /
• v.81 no.6
• /
• pp.1305-1333
• /
• 2020

Deep learning has recently achieved remarkable results in the field of medical imaging. However, as a deep learning network becomes deeper to improve its performance, it becomes more difficult to interpret the processes within. This can especially be a critical problem in medical fields where diagnostic decisions are directly related to a patient's survival. In order to solve this, explainable artificial intelligence techniques are being widely studied, and an attention mechanism was developed as part of this approach. In this paper, attention techniques are divided into two types: post hoc attention, which aims to analyze a network that has already been trained, and trainable attention, which further improves network performance. Detailed comparisons of each method, examples of applications in medical imaging, and future perspectives will be covered.

• Journal of Elementary Mathematics Education in Korea
• /
• v.7 no.1
• /
• pp.1-22
• /
• 2003

This study was done in order to suggest a desirable organizational and developmental strategy of electronic textbooks for elementary school mathematics. First of all, it was intended to set up the exact definition of electronic textbooks for elementary school mathematics by surveying previous researches and examinations regarding elementary mathematics and electronic textbooks, and showed were the total organizational model of electronic textbooks for elementary mathematics by analyzing related cases. Finally, it was intend to present a developmental strategy for each level and an effective method to secure its content.