• 로봇학회논문지
• /
• 제10권2호
• /
• pp.90-95
• /
• 2015

The main goal of e-learning systems is just-in-time knowledge acquisition. Rule-based e-learning systems, however, suffer from the mesa effect and the cold start problem, which both result in low user acceptance. E-learning systems suffer a further drawback in rendering the implementation of a natural interface in humanoids difficult. To address these concerns, even exceptional questions of the learner must be answerable. This paper aims to propose a method that can understand the learner's verbal cues and then intelligently explore additional domains of knowledge based on crowd data sources such as Wikipedia and social media, ultimately allowing for better answers in real-time. A prototype system was implemented using the NAO platform.

• Educational Technology International
• /
• 제23권2호
• /
• pp.129-155
• /
• 2022

This study sought to design and develop an interactive video player (IVP) capable of promoting student engagement through the use of online video content. We designed features built upon interactive, constructive, active, passive (ICAP), and crowd learning frameworks. In the development stage of this study, we integrated numerous interactive features into the IVP intended to help learners shift from passive to interactive learning activities. We then explored the effectiveness and usability of the developed IVP by conducting an experiment in which we evaluated students' exam scores after using either our IVP or a conventional video player. There were 158 college students who participated in the study; 76 students in the treatment group used the IVP and 82 students in the control group used a conventional video player. Results indicate that the participants in the experiment group demonstrated better achievement than the participants in the control group. We further discuss the implications of this study based on an additional survey that was administered to disclose how usable the participants perceived the IVP to be.

• 한국전자통신학회논문지
• /
• 제8권6호
• /
• pp.847-854
• /
• 2013

본 논문은 모바일 학습의 사운드 레코딩과 플레이어를 위한 스마트폰 애플리케이션을 구현한다. 스마트폰은 유비쿼터스로 언제 어디서나 사용 가능하고, 오디오를 지원하고 마이크로폰을 내장하고 있기 때문에 본 논문에서 제안하는 사운드 레코딩과 플레이어 애플리케이션의 개발은 추가적인 인프라가 필요없이 가격이 싸고 쉬운 방법으로 프로그래밍을 개발할 수 있다. 그리고 안드로이드 플랫폼에 내장된 DBMS인 SQLite를 이용하여 내장된 데이터베이스 기술에 기반한 노래의 가사 데이터 처리에 대한 기법을 설명한다. 따라서 스마트폰의 사운드 레코딩과 플레이어 앱을 개발하여 모바일 폰에 음원 파일만 있다면 언제 어디서나 음원에 맞춰 자신의 음성을 녹음할 수 있다. 따라서 본 논문은 학습자가 추가적인 인프라를 구성하지 않고 모바일 학습의 활성화를 기대할 수 있다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제34권7호
• /
• pp.585-594
• /
• 2007

오류역전파 방법을 이용하는 신경망들은 패턴들의 학습시간이 매우 오래 걸리고 또한 추가학습과 반복학습의 한계를 가지며, 이런 단점을 보완할 수 있는 이진신경망(Binary Neural Network, BNN)이 Aleksander에 의해 제안되었다. 그러나 BNN도 반복학습에 있어서는 단점을 가지고 있으며, 일반화 패턴을 추출하기 어렵다. 본 논문에서는 BNN의 구조를 개선하여 반복학습과 추가학습이 가능할 뿐 아니라, 특징점들까지 추출할 수 있는 다중 판별자를 가지는 삼차원 뉴로 시스템을 제안한다. 제안된 모델은 기존의 BNN을 기반으로 하여 만들어진 이차원 특징을 가지는 Single Layer Network(SLN)에 귀환회로가 추가되어 특징점들을 누적할 수 있는 삼차원 신경망이다. 학습을 통해 누적된 정보는 판별자의 각 신경세포에 임계치를 조정함으로써 일반화 패턴을 추출할 수 있다. 그리고 생성된 일반화 패턴을 인식에 재사용함으로써 반복학습의 효율성을 높였다. 최종 판정 단계에서는 Maximum Response Detector(MRD)를 이용하였다. 본 논문에서 제안한 시스템을 평가하기 위하여 NIST에서 제공하는 숫자 자료를 이용하였으며, 99.3%의 인식률을 얻었다.

• Design & Manufacturing
• /
• 제15권4호
• /
• pp.24-31
• /
• 2021

In this study, an artificial neural network model was constructed to convert CAE analysis data into similar experimental data. In the analysis and experiment, the injection molding data for 50 conditions were acquired through the design of experiment and random selection method. The injection molding conditions and the weight, height, and diameter of the product derived from CAE results were used as the input parameters for learning of the convert model. Also the product qualities of experimental results were used as the output parameters for learning of the convert model. The accuracy of the convert model showed RMSE values of 0.06g, 0.03mm, and 0.03mm in weight, height, and diameter, respectively. As the next step, additional randomly selected conditions were created and CAE analysis was performed. Then, the additional CAE analysis data were converted to similar experimental data through the conversion model. An artificial neural network model was constructed to predict the quality of injection molded product by using converted similar experimental data and injection molding experiment data. The injection molding conditions were used as input parameters for learning of the predicted model and weight, height, and diameter of the product were used as output parameters for learning. As a result of evaluating the performance of the prediction model, the predicted weight, height, and diameter showed RMSE values of 0.11g, 0.03mm, and 0.05mm and in terms of quality criteria of the target product, all of them showed accurate results satisfying the criteria range.

• 영어어문교육
• /
• 제10권2호
• /
• pp.133-158
• /
• 2004

The purpose of the present study was to scrutinize computer games that can motivate elementary school students through their interactive "edutainment" effects. The types of elements in computer games that students find interesting as learning media and their impact were studied. The current status of Korean computer games, issues related to learning English, and methods to stimulate the motivation and interest in learning by elementary school students were explored. A computer game model for efficiently teaching English to elementary school students through a connection between computer games and education was suggested. In this model, overall games were designed with the focus on the integration of curriculum and content subjects related to learning activities. For games not to be biased toward entertainment and to have systemized learning steps, the games are composed of an introduction, presentation, practice, production and evaluation, in that order. The model suggested by this plan and composition make it possible to approach learning efficiently with entertaining games based on a systematic learning curriculum. As shown above, developing the model of educational computer games can be seen as an opportunity, which can provide amusement and interests and a broad learning experience as an additional learning method.

• 한국간호교육학회지
• /
• 제16권2호
• /
• pp.202-212
• /
• 2010

Purpose: The purpose of this study was to identify the effectiveness of the JigsawⅣ cooperative learning in a facilitative communication class of nursing students. Achievement, communication skill, self-directed learning and experience during the class were measured. Method: This study was a pretest and posttest design with two subject groups. 43 students were in experimental (JigsawⅣ) group and 47 ones were in control (general small discussion) group. Classes were conducted over a 6-week period. The collected data was analyzed by the SPSS 12.0 program. Result: After taking part in the educational program, the experimental group had significantly more improvement in communication skill (F=6.81, p=.002) and self-directed learning (F=11.81, p=.000). In addition, the experimental group showed significantly higher scores for concentration in the class (t=2.26, p=.27), positive emotional state (t=3.01, p=.003) and active participation (t=2.78, p=.007) compared to the control group. However, the achievement between the two groups was not significantly different (F=3.29, p=.073). Conclusion: The findings of this study show that JigsawⅣ cooperative learning has positive effects in improvement of communication skill and self-directed learning. Also, students were excited and interested in the class during cooperative learning. Based on these findings, the author suggests developing additional educational programs focusing on nursing students.

• KEPCO Journal on Electric Power and Energy
• /
• 제7권2호
• /
• pp.323-328
• /
• 2021

Diagnostic models are required. Data augmentation is one of the best ways to improve deep learning performance. Traditional augmentation techniques that modify image brightness or spatial information are difficult to achieve great results. To overcome this, a generative adversarial network (GAN) technology that generates virtual data to increase deep learning performance has emerged. GAN can create realistic-looking fake images by competitive learning two networks, a generator that creates fakes and a discriminator that determines whether images are real or fake made by the generator. GAN is being used in computer vision, IT solutions, and medical imaging fields. It is essential to secure additional learning data to advance deep learning-based fault diagnosis solutions in the power industry where facilities are strictly maintained more than other industries. In this paper, we propose a method for generating power facility images using GAN and a strategy for improving performance when only used a small amount of data. Finally, we analyze the performance of the augmented image to see if it could be utilized for the deep learning-based diagnosis system or not.

• 대한후두음성언어의학회지
• /
• 제33권3호
• /
• pp.142-155
• /
• 2022

Diagnosis using voice is non-invasive and can be implemented through various voice recording devices; therefore, it can be used as a screening or diagnostic assistant tool for laryngeal voice disease to help clinicians. The development of artificial intelligence algorithms, such as machine learning, led by the latest deep learning technology, began with a binary classification that distinguishes normal and pathological voices; consequently, it has contributed in improving the accuracy of multi-classification to classify various types of pathological voices. However, no conclusions that can be applied in the clinical field have yet been achieved. Most studies on pathological speech classification using speech have used the continuous short vowel /ah/, which is relatively easier than using continuous or running speech. However, continuous speech has the potential to derive more accurate results as additional information can be obtained from the change in the voice signal over time. In this review, explanations of terms related to artificial intelligence research, and the latest trends in machine learning and deep learning algorithms are reviewed; furthermore, the latest research results and limitations are introduced to provide future directions for researchers.

• Asia pacific journal of information systems
• /
• 제3권1호
• /
• pp.155-189
• /
• 1993

Empirical studies have shown that the performance of decision tree induction usually improves when the trees are pruned. Whether these results hold in general and to what extent pruning improves the accuracy of a concept have not been investigated theoretically. This paper provides a theoretical study of pruning. We focus on a particular type of pruning and determine a bound on the error due to pruning. This is combined with PAC (Probably Approximately Correct) Learning theory to determine a sample size sufficient to guarantee a probabilistic bound on the concept error. We also discuss additional pruning rules and give an analysis for the pruning error.