• 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.

• Educational Technology International
• /
• 제18권1호
• /
• pp.1-25
• /
• 2017

Educational applications of big data analysis have been of interest in order to improve learning effectiveness and efficiency. As a basic challenge for educational applications, the purpose of this study is to develop a comprehensive data set scheme for learning analytics in the context of digital textbook usage within the K-12 school environments of Korea. On the basis of the literature review, the Start-up Mega Planning model of needs assessment methodology was used as this study sought to come up with negotiated solutions for different stakeholders for a national level of learning metrics framework. The Ministry of Education (MOE), Seoul Metropolitan Office of Education (SMOE), and Korean Education and Research Information Service (KERIS) were involved in the discussion of the learning metrics framework scope. Finally, we suggest a proposal for the national learning metrics framework to reflect such considerations as dynamic education context and feasibility of the metrics into the K-12 Korean schools. The possibilities and limitations of the suggested framework for learning metrics are discussed and future areas of study are suggested.

• 지식경영연구
• /
• 제5권1호
• /
• pp.19-38
• /
• 2004

The present paper examines the effect of "community of learning" factors as well as learning and contextual factors on the e-learning performance empirically. The concept of community of learning, which was derived from community of practice, has not been emphasized in previous studies on e-learning. Data were collected from 226 people who had experienced e-learning and multiple regression analysis was used to analyze the data. The results are as follows; First, learning motivation and appropriateness of learning contents, ease of system use, and knowledge sharing have a positive effect on learner's satisfaction. Whereas, learning motivation, appropriateness of learning contents, ease of system use, knowledge sharing, and activated communication are appeared to affect the ability of performing tasks significantly.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• 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.

• International Journal of Computer Science & Network Security
• /
• 제22권9호
• /
• pp.1-6
• /
• 2022

Teaching and learning are one of the major issues during this pandemic (COVID-19). Since the pandemic started, there are many changes in teaching and learning styles as everything related to studies started online. Game-Based Learning has got remarkable importance in the educational system and pedagogy as an effective way of increasing student inspiration and engagement. In this field, most of the work has been carried out in digital games. This research uses an Animated Game-Based Learning design in enhancing student engagement and perception of learning. In teaching Computer Science (CS) concepts in higher education, to enhance the pedagogy activities in CS concepts, more specifically the concepts of "Data Structures (DS)" i.e., Array, Stack, and Queue concepts are focused. This study aims to observe the difference in students' learning with the use of different learning methods i.e., the traditional learning (TL) method and the Animated Game-Based Learning (AGBL) Method. The experimental results show that learning DS concepts has been improved by the AGBL method as compared to the TL method.

• 한국인공지능학회지
• /
• 제5권1호
• /
• pp.18-28
• /
• 2017

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.

• 전자통신동향분석
• /
• 제33권5호
• /
• pp.103-110
• /
• 2018

Studies on artificial intelligence have been developed for the past couple of decades. After a few periods of prosperity and recession, a new machine learning method, so-called Deep Learning, has been introduced. This is the result of high-quality big- data, an increase in computing power, and the development of new algorithms. The main targets for deep learning are 1D audio and 2D images. The application domain is being extended from a discriminative model, such as classification/segmentation, to a generative model. Currently, deep learning is used for processing 3D data. However, unlike 2D, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become more popular owing to advances in 3D vision technology, the generation/acquisition of 3D data remains a very difficult problem. Moreover, it is not easy to directly apply an existing network model, such as a convolution network, owing to the variety of 3D data representations. In this paper, we summarize the 3D deep learning technology that have started to be developed within the last 2 years.

• 한국전자통신학회논문지
• /
• 제14권3호
• /
• pp.547-552
• /
• 2019

최근, 빅데이터 분야에서는 빅 데이터의 양적 팽창이 주요 이슈로 떠오르고 있다. 더군다나 이러한 빅데이터는 기계학습의 입력값으로 사용되어지고 있으며 이들의 성능을 향상시키기 위해 정규화 전처리가 필요하다. 이러한 성능은 빅데이터 컬럼의 범위나 정규화 전처리 방식에 따라 크게 좌우된다. 본 논문에서는 다양한 종류의 정규화 전처리 방식과 빅데이터 컬럼의 범위를 조절하면서 서포트벡터머신(SVM)의 기계학습방식에 적용함으로써 더욱 효과적인 정규화 전처리 방식을 파악하고자 하였다. 이를 위하여 파이썬언어와 주피터 노트북 환경에서 기계학습을 수행하고 분석하였다.

• International journal of advanced smart convergence
• /
• 제11권4호
• /
• pp.68-80
• /
• 2022

Since the launch of AI, technology development to implement complete and sophisticated AI functions has continued. In efforts to develop technologies for complete automation, Machine Learning techniques and deep learning techniques are mainly used. These techniques deal with supervised learning, unsupervised learning, and reinforcement learning as internal technical elements, and use the Big-data Analysis method again to set the cornerstone for decision-making. In addition, established decision-making is being improved through subsequent repetition and renewal of decision-making standards. In other words, big data analysis, which enables data classification and recognition/recognition, is important enough to be called a key technical element of AI function. Therefore, big data analysis itself is important and requires sophisticated analysis. In this study, among various tools that can analyze big data, we will use a Python program to find out what variables can affect addiction according to smartphone use in a decision tree environment. We the Python program checks whether data classification by decision tree shows the same performance as other tools, and sees if it can give reliability to decision-making about the addictiveness of smartphone use. Through the results of this study, it can be seen that there is no problem in performing big data analysis using any of the various statistical tools such as Python and R when analyzing big data.

• International Journal of Computer Science & Network Security
• /
• 제22권5호
• /
• pp.342-347
• /
• 2022

On Cloud, the important data of the user that is protected on remote servers can be accessed via internet. Due to rapid shift in technology nowadays, there is a swift increase in the confidential and pivotal data. This comes up with the requirement of data security of the user's data. Data is of different type and each need discrete degree of conservation. The idea of data security data science permits building the computing procedure more applicable and bright as compared to conventional ones in the estate of data security. Our focus with this paper is to enhance the safety of data on the cloud and also to obliterate the problems associated with the data security. In our suggested plan, some basic solutions of security like cryptographic techniques and authentication are allotted in cloud computing world. This paper put your heads together about how machine learning techniques is used in data security in both offensive and defensive ventures, including analysis on cyber-attacks focused at machine learning techniques. The machine learning technique is based on the Supervised, UnSupervised, Semi-Supervised and Reinforcement Learning. Although numerous research has been done on this topic but in reference with the future scope a lot more investigation is required to be carried out in this field to determine how the data can be secured more firmly on cloud in respect with the Machine Learning Techniques and cryptographic methods.