• Journal of the Korea Society of Computer and Information
• /
• v.16 no.8
• /
• pp.39-47
• /
• 2011

Ergezinger's method, one of the layer-by-layer algorithms used for multilyer perceptrons, consists of an output node and can make premature saturations in the output's weight because of using linear least squared method in the output layer. These saturations are obstacles to learning time and covergence. Therefore, this paper expands Ergezinger's method to be able to use an output vector instead of an output node and introduces a learning rate to improve learning time and convergence. The learning rate is a variable rate that reflects the correlation coefficient between new weight and previous weight while updating hidden's weight. To compare the proposed method with Ergezinger's method, we tested iris recognition and nonlinear approximation. It was found that the proposed method showed better results than Ergezinger's method in learning convergence. In the CPU time considering correlation coefficient computation, the proposed method saved about 35% time than the previous method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.11
• /
• pp.2127-2134
• /
• 2007

The electronic learning helped a learner to overcome the time restriction by providing mobility, instantly and flexibility but the restriction in connection with space on cable computer remained unsolved. Accordingly, the electronic learning has tendency to change into mobile learning environment which allows a learner to overcome time and spatial restriction. However, these mobile devices have a limitation to awareness of learning contents provided over the realtime video movie due to its small display size. Therefore, this paper suggests a technique according to the following priority: for a real time learning image, extract region of study for region of interest, rescale the real time image to its proper size suitable for the display device, and then make it displayed on a wireless PDA. As a result of the experiment, we reduced the calculating time by sampling the field centering on learning contents adaptively and computing the field best suited for device size of the user effectively.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.2
• /
• pp.20-25
• /
• 2021

The target-object classification method was implemented using a deep-learning-based detection model in real-time images. The object detection model was a deep-learning-based detection model that allowed extensive data collection and machine learning processes to classify similar target-objects. The recognition model was implemented by changing the processing structure of the detection model and combining developed the vision-processing module. To classify the target-objects, the identity and similarity were defined and applied to the detection model. The use of the recognition model in industry was also considered by verifying the effectiveness of the recognition model using the real-time images of an actual soccer game. The detection model and the newly constructed recognition model were compared and verified using real-time images. Furthermore, research was conducted to optimize the recognition model in a real-time environment.

• Journal of The Korean Association of Information Education
• /
• v.9 no.1
• /
• pp.79-86
• /
• 2005

With the rapid advance of computer and communication technology, the amount of data transferred is also increasing more than ever. The recent trend of education systems is connecting related information semantically in different systems in order to improve the utilization of computerized information Therefore, Web-based teaching-learning is developing in the ubiquitous learning direction that learners select and organize the contents, time and order of learning by themselves. That is, it is evolving to provide teaching-learning environment adaptive to individual learners' characteristics (their level of knowledge, pattern of study, areas of interest). This paper proposes the efficient evaluation method of learning contents in a mediator for the integration of heterogeneous information resources. This means that the autonomy of a remote server can be preserved to the highest degree. In addition, this paper proposes the adaptive optimization of learning contents such that available storage in a mediator can be highly utilized at any time. In order to differentiate the recent usage of a learning content from the past, the accumulated usage frequency of a learning content decays as time goes by.

• Journal of Digital Contents Society
• /
• v.18 no.3
• /
• pp.499-508
• /
• 2017

With the recent advance of IT technology and the change of education paradigm, vocational training has been also evolved. In the background of mobilization of learning, increase of bite-size contents, and the agility of just-in-time learning, this study surveyed the online learners' motivation, perceptions, and learning behaviour. Total 4,021 learners from 6 distance learning institutions revealed that learners take the e-learning courses due to more for their self-development than the company's supports and policy. Also, they perceived the subject matter in contents are the most important. The results from this study suggest that the development of contents should focus on the subject matter that can be utilized for their jobs immediately. Lastly, the study confirms that learning space and time has been changed in the flexible way to use their spare time between work and life. Irregularity of learning and hasty preparations were one of major characteristics in the aspect of learning behaviour.

• The Journal of Korean Association of Computer Education
• /
• v.22 no.5
• /
• pp.27-37
• /
• 2019

In this study, for the purpose of reflection level analysis of high school students in HW design learning which is based on online simulation, we carried out 5 lessons of HW learning and analyzed there reflection levels for 5 individual time of reflection content. The reflection level analysis results for each time of learning shows that the reflection level of the $3^{rd}$ time learning of D-Flip Flop is the highest score with 1.23. The correlation analysis result between the reflection contents presents that high positive correlation between learning content and task resolving method(r=.781, p<.01), and negative design correlation between task resolving method and alternative resolving method. The HW learning satisfaction survey result shows 4.2, and most of the participant students provided opinions that the HW design learning is required and current learning contents is a bit difficult to follow. We could recognize HW design learning is required to have composition of curriculum with basic and advanced contents, and on-off lines combined.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.4
• /
• pp.105-112
• /
• 2022

Recently, many studies using reinforcement learning-based autoscaling have been performed to make autoscaling policies that are adaptive to changes in the environment and meet specific purposes. However, training the reinforcement learning-based Horizontal Pod Autoscaler(HPA) policy in a real environment requires a lot of money and time. And it is not practical to retrain the reinforcement learning-based HPA policy from scratch every time in a real environment. In this paper, we implement a reinforcement learning-based HPA in Kubernetes, and propose a transfer leanring technique using a queuing model-based simulation to accelerate the training of a reinforcement learning-based HPA policy. Pre-training using simulation enabled training the policy through simulation experience without consuming time and resources in the real environment, and by using the transfer learning technique, the cost was reduced by about 42.6% compared to the case without transfer learning technique.

• International Commerce and Information Review
• /
• v.9 no.2
• /
• pp.103-120
• /
• 2007

The knowledge based economy requires more and more people to learn new knowledge and skills in a timely and effective manner. These needs and new technology such as computer and Internet are fueling a transition in e-learning. According to specialist's opinion, imagination experience studying is generalized, and learning environment that language barrier by studying, multi-language studying Machine that experience past things that disappear through simulation, and travel area, and experience future changed state disappears is forecasting to come. This is previewing finally that it may become future education that education and IT, element of entertainment is combined. Already, became story that argument for party satellite of e-Learning existence passes one season already. e-Learning is utilized already in all educations that we touch by effectiveness by corporation's competitive power improvement and implement of lifelong education in educational institutions through present e-Learning. It is obvious that when see from our viewpoint which is defining e-Learning by one industry and rear by application to education as well as one new growth power about these, e-Learning industry becomes very important means that can solve dilemma of growth real form. Only, special quality of digital industry that e-Learning is being same with other digital industry and repeat putting out a fire rapidly, and is repeating sudden change that these evolution is not gradual growth of accumulation and improvement of technology that is appearing consider need to. In the meantime, we need to observe about evolution of Information Technology. Because there is some scholars who e-Learning's concept foresees to evolve by u-Learning.(although, a person who see that these concept is not more in marketing terminology by some scholars' opinion is). This u-Learning's concept means e-Learning that take advantage of ubiquitous technology as Ubiquitous-Learning's curtailment speech. Ubiquitous, user means Information-Communication surrounding that can connect to network freely regardless of place without feeling network or computer. There is controversy about introduction time regarding these direction, but e-Learning is judged to evolve by u-Learning necessarily. Because keep in step and age that study all contents that learner wants under environment of 3A (any time, any whrer, any device) by individual order thoroughly is foreseen to come in ubiquitous learning environment that approach more festinately.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.6
• /
• pp.47-58
• /
• 2004

To generate individualized and adaptive course, it's required to have the foundation structure in which learning objects are connected with each other with logical relevances. Each learner can have peculiar learning path at each point of time of learning through the logical relevancy between those learning objects and various links, considering individual learner. The purpose of this study is to design a learning object-basis individualized learning system structure, considering semantic sequencing by learning task types. It is our understanding that the individualized learning system design model of this study, considering the relevancy between learning objects, can be a fresh trial to accommodate semantic learning and true educational spirits in e-Learning at this point of time when criticism, such as the learning object based course design is simply a collection of meaningless objects, etc., is becoming influential.

• International Journal of Precision Engineering and Manufacturing
• /
• v.7 no.1
• /
• pp.62-66
• /
• 2006

The learning control develops controllers that learn to improve their performance at executing a given task, based on experience performing this specific task. In a previous work, the authors presented an iterative precision of linear decentralized learning control based on p-integrated learning method for the vertical dynamic multiple systems. This paper develops an indirect decentralized learning control based on adaptive control method. The original motivation of the learning control field was learning in robots doing repetitive tasks such as an assembly line works. This paper starts with decentralized discrete time systems, and progresses to the robot application, modeling the robot as a time varying linear system in the neighborhood of the nominal trajectory, and using the usual robot controllers that are decentralized, treating each link as if it is independent of any coupling with other links. Some techniques will show up in the numerical simulation for vertical dynamic robot. The methods of learning system are shown for the iterative precision of each link.