• Journal of Korea Game Society
• /
• v.10 no.6
• /
• pp.115-124
• /
• 2010

In the beginning brain waves were used for monkeys to control robot arm with neural activity. In recent years there are research that measured brain waves are used for the control of programs which monitor the progression of dementia or enhance of attention in children diagnosed with Attention Deficit Hyperactivity Disorder (ADHD). Moreover, low-price devices that can be used as a game control interface have become available. One of the problems associated with control using brain waves is that the mean amplitude, mean wavelength, and mean vibrational frequency of the brain waves differ from individual to individual. This paper attempts to propose a method to normalize measured brain waves using normal distribution and calculate the waveforms that can be used in controlling games. For this, a framework in which brain waves are converted in seven stages has been suggested. In addition, the estimation process in each stage has been described. In an experiment the waveforms of two subjects have been compared using the proposed method in the BCI English word learning program. The level of similarity between two subjects' waveforms has been compared with correlation coefficient. When the proposed method was applied, both meditation and concentration increased by 13% and 8%, respectively. Because the proposed regularization method is converted into a waveform fit for control functions by reducing personal characteristics reflected in the brain waves, it is fitting for application programs such as games.

• Journal of Korea Multimedia Society
• /
• v.7 no.11
• /
• pp.1597-1609
• /
• 2004

A lot of lipreading system has been proposed to compensate the rate of speech recognition dropped in a noisy environment. Previous lipreading systems work on some specific conditions such as artificial lighting and predefined background color. In this paper, we propose a real-time lipreading system which allows the motion of a speaker and relaxes the restriction on the condition for color and lighting. The proposed system extracts face and lip region from input video sequence captured with a common PC camera and essential visual information in real-time. It recognizes utterance words by using the visual information in real-time. It uses the hue histogram model to extract face and lip region. It uses mean shift algorithm to track the face of a moving speaker. It uses PCA(Principal Component Analysis) to extract the visual information for learning and testing. Also, it uses HMM(Hidden Markov Model) as a recognition algorithm. The experimental results show that our system could get the recognition rate of 90% in case of speaker dependent lipreading and increase the rate of speech recognition up to 40～85% according to the noise level when it is combined with audio speech recognition.

• Journal of Korea Multimedia Society
• /
• v.13 no.3
• /
• pp.417-429
• /
• 2010

Though background subtraction has been widely studied for last decades, it is still a poorly solved problem especially when it meets real environments. In this paper, we first address some common problems for background subtraction that occur in real environments and then those problems are resolved by improving an existing GMM-based background modeling method. First, to achieve low computations, fixed point operations are used. Because background model usually does not require high precision of variables, we can reduce the computation time while maintaining its accuracy by adopting fixed point operations rather than floating point operations. Secondly, to avoid erroneous backgrounds that are induced by high pedestrian traffic, static levels of pixels are examined using shot-time statistics of pixel history. By using a lower learning rate for non-static pixels, we can preserve valid backgrounds even for busy scenes where foregrounds dominate. Finally, to adapt rapid illumination changes, we estimated the intensity change between two consecutive frames as a linear transform and compensated learned background models according to the estimated transform. By applying the fixed point operation to existing GMM-based method, it was able to reduce the computation time to about 30% of the original processing time. Also, experiments on a real video with high pedestrian traffic showed that our proposed method improves the previous background modeling methods by 20% in detection rate and 5~10% in false alarm rate.

• Journal of Korea Multimedia Society
• /
• v.11 no.9
• /
• pp.1204-1212
• /
• 2008

The vehicle simulation (flight simulator) in 1920's was the first in the virtual reality. With the development of precise optical and electromagnetic equipment, the virtual reality widened its application for other purposes than military one. Based on the realistic display technology, it is more and more common in the various areas such as entertainment, medical profession, learning, film, architectural design, tourism and etc. In 1989, Jaron Ranier was the first to use the terminology 'Virtual Reality'. With this term, all virtual projects could be classified in a single item. But even before the term was used, the virtual reality has been studied up to now. As a part of virtual reality, the human thirst for the impossible thing has led to the development of ride film. The ride film consists of the special technical elements as well as the psychological analysis of human being. The ultimate purpose of virtual reality is engrossment through interaction. Even though the real interaction requires interface, input sensor and reaction ability, the ride film is not an element of the typical interaction. The virtual reality is mostly defined in technical terms now. But in this study, we will analyze the concepts worked out by Professor Michael Haim who is called a philosopher in the cyberspace in aspect of experience-oriented definition. We will analyze the adaptability of virtual reality based on his concepts such as artificial reality/ interaction/ engrossment/ networked world/ remote display/ simulation/ onmon engrossment. And also, we aim to suggest the directions of developing the ride films for perfect engrossment and to draw optimized conclusion thereon. In this viewpoint, we consider that the study of ride film on which there were few case studies will contribute to level up the basic frameworks of IT technology and the digital image.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.1
• /
• pp.19-26
• /
• 2021

Cultural assets excavated in historical areas have their own characteristics based on the background of the times, and it can be seen that their patterns and characteristics change little by little according to the history and the flow of the spreading area. Cultural properties excavated in some areas represent the culture of the time and some maintain their intact appearance, but most of them are damaged/lost or divided into parts, and many experts are mobilized to research the composition and repair the damaged parts. The purpose of this research is to learn patterns and characteristics of the past through artificial intelligence neural networks for such restoration research, and to restore the lost parts of the excavated cultural assets based on Generative Adversarial Network(GAN)[1]. The research is a process in which the rest of the damaged/lost parts are restored based on some of the cultural assets excavated based on the GAN. To recover some parts of dammed of cultural asset, through training with the 2D image of a complete cultural asset. This research is focused on how much recovered not only damaged parts but also reproduce colors and materials. Finally, through adopted this trained neural network to real damaged cultural, confirmed area of recovered area and limitation.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.745-755
• /
• 2017

University campuses try to satisfy students' demands. Therefore, the physical environment of university campuses keeps changing. Due to the increasing the number of students and shortage of school building facilities, it is necessary to improve the facilities and create new space in the campus, in order to solve this problem and improve the universities. At the moment, the learning method of university students is evolving toward discussion sessions involving fellow students and presentations utilizing multimedia facilities. In response to these changes, a new type of independent space has appeared, which is called the Group Study Room. In this study, we analyze the spatial characteristics of the Group Study Room. Also, through an IPA(Importance Performance Analysis), this study tries to examine the relationship between the spatial characteristics and users' satisfaction. This analysis is expected to reveal the importance of the spatial characteristics of the group study rooms from the users' point of view. This research can be used for facility planning in universities in the future. The primary aim of this study is to analyze the physical environment of the Group Study Rooms of K university. The secondary aim of this study is to manifest the characteristics of these new learning spaces and to check the space elements of the group study rooms for the sake of efficient planning and management.

• Journal of The Korean Association of Information Education
• /
• v.6 no.3
• /
• pp.298-307
• /
• 2002

Recent advances in the Web technology have been changing our life in various aspects. These advances have brought us new paradigms of education. The Web provides teachers with many opportunities to implement wide ranges of new teaching and learning practices, which supplement the traditional classroom teaching-learning. Especially, the Web enables so-called WBI (Web-based instruction) system as a teaching aid. Now the WBI system can incorporate multimedia information with various communication and collaborative tools. In order for the WBI system to be successful, various supports are necessary. One of such supports comes from assessment. In this work, an item pool system for leveled assessment is designed and implemented. The proposed system has the following characteristics. First, the item pool is classified into three categories subject, semester, and chapter. This categorization makes lookup easier and faster. Second, any teacher can use the item pool system and enter their questions into the item pool. Third, the proposed system reflects various levels of students for each course. Thus, students can select their exams based on their progress and background. Finally, it can make difficulty of each item to be objective by repeated tests and refinements.

• Journal of The Korean Association of Information Education
• /
• v.16 no.3
• /
• pp.327-336
• /
• 2012

The Korea government has recently announced "A Master Plan for Smart Education", including application of digital textbooks and composition of education system using cloud computing. Our education system in future circumstance, over the conventional e-learning methods, needs the smart education solutions which enable students to study and communicate on various types of devices. The ongoing government project related with the digital textbook has been performed as mid- and long-term goals, whereas PDF-based e-textbook project, similar to e-book model and, has been already completed for the short-term goal. For the purpose of improved future smart education circumstance, however, a specific strategy is required in the following areas: flexibility of format conversion and independency of original text sources among the multiple device platforms. Therefore, in this paper, we propose a standardization scheme for e-textbook format based on e-book structure. To do this, we survey trends in e-book technologies, and research on standardization of e-book format for digitalization of textbooks, based on the analysis of existing textbooks. Moreover, we produce an example e-book content using our proposed standard method. As a result, our approach can be applied to the future smart education circumstance, and we may say that it will be efficiently applicable to the long-term digital textbook project.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.9
• /
• pp.440-446
• /
• 2016

Military secrets or confidential data of any organization are extremely important assets. They must be discluded from outside. To do this, methods for detecting anomalous attacks and intrusions inside the network have been proposed. However, most anomaly-detection methods only cover aspects of intrusion from outside and do not deal with internal leakage of data, inflicting greater damage than intrusions and attacks from outside. In addition, applying conventional anomaly-detection methods to data exfiltration creates many problems, because the methods do not consider a number of variables or the internal network environment. In this paper, we describe issues considered in data exfiltration detection for anomaly detection (DEDfAD) to improve the accuracy of the methods, classify the methods as profile-based detection or machine learning-based detection, and analyze their advantages and disadvantages. We also suggest future research challenges through comparative analysis of the issues with classification of the detection methods.

• Journal of Korean Elementary Science Education
• /
• v.41 no.2
• /
• pp.418-431
• /
• 2022

In this study, we analyzed the form, presentation, and interactivity of external representations presented in the matter units of elementary school science digital textbooks developed under the 2015 Revised National Curriculum. The analytic framework of the previous study was modified and supplemented. The matter units in the 3rd-6th grade science digital textbooks were analyzed by dividing them into "body texts" and "inquiries" area. The results revealed that visual-verbal and visual-nonverbal representations were presented the most. Conversely, audial-nonverbal representations were presented at a high frequency only in the body texts, and audial-verbal representations were presented at a low frequency in both the body texts and the inquiries. Regarding the presentation, when verbal and visual-nonverbal representations appeared together, visual-verbal and visual-nonverbal representations were primarily presented together. In some cases where visual-verbal, audial-verbal, and visual-nonverbal representations were presented together, information on visual-verbal and audial-verbal representations was presented redundantly. Audial-nonverbal representations unrelated to contents were presented along with other external representations, and the frequency was particularly high in the body texts. Regarding the contiguity, no visual-verbal and visual-nonverbal representations were presented on different pages, and no audial-verbal representations were presented asynchronously with visual-nonverbal representations. Regarding the interactivity, explanatory feedback and low-level manipulations were mainly presented. Based on the results, implications to improve digital textbooks are discussed from the perspective of multiple representation-based learning.