• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1251-1258
• /
• 2019

Intelligent tutoring system enables users to effectively learn by utilizing various artificial intelligence techniques. For instance, it can recommend a proper curriculum or learning method to individual users based on their learning history. To do this effectively, user's characteristics need to be analyzed and classified based on various aspects such as interest, learning ability, and personality. Even though data labeled by the characteristics are required for more accurate classification, it is not easy to acquire enough amount of labeled data due to the labeling cost. On the other hand, unlabeled data should not need labeling process to make a large number of unlabeled data be collected and utilized. In this paper, we propose a semi-supervised learning method based on feedback variational auto-encoder(FVAE), which uses both labeled data and unlabeled data. FVAE is a variation of variational auto-encoder(VAE), where a multi-layer perceptron is added for giving feedback. Using unlabeled data, we train FVAE and fetch the encoder of FVAE. And then, we extract features from labeled data by using the encoder and train classifiers with the extracted features. In the experiments, we proved that FVAE-based semi-supervised learning was superior to VAE-based method in terms with accuracy and F1 score.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.14 no.2
• /
• pp.87-92
• /
• 2014

Smartphones, as well as providing a number of convenience features such as an individual's personality to express the range is gradually increasing. Changed when we met another person, such as a change of outward change in the smartphone became responsive individuals. Each other, it is common to observe smartphones smartphones. Smartphone now due to the common use of information leakage has become a serious problem. In this paper, when sharing smart phone, smartphones to separate the user's area, and the constraints of privacy and the need to apply encryption to prevent information leakage or add application-specific information is encrypted and stored in other similar applications it is not accessible to protect the personal information was through this smartphone to share your private information even improved.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.113-119
• /
• 2020

Numerous tourist-related data produced on the Internet contain not only simple tourist information but also diverse ideas and opinions from users. In order to derive meaningful information about tourist sites from such big data, the social network analysis of tourist keywords can identify the frequency of keywords and the relationship between keywords. Thus, it is possible to make recommendations more suitable for users by utilizing the clear recommendation criteria of tourist attractions and the relationship between tourist attractions. In this paper, a recommendation system was designed based on tourist site information through big data social network analysis. Based on user personality information, the types of tourism suitable for users are classified through deep learning and the network analysis among tourist keywords is conducted to identify the relationship between tourist attractions belonging to the type of tourism. Tour information for related tourist attractions shown on SNS and blogs will be recommended through tagging.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.3
• /
• pp.32-38
• /
• 2015

In this paper, we propose a smallcell local caching algorithm under user's context in smallcell environment. The proposed system reduces traffic to core network and the network cost, but increases it's performance. The proposed algorithm precache suitable files using smallcell's regional characteristics and target's personality. It can adjusts a storage allocation to make effective usage of our limited cache storage capacity. In order to evaluate the performance of the proposed cache algorithm, we define the cache efficiency, the decrement of core network traffic. The simulation results show that the proposed algorithm can improve performance by about 200% compared to existing web cache scheme.

• Proceedings of the Korea Contents Association Conference
• /
• 2005.11a
• /
• pp.412-415
• /
• 2005

Recently, new games have been experimented to be given the adaptive interfaces equipped with AI algorithms which could interpret the user's personality, behavioral patterns, and physiological conditions in realtime. In this paper, we propose the intermediate form of tangible interface for PC package, which is currently decaying in commercial market.

• Journal of Korea Society of Industrial Information Systems
• /
• v.21 no.4
• /
• pp.1-11
• /
• 2016

Recently numerous studies are conducted to estimate the human personality from the online social activities. This paper develops a comprehensive model for political attitude estimation leveraging the Facebook Like information of the users. We designed a Facebook Crawler that efficiently collects data overcoming the difficulties in crawling Ajax enabled Facebook pages. We show that the category level selection can reduce the data analysis complexity utilizing the sparsity of the huge like-attitude matrix. In the Korean Facebook users' context, only 28 criteria (3% of the total) can estimate the political polarity of the user with high accuracy (AUC of 0.82).

• Korean Institute of Interior Design Journal
• /
• v.15 no.6 s.59
• /
• pp.221-228
• /
• 2006

The purpose of this research is to investigate the tendency of color preference for the elderly in housing. For this, a questionnaire survey was carried out with color chips and 9 photos of the living rooms which were chosen among apartment model houses in Pusan. Preference of color usage was measured by SD scale developed by advertising adjectives for the model houses. The result of this study are as follows: 1) The preferred color image was characterized as soft, warm and simple. The main factors of color image were identified and named as 'dignity factor' and 'personality factor'. 2) The elderly preferred G generally, but R for dominant color of the living room. They distinguished their attitudes about the color by the purpose of color usage. 3) For colors of architectural components of the living room, preferred colors were narrowed Y, YR and R for wall, art wall and floor. Beige was the most popular color in the living room for the elderly. This research can contribute to the basic data of color planning for the elderly housing.

• Journal of Korea Game Society
• /
• v.14 no.2
• /
• pp.7-18
• /
• 2014

Emotion is one of the elements of the game that will help the user interaction. The way to express the emotions and personality of the character was taken into account severity of reaction to action or a specific graphics in the game so far. However recently structured for the interest in the study of emotion increases and to utilize a variety of feelings in the game is needed. In the field of autonomous agents, studies of the possibility of the use of emotion, defined 12 different emotion rules. In this paper, we dilate by defining the terms used in the game rules of emotion made the rules of the emotion of the game. And, we analyzed emotions in actual game character used Game Emotions Rule. As a result, it was possible to see the rules of the game feeling separate from that being used for game genre similar.

• International Journal of Advanced Culture Technology
• /
• v.12 no.2
• /
• pp.110-118
• /
• 2024

This study was conducted to analyze the metaverse usage behavior of college students through in-depth interviews and to explore the characteristics of the major metaverse platforms with a focus on keywords. This study derived elements such as metaverse participation activities, real-world order, metaverse system, presence, and self-expression from previous research. This study examined how college students who use the metaverse perceive these variables. We present the following research results: First, the college students who participated in the study showed interest in content with many interactive elements on the metaverse platform and appeared to participate more actively in such content. Second, college students cited the ability to engage in economic activities in the metaverse as their greatest strength. It was expected that social norms applied in the real world would also be applied in the metaverse. Third, the Metaverse system, such as the Metaverse UI, UX, and servers, was found to be a factor that needs to meet users' expectations and hinders immersion. In this study, the characteristics of the metaverse platform were analyzed, focusing on essential keywords from in-depth interviews. The analysis results are as follows: It was expressed with keywords such as Zepeto has 'avatar' and 'personality expression,' Ifland has 'free decoration' and 'communication convenience,' Gathertown has 'movement convenience' and 'video chat.' Roblox has 'game-based' and 'dynamic.'

• Journal of Information Technology Applications and Management
• /
• v.31 no.3
• /
• pp.149-163
• /
• 2024

As conversational AI systems such as ChatGPT have become more advanced, researchers are exploring ways to use them in education. However, we need effective ways to evaluate these systems before allowing them to help teach students. This study proposes a detailed framework for testing conversational AI across three important criteria as follow. First, specialized benchmarks that measure skills include giving clear explanations, adapting to context during long dialogues, and maintaining a consistent teaching personality. Second, adaptive standards check whether the systems meet the ethical requirements of privacy, fairness, and transparency. These standards are regularly updated to match societal expectations. Lastly, evaluations were conducted from three perspectives: technical accuracy on test datasets, performance during simulations with groups of virtual students, and feedback from real students and teachers using the system. This framework provides a robust methodology for identifying strengths and weaknesses of conversational AI before its deployment in schools. It emphasizes assessments tailored to the critical qualities of dialogic intelligence, user-centric metrics capturing real-world impact, and ethical alignment through participatory design. Responsible innovation by AI assistants requires evidence that they can enhance accessible, engaging, and personalized education without disrupting teaching effectiveness or student agency.