• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2399-2413
• /
• 2021

A recommendation system is an information filter tool, which uses the ratings and reviews of users to generate a personalized recommendation service for users. However, the cold-start problem of users and items is still a major research hotspot on service recommendations. To address this challenge, this paper proposes a high-efficient hybrid recommendation system based on Fuzzy C-Means (FCM) clustering and supervised learning models. The proposed recommendation method includes two aspects: on the one hand, FCM clustering technique has been applied to the item-based collaborative filtering framework to solve the cold start problem; on the other hand, the content information is integrated into the collaborative filtering. The algorithm constructs the user and item membership degree feature vector, and adopts the data representation form of the scoring matrix to the supervised learning algorithm, as well as by combining the subjective membership degree feature vector and the objective membership degree feature vector in a linear combination, the prediction accuracy is significantly improved on the public datasets with different sparsity. The efficiency of the proposed system is illustrated by conducting several experiments on MovieLens dataset.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1997.06a
• /
• pp.75-81
• /
• 1997

A new DTPP (Desk-Top Program Production) system has been developed that enables multiple program producers (directors) working at different locations to collaborate over a computer network and prepare a single program for broadcasting. In this system, information is shared among users by exchanging data edited on non-linear editing terminals in program post-production work over a network in real time. In short, the new DTPP system provides a collaborative work space for producing TV programs. The system does not make use of a special server for collaborative work but rather multiple interconnected editing terminals having the same functions. In this configuration, data at a terminal which has just been edited by some operation is forwarded to all other connected terminals for updating. This form of information sharing, however, requires that some sort of data synchronizing method be established since multiple terminals are operating on the same data simultaneously. We therefore adopt a method whereby the system synchronizes the clocks on each terminal at the time of connection and sends an operation time stamp together with edited data. This enables most recently modified data to be identified and all information on all terminals to be updated appropriately. This paper provides an overview of this new collaborative DTPP system and describes the techniques for exchanging edited data and synchronizing data.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.31-33
• /
• 2022

Research information services such as ScienceON, RISS, and DBpia used by researchers during the R&D process mainly consist of a user interface in the form of a portal and search functions that respond to demands. However, the importance of open collaboration that freely shares and utilizes the research process and results and provides various tools and services necessary for collaborative research is gradually increasing, so there are also limitations to these service roles. Thus, we design WithON, which provides collaborative research environments of a preemptive response method, focusing on a personalized user interface to support the entire R&D cycle. We expect WithON would fundamentally change the existing research information services into collaborative research-centric ones.

• Industrial Engineering and Management Systems
• /
• v.13 no.4
• /
• pp.421-431
• /
• 2014

The market basket data in the form of a binary user-item matrix or a binary item-user matrix can be modelled as a binary classification problem. The binary logistic regression approach tackles the binary classification problem, where principal components are predictor variables. If users or items are sparse in the training data, the binary classification problem can be considered as a cold-start problem. The binary logistic regression approach may not function appropriately if the principal components are inefficient for the cold-start problem. Assuming that the market basket data can also be considered as a special regression problem whose response is either 0 or 1, we propose three supervised learning approaches: random forest regression, random forest classification, and elastic net to tackle the cold-start problem, comparing the performance in a variety of experimental settings. The experimental results show that the proposed supervised learning approaches outperform the conventional approaches.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.3
• /
• pp.659-668
• /
• 2007

Collaborative filtering approach for recommender systems are now widely applied in e-commerce to assist customers to find their needs from many that are frequently available. this approach makes recommendations for users based on the opinions to similar users in the system. But this approach is opened to users who present their preference to items or acquire the preference information form other users, noise in the system makes significant problem for accurate recommendation. In this paper, we analyze the relationship between the standard deviation of preference ratings for each user and the estimated ratings of them. The result shows that the possibility of the pre-filtering condition which detecting the factor of bad effect on the prediction of user's preference. It is expected that using this result will reduce the possibility of bad effect on recommender systems.

• Asian-Australasian Journal of Animal Sciences
• /
• v.33 no.7
• /
• pp.1180-1190
• /
• 2020

Objective: To develop healthier comminuted meat products to meet consumer demand, the gel properties, rheological properties, microstructure and water distribution of pork meat batters formulated with various amounts of bamboo shoot dietary fiber (BSDF) were investigated. Methods: Different levels of BSDF (0% to 4%) were added to pork batters, and the pH, color, water-holding capacity, texture and rheological properties of pork batters were determined. Then, pork batters were analyzed for their microstructure and water distribution using scanning electron microscopy (SEM) and low-field nuclear magnetic resonance (LF-NMR). Results: Compared with the control, BSDF addition into meat batters showed a significant reduction in L^*-value and a significant increase in b^*-value (p<0.05). BSDF addition of up to 4% reduced the pH value of pork batters by approximately 0.15 units; however, the cooking loss and expressible water loss decreased significantly (p<0.05) with the increased addition of BSDF. The hardness and gel strength were noticeably enhanced (p<0.05) as the content of BSDF increased. The rheological results showed that BSDF added into pork batters produced higher storage modulus (G') and loss modulus (G") values. The SEM images suggested that the addition of BSDF could promote pork batters to form a more uniform and compact microstructure. The proportion of immobilized water increased significantly (p<0.05), while the population of free water was decreased (p<0.05), indicating that BSDF improved the water-holding capability of pork batters by decreasing the fraction of free water. Conclusion: BSDF could improve the gel properties, rheological properties and water distribution of pork meat batters and decrease the proportion of free water, suggesting that BSDF has great potential as an effective binder in comminuted meat products.

• Electronic Materials Letters
• /
• v.14 no.6
• /
• pp.718-724
• /
• 2018

With the development of photovoltaic industry, the cost of photovoltaic power generation has become the significant issue. And the metallization process has decided the cost of original materials and photovoltaic efficiency of the solar cells. Nowadays, double printing process has been introduced instead of one-step printing process for front contact of polycrystalline silicon solar cells, which can effectively improve the photovoltaic conversion efficiency of silicon solar cells. Here, the relative cheap Cu paste has replaced the expensive Ag paste to form Ag/Cu composite front contact of silicon solar cells. The photovoltaic performance and the cost of photovoltaic power generation have been investigated. With the optimization on structure and height of Cu finger layer for Ag/Cu composite double-printed front contact, the silicon solar cells have exhibited a photovoltaic conversion efficiency of 18.41%, which has reduced 3.42 cent per Watt for the cost of photovoltaic power generation.

• Journal of the Korean Society for Library and Information Science
• /
• v.47 no.2
• /
• pp.123-142
• /
• 2013

The aim of this study is to find out the impact of collaborative instruction between the teacher librarian and the classroom teacher on learning interest and academic achievement by running Library and Information Life, which is the textbook of information literacy for teacher librarians and the Korean language curriculum for the first grade of middle school through library-based instruction. The result of this study has a positive influence on academic achievement by facilitating learning interest on Korean language classes under coplanning, co-operating and coevaluating in the school library. Therefore, it is important to establish the institutional system for collaborative instruction in order to increase information literacy instruction in the school community. A local school should expand the physical environment and educational equipment of its school library and form a flexible schedule to have enough time for teaching information literacy skills and for using of materials.

• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.193-201
• /
• 2009

The use of tagging to describes web documents in the form of keyword has experienced rising popularity among various web services. Tagging also plays an important role in collaborative bookmarking services which can be regarded as an online favorite bookmark service. Tags which are created by users make it easier to search other users' bookmarks as well as user's own bookmarks. In this paper we analyze usage patterns of collaborative tagging for exploring factors influencing the number of tags in web documents and users. We discovered that user's characteristics have more effect on the tags than the web documents' characteristics. Moreover, leading users contribute to make a variety of tag than following users. Our study implies that more knowledge can be created through the incentives for leading user in order to improve the service quality of tagging service.

• 한국정보교육학회:학술대회논문집
• /
• 2011.01a
• /
• pp.167-173
• /
• 2011

Recently, the Web 2.0 bas gained much attention as an advanced form of Web technology. It is well observed that openness, participation, and sharing are the key ideas of Web 2.0 among many desirable characteristics of the technology. Furthermore, Wiki is one of the best representing tools that reflect effectively most of the characteristics of Web 2.0. Wiki is widely used to provide a Web-based communication tool for collaborative writing and editing freely. Therefore, it may be used for collaborative learning so that students can learn how to interact online with each other effectively and also acquire communication skills in an affirmative way. In the paper, we will discuss how students can change their aggresive, offensive, judgemental attitudes to affirmative, aggreable, thoughtful ones by way of exposing them to collaborative learning environment using Wiki as their interactive communication tool.