• Journal of Information Processing Systems
• /
• v.15 no.3
• /
• pp.616-631
• /
• 2019

With the rapid increase of information on the World Wide Web, finding useful information on the internet has become a major problem. The recommendation system helps users make decisions in complex data areas where the amount of data available is large. There are many methods that have been proposed in the recommender system. Collaborative filtering is a popular method widely used in the recommendation system. However, collaborative filtering methods still have some problems, namely cold-start problem. In this paper, we propose a movie recommendation system by using social network analysis and collaborative filtering to solve this problem associated with collaborative filtering methods. We applied personal propensity of users such as age, gender, and occupation to make relationship matrix between users, and the relationship matrix is applied to cluster user by using community detection based on edge betweenness centrality. Then the recommended system will suggest movies which were previously interested by users in the group to new users. We show shown that the proposed method is a very efficient method using mean absolute error.

• Proceedings of the IEEK Conference
• /
• 2002.07c
• /
• pp.1752-1755
• /
• 2002

The world wide web (WWW) already accounts f3r more Internee network traffic than any other application, including il and simple file transfer. It is also a collaborative technology in a weak sense of the word - it allows people to share information. Synchronous collaboration is where an interactive activity is simultaneous and in teal-time. Computer based real time collaborative systems like shared whiteboards. collaborative editor etc. are only beginning to emerge recently. These applications invoking more than two users exchanging information, require Multicast communication. Multicast communication is a transmission mode that is now supported by a variety of local and wide area networks. Multicasting enables multiparty communication across a wide area to sparsely distributed groups by minimizing the network load. Multicasting itself is one of the key technologies in the nut generation of the Internet This paper describes the technical issues from the aspect of multicast communication and its reliability in synchronous collaborative application.

• Journal of Korea Multimedia Society
• /
• v.23 no.6
• /
• pp.756-764
• /
• 2020

A typical algorithm used for image analysis is the Convolutional Neural Network(CNN). R-CNN, Fast R-CNN, Faster R-CNN, etc. have been studied to improve the performance of the CNN, but they essentially require large amounts of data and high algorithmic complexity., making them inappropriate for small and medium-sized services. Therefore, in this paper, the image label prediction algorithm based on CNN with collaborative layer with low complexity, high accuracy, and small amount of data was proposed. The proposed algorithm was designed to replace the part of the neural network that is performed to predict the final label in the existing deep learning algorithm by implementing collaborative filtering as a layer. It is expected that the proposed algorithm can contribute greatly to small and medium-sized content services that is unsuitable to apply the existing deep learning algorithm with high complexity and high server cost.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3730-3744
• /
• 2020

This study proposes a deep learning-based evolutionary recommendation model for heterogeneous big data integration, for which collaborative filtering and a neural-network algorithm are employed. The proposed model is used to apply an individual's importance or sensory level to formulate a recommendation using the decision-making feedback. The evolutionary recommendation model is based on the Deep Neural Network (DNN), which is useful for analyzing and evaluating the feedback data among various neural-network algorithms, and the DNN is combined with collaborative filtering. The designed model is used to extract health information from data collected by the Korea National Health and Nutrition Examination Survey, and the collaborative filtering-based recommendation model was compared with the deep learning-based evolutionary recommendation model to evaluate its performance. The RMSE is used to evaluate the performance of the proposed model. According to the comparative analysis, the accuracy of the deep learning-based evolutionary recommendation model is superior to that of the collaborative filtering-based recommendation model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.861-880
• /
• 2023

Semantic segmentation of road scene is the key technology of autonomous driving, and the improvement of convolutional neural network architecture promotes the improvement of model segmentation performance. The existing convolutional neural network has the simplification of learning knowledge and the complexity of the model. To address this issue, we proposed a road scene semantic segmentation algorithm based on multi-task collaborative learning. Firstly, a depthwise separable convolution atrous spatial pyramid pooling is proposed to reduce model complexity. Secondly, a collaborative learning framework is proposed involved with saliency detection, and the joint loss function is defined using homoscedastic uncertainty to meet the new learning model. Experiments are conducted on the road and nature scenes datasets. The proposed method achieves 70.94% and 64.90% mIoU on Cityscapes and PASCAL VOC 2012 datasets, respectively. Qualitatively, Compared to methods with excellent performance, the method proposed in this paper has significant advantages in the segmentation of fine targets and boundaries.

• Journal of the Korea Institute of Building Construction
• /
• v.14 no.1
• /
• pp.102-109
• /
• 2014

The purpose of this study is to analyze collaborative relationship between members of a building construction organization. For the analysis of collaborative relationship, this researcher collected data by conducting a questionnaire survey with members of three large building construction organizations for apartment housing. The analyzed contents of collaborative relationship were the 'frequency of communication between organizational members' and their 'reliability'. According to the analysis of communication network, construction managers had low frequency of communication, whereas those responsible for each area, like construction deputy managers, had high frequency of communication. It indicates that middle managers are at the center of communication related to construction work in construction organizations. According to the analysis of reliability network, construction managers showed highest reliability, and employees at the top level in an organizational map also showed high reliability. Since they generally have a lot of experience, are some older of age, and assume responsibility for work, they are considered to receive reliability from other organizational members. This study proved that it was possible to numerically express reliability of organizational members, which is an abstract concept, and analyze it. Therefore, it is expected that the analysis result will highly be likely to be used in the area of construction management.

• Journal of Computing Science and Engineering
• /
• v.9 no.2
• /
• pp.98-107
• /
• 2015

Hierarchical constraints and constraint satisfaction were analyzed in order to solve the problem of conflict detection in collaborative design. The constraints were divided into two sets: one set consisted of known constraints and the other of unknown constraints. The constraints of the two sets were detected with corresponding methods. The set of the known constraints was detected using an interval propagation algorithm, a back propagation (BP) neural network was proposed to detect the set with the unknown constraints. An immune algorithm (IA) was utilized to optimize the weights and the thresholds of the BP neural network, and the steps were designed for the optimization process. The results of the simulation indicated that the BP neural network that was optimized by IA has a better performance in terms of convergent speed and global searching ability than a genetic algorithm. The constraints were described using the eXtensible Markup Language (XML) for computers to be able to automatically recognize and establish the constraint network. The implementation of the conflict detection system was designed based on constraint satisfaction. A wind planetary gear train is taken as an example of collaborative design with a conflict detection system.

• Asian Journal of Innovation and Policy
• /
• v.6 no.1
• /
• pp.85-93
• /
• 2017

This paper focuses on the relationship between the characteristics of network and the productivity of scientists, which is rarely examined in previous studies. Utilizing a unique dataset from the Korean Citation Index (KCI), we examine the overall characteristics of the research network (e.g. distribution of nodes, density and mean distance), and analyze whether the network centrality is related to the scientific productivity. According to the results, firstly we have found that the collaborative research network of the Korean academics in the field of statistics and computer science is a scale-free network. Secondly, these research networks show a disciplinary difference. The network of statisticians is denser than that of computer scientists. In addition, computer scientists are located in a fragmented network compared to statisticians. Thirdly, with regard to the relationship between the researchers' network position and scientific productivity, a significant relation and their disciplinary difference have been observed. In particular, the degree centrality is the strongest predictor for the scientists' productivity. Based on these findings, some policy implications are put forward.

• The Journal of Korean Association of Computer Education
• /
• v.3 no.1
• /
• pp.23-30
• /
• 2000

The educational effect and practical use of collaborative learning produced in virtual learning communities are being discussed actively in these days. A higher-level interactive tool is essential for successful Internet-based collaborative learning through the network. In this paper, we designed and implemented an integrated browser which has the integrated learning environment to support collaborative learning, and thus the user interface of the network client(News, FTP, HTTP, SMTP, voice text chatting Clients) is improved. Therefore, the educational effect of Internet-based collaborative learning is get closer to that of face-to-face learning.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.3
• /
• pp.89-108
• /
• 2022

The purpose of this study is to reveal the specific current and future shapes of the collaborative network among organizations witch cope the COVID-19 in Korea. For this, this study conducted social network analysis, based on the response data of 73 experts from 36 COVID-19-related organizations. As a result of the analysis, it was confirmed that the Korea Disease Control and Prevention Agency (KDCA) plays a pivotal role as a control tower in coping COVID-19 in all of the analysis of degree, betweenness, and closeness centrality. In addition, the results revealed concrete forms of collaborative relationships among participating organizations in the public and private sectors that constitute the present and future networks centered on the KDCA. Furthermore, this study presented which organizations and relationships should be the focus of establishing a future collaborative network through comparative analysis between the current cooperative network and the network to be built in the future. The analysis results and discussions of this study are expected to be used as useful information for policy development related to collaborative networks that can effectively respond to disasters caused by new diseases in the future.