• Journal of The Korean Association of Information Education
• /
• v.11 no.3
• /
• pp.281-288
• /
• 2007

Collaborative filtering is a method to predict preference items of a user based on the evaluations of items provided by others with similar preferences. Collaborative filtering helps general people make smart decisions in today's information society where information can be easily accumulated and analyzed. We designed, implemented, and evaluated a course recommendation system experimentally. This system can help university students choose courses they prefer to. Firstly, the system needs to collect the course preferences from students and store in a database. Users showing similar preference patterns are considered into similar groups. We use Pearson correlation as a similarity measure. We select K-nearest students to predict the unknown preferences of the student and provide a ranked list of courses based on the course preferences of K-nearest students. We evaluated the accuracy of the recommendation by computing the mean absolute errors of predictions using a survey on the course preferences of students.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2012.10a
• /
• pp.898-902
• /
• 2012

A descriptor which is suitable for motion analysis by using the motion features of moving objects from the real time image sequence is proposed. To segment moving objects from the background, the background learning is performed. We extract motion trajectories of individual objects by using the sequence of the $1^{st}$ order moment of moving objects. The center points of each object are managed by linked list. The descriptor includes the $1^{st}$ order coordinates of moving object belong to neighbor of the per-defined position in grid pattern, the start frame number which a moving object appeared in the scene and the end frame number which it disappeared. A video retrieval by the proposed descriptor combining global and local feature is more effective than conventional methods which adopt a single feature among global and local features.

• Convergence Security Journal
• /
• v.10 no.1
• /
• pp.41-48
• /
• 2010

Greedy protocols show good performance in Vehicular Ad-hoc Networks (VANETs) environment in general. But they make longer routes causing by surroundings or turn out routing failures in some cases when there are many traffic signals which generate empty streets temporary, or there is no merge roads after a road divide into two roads. When a node selects the next node simply using the distance to the destination node, the longer route is made by traditional greedy protocols in some cases and sometimes the route ends up routing failure. Most of traditional greedy protocols just take into account the distance to the destination to select a next node. Each node needs to consider not only the distance to the destination node but also the direction to the destination while routing a packet because of geographical environment. The proposed routing scheme considers both of the distance and the direction for forwarding packets to make a stable route. And the protocol can configure as the surrounding environment. We evaluate the performance of the protocol using two mobility models and network simulations. Most of network performances are improved rather than in compared with traditional greedy protocols.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38B no.10
• /
• pp.785-800
• /
• 2013

In MANET, AODV(Ad hoc On-demand Distance Vector) has its advantages as on-demand approach but it also has a disadvantage that the control packet overhead is high compared to other routing protocols. This paper improves the problem caused by Hello messages that are broadcasted periodically to detect the local connectivity and maintain neighbor list. Periodic hello messages reduce the Packet delivery ratio and the efficiency in the limited bandwidth. And its increased Control packet overhead leads to decrease the Residual battery capacity and the Network lifetime. Further, non-reactive nature of periodic hello messages in AODV has also been the source of numerous controversies. In order to solve these problems, this paper improves the performance by using the interrupt driven approach which removes periodic hello messages and decreases the Control packet overhead. Performance comparisons between the traditional AODV and proposed mod_AODV done with network simulator QualNet 5.0 show that the mod_AODV performs better in most performance metrics under scenarios with various values of simulation parameters.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.7
• /
• pp.1554-1560
• /
• 2015

802.11p WAVE is the next-generation wireless communication that can make Ad-hoc network communication possible for Vehicle-to-Vehicle. GBSR protocol, one of the 802.11p WAVE protocols, mainly focuses on improvements in networks that have a tendency to disconnect. However, it does not consider the transmission time and velocity of a packet thus, there is a disadvantage of there being a delay in the transmission velocity, in urgent situations like car accidents, emergency patients transportation and crimes. In this paper, we proposed A-GBSR protocol for transmission of a packet to mobile node which has a high speed through the improved beacon message and Adaptive Neighbor list Management that are considering of the GBSR protocol transmission velocity.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.9
• /
• pp.149-155
• /
• 2022

The popularity of e-commerce systems on the Internet is increasing day by day, and the recommendation system, as a core function of these systems, greatly reduces the effort to search for desired products by recommending products that customers may prefer. The collaborative filtering technique is a recommendation algorithm that has been successfully implemented in many commercial systems, but despite its popularity and usefulness in academia, the memory-based implementation has inaccuracies in its reference neighbor. To solve this problem, this study proposes a new time-aware collaborative filtering technique that integrates and utilizes the neighbors of each item and each user, weighting the recent similarity more than the past similarity with them, and reflecting it in the recommendation list decision. Through the experimental evaluation, it was confirmed that the proposed method showed superior performance in terms of prediction accuracy than other existing methods.

• Journal of the Korea Society of Computer and Information
• /
• v.14 no.9
• /
• pp.85-94
• /
• 2009

It is becoming increasingly difficult for learners to find the lectures they are looking for. In turn, the ability to find the particular lecture sought by the learner in an accurate and prompt manner has become an important issue in e-Learning. To deal this issue, in this paper. we present a collaborative approach to provide personalized recommendations of online video lectures. The proposed approach first identifies candidated video lectures that will be of interest to a certain user. Partitioned collaborative filtering is employed as an approach in order to generate neighbor learners and predict learners'preferences for the lectures. Thereafter, Attribute-based filtering is employed to recommend a final list of video lectures that the target user will like the most.

• The Bulletin of The Korean Astronomical Society
• /
• v.44 no.2
• /
• pp.77.3-77.3
• /
• 2019

We present an analysis of the stellar population of compact elliptical galaxies (cEs) in various environments. Following conventional selection criteria of cEs, we created a list of cE candidates in the redshift range of z < 0.05 using SDSS DR12 catalog. We finally selected cEs with low-luminosity (Mg > 18.7 mag), small effective radius (Re < 600 pc), and high velocity dispersion (> 60 kms-1). We divide our cE sample into those inside and outside of the one virial radius of the bright (Mr < -21 mag) nearby host galaxy which is then defined as cEs with (cEw) and without (cEw/o) host galaxy, respectively. We investigated the stellar population properties of cEs based on the Hb, Mgb, Fe 5270, and Fe 5335 line strengths from the OSSY catalog. We found that cEw has a systematically higher metallicity than cEw/o. In the velocity dispersion-Mgb distribution, while cEw/o follows the relation of early-type galaxies, cEw are found to have a systematically higher metallicity than cEw/o at a given velocity dispersion. The different feature in the metallicity between cEw and cEw/o can suggest that two different scenarios can be provided in the formation of cEs. cEw would be the remnant cores of the massive progenitor galaxies that their outer parts have been tidally stripped by massive neighbor galaxies (i.e., nurture origin). On the other hand, cEw/o are likely to be faint-end of early-type galaxies maintaining in-situ evolution (i.e., nurture origin).

• The KIPS Transactions:PartB
• /
• v.8B no.5
• /
• pp.455-462
• /
• 2001

The World Wide Web has become one of the major services provided through Internet. When searching the vast web space, users use bookmarking facilities to record the sites of interests encountered during the course of navigation. One of the typical problems arising from bookmarking is that the list of bookmarks lose coherent organization when the the becomes too lengthy, thus ceasing to function as a practical finding aid. In order to maintain the bookmark file in an efficient, organized manner, the user has to classify all the bookmarks newly added to the file, and update the folders. This paper introduces our learning agent called BClassifier that automatically classifies bookmarks by analyzing the contents of the corresponding web documents. The chief source for the training examples are the bookmarks already classified into several bookmark folders according to their subject by the user. Additionally, the web pages found under top categories of Yahoo site are collected and included in the training examples for diversifying the subject categories to be represented, and the training examples for these categories as well. Our agent employs naive Bayesian learning method that is a well-tested, probability-based categorizing technique. In this paper, the outcome of some experimentation is also outlined and evaluated. A comparison of naive Bayesian learning method alongside other learning methods such as k-Nearest Neighbor and TFIDF is also presented.

• Journal of Korean Library and Information Science Society
• /
• v.50 no.1
• /
• pp.23-41
• /
• 2019

This study understand the subject domain of book which has been read by men and woman elderly by analizying the PFNET using library big data and confirm the difference between adult at age 30-40. This study extract co-occurrence matrix of book lending on the popular book list from library big data, for 4 group, men/woman elderly, men/woman adult. With these matrix, this study performs FP network analysis. And Pearson Correlation Analysis based on the Triangle Betweenness Centrality calculated on the loan book was performed to understand the correlation among the 4 clusters which has been created by PNNC algorithm. As a result, reading trend which has been focused on modern korean novel has been revealed in elderly regardless gender, among them, men elderly show extreme tendency concentrated on modern korean long series novel. In the correlation analysis, the male elderly showed a weak negative correlation with the adult male of r = -0.222, and the negative direction of all the other groups showed that the tendency of male elderly's loan book was opposite.