• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.101-108
• /
• 2020

Recommender system is a must-have feature of e-commerce, since it provides customers with convenience in selecting products. Collaborative filtering is a widely-used and representative technique, where it gives recommendation lists of products preferred by other users or preferred by the current user in the past. Recently, researches on the recommendation system using deep learning artificial intelligence technologies are actively being conducted to achieve performance improvement. This study develops a collaborative filtering based recommender system using restricted Boltzmann machines of the deep learning technology by utilizing user ratings. Moreover, a learning parameter update algorithm is proposed for learning efficiency and performance. Performance evaluation of the proposed system is made through experimental analysis and comparison with conventional collaborative filtering methods. It is found that the proposed algorithm yields superior performance than the basic restricted Boltzmann machines.

• The KIPS Transactions:PartA
• /
• v.11A no.4
• /
• pp.257-266
• /
• 2004

Mobile agents are defined as processes which can be autonomously delegated or transferred among the hosts in a network in order to perform some computations on behalf of the user and co-operate with other agents. Currently, mobile agents are used in various fields, such as electronic commerce, mobile communication, parallel processing, search of information, recovery, and so on. In pure P2P network environment, if mobile agents that require computing resources rashly migrate to another peers without consideration on the peer's capacity of resources, the peer may have a problem that the performance of the peer is degraded due to lack of resources. To solve this problem, we propose resource reservation based load balancing scheme of using RMA(Resource Management Agent) that monitors workload information of the peers and that decides migrating agents and destination peers. In mobile agent migrating procedure, if the resource of specific peer is already reserved, our resource reservation scheme prevents other mobile agents from allocating the resource.

• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.239-250
• /
• 2003

Recent recommender system user a method of combining collaborative filtering system and content based filtering system in order to slove the problem of the Sparsity and First-Rater in collaborative filtering system. In this paper, to make up for the prediction accuracy in hybrid Recommender system, the harmonic mean weight(CBCF_harmonic_mean) is used for calculating the user similarity weight. After setting up the threshold as 45 considering the performance of content based filtering, we apply significance weight of n/45 to user similarity weight. To estimate the performance of the proposed method, it if compared with that of combing both the existing collaborative filtering system and the content- based filtering system. As a result, it confirms that the suggested method is efficient at improving the prediction accuracy as solving problems of the exiting collaborative filtering system.

• Journal of KIISE:Software and Applications
• /
• v.29 no.4
• /
• pp.248-257
• /
• 2002

Clustering is a method for grouping objects with similar properties into a same cluster. SVD(Singular Value Decomposition) is known as an efficient preprocessing method for clustering because of dimension reduction and noise elimination for a high dimensional and sparse data set like E-Commerce data set. However, it is hard to evaluate the worth of original attributes because of information loss of a converted data set by SVD. This research proposes a cluster feature selection method, called ENTROPY-SVD, to find important attributes for each cluster based on entropy weighting and SVD. Using SVD, one can take advantage of the latent structures in the association of attributes with similar objects and, using entropy weighting one can find highly dense attributes for each cluster. This paper also proposes a model-based collaborative filtering recommendation system with ENTROPY-SVD, called CFS-CF and evaluates its efficiency and utilization.

• Journal of KIISE:Databases
• /
• v.34 no.5
• /
• pp.389-395
• /
• 2007

Collaborative filtering is a popular technique for information filtering to reduce information overload and widely used in application such as recommender system in the E-commerce domain. Collaborative filtering systems collect human ratings and provide Predictions based on the ratings of other people who share the same tastes. The quality of predictions depends on the number of items which are commonly rated by people. Therefore, it is difficult to apply pure collaborative filtering algorithm directly to dynamic collections where items are constantly added or removed. In this paper we suggest a method for managing dynamic collections. It creates taste space for items using a technique called Singular Vector Decomposition (SVD) and maintains clusters of core items on the space to estimate relevance of past and future items. To evaluate the proposed method, we divide database of user ratings into those of old and new items and analyze predicted ratings of the latter. And we experimentally show our method is efficiently applied to dynamic collections.

• Journal of KIISE:Databases
• /
• v.29 no.1
• /
• pp.1-14
• /
• 2002

Association rule discovery is a method of mining for the associated item set on large databases based on support and confidence threshold. The discovered association rules can be applied to the marketing pattern analysis in E-commerce, large shopping mall and so on. The association rule discovery makes multiple scan over the database storing large transaction data, thus, the algorithm requiring very high overhead might not be useful in real-time association rule discovery in dynamic environment. Therefore this paper proposes an active candidate set management model based on trigger and incremental update mechanism to overcome non-realtime limitation of association rule discovery. In order to implement the proposed model, we not only describe an implementation model for incremental updating operation, but also evaluate the performance characteristics of this model through the experiment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.285-288
• /
• 2010

Chinese hackers hack the e-commerce site by bypass South Korea IP to connect to the third country, finance damaging a violation incident that fake account. 7.7.DDoS attack was the case of a hacker attack that paralyzed the country's main site. In this paper, the analysis is about vulnerabilities that breaches by hackers and DDoS attacks. Hacker's attacks and attacks on the sign of correlation analysis is share the risk rating for in real time, Red, Orange, Yellow, Green. Create a blacklist of hackers and real-time attack will be studied security and air conditioning systems that attacks and defend. By studying generate forensic data and confirmed in court as evidence of accountability through IP traceback and detection about packet after Incident, contribute to the national incident response and development of forensic techniques.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.135-137
• /
• 2014

The expansion of the transportation card, and the popularity of smart phones has been increasing social concern about the NFC technology. Has been focused on the use of e-commerce, most of the NFC, fulfilling the security problems or technical topic for this, but the reality is that the current debate on the new value added contents industry and a nonexistent connection. Leverage NFC for efficient order management system in order to build lunch or dinner by being pushed to ease restrictions on remodeling and renovation projects Food Truck vehicle through a small business support programs in the current government, but increasing interest in the Food Truck I study a model of ordering system for food truch 재소 s-guide system. A lot of the effectiveness of management as appropriate to the use of NFC for small business that operates as a server system is highly Food Truck tendencies tied to one router and server on the intranet without the need of internet connection system. I believe in this study S-Guide system contributes for business success for food truck of small business.

• International Area Studies Review
• /
• v.14 no.2
• /
• pp.205-227
• /
• 2010

Where should a plant or service facility be located? The decision is crucial since the capital investment in land, factory construction, and facility is enormous. Once a firm has sunk a large sum of money into a factory, it lives with the decision for a long time. In this age of global markets and global production, this is a key decision problem for contemporary manufacturing and/or service. Using data from Korean and Chinese managers and the AHP (Analytic Hierarchy Process), this paper did study on the actual condition for identifying the differences of opinion between the two group's(Shanghai and Shenyang managers) in how to make decisions on the location problems. Since this study was carried out during recent global economy recession, and the limitation of the collected questionnaires, it is hard to avoid the possibility for those managers to show different view from their ordinary times. Nevertheless, this paper will provide managers with useful informations on successful facility location in China.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.31 no.3
• /
• pp.401-410
• /
• 2021

Recently, as cyber attacks targeting industrial control systems increase, various studies are being conducted on the detection of abnormalities in industrial processes. Considering that the industrial process is deterministic and regular, It is appropriate to determine abnormality by comparing the predicted value of the detection model from which normal data is trained and the actual value. In this paper, HAI Datasets 20.07 and 21.03 are used. In addition, an ensemble model is created by combining models that have applied different time steps to Gated Recurrent Units. Then, the detection performance of the single model and the ensemble recurrent neural networks model were compared through various performance evaluation analysis, and It was confirmed that the proposed model is more suitable for abnormal detection in industrial control systems.