• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2016년도 추계학술발표대회
• /
• pp.196-198
• /
• 2016

Online social networking sites such as MySpace, Facebook, Twitter are becoming very preeminent, and the quantities of their users are escalating very quickly. Due to the significant escalation of security vulnerabilities in social networks, user's confidentiality, authenticity, and privacy have been affected too. In this paper, a short study of online social network attacks is presented in order to identify the problems and impact of the attacks on World Wide Web (WWW).

• International Journal of Computer Science & Network Security
• /
• 제21권2호
• /
• pp.193-197
• /
• 2021

Customers are increasingly attracted towards different e-commerce websites and applications for the purchase of products significantly. This is the reason the sellers are moving to different internet based services to sell their products online. The growth of customers in this sector has resulted in the use of big data analytics to understand customers' behavior in predicting the demand of items. It uses a complex process of examining large amount of data to uncover hidden patterns in the information. It is established on the basis of finding correlation between various parameters that are recorded, understanding purchase patterns and applying statistical measures on collected data. This paper is a document of the bottom-up strategy used to manage the selling price of a first-time product for maximizing profit while selling it online. It summarizes how existing customers' expectations can be used to increase the sale of product and attract the attention of the new customer for buying the new product.

• International Journal of Computer Science & Network Security
• /
• 제22권6호
• /
• pp.256-274
• /
• 2022

The continuous information technology and telecommunication (ICT) developments inspire several Saudi Arabia citizens to transact and interact online. However, when using online platforms, several people are likely to lose their personal information to cybercriminals. In the survey, 553 Saudi Arabia citizens and 103 information technology (IT) specialists confirm the expansion of digital economy and the need for smart cities with various services, including e-commerce and solid cyber security. 96.6% of the participants believe Saudi Arabia is digitalizing its economy; yet, 33.3% of the participants believe that residents are uninformed about living and operating in smart cities. Several people (47.29%) with medium internet speed are more aware about smart cities than those with fastest internet speed (34%). Besides, online transactions via credit cards subjected 55.5% of the participants to privacy and security issues. These findings validate the essence of cyber security awareness programs among Saudi Arabia citizens and IT professionals to boost public trust and acceptance of cybersecurity frameworks.

• International Journal of Computer Science & Network Security
• /
• 제23권6호
• /
• pp.77-83
• /
• 2023

This research is conducted to minimize the potential security risks of conducting online exams to an acceptable level as vulnerabilities and threats to this type of exam are presented. This paper provides a general structure for the risk management process and some recommendations for increasing the level of security.

• Journal of Information Processing Systems
• /
• 제20권3호
• /
• pp.360-374
• /
• 2024

A personalized course recommendation algorithm based on deep learning in an online education cloud platform is proposed to address the challenges associated with effective information extraction and insufficient feature extraction. First, the user potential preferences are obtained through the course summary, course review information, user course history, and other data. Second, by embedding, the word vector is turned into a low-dimensional and dense real-valued vector, which is then fed into the compressed interaction network-deep neural network model. Finally, considering that learners and different interactive courses play different roles in the final recommendation and prediction results, an attention mechanism is introduced. The accuracy, recall rate, and F1 value of the proposed method are 0.851, 0.856, and 0.853, respectively, when the length of the recommendation list K is 35. Consequently, the proposed strategy outperforms the comparison model in terms of recommending customized course resources.

• 한국의류학회지
• /
• 제22권5호
• /
• pp.585-596
• /
• 1998

This report gathers data on current catalogue and online order market in the apparel products in order to: 1) identify the current status and critical issues in this area, and 2) identify the differences between the department store markets and the domestic markets on catalogue and online order. In addition, it collected the information on consumer shopping behaviors through surveys in both Korea and the U.S., in order to: 1) compare the consumer behaviors between both countries, and 2) identify any correlations with demographic factors such as sex, age, marriage status, income, education. This was discovered by means of the collected data that in Korea there were the problefls related to the apparel products and the apparel size specification, and related to the p.c.-network. Also in Korea the department store companies do not have properly worked out size specifications and are more likely to use 'freesize' categories, while in the U.S. and Europe the reverse was found and the size specification gave more detailed information. Results of the questionnaire suggested that the U.S. was superior in the almost part of questionnaires especially in terms of the user's experience and satisfaction with catalogue & online order in apparel. Additionally, the U.S. had 2.5 times more catalogues and online sites and those were more frequently used compared to those in Korea. The consumer shopping behaviors in Korea showed a correlation with sex, age, job, marriage status and income. And there were significant correlations with education, sex and income in the U.S.

• Journal of Information Processing Systems
• /
• 제9권4호
• /
• pp.633-650
• /
• 2013

All the imputation techniques proposed so far in literature for data imputation are offline techniques as they require a number of iterations to learn the characteristics of data during training and they also consume a lot of computational time. Hence, these techniques are not suitable for applications that require the imputation to be performed on demand and near real-time. The paper proposes a computational intelligence based architecture for online data imputation and extended versions of an existing offline data imputation method as well. The proposed online imputation technique has 2 stages. In stage 1, Evolving Clustering Method (ECM) is used to replace the missing values with cluster centers, as part of the local learning strategy. Stage 2 refines the resultant approximate values using a General Regression Neural Network (GRNN) as part of the global approximation strategy. We also propose extended versions of an existing offline imputation technique. The offline imputation techniques employ K-Means or K-Medoids and Multi Layer Perceptron (MLP)or GRNN in Stage-1and Stage-2respectively. Several experiments were conducted on 8benchmark datasets and 4 bank related datasets to assess the effectiveness of the proposed online and offline imputation techniques. In terms of Mean Absolute Percentage Error (MAPE), the results indicate that the difference between the proposed best offline imputation method viz., K-Medoids+GRNN and the proposed online imputation method viz., ECM+GRNN is statistically insignificant at a 1% level of significance. Consequently, the proposed online technique, being less expensive and faster, can be employed for imputation instead of the existing and proposed offline imputation techniques. This is the significant outcome of the study. Furthermore, GRNN in stage-2 uniformly reduced MAPE values in both offline and online imputation methods on all datasets.

• 한국인터넷방송통신학회논문지
• /
• 제9권4호
• /
• pp.39-45
• /
• 2009

최근 무선 모바일 컴퓨팅 응용 기술과 휴대용 모바일 단말장치 개발 기술의 급속한 발전과 더불어, 요즈음 가장 각광을 받는 이 분야의 이슈는 무선 모바일 애드 혹 네트워크 환경에서의 온라인 게임의 설계에 관한 것이다. 모바일 컴퓨팅 환경에서의 온라인 게임은 이동 단말들이 갖는 제약들: 즉, 낮은 성능의 프로세서, 극히 제한적인 메모리 공간, 무선 기반의 적은 통신 대역폭과 한정된 배터리 파워 등의 제한으로 인해 본격 온라인 게임 개발에 많은 제약이 따른다. 따라서 지금까지의 대부분의 모바일 게임들은 온라인이나 멀티플레이 기능에 매우 제한적이다. 본 논문에서는 많은 제약을 갖는 이동 단말을 기반으로 모바일 컴퓨팅 환경에서 다수의 사용자들이 멀티플레이가 가능한 온라인 MMORPG를 설계하고 구현하였다. 제안한 온라인 게임은 Blutooth를 이용하여 국부적으로 무선 모바일 애드혹 네트워크를 클라이언트들 간에 일시적으로 구축하고 MMORPG 게임을 온라인으로 수행할 수 있도록 설계하였으며, 또한 이들 간의 멀티플레이를 지원한다.

• 유통과학연구
• /
• 제16권7호
• /
• pp.57-65
• /
• 2018

Purpose - Recently, internet access and social network utilization using smart phone are increasing. In such a smart environment, interactive activities such as information generation, information searching and information sending are increasing rapidly on-line environment. Therefore, consumers tend to purchase something according to eWOM and also meet the social consensus online environment. In connectivity society, consumers became accessible and engaged in the opinions of others easily. Many decisions that seem like personal decisions are actually social decisions on online connectivity. This paper seeks to explore factors that can help generate a social decision on purchasing of new products in an online environment. Research design, data, and methodology - The process of collecting a lot of wisdom and making an agreement online is called social decision. The purpose of this paper is to examine empirically the influence of factors such as online ties, online eWOM expectancy and online information behavior on online social decision. In addition, We studied online social decision by analyzing the moderating effect of new product innovation. To understand this structural relationship, research hypotheses and research models were set up and empirical analysis was conducted. In order to verify the hypothesis, 208 questionnaires were collected from the residents of Seoul city/Gyeonggi province. The answered questionnaire verifies reliability and validity using SPSS/AMOS and test hypotheses through path analysis and multiple regression analysis. Results - According to the research results, First, online ties don't have a positive impact on online social decision, Second, online eWOM expectancy have a positive impact on online social decision. Third, online information behaviors have a positive impact on online social decision. The degree of innovation of new products have a moderating effect between Independent variables of three factors and dependent variable of social decision. Conclusions - Social decisions have a positive impact on purchasing decisions about new product. There is a great significance in the fact that the online social influence and online social decision have been studied academically. It is meaningful that we have studied in depth the changing phenomenon of consumer purchase decision process in smart environment. The results of these studies provide academic and practical implications.

• Journal of Electrical Engineering and Technology
• /
• 제13권6호
• /
• pp.2468-2478
• /
• 2018

We propose the Sparse Feature Convolutional Neural Network (SFCNN) to reduce the volume of convolutional neural networks (CNNs). Despite the superior classification performance of CNNs, their enormous network volume requires high computational cost and long processing time, making real-time applications such as online-training difficult. We propose an advanced network that reduces the volume of conventional CNNs by producing a region-based sparse feature map. To produce the sparse feature map, two complementary region-based value extraction methods, cluster max extraction and local value extraction, are proposed. Cluster max is selected as the main function based on experimental results. To evaluate SFCNN, we conduct an experiment with two conventional CNNs. The network trains 59 times faster and tests 81 times faster than the VGG network, with a 1.2% loss of accuracy in multi-class classification using the Caltech101 dataset. In vehicle classification using the GTI Vehicle Image Database, the network trains 88 times faster and tests 94 times faster than the conventional CNNs, with a 0.1% loss of accuracy.