• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권9호
• /
• pp.4684-4705
• /
• 2019

Collaborative filtering recommender systems are vulnerable to shilling attacks in which malicious users may inject biased profiles to promote or demote a particular item being recommended. To tackle this problem, many robust collaborative recommendation methods have been presented. Unfortunately, the robustness of most methods is improved at the expense of prediction accuracy. In this paper, we construct a robust Bayesian probabilistic matrix factorization model for collaborative filtering recommender systems by incorporating the detection of user anomaly rating behaviors. We first detect the anomaly rating behaviors of users by the modified K-means algorithm and target item identification method to generate an indicator matrix of attack users. Then we incorporate the indicator matrix of attack users to construct a robust Bayesian probabilistic matrix factorization model and based on which a robust collaborative recommendation algorithm is devised. The experimental results on the MovieLens and Netflix datasets show that our model can significantly improve the robustness and recommendation accuracy compared with three baseline methods.

• 한국지능시스템학회논문지
• /
• 제16권3호
• /
• pp.259-265
• /
• 2006

학습과 감정은 지능형 시스템을 구현하는데 있어 가장 중요한 요소이다. 본 논문에서는 강화학습을 이용하여 사용자와 상호작용을 하면서 학습을 수행하고 내부적인 감정모델을 가지고 있는 지능적인 가상 캐릭터를 구현하였다. 가상 캐릭터는 여러 가지 사물들로 이루어진 3D의 가상 환경 내에서 내부상태에 의해 자율적으로 동작하며, 또한 사용자는 가상 캐릭터에게 반복적인 명령을 통해 원하는 행동을 학습시킬 수 있다. 이러한 명령은 인공신경망을 사용하여 마우스의 제스처를 인식하여 수행할 수 있고 감정의 표현을 위해 Emotion-Mood-Personality 모델을 새로 제안하였다. 그리고 실험을 통해 사용자와 상호작용을 통한 감정의 변화를 살펴보았고 가상 캐릭터의 훈련에 따른 학습이 올바르게 수행되는 것을 확인하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권6호
• /
• pp.2069-2085
• /
• 2021

A Social Networking Service (SNS) platform provides digital footprints to discover users' interests and track the social diffusion of product adoptions. How to identify a small set of seed users in a SNS who is potential to adopt a new promoting product with high probability, is a key question in social networks. Existing works approached this as a social influence maximization problem. However, these approaches relied heavily on text information for topic modeling and neglected the impact of seed users' relation in the model. To this end, in this paper, we first develop a general product adoption function integrating both users' interest and social influence, where the user interest model relies on historical user behavior and the seed users' evaluations without any text information. Accordingly, we formulate a product adoption maximization problem and prove NP-hardness of this problem. We then design an efficient algorithm to solve this problem. We further devise a method to automatically learn the parameter in the proposed adoption function from users' past behaviors. Finally, experimental results show the soundness of our proposed adoption decision function and the effectiveness of the proposed seed selection method for product adoption maximization.

• 지식경영연구
• /
• 제17권1호
• /
• pp.155-174
• /
• 2016

Recent years, a smartphone has been playing a role of searching, booking, and decision-makings in the tourism industry through tourists' user experiences and engagements. This study investigated the tourists' behavior toward smartphone usage regarding Chinese visitors who were ranked in Korea inbound tourism. This research model formulated two types of usage which identified explorlative use and exploitive use and the antecedent relationships of user empowerment including user competence, user impact, usage meaning, user trust. We analyzed SmartPLS2.0 for the hypotheses and found that first, user competence has a positive influence both of exploitative use and explorative use, second, user impact has a positive influence on exploitative use, but has not influenced on explorative use, third, usage meaning has not influence on exploitive use, but has a postitive influence on explorative use, and finally user trust has influence on both of exploitive and explorative use. Based on the results we found, we suggested Chinese tourists' smartphone usages' behaviors and theoretical and practical implications.

• 한국IT서비스학회지
• /
• 제12권4호
• /
• pp.381-397
• /
• 2013

User enjoyment is a key factor to understand online and mobile game users' behaviors. This study aims to understand the differences between mobile and online games, and the differences between Korean and Chinese game users in terms of the perceived importance of user enjoyment elements. To use AHP (Analytic Hierarchical Process), we decompose user enjoyment into sub-elements; sensory enjoyment, content enjoyment, enjoyment of the achievement, and enjoyment of interaction. Though the empirical study and independent t-test, we can find that there are the differences in the perceived importance of user enjoyment elements between Korean and Chinese game players, and between mobile and online games. Chinese users more stress on enjoyment of interaction and Korean users more emphasize on enjoyment of the achievement.

• 지식경영연구
• /
• 제12권4호
• /
• pp.41-54
• /
• 2011

Given the prevalence of home trading systems, it has become important to examine user behaviors in a stock investment environment. In this vein, this paper developed an integrated model to deeply understand the key determinants of user's continuance intention to use investment information through constructs prescribed by incorporating trust and perceived risk into expectation-confirmation model. The proposed research model was tested by using survey data collected from 160 users who have experience with stock investment. PLS (partial least squares) was employed for the analysis of the data. The findings of this study showed that the proposed framework provides a statistically significant explanation of the variation in continuance intention to search investment information. The findings revealed that trust and perceived risk are more prevalent predictors of continuance intention to use investment information compared to perceived usefulness. It was also found that user satisfaction serves as the salient antecedents of continuance intention to use investment information. The theoretical and practical implications of the findings were described.

• 대한인간공학회지
• /
• 제18권3호
• /
• pp.73-86
• /
• 1999

Nowadays, VCR(Video Cassette Recorder) has various functions, but users use to fail operating these function because of the complexity of operation. The process of operating VCR contains user's cognitive characteristics. It is necessary for designing it that we must identify a user's mental process in the behind of operational behaviors. This effort, as well as considering physical dimensions and layout, can make VCR easy to use. In this research, VCR remote controller are analyzed by the cognitive method and experiments. Three types of VCR remote controllers, cognitive VCR models and two non-cognitive(typical) VCR models, are adopted as experimental objects to test the validation of the suggested user's cognitive mode of VCR. As results, when VCR was operated by the cognitive prototype of remote controller, task completion time was reduced to 80.5%, and the number of errors was reduced to 96.8%.

• International Journal of Aeronautical and Space Sciences
• /
• 제7권1호
• /
• pp.91-98
• /
• 2006

The thermomechanical behaviors of SMA thin film actuator and their application are investigated. The numerical algorithm of the 2-D SMA thermomechanical constitutive equation is developed and implemented into the ABAQUS finite element program by using the user defined material (UMAT) subroutine. To verify the numerical algorithm of SMAs, the results are compared with experimental data. For the application of SMA thin film actuator, the methodology to maintain the precise configuration of inflatable membrane structure is demonstrated.

• 융합보안논문지
• /
• 제14권4호
• /
• pp.61-71
• /
• 2014

최근 안드로이드 스마트폰에서 악성 앱의 출현이 증가하고 있다. 하지만 매일 많은 앱이 출현되기 때문에 이들 앱을 분석하여 악성 앱을 탐지하기에는 많은 시간과 자원이 요구된다. 이로 인해 악성 앱이 많이 확산된 후에 대처하는 상황도 적지 않다. 본 논문은 악성 앱 가능성이 높은 앱을 우선적으로 분석할 수 있도록 앱 행위를 동적으로 추적하고 고위험성의 앱을 분류하는 TAU 기법을 제안한다. 이 기법은 사용자와 스마트폰의 상호작용으로 발생하는 앱의 설치, 유포 경로 및 실행 행위를 추적한다. 이런 추적된 행위 분석하여 Drive-by download 및 Update attack 공격 가능성이 있는 앱을 분류한다. 또한 악성 앱의 유포 경로로 많이 사용되는 리패키징 여부를 판별한다. 이런 분류를 통해 고위험성의 앱에 대한 악성 코드 분석을 우선적으로 실행하게 하여 악성 앱의 유포를 빨리 막을 수 있도록 한다.

• 방송공학회논문지
• /
• 제19권1호
• /
• pp.3-13
• /
• 2014

본 논문은 매우 빠른 속도로 개발 및 보급되고 있는 개인형 클라우드 서비스의 이용에 관한 탐색적 연구이다. 특히, 이용자 특성과 이용 행태에 주목하여, 플랫폼 및 콘텐츠 연계이용이 클라우드 서비스 이용에 미치는 영향을 실증적으로 검증하였다. 연구결과, 첫째 클라우드 서비스 이용은 사진, 음악, 음원과 같은 데이터 용량이 작은 콘텐츠를 중심으로 주로 연계이용되었다. 둘째, 클라우드 서비스 이용에 있어 '플랫폼 연계이용'이 제일 영향력 있는 요인으로 밝혀졌으며, SNS 이용, 이메일 이용, 개인의 혁신성 등도 통계적으로 유의미하게 나타났다. 본 연구는 개인형 클라우드 서비스에 대한 이론적 분석에 있어 선도적인 연구로서, 클라우드 서비스의 개발 및 관련 산업 진흥 정책의 수립에 있어 이용자 특성과 이용 행태의 고려가 필요하다는 함의를 제공하고 있다.