• Journal of KIISE
• /
• v.43 no.7
• /
• pp.786-794
• /
• 2016

Recommender systems can be used to assist users in selecting required services for their tasks in Internet of Things (IoT) environments in which diverse services can be provided by utilizing IoT devices. Traditional research on recommendation mainly focuses on predicting preferences of individual users. However, in IoT environments, not only individual users but also groups of users can access services in the environments. In this study, we analyzed user groups' preferences on services and developed service recommendation approach for new groups that do not have a history of accessing IoT-services in a certain place. Our approach extends the traditional user-based collaborative filtering by considering the similarity between user groups based on their member organization. We conducted experiments with a real-world dataset collected from IoT testbed environments. The results demonstrate that the proposed approach is effective to recommend services to new user groups in IoT environments.

• 지역과문화
• /
• v.8 no.2
• /
• pp.1-20
• /
• 2021

This study analyzed the effect of perceived service quality for the local content production policy on the service user satisfaction, reuse intention, and the recommendation intention. First, reliability, responsiveness, and adequacy were identified as the service quality evaluation criteria of the local content production policy. Second, all of the quality evaluation criteria had a positive effect on the service user satisfaction. Third, responsiveness had a positive effect on reuse intention, and responsiveness and reliability had a positive effect on recommendation intention. Fourth, the service user satisfaction had a positive effect on the reuse intention and recommendation intention. Therefore, this study has the significance of presenting a theoretical model for the service quality evaluation of the local content production policy, and suggesting perspective for the improvement of the policy.

• The Journal of Bigdata
• /
• v.2 no.1
• /
• pp.41-48
• /
• 2017

Recently, the popularity of the recommendation system and the evaluation of the performance of the algorithm of the recommendation system have become important. In this study, we used modeling and RMSE to verify the effectiveness of various algorithms in movie data. The data of this study is based on user-based collaborative filtering using Pearson correlation coefficient, item-based collaborative filtering using cosine correlation coefficient, and item-based collaborative filtering model using singular value decomposition. As a result of evaluating the scores with three recommendation models, we found that item-based collaborative filtering accuracy is much higher than user-based collaborative filtering, and it is found that matrix recommendation is better when using matrix decomposition.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.369-384
• /
• 2021

In a personalized product recommendation system, when the amount of log data is large or sparse, the accuracy of model recommendation will be greatly affected. To solve this problem, a personalized product recommendation method using deep factorization machine (DeepFM) to analyze user behavior is proposed. Firstly, the K-means clustering algorithm is used to cluster the original log data from the perspective of similarity to reduce the data dimension. Then, through the DeepFM parameter sharing strategy, the relationship between low- and high-order feature combinations is learned from log data, and the click rate prediction model is constructed. Finally, based on the predicted click-through rate, products are recommended to users in sequence and fed back. The area under the curve (AUC) and Logloss of the proposed method are 0.8834 and 0.0253, respectively, on the Criteo dataset, and 0.7836 and 0.0348 on the KDD2012 Cup dataset, respectively. Compared with other newer recommendation methods, the proposed method can achieve better recommendation effect.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.3
• /
• pp.129-137
• /
• 2019

Recommendation systems help users by suggesting items such as products, services, and information. However, most research on recommendation systems has not considered people's moods although the appropriate contents recommended to people would be changed by people's moods. In this paper, we propose a situation-based recommendation system which exploits people's mood. The proposed scheme is based on the fact that the mood of a user is changed frequently by the surrounding environments such as time, weather, and anniversaries. The environments are defined as feature identifications, and the rating values on items are stored as feature identifications at a database. Then, people can be recommended diverse items according to their environments. Our proposed scheme has some advantages such as no problem of cold start, low processing overhead, and serendipitous recommendation. The proposed scheme can be also a good option as of assistance to other recommendation systems.

• Journal of Information Technology Services
• /
• v.20 no.3
• /
• pp.57-73
• /
• 2021

Recently, online job websites have been activated as unemployment problems have emerged as social problems and demand for job openings has increased. However, while the online job platform market is growing, users have difficulty choosing their jobs. When users apply for a job on online job websites, they check various information such as job contents and recruitment conditions to understand the details of the job. When users choose a job, they focus on various details related to the job rather than simply viewing and supporting the job title. However, existing online job websites usually recommend jobs using only quantitative preference information such as ratings. However, if recommendation services are provided using only quantitative information, the recommendation performance is constantly deteriorating. Therefore, job recommendation services should provide personalized services using various information about the job. This study proposes a recommended methodology that improves recommendation performance by elaborating on qualitative preference information, such as details about the job. To this end, this study performs a topic modeling analysis on the job content of the user profile. Also, we apply LDA techniques to explore topics from job content and extract qualitative preferences. Experiments show that the proposed recommendation methodology has better recommendation performance compared to the traditional recommendation methodology.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2003.11a
• /
• pp.191-194
• /
• 2003

As internet commerce grows, many company has begun to use a CF (Collaborative Filtering) as a Recommender System. To achieve an accuracy of CF, we need to obtain sufficient account of voting scores from customers. Moreover, those scores may not be consistent. To overcome this problem, we propose a new recommendation scheme using binary user-item matrix, which represents whether a user purchases a product instead of using the voting scores. Through the experiment regarding this new scheme, a better accuracy is demonstrated.

• KIISE Transactions on Computing Practices
• /
• v.22 no.10
• /
• pp.504-512
• /
• 2016

In this paper, we propose a personalized event recommendation scheme using user's activity analysis and collaborative filtering in social network environments. The proposed scheme predicts un-evaluated attribute values through analysis of user activities, relationships, and collaborative filtering. The proposed scheme also incorporates a user's recent preferences by considering the recent history for the user or context-aware information to precisely grasp the user's preferences. As a result, the proposed scheme can recommend events to users with a high possibility to participate in new events, preventing indiscriminate recommendations. In order to show the superiority of the proposed scheme, we compare it with the existing scheme through performance evaluation.

• Convergence Security Journal
• /
• v.19 no.2
• /
• pp.73-81
• /
• 2019

In this paper, we propose a user-dependent mid-point navigation system using a time weighted mid-point navigation algorithm and a user preference based mid-point neighborhood recommendation system. The proposed system consists of a mid-point navigation module for calculating an mid-point by applying a time weight of each user based on a departure point between users, and a search module for providing a search for a route to the calculated mid-point. In addition, based on the mid-point search result, it is possible to increase the utilization rate of users by including a place recommending function based on user's preference. Experimental results show that the proposed system can increase the efficiency of using by the user-dependent mid-point navigation and place recommendation function.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.12 no.1
• /
• pp.257-264
• /
• 2012

The development of mobile devices and the spread of wireless network help share and exchange information and resources more easily. The bond them to Cloud Computing technology help pay attention to "Mobile Cloud" service, so there have been being a lot of studies on "Mobile Cloud" service. Especially, the important of 'Recommendation Service' which is customized for each user's preference and context has been increasing. In order to provide appropriate recommendation services, it enables to recognize user's current state, analyze the user's profile like user's tendency and preference, and draw the service answering the user's request. Most existing frameworks, however, are not very suitable for mobile devices because they were proposed on the web-based. And other context information except location information among user's context information are not much considered. Therefore, this paper proposed the context-aware framework, which provides more suitable services by using user's context and profile.