• Journal of Information Science Theory and Practice
• /
• v.7 no.3
• /
• pp.31-39
• /
• 2019

Nowadays, recommender systems suggest lists of items to users considering not only accuracy but also diversity and novelty. However, suggesting the most diverse list of items to all users is not always acceptable, since different users prefer and/or tolerate different degree of diversity. Hence suggesting a personalized list with a diversity degree considering each user preference would improve the efficiency of recommender systems. The main contribution and novelty of this study is to tune the diversity degree of the recommendation list based on the users' variety-seeking feature, which ultimately leads to users' satisfaction. The proposed approach considers the similarity of users' desire diversity as a new parameter in addition to the usual similarity of users in the state-of-the-art collaborative filtering algorithm. Experimental results show that the proposed approach improves the personal diversity criterion comparing to the closest method in the literature, without decreasing accuracy.

• Communications for Statistical Applications and Methods
• /
• v.10 no.1
• /
• pp.61-77
• /
• 2003

Due to the wide expansion of the internet, people can freely get information what they want with lesser efforts. However without adequate forms or rules to follow, it is getting more and more difficult to get necessary information. Because of seemingly chaotic status of the current web environment, it is sometimes called "Dizzy web" The user should wander from page to page to get necessary information. Therefore we need to construct system which properly recommends appropriate information for general user. The representative research field for this system is called Recommendation System(RS), The collaborative recommendation system is one of the RS. It was known to perform better than the other systems. When we perform the web user modeling or other web-mining tasks, the continuous feedback data is very important and frequently used. In this paper, we propose a collaborative recommendation system which can deal with the continuous feedback data and tried to construct the web page prediction system. We use a sojourn time of a user as continuous feedback data and combine the traditional model-based algorithm framework with the Support Vector Regression technique. In our experiments, we show the accuracy of our system and the computing time of page prediction compared with Pearson's correlation algorithm.algorithm.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1673-1681
• /
• 2021

Item cold start is a well studied problem in the research field of recommender systems. Still, many existing collaborative filters cannot recommend items accurately when only a few user-item interaction data are available for newly introduced items (Cold items). We propose a interaction feature prediction method to mitigate item cold start problem. The proposed method predicts the interaction features that collaborative filters can calculate for the cold items. For prediction, in addition to content features of the cold-items used by state-of-the-art methods, our method exploits the interaction features of k-nearest content neighbors of the cold-items. An attention network is adopted to extract appropriate information from the interaction features of the neighbors by examining the contents feature similarity between the cold-item and its neighbors. Our evaluation on a real dataset CiteULike shows that the proposed method outperforms state-of-the-art methods 0.027 in Recall@20 metric and 0.023 in NDCG@20 metric.

• 유체기계공업학회:학술대회논문집
• /
• 2004.12a
• /
• pp.711-714
• /
• 2004

A project to develop internet based collaborative engineering environments using agent technology is started to develop an agent based soft system for design and performance analysis of centrifugal pumps. This paper introduces the feasible technology needed to construct a pump design system based on software agent.

• International conference on construction engineering and project management
• /
• 2024.07a
• /
• pp.909-916
• /
• 2024

The emergence of Building Information Modelling (BIM), reality data, Virtual Reality (VR), and Augmented Reality (AR) has significantly enhanced the collaboration between stakeholders in construction management. The utilization of VR/AR devices holds considerable potential for monitoring safety in complex and constrained working environments on the construction site. On the other hand, near-miss incidents remain an important early sign of struck-by accidents. However, research on early warning and prevention methods for this risk is still limited. This paper, therefore, presents a framework for on-site and off-site collaborative safety monitoring framework using augmented and virtual reality for near-miss incidents. In the proposed framework, three phases to develop a VR/AR-based safety monitoring system include (1) construction safety simulation environment, (2) localization-based interaction system, and (3) safety monitoring system. The system can undertake the processing of data and enables communication among disparate VR/AR devices. VR clients are observational tools and offer guidance, while the AR client stays onsite for construction tasks. All clients connect to a processing computer, which also works as a host. The system embedded in the AR device can trigger an alarm or receive signals from the VR client when a near-miss issue happens. Additionally, all device clients possess the capability to share data acquired from onsite monitoring cameras, thereby fostering effective discussions and decision-making. The efficacy of this cross-platform system has been validated through the implementation of an outdoor coordination case study.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.1
• /
• pp.113-118
• /
• 2015

Recommendation system is filtering for users require appropriate information from increasing information. Recommendation system is provides the information based on user information or content that information entered in the original through process of filtering through the algorithm. Recommend system is problems with Cold-start, and Cold-start is not enough information in the occurrences for new users of recommend system in the new information to the user when recommend. Cold-start is should meet to resolve the user of information and item information. In this paper, Suggest for movie recommendation system on collaborative filtering techniques and content-based filtering techniques based to a hybrid of a hybrid filtering techniques to solve problems in cold-start.

• Journal of Ginseng Research
• /
• v.44 no.2
• /
• pp.222-228
• /
• 2020

Background: 20(S)-ginsenoside-Rg3 (C₄₂H₇₂O₁₃), a natural triterpenoid saponin, is extracted from red ginseng. The increasing use of 20(S)-ginsenoside Rg3 has raised product safety concerns. Methods: In acute toxicity, 20(S)-ginsenoside Rg3 was singly and orally administrated to Kunming mice and Sprague-Dawley (SD) rats at the maximum doses of 1600 mg/kg and 800 mg/kg, respectively. In the 26-week toxicity study, we used repeated oral administration of 20(S)-ginsenoside Rg3 in SD rats over 26 weeks at doses of 0, 20, 60, or 180 mg/kg. Moreover, a 4-week recovery period was scheduled to observe the persistence, delayed occurrence, and reversibility of toxic effects. Results: The result of acute toxicity shows that oral administration of 20(S)-ginsenoside Rg3 to mice and rats did not induce mortality or toxicity up to 1600 and 800 mg/kg, respectively. During a 26-week administration period and a 4-week withdrawal period (recovery period), there were no significant differences in clinical signs, body weight, food consumption, urinalysis parameters, biochemical and hematological values, or histopathological findings. Conclusion: The mean oral lethal dose (LD₅₀) of 20(S)-ginsenoside Rg3, in acute toxicity, is above 1600 mg/kg and 800 mg/kg in mice and rats, respectively. In a repeated-dose 26-week oral toxicity study, the no-observed-adverse-effect level for female and male SD rats was 180 mg/kg.

• The KIPS Transactions:PartB
• /
• v.8B no.2
• /
• pp.144-154
• /
• 2001

협력적 여과 시스템은 사용자가 검색하고 읽었던 웹문서를 기반으로 사용자 군집을 생성하여 웹문서의 정확한 추천을 가능하게 한다. 이러한 목적으로 설계된 다양한 알고리즘이 있으나 속도가 느리거나 정확도가 낮다는 등의 단점이 있다. 본 논문에서는 이러한 단점을 보완하기 위하여 협력적 여과 시스템을 위한 효과적인 사용자 군집 알고리즘인 CUG알고리즘은 사용자 군집을 생성하기 위해 Apriori 알고리즘, Native Bayes 알고리즘을 이용한다. Apriori 알고리즘은 연관 단어 지식 베이스를 구축하고, Native Bayes 알고리즘은 구축된 연관 단어 지식 베이스에 가중치를 추가하며, 사용자가 검색하여 읽은 웹문서를 클래스별로 분류한다. CUG 알고리즘은 분류된 웹문서를 기반으로 하여 사용자 군집을 만든다. 이러한 방법으로 설계된 CUG 알고리즘은 사용자들이 사용할 문서를 미리 검색하여 저장함에 의해 정보검색의 효율성을 향상시키는데 사용될 수 있다. 본 논문에서 설계한 CUG 알고리즘의 선능을 평가하기 위하여 기존의 K-means 방법과 Gibbs샘플링 방법에 의한 군집과 비교한다.

• Journal of the Korean Society of Industry Convergence
• /
• v.25 no.5
• /
• pp.909-915
• /
• 2022

In this paper, a robot automation technology for chemical tank lorry unloading is presented. Handling chemical coupler between tank lorry and ACQC system may be hazardous or toxic to human operators, therefore robot automation is essential. Due to tight tolerance between couplers, even small pose error may result in very large internal force. In order to resolve the problem, compliance between male and female couplers should be introduced with 6-axis compliance device with F/T sensing. The proposed robot automation system consists of a collaborative robot, 6-ax is compliance device with F/T sensing, linear gripper, and robot vision. The position/force control algorithm and experimental results for assembling chemical couplers are presented.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.655-656
• /
• 2022

Among the analysis methods for a recommendation system, collaborative filtering is a major representative method in a recommendation system based on data analysis. A general usage method is a technique of finding a common pattern by using evaluation data of users for various items, and recommending a preferred item for a specific user. Therefore, in this paper, various algorithms were used to measure the index, and an algorithm suitable for prediction of user preference was found and presented.