• The Transactions of the Korea Information Processing Society
• /
• v.7 no.5S
• /
• pp.1599-1608
• /
• 2000

Automated collaborative filtering is on the verge of becoming a popular technique to reduce overloaded information as well as to solve the problems that content-based information filtering systems cannot handle. In this paper, we describe three different algorithms that perform collaborative filtering: GroupLens that is th traditional technique; Best N, the modified one; and an algorithm that uses clustering. Based on the exeprimental results using real data, the algorithm using clustering is compared with the existing representative collaborative filtering agent algorithms such as GroupLens and Best N. The experimental results indicate that the algorithms using clustering is similar to Best N and better than GroupLens for prediction accuracy. The results also demonstrate that the algorithm using clustering produces the best performance according to the standard deviation of error rate. This means that the algorithm using clustering gives the most stable and the best uniform recommendation. In addition, the algorithm using clustering reduces the time of recommendation.

• Journal of Information Processing Systems
• /
• v.4 no.3
• /
• pp.103-112
• /
• 2008

This paper proposes a policy adjuster-driven Grid workflow management system for collaborative healthcare platform, which supports collaborative heart disease diagnosis applications. To select policies according to service level agreement of users and dynamic resource status, we devised a policy adjuster to handle workflow management polices and resource management policies using policy decision scheme. We implemented this new architecture with workflow management functions based on policy quorum based resource management system for providing poincare geometrycharacterized ECG analysis and virtual heart simulation service. To evaluate our proposed system, we executed a heart disease identification application in our system and compared the performance to that of the general workflow system and PQRM system under different types of SLA.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.228-230
• /
• 2020

The emergence of collaborative learning to the public is to tackle the user's privacy issue in centralized learning by bringing the AI models to the data source or client device for training Collaborative learning employs computing and storage resources on the client's device. Thus, it is privacy preserved by design. In harmony, blockchain is also prominent since it does not require an intermediary to process a transaction. However, these approaches are not yet fully ripe to be implemented in the real world, especially for the complex system (several challenges need to be addressed). In this work, we present the performance of collaborative learning and potential use case of blockchain. Further, we discuss privacy issues in the system.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1999-2005
• /
• 2005

Collaboration in wireless sensor networks must be fault-tolerant due to the harsh environmental conditions in which such networks can be deployed. This paper focuses on finding signal processing algorithms for collaborative target detection based on the generalized approach to signal processing in the presence of noise that are efficient in terms of communication cost, precision, accuracy, and number of faulty sensors tolerable in the wireless sensor network. Two algorithms, namely, value fusion and decision fusion constructed according to the generalized approach to signal processing in the presence of noise, are identified first. When comparing their performance and communication overhead, decision fusion is found to become superior to value fusion as the ratio of faulty sensors to fault free sensors increases. The use of the generalized approach to signal processing in the presence of noise under designing value and decision fusion algorithms in wireless sensor networks allows us to obtain the same performance, but at low values of signal energy, as under the employment of universally adopted signal processing algorithms widely used in practice.

• Asian-Australasian Journal of Animal Sciences
• /
• v.30 no.1
• /
• pp.71-77
• /
• 2017

Objective: This experiment was conducted to investigate the effects of dietary supplementation with marigold extract on growth performance, pigmentation, antioxidant capacity and meat quality in broiler chickens. Methods: A total of 320 one-day-old Arbor Acres chickens were randomly divided into 5 groups with 8 replicates of 8 chickens each. The chickens of control group were fed with basal diet and other experimental groups were fed with basal diet supplemented with 0.075%, 0.15%, 0.30%, and 0.60% marigold extract respectively (the corresponding concentrations of lutein were 15, 30, 60, and 120 mg/kg). Results: The results showed that marigold extract supplementation increased the yellowness values of shank, beak, skin and muscle and the redness ($a^*$) value of thigh muscle (linear, p<0.01). Marigold extract supplementation significantly increased the total antioxidant capacity, and the activities of superoxide dismutase in liver and thigh muscle (linear, p<0.01) and significantly decreased the malondialdehyde contents of liver and thigh muscle (linear, p<0.01). Marigold extract supplementation significantly decreased the drip loss and shear force of thigh muscles (linear, p<0.01). There was no significant effect on growth performance with marigold extract supplementation. Conclusion: In conclusion, dietary supplementation of marigold extract significantly increased the yellowness values of carcass, antioxidant capacity and meat quality in broiler chickens.

• Asian-Australasian Journal of Animal Sciences
• /
• v.30 no.12
• /
• pp.1764-1772
• /
• 2017

Objective: This study investigated the effects of different dietary energy sources on early postmortem muscle metabolism of finishing pigs. Methods: Seventy-two barrow ($Duroc{\times}Landrace{\times}Yorkshire$, DLY) pigs ($65.0{\pm}2.0kg$) were allotted to three iso-energetic and iso-nitrogenous diets: A (44.1% starch, 5.9% crude fat, and 12.6% neutral detergent fibre [NDF]), B (37.6% starch, 9.5% crude fat, and 15.4% NDF) or C (30.9% starch, 14.3% crude fat, and 17.8% NDF). After the duration of 28-day feeding experiment, 24 pigs (eight per treatment) were slaughtered and the M. longissimus lumborum (LL) samples at 45 min postmortem were collected. Results: Compared with diet A, diet C resulted in greater adenosine triphosphate and decreased phosphocreatine (PCr) concentrations, greater activity of creatine kinase and reduced percentage bound activities of hexokinase (HK), and pyruvate kinase (PK) in LL muscles (p<0.05). Moreover, diet C decreased the phosphor-AKT level and increased the hydroxy-hypoxia-inducible $factor-1{\alpha}$ ($HIF-1{\alpha}$) level, as well as decreased the bound protein expressions of HK II, PKM2, and lactate dehydrogenase A (p<0.05). Conclusion: Diet C with the lowest level of starch and the highest levels of fat and NDF could enhance the PCr utilization and attenuate glycolysis early postmortem in LL muscle of finishing pigs.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.10a
• /
• pp.716-719
• /
• 2019

Collaborative filtering has been used frequently as a recommendation system. To reduce the errors on predicting the ratings that may be given by the user, we propose a new aggregation method to do so. We used a real-world dataset MovieLens to compare our proposed method from previously existing methods, and accordingly to the results, ours was more accurate.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1158-1159
• /
• 2013

It gives to users a difficulty for searching between this huge numbers of programs. Searching the best applications for our needs is a big challenge today. In this paper, we propose a study on collaborative filtering based app recommendation system. The proposed method is composed of three steps. In the first step, we extract the data set from the target website. In the second step, we parse the extracted raw data according to the types, and store in a database. In the third, we perform recommendations based on the stored data in database.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.04a
• /
• pp.353-354
• /
• 2010

최근 사용자의 취향에 맞는 콘텐츠를 필터링하여 자동으로 추천하는 연구가 활발히 진행되고 있다. 참여형, 개방형, 공유형 서비스들의 증가와 함께 웹 3.0 시대에는 더욱 지능화되고 개인화된 서비스가 중요시되고, 이를 위한 맞춤형 정보 제공 연구가 필수적이다. 본 논문에서는 사용자 맞춤형 추천 방법의 대표적인 기술인 협업 필터링(Collaborative Filtering) 방안 분석에 대해 설명하고, 협업 필터링 방법의 적용 연구를 설명한다.

• The Journal of Society for e-Business Studies
• /
• v.7 no.2
• /
• pp.129-141
• /
• 2002

This paper deals with the collaborative procurement process in a two-echelon supply chain that a manufacturing company and a contractor are connected through the information system. The real time information about inventory and production processing becomes available through this information system. We raise two issues related to the collaborative procurement process. First, we propose a VMI(Vendor-Managed Inventory) type of the procurement policy which focuses on the cost minimization for the total supply chain rather than individual companies. Second, based on the simulation study, we demonstrate that a collaborative procurement process is more cost-effective over classical procurement processes such as (Q, r). The result obtained in this paper can be applied to the quantitative evaluation of the cost saving effect when companies build the information sharing based, collaborative procurement system.