• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.63-70
• /
• 2022

Fashion is a field in which personal taste acts as the first criterion for purchase, and it is being refined as an important strategy to increase purchase conversion on mobile. Although related studies have been conducted, there are insufficient studies to confirm this according to the detailed purchasing journey of consumers. The purpose of this study is to examine whether the evaluation of user experience factors of personalized recommendation service differs by purchase journey, and to reveal whether it affects purchase intention and satisfaction. Variety, reliability, and convenience showed a significant difference at the level of 0.001% and usefulness at the level of 0.05%. Satisfaction levels were different for each stage, such as novelty and usefulness in the cognitive and interest stage, and high reliability and diversity in the search stage. It has theoretical significance in that it enhances the understanding of the purchase journey by revealing that there is a difference in user evaluation of the personalized recommendation service, and it has practical significance in that it suggests the direction of improvement of the personalized recommendation service strategy. If research on effectiveness is conducted in the future, it will be able to contribute to an advanced strategy.

• Korean Journal of Soil Science and Fertilizer
• /
• v.42 no.6
• /
• pp.467-471
• /
• 2009

An attempt was made to provide the most resonable fertilizer recommendation for carrot crop based on soil analytical data and yield response to the NPK fertilizers, which was obtained from field experiments on 2003 in highland, 850 meters above the sea level. Optimum times of N, P, K application to current application methods based on soil test were 0.75-0.50-0.50 for carrot. The adjusted N, P, K recommendation models of highland soil were made by adding the application times to past application methods which were based on chemical properties of soil. The revised models for fertilizer application were recommended to decrease the amount of N-P-K by 25-50-50% for carrot in highland. In application to total cultivation area, 135ha for carrot, saving amounts of NPK fertilizers with these adjusted recommendation in comparison with past application levels will be 23.0 tons for carrot. Using the optimal application amounts for carrot, we will can reduce agricultural pollution without affecting crop yields.

• Korean Journal of Soil Science and Fertilizer
• /
• v.42 no.3
• /
• pp.167-171
• /
• 2009

An attempt was made to provide the most reasonable fertilizer recommendation for radish crop based on soil analysis data and yield response to the N, P, K fertilizers, which was obtained from field experiments on 2004 in highland, 850 meters above the sea level. Optimum times of NPK application to past application amount based on soil test were 0.90-0.77-0.50 for radish. The adjusted NPK recommendation models of highland soil were made by adding the application times to past application methods which were based on chemical properties of soil. The revised models for fertilizer application were recommended to decrease the amount of N, P, K by 10-23-50% for radish in highland. In application to total cultivation area, 2,546ha for radish, saving amounts of NPK fertilizers with these adjusted recommendation in comparison with past application levels will be 244.4 tons for radish. Using the optimal application amounts for radish, we will can reduce agricultural pollution without affecting crop yields.

• Journal of Information Processing Systems
• /
• v.9 no.3
• /
• pp.435-460
• /
• 2013

Recommender systems are popular applications that help users to identify items that they could be interested in. A recent research area on recommender systems focuses on detecting several kinds of inconsistencies associated with the user preferences. However, the majority of previous works in this direction just process anomalies that are intentionally introduced by users. In contrast, this paper is centered on finding the way to remove non-malicious anomalies, specifically in collaborative filtering systems. A review of the state-of-the-art in this field shows that no previous work has been carried out for recommendation systems and general data mining scenarios, to exactly perform this preprocessing task. More specifically, in this paper we propose a method that is based on the extraction of knowledge from the dataset in the form of rating regularities (similar to frequent patterns), and their use in order to remove anomalous preferences provided by users. Experiments show that the application of the procedure as a preprocessing step improves the performance of a data-mining task associated with the recommendation and also effectively detects the anomalous preferences.

• Journal of Korea Society of Industrial Information Systems
• /
• v.13 no.5
• /
• pp.133-141
• /
• 2008

Social Web is turning current Web into social platform for knowing people and sharing information. This paper takes major social tagging systems as examples, namely delicious, flickr and youtube, to analyze the social phenomena in the Social Web in order to identify the way of mediating and linking social data. A simple Tag Ontology (TO) is proposed to integrate different social tagging data and mediate and link with other related social metadata. Through several machine learning for tagging data, tag groups and similar user groups are extracted, and then used to learn the tagging ontology. A recommender system adopting the tag ontology is also suggested as an applying field.

• 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.

• Journal of the Korean Institute of Navigation
• /
• v.20 no.2
• /
• pp.59-76
• /
• 1996

We have implemented the questionnaire survey to study the structure of consciousness of collegian and the Change of the worth view of the vocation on totally 832 collegians who attended to fisheries and martime colleges. The results were as follows : Most collegian had selected college and department by means of surrounding recommendation and acquired scores without regarding his own aptitude and prospect. The educational aims of the collegian who majored in fisheries and maritime field are to carry out the theory and practise along with emphasizing technical education and human-being education together. Concerning to the status of professor. Most collegian had wanted professor not only who had much comprehensive faculty but also who pointed out than well teaching professor. The collegian who consult their prospect with professor was very rare and they were very negative for the learning majoring in fisheries and maritime field. Because the practice guidance was not accomplished effectively on the account of social aspect, most collegian has avoided jobs relating to fisheries and maritime field. Also, they had selected short term on the job training couse aboard the ship.

• Journal of the Society of Naval Architects of Korea
• /
• v.56 no.2
• /
• pp.117-127
• /
• 2019

Vessel's ice speed performances will be verified in ice sea trial but environmental conditions of ice fields are changeable according to the weather condition of ice trial area. Speed performance has to correct in the no wind, wave and current etc. after sea trial. Especially finding ice fields which is exact the same as owner's ice thickness and strength requirements is not easy. Therefore speed correction according to environment condition has to be done after sea trial measurements. Correction methods for ice thickness, ice strength, wave, wind and ship draft, trim, ice drift etc. are checked in ice sea trial based on literature review such as ISO standard, ITTC recommendation, journal papers and proceedings of conferences. Possibility of application for current and ice drift correction in ice field are discussed and measuring schemes and procedures of correction methods are described in this paper. All of correction schemes are calculated for 'Araon' which is ice breaking research vessel with Arctic and Antarctic ice field test results. Analyzed results shows that Araon is satisfied with her official ice speed performance of 3 knots with 10MW power at 1m ice thickness, 570kPa ice flexural strength.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.1
• /
• pp.35-44
• /
• 2021

Recent advances in the 4th Industrial Revolution have accelerated the change of the working environment, such that the paradigm of education has been shifted in accordance with career education including the free semester system and the high school credit system. While the purpose of those systems is students' self-motivated career exploration, educational limitations for teachers and students exist due to the rapid change of the information on education. Also, education technology research to tackle these limitations is relatively insufficient. To this end, this study first defines three requirements that education technologies for the career education system should consider. Then, through data-driven artificial intelligence technology, this study proposes a data system and an artificial intelligence recommendation model that incorporates the topics for career exploration, courses, and majors in one scheme. Finally, this study demonstrates that the set-based artificial intelligence model shows satisfactory performances on recommending career education contents such as courses and majors, and further confirms that the actual application of this system in the educational field is acceptable.

• Journal of The Korean Society of Integrative Medicine
• /
• v.11 no.2
• /
• pp.231-242
• /
• 2023

Purpose : This study aimed to identify ways to improve the quality of physical therapy research and ultimately review the current situation to improve evidence-based decision-making in physical therapy. Methods : For better evidence-based decision-making in physical therapy, researchers should review the quality assessment of articles in more detail and report their findings for valid and appropriate level of evidence and strength of recommendations. The level of evidence affects how well the findings are derived from well-designed literature. The evaluation of the evidence focuses primarily on the study design and the degree of bias that may compromise the validity of the findings. The final recommendation is based on a combination of the study design and literature quality. To uncover gems of information in each paper, a risk of bias assessment should be performed after the literature has been initially selected. Results : Researchers should consider the complexity of the intervention, appropriate grouping, and calculation of effect sizes for the intervention. Researchers conducting systematic reviews should provide a detailed description of the quality assessment performed and present a detailed analysis of their interpretation of the results. The results of systematic reviews and meta-analyses should be interpreted with caution and include a risk of bias assessment. Guidelines for the level of evidence and strength of recommendations should be developed and utilized more broadly to improve reporting practices in physical therapy. Conclusion : Researchers should be knowledgeable about the strengths and limitations of each study design and methodology. In the future, researchers will also need to improve their ability to critically evaluate their findings, given the potential for their results to influence clinical practice.