• Journal of Intelligence and Information Systems
• /
• v.22 no.3
• /
• pp.113-127
• /
• 2016

Among the techniques for recommendation, collaborative filtering (CF) is commonly recognized to be the most effective for implementing recommender systems. Until now, CF has been popularly studied and adopted in both academic and real-world applications. The basic idea of CF is to create recommendation results by finding correlations between users of a recommendation system. CF system compares users based on how similar they are, and recommend products to users by using other like-minded people's results of evaluation for each product. Thus, it is very important to compute evaluation similarities among users in CF because the recommendation quality depends on it. Typical CF uses user's explicit numeric ratings of items (i.e. quantitative information) when computing the similarities among users in CF. In other words, user's numeric ratings have been a sole source of user preference information in traditional CF. However, user ratings are unable to fully reflect user's actual preferences from time to time. According to several studies, users may more actively accommodate recommendation of reliable others when purchasing goods. Thus, trust relationship can be regarded as the informative source for identifying user's preference with accuracy. Under this background, we propose a new hybrid recommender system that fuses CF and social network analysis (SNA). The proposed system adopts the recommendation algorithm that additionally reflect the result analyzed by SNA. In detail, our proposed system is based on conventional memory-based CF, but it is designed to use both user's numeric ratings and trust relationship information between users when calculating user similarities. For this, our system creates and uses not only user-item rating matrix, but also user-to-user trust network. As the methods for calculating user similarity between users, we proposed two alternatives - one is algorithm calculating the degree of similarity between users by utilizing in-degree and out-degree centrality, which are the indices representing the central location in the social network. We named these approaches as 'Trust CF - All' and 'Trust CF - Conditional'. The other alternative is the algorithm reflecting a neighbor's score higher when a target user trusts the neighbor directly or indirectly. The direct or indirect trust relationship can be identified by searching trust network of users. In this study, we call this approach 'Trust CF - Search'. To validate the applicability of the proposed system, we used experimental data provided by LibRec that crawled from the entire FilmTrust website. It consists of ratings of movies and trust relationship network indicating who to trust between users. The experimental system was implemented using Microsoft Visual Basic for Applications (VBA) and UCINET 6. To examine the effectiveness of the proposed system, we compared the performance of our proposed method with one of conventional CF system. The performances of recommender system were evaluated by using average MAE (mean absolute error). The analysis results confirmed that in case of applying without conditions the in-degree centrality index of trusted network of users(i.e. Trust CF - All), the accuracy (MAE = 0.565134) was lower than conventional CF (MAE = 0.564966). And, in case of applying the in-degree centrality index only to the users with the out-degree centrality above a certain threshold value(i.e. Trust CF - Conditional), the proposed system improved the accuracy a little (MAE = 0.564909) compared to traditional CF. However, the algorithm searching based on the trusted network of users (i.e. Trust CF - Search) was found to show the best performance (MAE = 0.564846). And the result from paired samples t-test presented that Trust CF - Search outperformed conventional CF with 10% statistical significance level. Our study sheds a light on the application of user's trust relationship network information for facilitating electronic commerce by recommending proper items to users.

• Journal of the Korean Society of Radiology
• /
• v.10 no.7
• /
• pp.477-482
• /
• 2016

This study is tried to determine whether the management of medical radiation is well handled by comparison the guidelines of KFDA(korea food & drug administration) with analysis of dose indicator in mammography. As a method, it is analysed that kVp, exposure time, mAs, compressed breast thickness, average glandular dose and body mass index that were classified in the examination of both breasts by CC(cranio-caudal) and MLO(medio-lateral oblique) with EMR(electronic medical record) and dose report that were sent to the PACS(picture archiving communication system). As a result, in the site inspection according to the age, Compressed breast thickness in CC and MLO were the thickest of 45.6 mm and 49.6 mm in the 50-59 year old respectively. In the overall average compressed breast thickness, CC were 44.2 mm and MLO were 48.9 mm. MLO has more thick by 4.7 mm. In average glandular dose, CC were 1.05 mGy and MLO were 1.14 mGy. MLO has higher by 0.09 mGy than CC. As the compressed breast thickness increases 10mm, CC and MLO increases 0.15 mGy and 0.17 mGy respectively. When it was compared with the average glandular dose of 1.16 mGy per 1 film presented by KFDA, CC was showed 1.05 mGy. However, the 60 mm or more was found to exceed a 1.30 mGy. Also, As the compressed breast thickness was higher, body mass index showed high score. And in the case of 25 or more in the obese body index according to body mass index, it was showed obesity in case of the compressed breast thickness was more than 50mm.

• Journal of radiological science and technology
• /
• v.28 no.2
• /
• pp.97-103
• /
• 2005

Objective : The aim of this study was to compare the knee joint displaying between the anteroposterior weight bearing(AP-WB) View and the metatarsophalangeal(MTP) view for assessing joint space narrowing(JSN) and osteophytes in osteoarthritis patients. Subjects and Materials : Two hundreds of twenty patients(38 men) who came rheumatoid caused by knee pain, had both AP-WB and MTP views taken on a day. Radiographs were evaluated independently by 13 experienced observers(3 orthopedics surgeon, 2 rheumatogist, 3 radiologist, 5 radiological technologist) They assessed JSN and osteophytes using by PACS monitor JSN was scored by the optic evaluation to the nearest at the narrowest point in medial compartments of the tibiofemoral joint in both knees. Osteophytes were graded 0 to 3(bad 0, not bad 1, good 2 and very good 3) according to a standard atlas. All exam was using by Philips(Buckey Diagnostic-TH) X-ray material. Exposure condition was 60 kv, 8 mAs and 100 cm focus to film distance. Results : JSN was scored $1.32{\pm}0.050$ in AP-WB view, $2.51{\pm}0.046$ in MTP view. MTP view of JSN score is higher to AP-WB view significantly(p<0.05). Osteophytes scored $2.14{\pm}0.054$ in AP-WB view, $2.10{\pm}0.054$ in MTP view. There was no difference(p<0.05) between MTP view and AP-WB view in osteophytes. But MTP view was more reproducible than AP-WB view Conclusions : Joint space narrowing is most important factor to diagnosis with knee joint Osteoarthritis patients. This study was summarized as follows; In comparision of JSN, MTP view was more widely displayed than AP-WB view. In comparision of Osteophytes, there was no difference between MTP view and AP-WB view. It was concluded MTP view was more useful method to diagnosis of knee joint Osteoarthritis patients.

• Journal of Bio-Environment Control
• /
• v.30 no.1
• /
• pp.77-84
• /
• 2021

This study attempted to find a way to maintain the quality of mixing baby wild leaf vegetables with existing baby leaf vegetables in various ratios. The crops for mixing baby leaf vegetables were Peucedanum japoincum Thunberg and Ligularia stenocephala, as wild vegetables, and red romaine, which is widely used in young leafy vegetables. The mixing ratio of red romaine and wild vegetables was red romaine 0: mantilla oil 5: L. stenocephala ratio 5 (R0: P5: L5), red romaine 3.3: P. japoincum 3.3: L. stenocephala ratio 3.3 (R3.3: P3.3: L3.3), red romaine 5: P. japoincum 2.5: L. stenocephala 2.5 (R5: P2.5: L2.5), red romaine 8: P. japoincum 1: L. stenocephala 1 (R8: P1: L1), red romaine 10: P. japoincum 0: L. stenocephala 0 (R10: P0: L0). All treatments were packaged in OTR (oxygen transmittance) 10,000 cc m-2·day-1·atm-1 film and stored for 27 days at 2℃/85% RH conditions. Fresh weight, carbon dioxide, oxygen, and ethylene concentrations of the baby leaf packages were examined approximately every 3 days, and visual quality, chlorophyll content, and chromaticity were examined on the 27th day of storage. The oxygen and carbon dioxide concentration in the packages were affected by the respiration rate of the crop. As the mixing ratio of lettuce, which had a low respiration rate, increased, the oxygen concentration in the packages was higher and the carbon dioxide concentration was lower. Oxygen concentration decreased significantly after 15 days, but was remained above 16%, and on the contrary, carbon dioxide concentration was kept at 1-4% until the 15th, and then gradually increased to 2-5% on the 27th day. The concentration of ethylene was maintained at 3-6 µL·L-1 until the end of storage (27th day). Visual quality score measured at the end of storage was slightly less than 3.0, which is the limit of marketability of all treatments. Although there was no significant difference, the chlorophyll content (SPAD) of red romaine and P. japoincum were most similar with an initial value in R8:P1:1 treatment, and L. stenocephala was higher value in R8:P1:L1 and R5:P2.5:L2.5 treatments at the end of storage. The leaf color (L∗, a∗, b∗, chroma) of the three crops at end of storage compared with the heat map showed the least change in the R5:P2.5:L2.5 and R8:P1:L1 treatments at the end of storage. Among them, R8:P1:L1 treatment maintained the highest chlorophyll content, the second lowest ethylene concentration, and adequate carbon dioxide concentration of 2-3%. Therefore, it is judged that the mixed ratio of red romaine 8: P. japoincum 1: L. stenocephala 1 (R8: P1: L1) is most suitable for the mixed package of baby leaf vegetables of these three crops.