• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.3
• /
• pp.197-210
• /
• 2003

The non-float midwater pair trawl was effective in the mouth opening and control of the working depth in midwater and bottom. In contrast, we confirmed that it was difficult to keep the net at surface above 30 m of the depth by means of the full scale experiment in the field and the model test in the circulation water channel. To solve this problem, the kites were attached to the head rope of the non-float midwater pair trawl. In this study, four kinds of the model experiments were carried out with the purpose of applying the kite to the korean midwater pair trawl. The results obtained can be summarized as follows: 1. The working depth of the non-float midwater pair trawl with the kite was shallower than that of the proto type and non-float type. The working depth of the kite type was approximately 20m with 2 kites and about 5m with 4 kites under 4.0 knot. The working depth was almost constant but the depth of the head rope sank approximately 15m and 10m according to the increase in the front weight and the wing-end weight, respectively. The changing aspect of the working depth was constant, but the depth of the head rope sank approximately 22m according to the increase in the lower warp length (dL). 2. The hydrodynamic resistance of the kite type was almost increased in a linear form in accordance with the flow speed increase from 2.0 to 5.0 knot. The increasing grate of the hydrodynamic resistance tended to increase in accordance with the increase in flow speed. The hydrodynamic resistance of the kite type was larger approximately 5～10 ton larger than that of the non-float type and the proto type. The hydrodynamic resistance of the kite type increased approximately 3ton with the changing of the front weight from 1.40 to 3.50 ton and approximately 4 ton with the changing of the wing-end weight from 0 to 1.11 ton and approximately 5.5 ton with the changing lower warp length (dL) from 0 to 40 m, respectively. 3. The net height of the kite type was increased approximately 10 m with the change in the kite area from $2,270mm^2$ to 4,540 $\textrm{mm}^2$. The net height of the kite type was aproximately 50 m and 30 m larger than that of the proto type and the non-float type, respectively. The changed aspect of the net width was approximately 5m with the variation of the flow speed from 2.0 to 5.0 knot. 4. The filtering volume of the kite type was larger than that of the proto type and the non-float type by 28%, 34% at 2.0 knot of the flow speed and 42%, 41% at 3.0 knot, and 62%, 45% at 4.0 knot, and 74%, 54% at 5.0knot, respectively. The optimal towing speed was approximately 3.0 knot for the proto type and was over 4.0 knot for the non-float type, and the optimal towing speed reached 5.0 knot for the kite type. 5. The opening efficiency of the kite type was approximately 50% and 25% larger than that of the proto type and the non-float type, respectively.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.39 no.3
• /
• pp.189-196
• /
• 2003

In this study, the vertical opening of the non-float midwater pair trawl net was maintained by controlling the length of upper warp. This was because the head rope was able to be kept linearly and the working depth was not nearly as changed with the variation of flow speed as former experiments in this series of studies have demonstrated. We confirmed that the opening efficiency of the non-float midwater pair trawl net was able to be developed according to the increase in front weight and wing-end weight. In this study, we described the opening efficiency of the non-float midwater pair trawl net according to the variation of front weight and wing-end weight obtained by model experiment in circulation water channel. We compared the opening efficiency of the proto type with that of the non-float type. The results obtained can be summarized as follows：1. The hydrodynamic resistance was almost increased linearly in proportion to the flow speed and was increased in accordance with the increase in front weight and wing-end weight. The increasing rate of hydrodynamic resistance was displayed as an increasing tendency in accordance with the increase in flow speed. 2. The net height of the non-float type was almost decreased linearly in accordance with the increase in flow speed. As the reduced rate of the net height of the non-float type was smaller than that of the net height of the proto type against increase of flow speed, the net height of the non-float type was bigger than that of the proto type over 4.0 knot. The net width of the non-float type was about 10 m bigger than that of the proto type and the change rate of net width varied by no more than 2 m according to the variation of the front weight and wing-end weight. 3. The mouth area of the non-float type was maximized at 1.75 ton of the front weight and 1.11 ton of the wing-end weight, and was smaller than that of the proto type at 2.0∼3.0 knot, but was bigger than that of the proto type at 4.0∼5.0 knot. 4. The filtering volume was maximized at 3.0 knot in the proto type and at 4.0 knot in the non-float type. The optimal front weight was 1.40 ton.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.29 no.3
• /
• pp.171-178
• /
• 2009

The study was conducted to clarify the mixed seeding rate of whole crop barley with hood type and forage pea for using of forage crops and to compare the forage yield and quality. At a mixed seeding rate between the whole crop barley (WCB) and forage pea, The heading date and plant height of WCB were not a difference according to mixed seeding rate of forage pea. The tillers of the WCB were a decrease and plant of the forage pea were a increase according to increased seeding rate of forage pea. The lodging index of the WCB was a appearance with distribution of $0{\sim}3$, The lodging index of WCB with a 20kg/10a seeding rate of a only WCB without seeding of the forage pea was 3. The overwintering rate of forage pea was a appearance more than 90% at all treatment. The plant height of forage pea was a increase according to increased seeding rate of forage pea at 14 kg/10a and 20 kg/10a plots of WCB. At a mixed seeding between the WCB and forage pea, The fresh weight was a increase according to increased seeding rate of forage pea and was a appearance more than 3,000 kg at all treatment plot. But the dry matter weight was decrease according to increased seeding rates of forage pea. The dry matter weight of 20 kg/10a seeding rate of a only WCB without seeding of the forage pea showed the most amount with 1,266 kg. The crude protein (CP) content was a tendency to increase according to increased seeding rates of forage pea. But, the relative feed value (RFV) was a tendency to decrease according to increased seeding rate of forage pea. The highest RFV was 183.8 at 14 kg/10a seeding rate of a only WCB without seeding of the forage pea. The acid detergent fiber (ADF) and neutral detergent fiber (NDF) were a increase according to increased seeding rate of forage pea at 14 kg/10a and 20 kg/10a plots of WCB. The highest content of ADF and NDF were 23.9% and 46.3% at mixed seeding rate of 20 kg/10a of WCB with 10 kg/10a of forage pea, respectively. The highest sum of standardized score by fresh weight, dry matter weight, CP, ADF, NDF and RFV was 2.309 at mixed seeding rate of 20 kg/10a of WCB with 7.5 kg/10a of forage pea. The optimum mixed seeding rate was a considered judgment in the order of mixed seeding rate of 20 kg/10a of WCB with 7.5 kg/10a of forage pea, mixed seeding rate of 20 kg/10a of WCB with 5.0 kg/10a of forage pea.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.27 no.1
• /
• pp.9-20
• /
• 2007

This experiment was conducted to investigate effects of application of diluted and undiluted cattle slurry with water on seasonal and annual dry matter yields and feed values of tall fescue in the uncultivated rice paddy and it was compared with chemical fertilizer in order to determine optimal application season and dilution level of cattle slurry. When diluted or undiluted cattle slurry with water was applied to uncultivated rice paddy, annual dry matter yields showed 11.31 to 14.81 ton DM/ha (average 13.13 ton DM/ha) for diluted and 10.57 to 12.51 ton DM/ha (average 11.50 ton DM/ha) for undiluted cattle slurries, these had a higher dry matter yield than those of no fertilizer (9.21 ton DM/ha). Furthermore, separate application of early spring and summer (SA plots), separate application of early and late spring, and summer (SUA plots) fur undiluted cattle slurries, and whole application of spring (DS plots), separate application of early spring and summer (DSA plots), separate application of early and late spring, and summer (DSUA plots) for diluted cattle slurries were significantly (P<0.05) higher for annual dry matter yield than no fertilizer plots. Plots applied chemical fertilizer with nitrogen (N), phorphorus (P) and potassium (K) had 15.38 ton DM/ha annually, resulted in significantly (P<0.05) higher DM yield than chemical fertilizer containing P and K, and no fertilizer plots. Moreover, average annual DM yield for the chemical fertilizer with P and K was lower than that of cattle slurry applications. The efinciency of DM production for mineral nitrogen of chemical fertilizers was annually average 31.3 kg DM/kg N. In terms of cutting time of tall fescue, it was lowered in the order of 2nd growth followed by 1st and 3rd growth. However, efficiencies of annual DM production of nitrogen for diluted and undiluted cattle slurries were 26.1 and 15.3 kg DM/kg N, respectively, especially, highest in 2nd growth. While, efficiencies of DM production for cattle slurry versus for mineral nitrogen were 48.9 (undiluted) and 83.4% (diluted), respectively. For annual crude protein (CP) contents of tall fescue, aqueous cattle slurry applications showed 9,9 to 11.6%, which were significantly (P<0.05) higher than no fertilization (9.5%) and chemical fertilizer (9.0 to 9.8%), but annual average NDF and ADF contents were lowest in no fertilization. On the contrary, relative feed value (RFV) and total digestible nutrients (TDN) of no fertilizer plots were significantly (P<0.05) higher than the other plots. The application of cattle slurry and their dilution significantly increased yields of crude protein and total digestible nutrients compared with no and/or P and K fertilizers (P<0.05). These trends were much conspicuous in water-diluted cattle slurries applied in the early and late spring and summer, separately (DSUA plots).

• Asian Journal of Turfgrass Science
• /
• v.17 no.4
• /
• pp.129-146
• /
• 2003

Research was initiated to compare establishment vigor, uniformity, rooting potential and turf quality in sods of cool-season grasses (CSG). Several turfgrasses grown under pure sand soil were tested. Establishment vigor, uniformity, rooting potential and turf quality were evaluated in the study. Turfgrass entries were comprised of three blends from Kentucky bluegrass (KB, Poa pratensis L.), perennial ryegrass (PR, Lolium perenne L.), and tall fescue (TF, Festuca arundinacea Schreb.), respectively and three mixtures among them. Differences by treatments were significantly observed in establishment vigor, uniformity, rooting potential and turf quality. Early establishment vigor was mainly influenced by germination speed, being fastest with PR, intermediate with TF and slowest with KB. In a late stage of growth, however, it was affected more by growth habit, resulting in highest with KB and slowest with TF. There were considerable variations in sod uniformity among turfgrasses. Best uniformity among monostand sods was associated with KB, while poorest one with TF. PR sod produced intermediate uniformity between KB and TF. The uniformity of polystand sods of CSG mixtures was inferior to that of monostands of KB, PR and TF, due to characteristics of mixtures comprised of a variety of color, density, texture and growth habit. The greatest potential of sod rooting was found with PR and the poorest with KB. Intermediate potential between PR and KB was associated with TF. In CSG mixtures, it was variable, depending on turfgrass mixing rates. Generally, the higher the PR in mixtures, the greater the sod rooting potential. At the time of sod harvest, however, turfgrass quality of KB was superior to that of PR. because of its characteristics of uniform surface, high density and good mowing quality. These results suggest that a careful expertise based on turf quality as well as sod characteristics like establishment vigor, uniformity and rooting potential be strongly required for the success of golf course or athletic field in establishment.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.1-23
• /
• 2018

From the 21st century, various high-quality services have come up with the growth of the internet or 'Information and Communication Technologies'. Especially, the scale of E-commerce industry in which Amazon and E-bay are standing out is exploding in a large way. As E-commerce grows, Customers could get what they want to buy easily while comparing various products because more products have been registered at online shopping malls. However, a problem has arisen with the growth of E-commerce. As too many products have been registered, it has become difficult for customers to search what they really need in the flood of products. When customers search for desired products with a generalized keyword, too many products have come out as a result. On the contrary, few products have been searched if customers type in details of products because concrete product-attributes have been registered rarely. In this situation, recognizing texts in images automatically with a machine can be a solution. Because bulk of product details are written in catalogs as image format, most of product information are not searched with text inputs in the current text-based searching system. It means if information in images can be converted to text format, customers can search products with product-details, which make them shop more conveniently. There are various existing OCR(Optical Character Recognition) programs which can recognize texts in images. But existing OCR programs are hard to be applied to catalog because they have problems in recognizing texts in certain circumstances, like texts are not big enough or fonts are not consistent. Therefore, this research suggests the way to recognize keywords in catalog with the Deep Learning algorithm which is state of the art in image-recognition area from 2010s. Single Shot Multibox Detector(SSD), which is a credited model for object-detection performance, can be used with structures re-designed to take into account the difference of text from object. But there is an issue that SSD model needs a lot of labeled-train data to be trained, because of the characteristic of deep learning algorithms, that it should be trained by supervised-learning. To collect data, we can try labelling location and classification information to texts in catalog manually. But if data are collected manually, many problems would come up. Some keywords would be missed because human can make mistakes while labelling train data. And it becomes too time-consuming to collect train data considering the scale of data needed or costly if a lot of workers are hired to shorten the time. Furthermore, if some specific keywords are needed to be trained, searching images that have the words would be difficult, as well. To solve the data issue, this research developed a program which create train data automatically. This program can make images which have various keywords and pictures like catalog and save location-information of keywords at the same time. With this program, not only data can be collected efficiently, but also the performance of SSD model becomes better. The SSD model recorded 81.99% of recognition rate with 20,000 data created by the program. Moreover, this research had an efficiency test of SSD model according to data differences to analyze what feature of data exert influence upon the performance of recognizing texts in images. As a result, it is figured out that the number of labeled keywords, the addition of overlapped keyword label, the existence of keywords that is not labeled, the spaces among keywords and the differences of background images are related to the performance of SSD model. This test can lead performance improvement of SSD model or other text-recognizing machine based on deep learning algorithm with high-quality data. SSD model which is re-designed to recognize texts in images and the program developed for creating train data are expected to contribute to improvement of searching system in E-commerce. Suppliers can put less time to register keywords for products and customers can search products with product-details which is written on the catalog.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.135-149
• /
• 2020

Artificial intelligences are changing world. Financial market is also not an exception. Robo-Advisor is actively being developed, making up the weakness of traditional asset allocation methods and replacing the parts that are difficult for the traditional methods. It makes automated investment decisions with artificial intelligence algorithms and is used with various asset allocation models such as mean-variance model, Black-Litterman model and risk parity model. Risk parity model is a typical risk-based asset allocation model which is focused on the volatility of assets. It avoids investment risk structurally. So it has stability in the management of large size fund and it has been widely used in financial field. XGBoost model is a parallel tree-boosting method. It is an optimized gradient boosting model designed to be highly efficient and flexible. It not only makes billions of examples in limited memory environments but is also very fast to learn compared to traditional boosting methods. It is frequently used in various fields of data analysis and has a lot of advantages. So in this study, we propose a new asset allocation model that combines risk parity model and XGBoost machine learning model. This model uses XGBoost to predict the risk of assets and applies the predictive risk to the process of covariance estimation. There are estimated errors between the estimation period and the actual investment period because the optimized asset allocation model estimates the proportion of investments based on historical data. these estimated errors adversely affect the optimized portfolio performance. This study aims to improve the stability and portfolio performance of the model by predicting the volatility of the next investment period and reducing estimated errors of optimized asset allocation model. As a result, it narrows the gap between theory and practice and proposes a more advanced asset allocation model. In this study, we used the Korean stock market price data for a total of 17 years from 2003 to 2019 for the empirical test of the suggested model. The data sets are specifically composed of energy, finance, IT, industrial, material, telecommunication, utility, consumer, health care and staple sectors. We accumulated the value of prediction using moving-window method by 1,000 in-sample and 20 out-of-sample, so we produced a total of 154 rebalancing back-testing results. We analyzed portfolio performance in terms of cumulative rate of return and got a lot of sample data because of long period results. Comparing with traditional risk parity model, this experiment recorded improvements in both cumulative yield and reduction of estimated errors. The total cumulative return is 45.748%, about 5% higher than that of risk parity model and also the estimated errors are reduced in 9 out of 10 industry sectors. The reduction of estimated errors increases stability of the model and makes it easy to apply in practical investment. The results of the experiment showed improvement of portfolio performance by reducing the estimated errors of the optimized asset allocation model. Many financial models and asset allocation models are limited in practical investment because of the most fundamental question of whether the past characteristics of assets will continue into the future in the changing financial market. However, this study not only takes advantage of traditional asset allocation models, but also supplements the limitations of traditional methods and increases stability by predicting the risks of assets with the latest algorithm. There are various studies on parametric estimation methods to reduce the estimated errors in the portfolio optimization. We also suggested a new method to reduce estimated errors in optimized asset allocation model using machine learning. So this study is meaningful in that it proposes an advanced artificial intelligence asset allocation model for the fast-developing financial markets.

• Journal of Intelligence and Information Systems
• /
• v.26 no.1
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.

• Journal of Chest Surgery
• /
• v.32 no.2
• /
• pp.97-107
• /
• 1999

Background: This study was designed to develop a Korean version of the heparin-coated vascular bypass shunt by using a physical dispersing technique. The safety and effectiveness of the thrombo-resistant shunt were tested in experimental animals. Material and Method: A bypass shunt model was constructed on the descending thoracic aorta of 21 adult mongrel dogs(17.5-25 kg). The animals were divided into groups of no-treatment(CONTROL group; n=3), no-treatment with systemic heparinization(HEPARIN group; n=6), Gott heparin shunt (GOTT group; n=6), or Korean heparin shunt(KIST group; n=6). Parameters observed were complete blood cell counts, coagulation profiles, kidney and liver function(BUN/Cr and AST/ ALT), and surface scanning electron microscope(SSEM) findings. Blood was sampled from the aortic blood distal to the shunt and was compared before the bypass and at 2 hours after the bypass. Result: There were no differences between the groups before the bypass. At bypass 2 hours, platelet level increased in the HEPARIN and GOTT groups(p<0.05), but there were no differences between the groups. Changes in other blood cell counts were insignificant between the groups. Activated clotting time, activated partial thromboplastin time, and thrombin time were prolonged in the HEPARIN group(p<0.05) and differences between the groups were significant(p<0.005). Prothrombin time increased in the GOTT group(p<0.05) without having any differences between the groups. Changes in fibrinogen level were insignificant between the groups. Antithrombin III levels were increased in the HEPARIN and KIST groups(p<0.05), and the inter-group differences were also significant(p<0.05). Protein C level decreased in the HEPARIN group(p<0.05) without having any differences between the groups. BUN levels increased in all groups, especially in the HEPARIN and KIST groups(p<0.05), but there were no differences between the groups. Changes of Cr, AST, and ALT levels were insignificant between the groups. SSEM findings revealed severe aggregation of platelets and other cellular elements in the CONTROL group, and the HEPARIN group showed more adherence of the cellular elements than the GOTT or KIST group. Conclusion: Above results show that the heparin-coated bypass shunts(either GOTT or KIST) can suppress thrombus formation on the surface without inducing bleeding tendencies, while systemic heparinization(HEPARIN) may not be able to block activation of the coagulation system on the surface in contact with foreign materials but increases the bleeding tendencies. We also conclude that the thrombo-resistant effects of the Korean version of heparin shunt(KIST) are similar to those of the commercialized heparin shunt(GOTT).

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.85-109
• /
• 2018

Recommender system recommends the items expected to be purchased by a customer in the future according to his or her previous purchase behaviors. It has been served as a tool for realizing one-to-one personalization for an e-commerce service company. Traditional recommender systems, especially the recommender systems based on collaborative filtering (CF), which is the most popular recommendation algorithm in both academy and industry, are designed to generate the items list for recommendation by using 'overall rating' - a single criterion. However, it has critical limitations in understanding the customers' preferences in detail. Recently, to mitigate these limitations, some leading e-commerce companies have begun to get feedback from their customers in a form of 'multicritera ratings'. Multicriteria ratings enable the companies to understand their customers' preferences from the multidimensional viewpoints. Moreover, it is easy to handle and analyze the multidimensional ratings because they are quantitative. But, the recommendation using multicritera ratings also has limitation that it may omit detail information on a user's preference because it only considers three-to-five predetermined criteria in most cases. Under this background, this study proposes a novel hybrid recommendation system, which selectively uses the results from 'traditional CF' and 'CF using multicriteria ratings'. Our proposed system is based on the premise that some people have holistic preference scheme, whereas others have composite preference scheme. Thus, our system is designed to use traditional CF using overall rating for the users with holistic preference, and to use CF using multicriteria ratings for the users with composite preference. To validate the usefulness of the proposed system, we applied it to a real-world dataset regarding the recommendation for POI (point-of-interests). Providing personalized POI recommendation is getting more attentions as the popularity of the location-based services such as Yelp and Foursquare increases. The dataset was collected from university students via a Web-based online survey system. Using the survey system, we collected the overall ratings as well as the ratings for each criterion for 48 POIs that are located near K university in Seoul, South Korea. The criteria include 'food or taste', 'price' and 'service or mood'. As a result, we obtain 2,878 valid ratings from 112 users. Among 48 items, 38 items (80%) are used as training dataset, and the remaining 10 items (20%) are used as validation dataset. To examine the effectiveness of the proposed system (i.e. hybrid selective model), we compared its performance to the performances of two comparison models - the traditional CF and the CF with multicriteria ratings. The performances of recommender systems were evaluated by using two metrics - average MAE(mean absolute error) and precision-in-top-N. Precision-in-top-N represents the percentage of truly high overall ratings among those that the model predicted would be the N most relevant items for each user. The experimental system was developed using Microsoft Visual Basic for Applications (VBA). The experimental results showed that our proposed system (avg. MAE = 0.584) outperformed traditional CF (avg. MAE = 0.591) as well as multicriteria CF (avg. AVE = 0.608). We also found that multicriteria CF showed worse performance compared to traditional CF in our data set, which is contradictory to the results in the most previous studies. This result supports the premise of our study that people have two different types of preference schemes - holistic and composite. Besides MAE, the proposed system outperformed all the comparison models in precision-in-top-3, precision-in-top-5, and precision-in-top-7. The results from the paired samples t-test presented that our proposed system outperformed traditional CF with 10% statistical significance level, and multicriteria CF with 1% statistical significance level from the perspective of average MAE. The proposed system sheds light on how to understand and utilize user's preference schemes in recommender systems domain.