• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.305-316
• /
• 2011

Recommender system is the system which, by using automated information filtering technology, recommends products or services to the customers who are likely to be interested in. Those systems are widely used in many different Web retailers such as Amazon.com, Netfix.com, and CDNow.com. Various recommender systems have been developed. Among them, Collaborative Filtering (CF) has been known as the most successful and commonly used approach. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. However, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting in advance whether the performance of CF recommender system is acceptable or not is practically important and needed. In this study, we propose a decision making guideline which helps decide whether CF is adoptable for a given application with certain transaction data characteristics. Several previous studies reported that sparsity, gray sheep, cold-start, coverage, and serendipity could affect the performance of CF, but the theoretical and empirical justification of such factors is lacking. Recently there are many studies paying attention to Social Network Analysis (SNA) as a method to analyze social relationships among people. SNA is a method to measure and visualize the linkage structure and status focusing on interaction among objects within communication group. CF analyzes the similarity among previous ratings or purchases of each customer, finds the relationships among the customers who have similarities, and then uses the relationships for recommendations. Thus CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. Under the assumption that SNA could facilitate an exploration of the topological properties of the network structure that are implicit in transaction data for CF recommendations, we focus on density, clustering coefficient, and centralization which are ones of the most commonly used measures to capture topological properties of the social network structure. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. We explore how these SNA measures affect the performance of CF performance and how they interact to each other. Our experiments used sales transaction data from H department store, one of the well?known department stores in Korea. Total 396 data set were sampled to construct various types of social networks. The dependant variable measuring process consists of three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used UCINET 6.0 for SNA. The experiments conducted the 3-way ANOVA which employs three SNA measures as dependant variables, and the recommendation accuracy measured by F1-measure as an independent variable. The experiments report that 1) each of three SNA measures affects the recommendation accuracy, 2) the density's effect to the performance overrides those of clustering coefficient and centralization (i.e., CF adoption is not a good decision if the density is low), and 3) however though the density is low, the performance of CF is comparatively good when the clustering coefficient is low. We expect that these experiment results help firms decide whether CF recommender system is adoptable for their business domain with certain transaction data characteristics.

• Journal of Intelligence and Information Systems
• /
• v.16 no.4
• /
• pp.159-172
• /
• 2010

The recommender system is one of the possible solutions to assist customers in finding the items they would like to purchase. To date, a variety of recommendation techniques have been developed. One of the most successful recommendation techniques is Collaborative Filtering (CF) that has been used in a number of different applications such as recommending Web pages, movies, music, articles and products. CF identifies customers whose tastes are similar to those of a given customer, and recommends items those customers have liked in the past. Numerous CF algorithms have been developed to increase the performance of recommender systems. Broadly, there are memory-based CF algorithms, model-based CF algorithms, and hybrid CF algorithms which combine CF with content-based techniques or other recommender systems. While many researchers have focused their efforts in improving CF performance, the theoretical justification of CF algorithms is lacking. That is, we do not know many things about how CF is done. Furthermore, the relative performances of CF algorithms are known to be domain and data dependent. It is very time-consuming and expensive to implement and launce a CF recommender system, and also the system unsuited for the given domain provides customers with poor quality recommendations that make them easily annoyed. Therefore, predicting the performances of CF algorithms in advance is practically important and needed. In this study, we propose an efficient approach to predict the performance of CF. Social Network Analysis (SNA) and Artificial Neural Network (ANN) are applied to develop our prediction model. CF can be modeled as a social network in which customers are nodes and purchase relationships between customers are links. SNA facilitates an exploration of the topological properties of the network structure that are implicit in data for CF recommendations. An ANN model is developed through an analysis of network topology, such as network density, inclusiveness, clustering coefficient, network centralization, and Krackhardt's efficiency. While network density, expressed as a proportion of the maximum possible number of links, captures the density of the whole network, the clustering coefficient captures the degree to which the overall network contains localized pockets of dense connectivity. Inclusiveness refers to the number of nodes which are included within the various connected parts of the social network. Centralization reflects the extent to which connections are concentrated in a small number of nodes rather than distributed equally among all nodes. Krackhardt's efficiency characterizes how dense the social network is beyond that barely needed to keep the social group even indirectly connected to one another. We use these social network measures as input variables of the ANN model. As an output variable, we use the recommendation accuracy measured by F1-measure. In order to evaluate the effectiveness of the ANN model, sales transaction data from H department store, one of the well-known department stores in Korea, was used. Total 396 experimental samples were gathered, and we used 40%, 40%, and 20% of them, for training, test, and validation, respectively. The 5-fold cross validation was also conducted to enhance the reliability of our experiments. The input variable measuring process consists of following three steps; analysis of customer similarities, construction of a social network, and analysis of social network patterns. We used Net Miner 3 and UCINET 6.0 for SNA, and Clementine 11.1 for ANN modeling. The experiments reported that the ANN model has 92.61% estimated accuracy and 0.0049 RMSE. Thus, we can know that our prediction model helps decide whether CF is useful for a given application with certain data characteristics.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.13 no.4
• /
• pp.2456-2470
• /
• 1971

Compaction of soil is very important for construction of soil structures such as highway fills, embankment of reservoir and seadike. With increasing compaction effort, the strength of soil, interor friction and Cohesion increas greatly while the reduction of permerbilityis evident. Factors which may influence compaction effort are moisture content, grain size, grain distribution and other physical properties as well as the variable method of compaction. The moisture content among these parameter is the most important thing. For making the maximum density to a given soil, the comparable optimum water content is required. If there is a slight change in water content when compared with optimum water content, the compaction ratio will decrease and the corresponding mechanical properties will change evidently. The results in this study of soil compaction with different water content are summarized as follows. 1) The maximum dry density increased and corresponding optimum moisture content decreased with increasing of coarse grain size and the compaction curve is steeper than increasing of fine grain size. 2) The maximum dry density is decreased with increasing of the optimum water content and a relationship both parameter becomes rdam-max=2.232-0.02785 $W_0$ But this relstionship will be change to $r_d=ae^{-bw}$ when comparable water content changes. 3) In case of most soils, a dry condition is better than wet condition to give a compactive effort, but the latter condition is only preferable when the liquid limit of soil exceeds 50 percent. 4) The compaction ratio of cohesive soil is greeter than cohesionless soil even the amount of coarse grain sizes are same. 5) The relationship between the maximum dry density and porosity is as rdmax=2,186-0.872e, but it changes to $r_d=ae^{be}$ when water content vary from optimum water content. 6) The void ratio is increased with increasing of optimum water content as n=15.85+1.075 w, but therelation becames $n=ae^{bw}$ if there is a variation in water content. 7) The increament of permeabilty is high when the soil is a high plasticity or coarse. 8) The coefficient of permeability of soil compacted in wet condition is lower than the soil compacted in dry condition. 9) Cohesive soil has higher permeability than cohesionless soil even the amount of coarse particles are same. 10) In generall, the soil which has high optimum water content has lower coefficient of permeability than low optimum water content. 11) The coefficient of permeability has a certain relations with density, gradation and void ratio and it increase with increasing of saturation degree.

• The Journal of Korean Academic Society of Nursing Education
• /
• v.7 no.2
• /
• pp.308-322
• /
• 2001

The purpose of this study was to investigate the relationship between climacteric symptoms and management of menopause of middle -aged women. The subjects of this study were 261 women(40 to 60 years old). Data were collected from Jun. 1 to Jul. 15, 2001 by a structured questionnaire. The instruments employed were : 1) The Climacteric Symptoms Scale developed by Aeri Song and Eun soon Chung(1998). 2) The Management of Menopause Scale developed by Aeri Song(1997). The data were analyzed by the SPSS p.c. program using t-test, ANOVA and Pearson correlation coefficient. The results of the study were as follows : 1. Mean score of climacteric symptoms was $2.18{\pm}0.39$(Maximum 4, Minimum 1). The mean scores among the categories of climacteric symptoms, in descending order, were : a) physical and physiological reactions ($2.62{\pm}0.53$), b) social and family relationships ($2.23{\pm}0.50$), c) psychiatric and psychological reactions ($2.08{\pm}0.49$), d) relationship with sexual partner($1.73{\pm}0.54$), e) genitourinary reactions ($1.72{\pm}0.55$). 2. Mean score of management of menopause was $1.79{\pm}0.45$ (Maximum 4, Minimum 1). The mean scores among the categories of management of menopause, in descending order, were : a) dietary management($2.57{\pm}0.52$), b) self control ($2.24{\pm}0.57$), c) management of exercise and physical activity($2.14{\pm}0.75$), d) management of sex life($1.71{\pm}0.47$), e) management of professional health maintenance($1.61{\pm}0.59$). 3. There were statistically significant differences in the score of middle-aged women's self reported climacteric symptoms according to : a) occupation (t=-2.79, p<0.001) b) marriage state (t=-2.29, p<0.05) c) age of menarche (F=4.66, p<0.001) d) method of Sanhujori (post natal care & treatment) (F=4.22, p<0.001) e) hormone replacement therapy (t=-3.09, p<0.05). From the above statistics, several significant findings were noted : a) There were more climacteric symptoms from those who were unemployed, those who had no partner or were divorced and those who started a menarche earlier. b) There were less climacteric symptoms reported from those on hormone replacement therapy and those who followed their parents or parents-in-law advice regarding Sanhujori (postnatal care) 4. There were statistically significant differences in the score of middle-aged women's self reported management of menopause according to : The educational background (F=7.63, p<0.001), religion (F=3.74, p<0.001), income (F=3.65, p<0.001), number of parity (F=4.87, p<0.001), method of Sanhujori(postnatal care) (F=5.73, p<0.001), period of Sanhujori (postnatal care) (F=2.81, p<0.05), hormone replacement therapy (t=3.81, p<0.001). Women with higher educational background, strong religion, higher income, large number of parity, managed their post natal care well, were on HRT, managed their menopause significantly better than the others who took part in the survey. 5. It will be noted from the above that women's degree of climacteric symptoms showed a negative correlation to the management of menopause(r=-0.2146, p<0.001). The findings shown above suggest the need to develop a variable management of menopause, in order to improve climacteric symptoms of middle-aged women. It is hoped that the above findings will stimulate more detailed research into this matter, and thereby enable guidance to be given to women going through the menopause to cope with it in a less stressful way.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.18
• /
• pp.88-123
• /
• 1975

To obtain useful fundamental informations for improving cultural practices of barley, an investigation was made on the influences of different fertilizer level and seeding rate as well as seeding date on yield and yield components and their balancing procedure using barley variety Suwon ＃ 18, and at the same time, 8 varieties including Suwon ＃ 18 were also tested to clarify the varietal responses in terms of their yield and yield components under different seeding date at Crop Experiment Station, Suwon, during the period of 1969 and 1970. The results obtained were summarized as follows; 1. Days to emergence of barley variety Suwon ＃ 18 at Suwon, took 8 to 19 days in accordance with given different seeding date (from Sept. 21 to Oct. 31). Earlier emergence was observed by early seeding and most of the seeds were emerged at 15$0^{\circ}C$ cumulated soil temperature at 5cm depth from surface under the favorable condition. 2. Degree of cold injury in different seeding date was seemed to be affected by the growth rate of seedlings and climatic condition during the wintering period. Over growth and number of leaves less than 5 to 6 on the main stem before wintering were brought in severe cold damage during the wintering period. 3. Even though the number of leaves on the main stem were variable from 11 to 16 depending upon the seeding date. this differences were occurred before wintering and less variation was observed after wintering. Particularly, differences of the number of main stem leaves from September 21 to October 11 seeding date were occurred due to the differences of number of main stem leaves before wintering. 4. Dry matter accumulation before wintering was high in early seeded plot and gradually decreased in accordance with delayed seeding date and less different in dry matter weight was observed after wintering. However, the increment rate of this dry matter was high from regrowth to heading time and became low during the ripening period. 5. Number of tillers per $\m^2$ was higher in early seeding than late one and dense planting was higher in the number of tillers than sparse planting. Number of tillers per plant was lower in number and variation in dense planting, and reverse tendency was observed in sparse planting. By increasing seedling rate in early seeding date the number of tiller per plant was remarkably decreased, but the seeding rate didn't affect the individual tillering capacity in the late seeding date. 6. Seedlings were from early planting reached maximum tillering stage earlier than those from the late planting and no remarkable changes was observed due to increased seeding rate. However. increased seeding rate tends to make it earlier the maximum tillering stage early. 7. Stage of maximum tillering was coincided with stage of 4-5 main stem leaves regardless the seeding date. 8. Number of heads per $\m^2$ was increased with increased seeding rate but considerable year variation in number of heads was observed by increased fertilizer level. Therefore, it was clear that there is no difficulties in increasing number of heads per $\m^2$ through increasing both fertilizer level and seeding rate. This type of tendency was more remarkable at optimum seeding time. In the other hand, seeding at optimum time is more important than increasing seeding rate, but increasing seeding rate was more effective in late seeding for obtaining desirable number of heads per $\m^2$. 9. Number of heads per $\m^2$ was decreased generally in all varieties tested in late seeding, but the degree of decrease by late seeding was lower in Suwon ＃ 18. Yuegi, Hangmi and Buheung compared with Suwon ＃ 4, Suwon ＃ 6, Chilbo and Yungwolyukak. 10. Highly significant positive correlations were obtained between number of head and tillers per $\m^2$ from heading date in September 21 seeding, from before-wintering in October 1 seeding and in all growth period from October 11 to October 31 seeding. However, relatively low correlation coefficient was estimated between number of heads and tillers counted around late March to early April in any seeding date. 11. Valid tiller ratio varied from 33% to 76% and highest yield was obtained when valid tiller ratio was about 50%. Therefore, variation of valid tiller ratio was greater due to seeding date differences than due to seeding rate. Early seeding decreased the valid tiller ratio and gradually increased by delaying seeding date but decreased by increasing seeding rate. Among the varieties tested Suwon ＃ 18, Hangmi, Yuegi as well as Buheung should be high valid tiller ratio not only in late seeding but also in early seeding. In contrast to this phenomena, Chilbo, Suwon ＃ 4, Suwon ＃ 6 and Yungwolyukak expressed low valid tiller ratio in general, and also exhibited the same tendency in late seeding date. 12. Number of grains per spike was increased by increasing fertilizer level and decreased by increasing seeding rate. Among the seeding date tested. October 21 (1969) and October 11 (1970) showed lowest number of grains per spike which was increased in both early seeding and late seeding date. There were no definite tendencies observed along with seeding date differences in respective varieties tested. 13. Variation of 1000 grain weight due to fertilizer level applied, seeding date and seeding rate was not so high as number of grains per spike and number of heads per $\m^2$, but exhibited high year variation. Increased seeding rate decreased the 1000 grain weight. Among the varieties tested Chilbo and Buheung expressed heavy grain weight, while Suwon ＃ 18, Hangmi and Yuegi showed comparatively light grain weight. 14. Optimum seeding date in Suwon area was around October 1 to October 11. Yield was generally increased by increasing fertilizer level. Yield decrease due to early seeding was compensated in certain extent by increased fertilizer application. 15. Yield variations due to seeding rate differences were almost negligible compare to the variations due to fertilizer level and seeding date. In either early seeding or law fertilizer level yield variation due to seeding rate was not so remarkable. Increment of fertilizer application was more effective for yield increase especially at increased seeding rate. And also increased seeding rate fairly compensated the decrease of yield in late seeding date. 16. Optimum seeding rate was considered to be around 18-26 liters per 10a at N-P-K=10.5-6-6 kg/10a fertilizer level considering yield stabilization. 17. Varietal differences in optimum seeding date was quite remarkable Suwon ＃ 6, Suwon ＃ 4. Buheung noted high yield at early seeding and Suwon ＃ 18, Yuegi and Hangmi yielded higher in seeding date of October 10. However, Buheung showed late seeding adaptability. 18. Highly significant positive correlations were observed between yield and yield components in all treatments. However, this correlation coefficient was increased positively by increased fertilizer level and decreased by increased seeding rate. Significant negative correlation coefficients were estimated between yield and number of grains per spike, since increased number of heads per m2 at the same level of fertilizer tends to decrease the number of grains per spike. Comparatively low correlation coefficients were estimated between 1000 grain weight and yield. 19. No significant relations in terms of correlation coefficients was observed between number of heads per $\m^2$ and 1000 grain weight or number of grains per head.

• Tuberculosis and Respiratory Diseases
• /
• v.41 no.1
• /
• pp.1-10
• /
• 1994

Background: Patients with mitral stenosis(MS) have been demonstrated to have a variable degree of pulmonary dysfunction and exercise impairment. The hemodynamic changes of MS can be reversed after percutaneous mitral balloon valvuloplasty(PMV), but the extent and time course of the imporvement in pulmonary function and exercise capacity are not defined. Methods: In order to investigate the early(3 weeks or less)and late(3 months or more) effects of PMV on pulmonary function and determine if the pulmonary dysfunction is reversible even in patients with moderate to severe pulmonary hypertension, we performed the spirometry, measurements of diffusing capacity and lung volumes, and incremental exercise tests in patients with MS before and after PMV. Results: In 46 patients with MS(age: $40{\pm}12$years, male to female ratio: 1:2, mitral valve area: $0.8{\pm}0.2cm^2$) there was a significant increase in FVC(P<0.0025), $FEV_1$(P<0.001), $FEF_{25-75%}$(P<0.001, $FEF_{50%}$(P<0.001), PEF(P<0.0005), MVV(P<0.005), $\dot{V}O_2$max (P<0.0001), and AT(P<0.0001) after average 10 days of PMV. Also there was a significant decrease in DLco(P<0.0001) and DL/VA(P<0.0001). At later($5{\pm}2$months) follow-up in 11 patients, there was no further improvement in any parameters of pulmonary function and exercise test. Twenty nine patients with sinus rhythm were divided into 16 patients with pulmonary arterial pressure(PAP) more than 35mmHg and/or tricuspid regurgitation grade n or more(group A) and 13 patients with PAP less than 35mmHg(group B). Group A Patients had significantly lower FVC(P<0.001), $FEV_1$(P<0.001), DLco(P<0.05), $\dot{V}O_2$ max(P<0.025) and mitral valve area(P<0.025) than group B patients. Group A patients after PMV, showed significant increase in FVC(P<0.001), maximum $O_2$ pulse(P<0.00001) and $\dot{V}O_2$ max(P<0.00025). Both group showed an increase in AT(P<0.0001, P<0.005), but group A showed greater decrease in $\dot{V}E/\dot{V}O_2$ and $\dot{V}E/\dot{V}CO_2$ both at AT(P<0.001, P<0.001) and $\dot{V}O_2$ max(P<0.0001, P<0.0001) after PMV compared with group B. Conclusion: These data suggest that patients with MS can show increased pulmonary function and exercise performance within 1 month after PMV. Patients with moderate to severe pulmonary hypertension had a significant increase in exercise performance compared with those with mild to no pulmonary hypertension and it is thought to be related to a significat decrease of ventilation for a given oxygen consumption at maximum exercise.