• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.39-54
• /
• 2013

Recent explosive increase of electronic commerce provides many advantageous purchase opportunities to customers. In this situation, customers who do not have enough knowledge about their purchases, may accept product recommendations. Product recommender systems automatically reflect user's preference and provide recommendation list to the users. Thus, product recommender system in online shopping store has been known as one of the most popular tools for one-to-one marketing. However, recommender systems which do not properly reflect user's preference cause user's disappointment and waste of time. In this study, we propose a novel recommender system which uses data mining and multi-model ensemble techniques to enhance the recommendation performance through reflecting the precise user's preference. The research data is collected from the real-world online shopping store, which deals products from famous art galleries and museums in Korea. The data initially contain 5759 transaction data, but finally remain 3167 transaction data after deletion of null data. In this study, we transform the categorical variables into dummy variables and exclude outlier data. The proposed model consists of two steps. The first step predicts customers who have high likelihood to purchase products in the online shopping store. In this step, we first use logistic regression, decision trees, and artificial neural networks to predict customers who have high likelihood to purchase products in each product group. We perform above data mining techniques using SAS E-Miner software. In this study, we partition datasets into two sets as modeling and validation sets for the logistic regression and decision trees. We also partition datasets into three sets as training, test, and validation sets for the artificial neural network model. The validation dataset is equal for the all experiments. Then we composite the results of each predictor using the multi-model ensemble techniques such as bagging and bumping. Bagging is the abbreviation of "Bootstrap Aggregation" and it composite outputs from several machine learning techniques for raising the performance and stability of prediction or classification. This technique is special form of the averaging method. Bumping is the abbreviation of "Bootstrap Umbrella of Model Parameter," and it only considers the model which has the lowest error value. The results show that bumping outperforms bagging and the other predictors except for "Poster" product group. For the "Poster" product group, artificial neural network model performs better than the other models. In the second step, we use the market basket analysis to extract association rules for co-purchased products. We can extract thirty one association rules according to values of Lift, Support, and Confidence measure. We set the minimum transaction frequency to support associations as 5%, maximum number of items in an association as 4, and minimum confidence for rule generation as 10%. This study also excludes the extracted association rules below 1 of lift value. We finally get fifteen association rules by excluding duplicate rules. Among the fifteen association rules, eleven rules contain association between products in "Office Supplies" product group, one rules include the association between "Office Supplies" and "Fashion" product groups, and other three rules contain association between "Office Supplies" and "Home Decoration" product groups. Finally, the proposed product recommender systems provides list of recommendations to the proper customers. We test the usability of the proposed system by using prototype and real-world transaction and profile data. For this end, we construct the prototype system by using the ASP, Java Script and Microsoft Access. In addition, we survey about user satisfaction for the recommended product list from the proposed system and the randomly selected product lists. The participants for the survey are 173 persons who use MSN Messenger, Daum Caf$\acute{e}$, and P2P services. We evaluate the user satisfaction using five-scale Likert measure. This study also performs "Paired Sample T-test" for the results of the survey. The results show that the proposed model outperforms the random selection model with 1% statistical significance level. It means that the users satisfied the recommended product list significantly. The results also show that the proposed system may be useful in real-world online shopping store.

• Journal of The Korean Society of Inherited Metabolic disease
• /
• v.21 no.1
• /
• pp.15-21
• /
• 2021

Purpose: Urea cycle disorder (UCD) is an inherited inborn error of metabolism, acting on each step of urea cycle that cause various phenotypes. The purpose of the study was to investigate the long-term clinical consequences in different groups of UCD to characterize it. Methods: Twenty-two patients with UCD genetically confirmed were enrolled at Pusan National University Children's hospital and reviewed clinical features, biochemical and genetic features retrospectively. Results: UCD diagnosed in the present study included ornithine transcarbamylase deficiency (OTCD) (n=10, 45.5%), argininosuccinate synthase 1 deficiency (ASSD) (n=6, 27.3%), carbamoyl-phosphate synthetase 1 deficiency (CPS1D) (n=3, 13.6%), hyperornithinemia-hyperammonemia-homocitrullinuria syndrome (HHHS) (n=2, 9.1%), and arginase-1 deficiency (ARG1D) (n=1, 4.5%). The age at the diagnosis was 32.7±66.2 months old (range 0.1 to 228.0 months). Eight (36.4%) patients with UCD displayed short stature. Neurologic sequelae were observed in eleven (50%) patients with UCD. Molecular analysis identified 37 different mutation types (14 missense, 6 nonsense, 6 deletion, 6 splicing, 3 delins, 1 insertion, and 1 duplication) including 14 novel variants. Progressive growth impairment and poor neurological outcomes were associated with plasma isoleucine and leucine concentrations, respectively. Conclusion: Although combinations of treatments such as nutritional restriction of proteins and use of alternative pathways for discarding excessive nitrogen are extensively employed, the prognosis of UCD remains unsatisfactory. Prospective clinical trials are necessary to evaluate whether supplementation with BCAAs might improve growth or neurological outcomes and decrease metabolic crisis episodes in patients with UCD.

• Journal of Preventive Medicine and Public Health
• /
• v.32 no.2
• /
• pp.123-129
• /
• 1999

Objectives: This study was performed to investigate sweets of genetic polymorphisms of glutathione S-transferase M1 (GSTM1), glutathione S-transferase M1 (GSTT1), cytochrome P450 1A1 (CYP1A1) and cytoehrome P450 2E1 (CYP2E1) on lung cancer development. Methods: Ninety-eight lung cancer patients and 98 age-sex matched non-cancer patients hospitalized in Chungbuk National University Hospital form March 1997 to August 1998, were the subjects of this case-control study. Direct interview was done and genotypes of GSTM1, GSTT1, CYP1A1 and CYP2E1 were investigated using multiplex PCR or PCR-RFLP methods with DNA extracted from venous blood. Effects of the polymorphisms of GSTM1, GSTT1, CYP1A1 and CYP2E1, lifestyle factors including smoking, and their interactions on lung rancor were statistically analyzed. Results: GSTM1 was deleted in 67.01% of the cases and 58.16% of the controls, and the odds ratio(95% CI) was 1.46(0.82-2.62). GSTT1 deletion was 58.76% for the lung cancer patients and 50.00% for the controls[OR:1.43(0.81-2.51)]. The frequencies of lle/lle, lle/Val and Val/Val of the CYP1A1 polymorphisms were 59.18-18%, 35.71%, and 5.10% for the cases, and 52.04%, 45.92%, 2.04% for the controls, respectively. Risk of lung cancer was not associated with polymorphism of CYP1A1 ($x^2trend=0.253$, p-value>0.05). The respective frequency of c1/c1 c1/c2, c2/c2 genotypes for CYP2E1 were 50.00%, 42.86%, 7.14% for the lung cancer patients, and 66.33%, 30.61%, 3.06% for the controls $(x^2trend=5.783,\;p<0.05)$. c2 allele was a significant risk factor for lung cancer. We also observed a significant association of cigarette smoking history with lung cancer risk. The odds ratio(95% Cl) of cigarette smoking was 3.03(1.58-5.81). In multiple logistic analysis including genotypes of GSTM1, GSTT1, CYP1A1 and CYP2E1, and smoking habit, only snaking habit came out to be a significant risk factor for lung cancer. Conclusion: Genetic polymorphisms of GSTM1, GSTT1, CYP1A1 and CYP2E1 are not so strongly associated with lung cancer as lifestyle factors including cigarette smoking.