• Asia Marketing Journal
• /
• v.13 no.3
• /
• pp.25-53
• /
• 2011

This study probes the effect of loyalty program on the customer retention based on the real transaction data(n=2,892) acquired from education service industry. We try to figure out the outcomes of reward program through more than 1 year-long data gathered and analyzed according to quasi-experimental design(i.e., before and after design). We adopt this kinds of research scheme in regard that previous studies measured the effect of loyalty program by dividing the customers into two group(i.e., members vs. non-members) after the firms or stores had started the program. We believe that it might not avoid the self-selection bias. The research questions of this study could be explained such as: First, most research said that the loyalty programs could increase the customer loyalty and contribute to the sustainable growth of company. But there are little confirmation that this promotional tool could be justified in terms of financial perspective. Thus, we are interested in both the retention rate and financial outcomes caused by the introduction of loyalty programs. Second, reward programs target mainly current customer. Especially CRM(customer relationship management) said that it is more profitable for company to build positive relationship with current customer instead of pursuing new customer. And it claims that reward program is excellent means to achieve this goal. For this purpose, we check in this study whether there is a interaction effect between loyalty program and customer type in retaining customer. Third, it is said that dis-satisfied customers are more likely to leave the company than satisfied customers. While, Bolton, Kannan and Bramlett(2000) claimed that reward program could contribute to minimize the effect of negative service by building emotional link with customer, it is not empirically confirmed. This point of view explained that the loyalty programs might work as exit barrier to current customer. Thus, this study tries to identify whether there is a interaction effect between loyalty program and service experience in keeping customer. To achieve this purpose, this study adopt both Kaplan-Meier survival analysis and Cox proportional hazard model. The research outcomes show that the average retention period is 179 days before introducing loyalty program but it is increased to 227 days after reward is given to the customers. Since this difference is statistically significant, it could be said that H1 is supported. In addition, the contribution margin coming from increased transaction period is bigger than the cost for administering loyalty programs. To address other research questions, we probe the interaction effect between loyalty program and other factors(i.e., customer type and service experience) affecting it. The analysis of Cox proportional hazard model said that the current customer is more likely to engage in building relationship with company compared to new customer. In addition, retention rate of satisfied customer is significantly increased in relation to dis-satisfied customer. Interestingly, the transaction period of dis-satisfied customer is notably increased after introducing loyalty programs. Thus, it could be said that H2, H3, and H4 are also supported. In summary, we found that the loyalty programs have values as a promotional tool in forming positive relationship with customer and building exit barrier.

• Korean Journal of Remote Sensing
• /
• v.31 no.6
• /
• pp.531-548
• /
• 2015

Atmospheric Motion Vector (AMV) from satellite images have shown Slow Speed Bias (SSB) in comparison with rawinsonde. The causes of SSB are originated from tracking, selection, and height assignment error, which is known to be the leading error. However, recent works have shown that height assignment error cannot be fully explained the cause of SSB. This paper attempts a new approach to examine the possibility of SSB reduction of COMS AMV by using a new target tracking algorithm. Tracking error can be caused by averaging of various wind patterns within a target and changing of cloud shape in searching process over time. To overcome this problem, Gaussian Mixture Model (GMM) has been adopted to extract the coldest cluster as target since the shape of such target is less subject to transformation. Then, an image filtering scheme is applied to weigh more on the selected coldest pixels than the other, which makes it easy to track the target. When AMV derived from our algorithm with sum of squared distance method and current COMS are compared with rawindsonde, our products show noticeable improvement over COMS products in mean wind speed by an increase of $2.7ms^{-1}$ and SSB reduction by 29%. However, the statistics regarding the bias show negative impact for mid/low level with our algorithm, and the number of vectors are reduced by 40% relative to COMS. Therefore, further study is required to improve accuracy for mid/low level winds and increase the number of AMV vectors.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.9
• /
• pp.351-360
• /
• 2018

The LWR (Locally Weighted Regression) model, which is traditionally a lazy learning model, is designed to obtain the solution of the prediction according to the input variable, the query point, and it is a kind of the regression equation in the short interval obtained as a result of the learning that gives a higher weight value closer to the query point. We study on an incremental ensemble learning approach for LWR, a form of lazy learning and memory-based learning. The proposed incremental ensemble learning method of LWR is to sequentially generate and integrate LWR models over time using a genetic algorithm to obtain a solution of a specific query point. The weaknesses of existing LWR models are that multiple LWR models can be generated based on the indicator function and data sample selection, and the quality of the predictions can also vary depending on this model. However, no research has been conducted to solve the problem of selection or combination of multiple LWR models. In this study, after generating the initial LWR model according to the indicator function and the sample data set, we iterate evolution learning process to obtain the proper indicator function and assess the LWR models applied to the other sample data sets to overcome the data set bias. We adopt Eager learning method to generate and store LWR model gradually when data is generated for all sections. In order to obtain a prediction solution at a specific point in time, an LWR model is generated based on newly generated data within a predetermined interval and then combined with existing LWR models in a section using a genetic algorithm. The proposed method shows better results than the method of selecting multiple LWR models using the simple average method. The results of this study are compared with the predicted results using multiple regression analysis by applying the real data such as the amount of traffic per hour in a specific area and hourly sales of a resting place of the highway, etc.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.3
• /
• pp.599-610
• /
• 2016

This paper reports the results of a systematic review (SR) and meta-analysis research to compare the effect of Kangaroo care, targeting mothers and premature infants. A randomized clinical trial study was performed until February 2015. The domestic literature contained the non-randomized clinical trial research without restriction according to the level of the study design. A search of the Ovid-Medline, CINAHL, PubMed and KoreaMed, the National Library of KOREA, the National Assembly Library, NDSL, KISS and RISS. Through the KMbase we searched and combined the main term ((kangaroo OR KC OR skin-to-skin) AND (care OR contact)) AND (infant OR preterm OR Low Birth Weight OR LBW), ((kangaroo OR kangaroo OR kangaroo) AND (care OR nursing care OR management OR skin contact)) was made; these were all combined with a keywords search through the selection process. They were excluded in the final 25 studies (n=3051). A methodology checklist for randomized controlled trials (RCTs) designed by SIGN (Scottish Intercollegiate Guidelines Network) was utilized to assess the risk of bias. The overall risk of bias was regarded as low. In 16 studies that were evaluated as a grade of "++", 9 studies were evaluated as a grade of "+". As a result of meta-analysis, kangaroo care regarding the effects of premature mortality, severe infection/sepsis had an insignificant effect. Hyperthermia incidence, growth and development (height and weight), mother-infant attachment, hypothermia incidence, length of hospital days, breast feeding rate, sleeping, anxiety, confidence, and gratification of mothering role were considered significant. In satisfaction of the role performance, depression and stress presented contradictory research results for individual studies showing overall significant difference. This study has some limitations due to the few RCTs comparing kangaroo care in the country. Therefore, further RCTs comparing kangaroo care should be conducted.

• Journal of Life Science
• /
• v.20 no.4
• /
• pp.481-486
• /
• 2010

The rates of synonymous and nonsynonymous nucleotide substitutions were studied for sequences of nuclear and chloroplast genes in Sorbus aucuparia. Results suggested that DNA evolution in this species had taken place, on average, at a slower rate in the chloroplast genes than in the nuclear genes: a rate variation pattern similar to those observed in eudicot plants. Within the nucleus, the synonymous substitution rates (Ks) (2.45-2.60) were two-fold higher than nonsynonymous substitution rates (Ka) (1.15-1.30). More notably, the values of Ks (1.20-1.26) were about six-fold higher than those of Ka (0.26-0.42) within the chloroplast genome. Ka/Ks ratios for nuclear and chloroplast genes of S. aucuparia had mean values of 0.178 and 0.056, respectively. A Ka/Ks ratio < 1 indicated negative (purifying) selection. The chloroplast genes had a lower effective number of codons (ENC) values (22.4-32.2) than those of nuclear genes (35.8-38.7). The analysis of the G+C content indicated that the chloroplast genes in this investigation had a higher preference for synonymous codons ending with A and T (G+C content range, 28.4-29.1%) where there was a slight bias toward codons ending with G+C (63.2-64.2%) in the nuclear genome.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.3
• /
• pp.89-97
• /
• 2012

In this paper, we propose a novel approach to noise power estimation for speech enhancement in noisy environments. The method based on IMCRA (improved minima controlled recursive averaging) which is widely used in speech enhancement utilizes a rough VAD (voice activity detection) algorithm which excludes speech components during speech periods in order to improves the performance of the noise power estimation by reducing the speech distortion caused by the conventional algorithm based on the minimum power spectrum derived from the noisy speech. However, since the VAD algorithm is not sufficient to distinguish speech from noise at non-stationary noise and low SNRs (signal-to-noise ratios), the speech distortion resulted from the minimum tracking during speech periods still remained. In the proposed method, minimum power estimate obtained by IMCRA is modified by SMT (spectral minima tracking) to reduce the speech distortion derived from the bias of the estimated minimum power. In addition, in order to effectively estimate minimum power by considering the distribution characteristic of the speech and noise spectrum, the presented method combines the minimum estimates provided by IMCRA and SMT depending on the weighting factor based on the subband. Performance of the proposed algorithm is evaluated by subjective and objective quality tests under various environments and better results compared with the conventional method are obtained.

• Asian Pacific Journal of Cancer Prevention
• /
• v.15 no.11
• /
• pp.4689-4695
• /
• 2014

Background: A great number of studies have shown that cytochrome P450 1A1 (CYP1A1) genetic polymorphisms, CYP1A1 Msp I and CYP1A1 Ile/Val, might be risk factors for digestive tract cancers, including esophageal cancer (EC), gastric cancer (GC), hepatic carcinoma (HC), as well as colorectal cancer (CC), but the results are controversial. In this study, a meta-analysis of this literature aimed to clarify associations of CYP1A1 genetic polymorphisms with digestive tract cancers susceptibility in Chinese populations. Materials and Methods: Eligible case-control studies published until December 2013 were retrieved by systematic literature searches from PubMed, Embase, CBM, CNKI and other Chinese databases by two investigators independently. The associated literature was acquired through deliberate search and selection based on established inclusion criteria. Fixed-effects or random-effects models were used to estimate odds ratios (ORs and 95%CIs). The meta-analysis was conducted using Review Manager 5.2 and Stata 12.0 softwares with stability evaluated by both stratified and sensitivity analyses. Moreover, sensitivity analysis and publication bias diagnostics confirmed the reliability and stability. Results: Eighteen case-control studies with 1,747 cases and 2,923 controls were selected for CYP1A1 MspI polymorphisms, and twenty case-control studies with 3, 790 cases and 4, 907 controls for the CYP1A1 Ile/Val polymorphisms. Correlation associations between CYP1A1 Ile/Val polymorphisms and digestive tract cancers susceptibility were observed in four genetic models in the meta-analysis (GG vs AA:OR= 2.03, 95%CI =1.52- 2.72; AG vs AA: OR=1.26, 95%CI =1.07-1.48; [GG+AG vs AA] :OR =1.42, 95%CI=1.20-1.68, [GG vs AA+AG]:OR=1.80, 95%CI =1.40-2.31). There was no association between CYP1A1 Msp I polymorphisms and digestive tract cancers risk. Subgroup analysis for tumor type showed a significant association of CYP1A1 Ile/Val genetic polymorphisms with EC in China. However, available data collected by the study failed to reveal remarkable associations of GC or HC with CYP1A1 Ile/Val genetic polymorphisms and EC, GC or CC with CYP1A1 MspI genetic polymorphisms. Conclusions: Our results indicated that CYP1A1 Ile/Val genetic polymorphisms, but not CYP1A1 Msp I polymorphisms, are associated with an increased digestive tract cancers risk in Chinese populations. Additional well-designed studies, with larger sample size, focusing on different ethnicities and cancer types are now warranted to validate this finding.

• Journal of Gastric Cancer
• /
• v.18 no.3
• /
• pp.264-273
• /
• 2018

Purpose: To investigate the current status of adjuvant chemotherapy (AC) regimens in Korea and the difference in efficacy of AC administered by surgical and medical oncologists in patients with stage II or III gastric cancers. Materials and Methods: We performed a retrospective observational study among 1,049 patients who underwent curative resection and received AC for stage II and III gastric cancers between February 2012 and December 2013 at 29 tertiary referral university hospitals in Korea. To minimize the influence of potential confounders on selection bias, propensity score matching (PSM) was used based on binary logistic regression analysis. The 3-year disease-free survival (DFS) rates were compared between patients who received AC administered by medical oncologists or surgical oncologists. Results: Between February 2012 and December 2013 in Korea, the most commonly prescribed AC by medical oncologists was tegafur/gimeracil/oteracil (S-1, 47.72%), followed by capecitabine with oxaliplatin (XELOX, 16.33%). After performing PSM, surgical oncologists (82.74%) completed AC as planned more often than medical oncologists (75.9%), with statistical significance (P=0.036). No difference in the 3-year DFS rates of stage II (P=0.567) or stage III (P=0.545) gastric cancer was found between the medical and surgical oncologist groups. Conclusions: S-1 monotherapy and XELOX are a main stay of AC, regardless of whether the prescribing physician is a medical or surgical oncologist. The better compliance with AC by surgical oncologists is a valid reason to advocate that surgical oncologists perform the treatment of AC for stage II or III gastric cancers.

• Journal of Korean Home Economics Education Association
• /
• v.23 no.3
• /
• pp.91-119
• /
• 2011

The purpose of this study was to suggest the framework reflecting the interests of students in practical problems and social issues regarding perennial problems which correspond to the characteristics and goals of the 2007 revised curriculum. This study was carried into a literature review and 406 questionnaires, filled out by the 9th grade middle school students in Seoul and Gyeonggi province, were used for analysis. The main results of this study are summarized as follows: First, six perennial problems are ascertained, Next, the middle school students were most interested in 27 items of practical problems such as mapping out their career path, self-improvement and interpersonal relations. And finally, the middle school students' important social interests are adolescence issues, job preference bias, career choice, suicide and addiction to computer, appearance and money management behavior, house ownership and conspicious consumption, and lack of time to spend with family. This study suggested the framework which corresponds to the characteristics and goals of the 2007 revised curriculum.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.5 no.4
• /
• pp.247-254
• /
• 2003

This study was conducted to develop site index equations by main species grown in Gyunggi and Chungcheong provinces using environmental factors obtained from a digital forest site map. For this, 28 environmental factors were regressed on site index by species. Four to five environmental factors by species were selected as independent variables in the best site index equations (coefficients of determination greater than 0.91). For these site index equations, three evaluation statistics, mean difference, standard deviation of difference, and standard error of difference, were applied to the data set. Site index equations by species relationships developed in this study effectively estimate forest productivity in the study area. However, the site index equation of Larix leptolepis showed a larger than expected bias between the estimated and the measured site index. The reason is not clear in this situation, but might be because of the small sample set. It will be necessary, therefore, to conduct more studies to determine the exact reason. It is also expected that the site index equations with a few environmental factors as independent variables could provide valuable information about species well suited to given site conditions. Site index equations for other species should be developed to establish a rational policy about the selection of best species for site conditions.