• The Journal of Information Systems
• /
• v.26 no.4
• /
• pp.17-37
• /
• 2017

Purpose Customer Loyalty is the most important factor of customer relationship management (CRM). Especially in retailing industry, where customers have many options of where to spend their money. Classifying loyal customers through customers' data can help retailing companies build more efficient marketing strategies and gain competitive advantages. This study aims to construct classification models of distinguishing the loyal customers within a Korean retailing company using data mining techniques with R language. Design/methodology/approach In order to classify retailing customers, we used combination of support vector machines (SVMs) and other classification algorithms of machine learning (ML) with the support of recursive feature elimination (RFE). In particular, we first clean the dataset to remove outlier and impute the missing value. Then we used a RFE framework for electing most significant predictors. Finally, we construct models with classification algorithms, tune the best parameters and compare the performances among them. Findings The results reveal that ML classification techniques can work well with CRM data in Korean retailing industry. Moreover, customer loyalty is impacted by not only unique factor such as net promoter score but also other purchase habits such as expensive goods preferring or multi-branch visiting and so on. We also prove that with retailing customer's dataset the model constructed by SVMs algorithm has given better performance than others. We expect that the models in this study can be used by other retailing companies to classify their customers, then they can focus on giving services to these potential vip group. We also hope that the results of this ML algorithm using R language could be useful to other researchers for selecting appropriate ML algorithms.

• Asian-Australasian Journal of Animal Sciences
• /
• v.15 no.12
• /
• pp.1725-1731
• /
• 2002

The distribution and activities of hydrolytic enzymes (cellulolyti, hemicellulolytic,pectinolytic and others) in the rumen compartments of Hereford bulls fed 100% alfalfa hay based diets were evaluated. The alfalfa proportion in the diet was gradually increased for two weeks. Whole rumen contents were processed into four fractions: Rumen contents including both the liquid and solid fractions were homogenized and centrifuged, and the supernatant was assayed for enzymes located in whole rumen contents (WRE); rumen contents were centrifuged and the supernatant was assayed for enzymes located in rumen fluids (RFE); feed particles in rumen contents were separated manually, washed with buffer, resuspended in an equal volume of buffer, homogenized and centrifuged and supernatant was assayed for enzymes associated with feed particles (FAE); and rumen microbial cell fraction was separated by centrifugation, suspended in an equal volume of buffer, sonicated and centrifuged, and the supernatant was assayed for enzymes bound with microbial cells (CBE). It was found that polysaccharide-degrading proteins such as $\beta$-1,4-D-endoglucanase, $\beta$-1,4-D-exoglucanase, xylanase and pectinase enzymes were located mainly with the cell bound (CBE) fraction. However, $\beta$-D-glucosidase, $\beta$-D-fucosidase, acetylesterase, and $\alpha$-L-arabinofuranosidase were located in the rumen fluids (RFE) fraction. Protease activity distributions were 37.7, 22.1 and 40.2%, and amylase activity distributions were 51.6, 18.2 and 30.2% for the RFE, FAE and CBE fractions, respectively. These results indicated that protease is located mainly in rumen fluid and with microbial cells, whereas amylase was located mainly in the rumen fluid.

• Journal of the Korean association of regional geographers
• /
• v.9 no.1
• /
• pp.1-23
• /
• 2003

The goal of this paper is to explore and compare the situations of North Korean and Chinese labor forces in the Russian Far East (RFE). First of all, the past and present pictures of North Korean and Chinese labor forces were reviewed, and then local Russinans' views about those foreign workers were analyzed in terms of political, economic, socio-psychological and public order aspects. As a result, it turned out that both North Korean and Chinese workers were regarded as useful to the RFE from economic viewpoint, but not as beneficial to local Russians in terms of maintenance of public order. According to the political and socio-psychological views of local Russians, North Korean labor forces were much more preferable to their Chinese counterparts. This paper implies that participation of South Korea in the development of RFE via North Korea workers is significant in that local Russians are very afraid of flooding Chinese workers there.

• International Journal of Computer Science & Network Security
• /
• v.23 no.5
• /
• pp.148-162
• /
• 2023

Classification systems can significantly assist the medical sector by allowing for the precise and quick diagnosis of diseases. As a result, both doctors and patients will save time. A possible way for identifying risk variables is to use machine learning algorithms. Non-surgical technologies, such as machine learning, are trustworthy and effective in categorizing healthy and heart-disease patients, and they save time and effort. The goal of this study is to create a medical intelligent decision support system based on machine learning for the diagnosis of heart disease. We have used a mixed feature creation (MFC) technique to generate new features from the UCI Cleveland Cardiology dataset. We select the most suitable features by using Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Elimination with Random Forest feature selection (RFE-RF) and the best features of both LASSO RFE-RF (BLR) techniques. Cross-validated and grid-search methods are used to optimize the parameters of the estimator used in applying these algorithms. and classifier performance assessment metrics including classification accuracy, specificity, sensitivity, precision, and F1-Score, of each classification model, along with execution time and RMSE the results are presented independently for comparison. Our proposed work finds the best potential outcome across all available prediction models and improves the system's performance, allowing physicians to diagnose heart patients more accurately.

• Proceedings of the Korean Society of Crop Science Conference
• /
• 2022.10a
• /
• pp.213-213
• /
• 2022

Pre-harvest sprouting(PHS) refers to germinating seeds in the mother plant before harvesting under low dormancy and humid climate, deteriorating grain quality, and rice yield. Rice varieties with floury endosperm(RFE) have been developed to boost domestic rice consumption by invigorating the processed rice industry, reducing milling and environmental cost. However, the PHS tolerance of RFE is relatively low in the rice varieties with transparent endosperm(RTE) since they soak moisture rapidly due to soft endosperm. In this study, Baromi2(BR2), floury endosperm, and Jomyeong1(JM1), PHS tolerance donor, were crossed to improve PHS tolerance. Major agronomic traits and PHS tolerance test of ten F₇(BR2/JM1) lines were conducted in NICS, 2022. The evaluations of PHS were carried out according to the method of RDA(2012) with slight modifications. Briefly, three panicles were treated and incubated 25℃ in a growth chamber 35 days after the heading date. Ten PHS tolerance promising lines demonstrated floury endosperm. The heading date of BR2 and JM1 was 7/27 and 8/5, respectively. The heading date of promising lines was 7/23~8/10. The PHS rate of BR2 and JM1 exhibited 56.3% and 10.7%, respectively. However, the PHS rate often promising lines demonstrated 2.4%~52.4%, 3 lines significantly lower than BR2. Further studies such as ABA contents are necessary to elucidate the mechanism of PHS tolerance in BR2/JM1. These results may contribute to developing elite RFE lines with improved PHS tolerance.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.40 no.8
• /
• pp.549-554
• /
• 2003

In this paper, we have designed and implemented by a monolithic microwave integrated circuit(MMIC) of a 5.8GHz-band low noise amplifier (LNA) composed of receiver front-end(RFE) in a on-board equipment system for dedicated short range communication. The designed LNA is provided with two active devices, matching circuits, and two drain bias circuits. Operating at a single supply of 3V and a consumption current of 18mA, The gain at center frequency 5.8GHz is 13.4dB, NF is 1.94dB, Input IP3 is -3dBm, S$_{11}$ is -18dB, and S$_{22}$ is -13.3dB. The circuit size is 1.2 $\times$ 0.7 $\textrm{mm}^2$.>.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.1 s.343
• /
• pp.79-88
• /
• 2006

In this paper, we designed and implemented ubiquitous u-Health system using RFE and ZigBee. We made a wireless protocol Kit which combines RFE Tag recognition and ZigBee data communication capability. The software is designed and developed on the TinyOS. Wireless communication technologies which hold multi-protocol stacks with RFID and result in the wireless ubiquitous world could be Bluetooth, ZigBee, 802.11x WLAN and so on. The environments that the suggested u-Health system may be used is un-manned nursing, which would be utilized in dense sensor networks such as a hospital. The the size of devices with RFID and ZigBee will be so smaller and smaller as a bracelet, a wrist watch and a ring. The combined wireless RFID-ZigBee system could be applied to applications which requires some actions corresponding to the collected (or sensed) information in WBAN(Wireless Body Area Network) and/or WPAN(Wireless Person Area Network). The proposed ubiquitous u-Health system displays some text-type alert message on LCD which is attached to the system or gives voice alert message to the adequate node users. RFE will be used as various combinations with other wireless technologies for some application-specific purposes.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.5
• /
• pp.1079-1094
• /
• 2014

In this paper, we study efficient gene selection methods by using conditional mutual information. We suggest gene selection methods using conditional mutual information based on semiparametric methods utilizing multivariate normal distribution and Edgeworth approximation. We compare our suggested methods with other methods such as mutual information filter, SVM-RFE, Cai et al. (2009)'s gene selection (MIGS-original) in SVM classification. By these experiments, we show that gene selection methods using conditional mutual information based on semiparametric methods have better performance than mutual information filter. Furthermore, we show that they take far less computing time than Cai et al. (2009)'s gene selection but have similar performance.

• Geomechanics and Engineering
• /
• v.25 no.1
• /
• pp.1-16
• /
• 2021

Machine learning models have been widely used for landslide susceptibility assessment (LSA) in recent years. The large number of inputs or conditioning factors for these models, however, can reduce the computation efficiency and increase the difficulty in collecting data. Feature selection is a good tool to address this problem by selecting the most important features among all factors to reduce the size of the input variables. However, two important questions need to be solved: (1) how do feature selection methods affect the performance of machine learning models? and (2) which feature selection method is the most suitable for a given machine learning model? This paper aims to address these two questions by comparing the predictive performance of 13 feature selection-based machine learning (FS-ML) models and 5 ordinary machine learning models on LSA. First, five commonly used machine learning models (i.e., logistic regression, support vector machine, artificial neural network, Gaussian process and random forest) and six typical feature selection methods in the literature are adopted to constitute the proposed models. Then, fifteen conditioning factors are chosen as input variables and 1,017 landslides are used as recorded data. Next, feature selection methods are used to obtain the importance of the conditioning factors to create feature subsets, based on which 13 FS-ML models are constructed. For each of the machine learning models, a best optimized FS-ML model is selected according to the area under curve value. Finally, five optimal FS-ML models are obtained and applied to the LSA of the studied area. The predictive abilities of the FS-ML models on LSA are verified and compared through the receive operating characteristic curve and statistical indicators such as sensitivity, specificity and accuracy. The results showed that different feature selection methods have different effects on the performance of LSA machine learning models. FS-ML models generally outperform the ordinary machine learning models. The best FS-ML model is the recursive feature elimination (RFE) optimized RF, and RFE is an optimal method for feature selection.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.112-112
• /
• 2020

하천에서 유해화학물질 유입 사고 발생 시 수환경 피해를 최소화하기 위해 신속한 초기 대응이 필요하다. 따라서, 본 연구에서는 수환경 화학사고 대응 시스템 구축을 위해 하천 실시간 모니터링 지점에서 관측된 유해화학물질의 농도 자료를 이용하여 발생원의 유입 지점과 유입량을 역추적하는 프레임워크를 개발하였다. 본 연구에서 제시하는 프레임워크는 첫 번째로 하천 저장대 모형(Transient Storage Zone Model; TSM)과 HEC-RAS 모형을 이용하여 다양한 유량의 수리 조건에서 화학사고 시나리오를 생성하는 단계, 두번째로 생성된 시나리오의 유입 지점과 유입량에 대한 시간-농도 곡선 (BreakThrough Curve; BTC)을 21개의 곡선특징 (BTC feature)으로 추출하는 단계, 최종적으로 재귀적 특징 선택법(Recursive Feature Elimination; RFE)을 이용하여 의사결정나무 모형, 랜덤포레스트 모형, Xgboost 모형, 선형 서포트 벡터 머신, 커널 서포트 벡터 머신 그리고 Ridge 모형에 대한 모형별 주요 특징을 학습하고 성능을 비교하여 각각 유입 위치와 유입 질량 예측에 대한 최적 모형 및 특징 조합을 제시하는 단계로 구축하였다. 또한, 현장 적용성 제고를 위해 시간-농도 곡선을 2가지 경우 (Whole BTC와 Fractured BTC)로 가정하여 기계학습 모형을 학습시켜 모의결과를 비교하였다. 제시된 프레임워크의 검증을 위해서 낙동강 지류인 감천에 적용하여 모형을 구축하고 시나리오 자료 기반 검증과 Rhodamine WT를 이용한 추적자 실험자료를 이용한 검증을 수행하였다. 기계학습 모형들의 비교 검증 결과, 각 모형은 가중항 기반과 불순도 감소량 기반 특징 중요도 산출 방식에 따라 주요 특징이 상이하게 산출되었으며, 전체 시간-농도 곡선 (WBTC)과 부분 시간-농도 곡선 (FBTC)별 최적 모형도 다르게 산출되었다. 유입 위치 정확도 및 유입 질량 예측에 대한 R²는 대부분의 모형이 90% 이상의 우수한 결과를 나타냈다.