• Journal of the Korean Data and Information Science Society
• /
• v.26 no.3
• /
• pp.639-652
• /
• 2015

In today's manufacturing environment, the process data can be easily measured and transferred to a computer for analysis in a real-time mode. As a result, it is possible to monitor several correlated quality variables simultaneously. Various multivariate statistical process control (MSPC) procedures have been presented to detect an out-of-control event. Although the classical MSPC procedures give the out-of-control signal, it is difficult to determine which variable has caused the signal. In order to solve this problem, data mining and machine learning techniques can be considered. In this paper, we applied the technique of decision tree learning to the MSPC, and we did simulation for MSPC procedures to monitor the bivariate normal process means. The results of simulation show that the overall performance of the MSPC procedure using decision tree learning technique is similar for several values of correlation coefficient, and the accurate classification rates for out-of-control are different depending on the values of correlation coefficient and the shift magnitude. The introduced procedure has the advantage that it provides the information about assignable causes, which can be required by practitioners.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.11
• /
• pp.5539-5543
• /
• 2012

Objective: The smoking prevalence in Malaysia is high, especially among men and adolescents. This study aimed to determine the prevalence and associated factors towards cigarette smoking among school teachers in Malaysia. Methodology: This study was a school-based cross-sectional study conducted among 495 secondary school teachers. The questionnaire used in this study consisted of 29 questions categorized into two sections: socio-demographic characteristics and smoking behaviour. Data were analyzed using the Statistical Package for the Social Sciences (SPSS) program 13.0. ANOVA; t-tests were used in univariate analysis; multiple linear regression was applied for multivariate analysis. Results: The majority of the participants were female (81.6%), in the age group ranged between 30-39 years (44%), Malay (90.1%), married (89.7%), degree holders (85.1%), with monthly income ranged between 3000-3999 Ringgit Malaysia (33.5%), from urban areas (94.7%), their specialty is social studies (33.9%) and with no family history of cancer (83.6%). The prevalence of smoking among school teachers in Malaysia was found to be 7.8%. Regarding reasons to start smoking among school teachers: the major reason was found to be relaxation (33.3%), followed by stress-relief (28.2%). Univariate analysis showed that sex, educational status, monthly income and residency were significantly associated with smoking among school teachers (p<0.001, p=0.004, p=0.031, p=0.010; respectively). Multivariate analysis showed that gender and marital status were significantly associated with smoking among school teachers (p<0.001, p=0.033; respectively). Conclusion: The prevalence of smoking among school teachers in Malaysia was found to be relatively low. Sex, marital status, educational status, monthly income and residency were significantly associated with smoking among school teachers.

• Journal of Microbiology and Biotechnology
• /
• v.23 no.2
• /
• pp.177-183
• /
• 2013

Bacterial blight, an important and potentially destructive bacterial disease in rice caused by Xanthomonas oryzae pv. oryzae (Xoo), has recently developed resistance to the available antibiotics. In this study, mass spectrometry (MS)-based metabolite profiling and multivariate analysis were employed to investigate the correlation between timedependent metabolite changes and antimicrobial activities against Xoo over the course of Phomopsis longicolla S1B4 fermentation. Metabolites were clearly differentiated based on fermentation time into phase 1 (days 4-8) and phase 2 (days 10-20) in the principal component analysis (PCA) plot. The multivariate statistical analysis showed that the metabolites contributing significantly for phases 1 and 2 were deacetylphomoxanthone B, monodeacetylphomoxanthone B, fusaristatin A, and dicerandrols A, B, and C as identified by liquid chromatography-mass spectrometry (LC-MS), and dimethylglycine, isobutyric acid, pyruvic acid, ribofuranose, galactofuranose, fructose, arabinose, hexitol, myristic acid, and propylstearic acid were identified by gas chromatography-mass spectrometry (GC-MS)-based metabolite profiling. The most significantly different secondary metabolites, especially deacetylphomoxanthone B, monodeacetylphomoxanthone B, and dicerandrol A, B and C, were positively correlated with antibacterial activity against Xoo during fermentation.

• Journal of Preventive Medicine and Public Health
• /
• v.56 no.1
• /
• pp.21-30
• /
• 2023

Objectives: To prevent the spread of coronavirus disease 2019 (COVID-19), behaviors such as mask-wearing, social distancing, decreasing mobility, and avoiding crowds have been suggested, especially in high-risk countries such as Indonesia. Unfortunately, the level of compliance with those practices has been low. This study was conducted to determine the predisposing, enabling, and reinforcing factors of COVID-19 prevention behavior in Indonesia. Methods: This cross-sectional study used a mixed-methods approach. The participants were 264 adults from 21 provinces in Indonesia recruited through convenience sampling. Data were collected using a Google Form and in-depth interviews. Statistical analysis included univariate, bivariate, and multivariate logistic regression. Furthermore, qualitative data analysis was done through content analysis and qualitative data management using Atlas.ti software. Results: Overall, 44.32% of respondents were non-compliant with recommended COVID-19 prevention behaviors. In multivariate logistic regression analysis, low-to-medium education level, poor attitude, insufficient involvement of leaders, and insufficient regulation were also associated with decreased community compliance. Based on in-depth interviews with informants, the negligence of the Indonesian government in the initial stages of the COVID-19 pandemic may have contributed to the unpreparedness of the community to face the pandemic, as people were not aware of the importance of preventive practices. Conclusions: Education level is not the only factor influencing community compliance with recommended COVID-19 prevention behaviors. Changing attitudes through health promotion to increase public awareness and encouraging voluntary community participation through active risk communication are necessary. Regulations and role leaders are also required to improve COVID-19 prevention behavior.

• Korean Journal of Remote Sensing
• /
• v.36 no.6_3
• /
• pp.1733-1741
• /
• 2020

This study analyzed the effect of meteorological factors on the concentration of PM10 (particulate matter 10) in the atmosphere and the variation of rainwater quality using multivariate statistical analysis. The concentration of PM10 in the atmosphere was continuously measured during eleven precipitation events with a custom-built PM sensor node. A total of 183 rainwater samples were analyzed for pH, EC (electrical conductivity), and water-soluble cations (Na+, Mg2+, K+, Ca2+, NH4+) and anions (Cl-, NO3-, SO42-). The data has been analyzed using two multivariate statistical techniques (principal component analysis, PCA, and Pearson correlation analysis) to identify relationships among PM10 concentrations in the atmosphere, meteorological factors, and rainwater quality factors. When the rainfall intensity was relatively strong (> 5 mm/h, rainfall type 1), the PM10 concentration in the atmosphere showed a negative correlation (r = -0.55, p < 0.05) with cumulative rainfall. The PM10 concentration increased the concentration of water-soluble ions (r = 0.25) and EC (r = 0.4), and decreased the pH (r = -0.7) of rainwater samples. However, for rainfall type 2 (< 5 mm/h), there was no negative correlation between the PM10 concentration in the atmosphere and cumulative rainfall and no statistically significant correlation between the PM10 concentration in the atmosphere and rainwater quality.

• Food Science and Biotechnology
• /
• v.17 no.1
• /
• pp.144-150
• /
• 2008

The main objective of this study was to understand the factors affecting the acceptance of fermented soybean products. Seventy-six consumers rated the acceptance and perceived intensity of 4 types of Korean and 4 types of Japanese style fermented soybean products. The consumer's food variety seeking tendency and the general attitude toward various fermented soybean products were measured. Ten descriptive analysis panelists evaluated the sensory characteristics of the 8 samples. Univariate and multivariate statistical analyses were applied to the data sets. Fermented soybean products consisting of sweet and moist sensory characteristics were preferred the most. The variety seeking tendency was not an effective predictor for understanding the acceptance of the products tasted in the experiment. K-means cluster analysis identified 3 sub-consumer segments sharing a common preference pattern for the 8 samples within each group. These 3 groups somewhat differed in the consumption frequency, acceptance, and familiarity of various fermented soybean products in general.

• Korean Journal of Child Studies
• /
• v.30 no.6
• /
• pp.489-504
• /
• 2009

This study explored differences in maternal parenting behaviors, children's emotional intelligence, and daily hassles by children's sex and types of aggression. Subjects were 200 children in 4th, 5th, and 6th grade and their mothers from four elementary schools. Instruments were the Maternal Parenting Behaviors Scale (Kim, 2006), the Emotional Intelligence Scale (Lee, 1997), the Daily Hassles Scale(Min & Yoo, 1998), and the Peer-nomination Measure (Crick, 1995; Crick & Grotpeter, 1995). Data were subjected to descriptive statistical analysis and multivariate analysis of variance. Findings revealed that the relational aggressive group had higher emotional intelligence and more daily hassles; girls had higher level of daily hassles than boys. Maternal parenting behaviors did not differ by child's sex and type of aggression.

• 한국생물공학회:학술대회논문집
• /
• 2003.04a
• /
• pp.157-160
• /
• 2003

ALA is an intermediate in the tetrapyrrole biosynthesis pathway and has extensive applications as a biodegradable herbicide and insecticide as well as medical applications including photodynamic therapy of cancers. For the development of mass production process of ALA it is necessary to on-line monitor some metabolites such as glycine, succinate, LA and ALA. In this study, medium compositions and fermentation conditions were investigated for enhancement of ALA production by recombinant E. coli. A 2-dimensional fluorescence sensor was employed to monitor the bioprocess of ALA production. The monitored data is analyzed using principal component analysis, a powerful tool for multivariate statistical analysis.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2006.05a
• /
• pp.1066-1070
• /
• 2006

Independent component analysis (ICA) is a statistical method for linearly transforming observed high-dimensional multivariate data into several statistically independent components. ICA has gained wide-spread attention in a variety of fields including spectrum application. We focus on the application of ICA for separating independent sources from a set of mixtures and estimating their fractions in a mixture. The proposed method of estimating fractions is based on the regression model subject to the non-negativity constraint on coefficients. Simulation experiments are performed to demonstrate the performance of the proposed approach.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.23 no.59
• /
• pp.69-77
• /
• 2000

To make internet shopping mall competitive, effective consumer service should be provided. The objective of this study is to analyse the consumer satisfaction for internet shopping mall. For this purpose, questionnaire survey has been used. For the statistical analysis, multivariate linear regression were utilized using the SAS program. According to the results in this study, the variables that positively affect toward consumer satisfaction are the quality of goods, the information of goods, the display method of goods, the convenience of ordering point of time and cancellation. On the contrary, the variables that negatively affect toward consumer satisfaction are the price of goods and the weakness of information security.