• Journal of Korea Multimedia Society
• /
• v.24 no.5
• /
• pp.667-675
• /
• 2021

The treatments for symptoms of Alzheimer's disease are being provided and for the early diagnosis several researches are undergoing. In this regard, by using T1-weighted images several classification techniques had been proposed to distinguish among AD, MCI, and Healthy Control (HC) patients. In this paper, we also used some traditional Machine Learning (ML) approaches in order to diagnose the AD. This paper consists of an improvised feature selection method which is used to reduce the model complexity which accounted an issue while utilizing the ML approaches. In our presented work, combination of subcortical and cortical features of 308 subjects of ADNI dataset has been used to diagnose AD using structural magnetic resonance (sMRI) images. Three classification experiments were performed: binary classification. i.e., AD vs eMCI, AD vs lMCI, and AD vs HC. Proposed Feature Selection method consist of a combination of Principal Component Analysis and Recursive Feature Elimination method that has been used to reduce the dimension size and selection of best features simultaneously. Experiment on the dataset demonstrated that SVM is best suited for the AD vs lMCI, AD vs HC, and AD vs eMCI classification with the accuracy of 95.83%, 97.83%, and 97.87% respectively.

• Journal of Environmental Health Sciences
• /
• v.48 no.5
• /
• pp.266-271
• /
• 2022

Background: The selection of distributions of input parameters is an important component in probabilistic exposure assessment. Goodness-of-fit (GOF) methods are used to determine the distribution of exposure factors. However, there are no clear guidelines for choosing an appropriate GOF method. Objectives: The outcomes of probabilistic consumer exposure assessment were compared by using five different GOF methods for the selection of input distributions: chi-squared test, Kolmogorov-Smirnov test (K-S), Anderson-Darling test (A-D), Akaike information criterion (AIC) and Bayesian information criterion (BIC). Methods: Individual exposures were estimated based on product usage factor combinations from 10,000 respondents. The distribution of individual exposure was considered as the true value of population exposures. Results: Among the five GOF methods, probabilistic exposure distributions using the A-D and K-S methods were similar to individual exposure estimations. Comparing the 95th percentiles of the probabilistic distributions and the individual estimations for 10 CPs, there were 0.73 to 1.92 times differences for the A-D method, and 0.73 to 1.60 times differences (excluding tire-shine spray) for the K-S method. Conclusions: There were significant differences in exposure assessment results among the selection of the GOF methods. Therefore, the GOF methods for probabilistic consumer exposure assessment should be carefully selected.

• Journal of Korea Trade
• /
• v.23 no.2
• /
• pp.59-75
• /
• 2019

Purpose - The International Maritime Organization (IMO) has promulgated strict regulations on emissions in the maritime shipping industry. LNG (Liquefied Natural Gas) is, therefore, recognized as the optimal fuel alternative solution. The aim of this study is to select the most suitable location for an LNG bunkering port. This is formulated as a multiple-criteria ranking problem regarding four candidate ports in South Korea: the ports of Busan, Gwangyang, Incheon, and Ulsan. Design/Methodology/approach - An analysis employing the Consistent Fuzzy Preference Relation (CFPR) methodology is carried out, and the multiple-criteria evaluation of various factors influencing the location selection, such as the average loading speed of LNG, the number of total ships, the distance of the bunkering shuttle, and the degree of safety is performed. Then, based on the combination of both the collected real data and experts' preferences, the final ranking of the four ports is formulated. Findings - The port of Busan ranks first, followed by the ports of Gwangyang and Ulsan, with the port of Incheon last on the list. Originality/value - The Korean government could proceed with a clear vision of the candidate ports' ranking in terms of the LNG bunkering terminal selection problem.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2455-2475
• /
• 2021

Patient Navigation Program (PNP) is considered as an important implementation of health care systems that can assist in patient's treatment. Due to the feasibility of PNP implementation, a systematic reuse is needed for a wide adoption of PNP computerized system. SPL is one of the promising systematic reuse approaches for creating a reusable architecture to enabled reuse in several similar applications of PNP systems which has its own variations with other applications. However, stakeholder decision making which result from the imprecise, uncertain, and subjective nature of architecture selection based on quality attributes (QA) further hinders the development of the product line architecture. Therefore, this study aims to propose a quality-driven approach using Multi-Criteria Decision Analysis (MCDA) techniques for Software Product Line Architecture (SPLA) to have an objective selection based on the QA of stakeholders in the domain of PNP. There are two steps proposed to this approach. First, a clear representation of quality is proposed by extending feature model (FM) with QA feature to determine the QA in the early phase of architecture selection. Second, MCDA techniques were applied for architecture selection based on objective preference for certain QA in the domain of PNP. The result of the proposed approach is the implementation of the PNP system with SPLA that had been selected using MCDA techniques. Evaluation for the approach is done by checking the approach's applicability in a case study and stakeholder validation. Evaluation on ease of use and usefulness of the approach with selected stakeholders have shown positive responses. The evaluation results proved that the proposed approach assisted in the implementation of PNP systems.

• Journal of Practical Engineering Education
• /
• v.9 no.2
• /
• pp.155-165
• /
• 2017

This study was conducted to explore differences of major selection regret and reasons by major selection motivation, and differences of college life, employment goal, first job satisfaction among groups by major selection motivation and regret of college graduates. For this study, '2013 Year Graduates Occupational Mobility Survey' of KEIS was examined by cross-tabulation analysis and one-way analysis of variance. The results were as follows: First, in the case of major selection by intrinsic motivation, less regrets were given than extrinsic motivation. Second, the biggest reason of regret was 'difficulty of unemployment' in case of intrinsic motivation and 'not fit in aptitude' in case of extrinsic motivation. Third, there were differences of college life, employment goal, first job satisfaction among four groups by major selection motivation and regret.

• Journal of Distribution Science
• /
• v.17 no.1
• /
• pp.73-87
• /
• 2019

Purpose - This research aims to investigate the effects that the selection of oriental medicine cosmetics and brand asset attributes have on consumers' economic, emotional and social values in order to shed light on the forms and characteristics of consumption within the globally developing oriental medicine cosmetics market, and in the end positively verify how such perceived values affect purchase intention. In addition, it proposes research outcomes by comparing the differences between national and cultural consumer purchase behavior based on the comparisons of consumer groups in South Korea and China, the major markets for oriental medicine cosmetics. Research design, data, and methodology - Based on advanced research a total of 9 hypotheses were designed and questionnaires consisting of 16 questions to identify six major variables were conducted. Research was carried out centered on Seoul, South Korea, and its surrounding metropolitan area as well as Beijing and Shanghai, China, and a total of 577 sets of significant data were collected. A comparison analysis was then conducted on the data from 285 Koreans and 292 Chinese. A regression analysis and path analysis were also carried out based on a structural equation model to suggest results. Results - Research results show brand value assets had a more crucial impact on consumers' perceived value than consumer selection of oriental medicine cosmetics, while emotional value had a bigger effect on purchase intension than social or economic values. For Chinese consumers in particular, social, economic and emotional values affected purchase intention, while emotional value was the most crucial factor for Korean consumers. Conclusions - With oriental medicine cosmetics, brand characteristics and images that helped express emotional desire proved to be more effective in marketing than the performance aspect of cosmetics, including their functions and ingredients. In the end, products that highlight individual desire and emotion should be introduced instead of those that emphasize price, functions and social characteristics in order to expand the global market of oriental medicine cosmetics.

• The Korean Journal of Community Living Science
• /
• v.28 no.3
• /
• pp.429-446
• /
• 2017

The current study aims to identify factors associated with private tutoring of college students in Korea. For this purpose, this study used the Korean Education and Employment Panel survey, which contains items regarding whether or not college students receive private tutoring as well as the monthly costs of private lessons. The current study focuses on private English lessons due to the very low response rates of other types of private tutoring. For the analysis, the 5th wave of KEEP collected in 2008 was selected, and a Heckman selection model was employed, including three categories of variables: individual, school, and parent/household factors. The results have revealed that for the selection model (receiving private English tutoring or not), having received private lessons in high school, gender, and level of satisfaction regarding the respondent's current university were significant. In terms of the outcome model (cost for private English tutoring in college), university admission type (rolling vs. regular), living with parents, school type (4-yr university vs. others), being in debt to cover private lesson fees in high school, and monthly household income had significant effects. This article also discusses the results and implications for future research and policy makers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.9
• /
• pp.4658-4679
• /
• 2017

Android is now the most popular smartphone platform and remains rapid growth. There are huge number of sensitive privacy information stored in Android devices. Kinds of methods have been proposed to detect Android malicious applications and protect the privacy information. In this work, we focus on extracting the fine-grained features to maximize the information of Android malware detection, and selecting the least joint features to minimize the number of features. Firstly, permissions and APIs, not only from Android permissions and SDK APIs but also from the developer-defined permissions and third-party library APIs, are extracted as features from the decompiled source codes. Secondly, feature selection methods, including information gain (IG), regularization and particle swarm optimization (PSO) algorithms, are used to analyze and utilize the correlation between the features to eliminate the redundant data, reduce the feature dimension and mine the useful joint features. Furthermore, regularization and PSO are integrated to create a new joint feature mining method. Experiment results show that the joint feature mining method can utilize the advantages of regularization and PSO, and ensure good performance and efficiency for Android malware detection.

• Journal of Korean Home Economics Education Association
• /
• v.12 no.3
• /
• pp.157-170
• /
• 2000

A Study of Factors Affecting on High School Students’Choice of ’The Science of Home-Economics’Course in the 7th National Curriculum The purpose of this study is to explore what kind of factors make high school students decide to select ‘The Science of Home Economics’as one of the course among various in-depth elective courses in high school curriculum. an empirical survey was conducted by administering a structured survey questionnaire to 463 male and female students who attend in a college-bound high school in Taegu. The major findings are as follows: 1) There were significant differences between the choice group of ‘The Science of Home Economics’and non-choice group of ‘The Science of Home Economics’in learning motivation to 5 units of ‘The Science of Home Economics’student’s perception of the traditional role and progressive role of Home Economics education impression of Home Economics teachers, mother’s academic career, academic achievement in general and mother’s request for selection of ‘The Science of Home Economics’as an elective course. 2) Significant variables which influenced students’selection of ‘The Science of Home Economics’relatively were, in descending order, student’s perception of the progressive role of home economics education. impression of Home Economics teachers. coeducational schooling. student’s learning motivation to the ‘food’unit. student’s attitude for sex-role, academic achievement in general and mother’s request for selection of ‘The Science of Home Economics’as an elective course.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.11
• /
• pp.5282-5300
• /
• 2017

Multi-hop cellular networks (MCNs) reduce the transmit power and improve the system performance. Recently, several research studies have been conducted on MCNs. The mobile relay selection scheme is a rising issue in the design of MCNs that achieves these advantages. The conventional opportunistic relaying (OR) is performed on the single factor for maximum signal-to-interference-plus-noise ratio (SINR). In this paper, a comprehensive OR scheme based on Bi-Target is proposed to improve the system throughput and reduce the relay handover by constraining the amount of required bandwidth and SINR. Moreover, the proposed algorithm captures the variability and the mobility that makes it more suitable for dynamic real scenarios. Numerical and simulation results show the superiority of the proposed algorithm in both enhancing the overall performance and reducing the handover.