• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.2
• /
• pp.89-102
• /
• 2018

With the development of mobile technology, asset management on the Internet have also developed a lot. Drawing on Technology Acceptance Model, this study examines YUEBAO deployment to model consumers' purchase intention to use financial products offered online. In this study, we hypothesized that the characteristics of online asset management product will affect the purchase intention through perceived usefulness and conduct empirical analysis on Chinese consumers. In the study model, the independent variables were considered to include individual involvement, experience, product protection, corporate credibility, convenience, mobility, and familiarity. In addition, the parameters constitute the usefulness, and the dependent variable is the purchase. The results are as follows. First, YUEBAO's complementarity, corporate credibility, convenience, and familiarity have a significant influence on YUEBAO's usefulness. Second, The YUEBAO's usefulness has a noticeable effect on the purchase intention. To perceive the high usefulness, the practicality strategy of enhancing the protection property, corporate reliability, convenience and familiarity of the online asset management product is needed. The study of consumer purchase behavior and consumer purchase intention of online wealth management products is very valuable for academic and practical work.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.121-139
• /
• 2014

Predicting corporate failure has been an important topic in accounting and finance. The costs associated with bankruptcy are high, so the accuracy of bankruptcy prediction is greatly important for financial institutions. Lots of researchers have dealt with the topic associated with bankruptcy prediction in the past three decades. The current research attempts to use ensemble models for improving the performance of bankruptcy prediction. Ensemble classification is to combine individually trained classifiers in order to gain more accurate prediction than individual models. Ensemble techniques are shown to be very useful for improving the generalization ability of the classifier. Bagging is the most commonly used methods for constructing ensemble classifiers. In bagging, the different training data subsets are randomly drawn with replacement from the original training dataset. Base classifiers are trained on the different bootstrap samples. Instance selection is to select critical instances while deleting and removing irrelevant and harmful instances from the original set. Instance selection and bagging are quite well known in data mining. However, few studies have dealt with the integration of instance selection and bagging. This study proposes an improved bagging ensemble based on instance selection using genetic algorithms (GA) for improving the performance of SVM. GA is an efficient optimization procedure based on the theory of natural selection and evolution. GA uses the idea of survival of the fittest by progressively accepting better solutions to the problems. GA searches by maintaining a population of solutions from which better solutions are created rather than making incremental changes to a single solution to the problem. The initial solution population is generated randomly and evolves into the next generation by genetic operators such as selection, crossover and mutation. The solutions coded by strings are evaluated by the fitness function. The proposed model consists of two phases: GA based Instance Selection and Instance based Bagging. In the first phase, GA is used to select optimal instance subset that is used as input data of bagging model. In this study, the chromosome is encoded as a form of binary string for the instance subset. In this phase, the population size was set to 100 while maximum number of generations was set to 150. We set the crossover rate and mutation rate to 0.7 and 0.1 respectively. We used the prediction accuracy of model as the fitness function of GA. SVM model is trained on training data set using the selected instance subset. The prediction accuracy of SVM model over test data set is used as fitness value in order to avoid overfitting. In the second phase, we used the optimal instance subset selected in the first phase as input data of bagging model. We used SVM model as base classifier for bagging ensemble. The majority voting scheme was used as a combining method in this study. This study applies the proposed model to the bankruptcy prediction problem using a real data set from Korean companies. The research data used in this study contains 1832 externally non-audited firms which filed for bankruptcy (916 cases) and non-bankruptcy (916 cases). Financial ratios categorized as stability, profitability, growth, activity and cash flow were investigated through literature review and basic statistical methods and we selected 8 financial ratios as the final input variables. We separated the whole data into three subsets as training, test and validation data set. In this study, we compared the proposed model with several comparative models including the simple individual SVM model, the simple bagging model and the instance selection based SVM model. The McNemar tests were used to examine whether the proposed model significantly outperforms the other models. The experimental results show that the proposed model outperforms the other models.

• Journal of the Korea Concrete Institute
• /
• v.14 no.5
• /
• pp.782-788
• /
• 2002

Several non-destructive test methods have been developed to estimate compressive strength of concrete in other countries. However, their applications are limited in domestic concrete due to their inaccuracies. The purpose of this study is to propose an aging coefficient of compressive strength of structural concrete in rebound number method and ultrasonic pulse velocity method for domestic concrete. The test variables include type of aggregate, curing condition, and compressive strength. Two approaches are used to estimate aging coefficient. One is evaluated by uniform linear regression equation for all ages and shows uniform strength reduction coefficient regardless of material properties and the other is evaluated by individual regression equation for each ages and shows nonuniform strength reduction and rebound increasing coefficients which decrease with increasing of rebound number and compressive strength. The latter result which can include the effect of rebound number and compressive strength is more resonable than the former.

• Journal of Digital Convergence
• /
• v.12 no.2
• /
• pp.577-586
• /
• 2014

As SNS has increased its influence on the society as a whole, companies also have started to consider how to take advantage of the new service paying specific attention to its characteristics of immediacy, sharability and interactivity. This study aims to circumstantiate the relationship between a task support tool of SNS and task-media fit, user characteristics and performance by focusing on its usage in work field. To address this issue, a Task-Technology Fit model is used to propose a research model considering the characteristics of SNS as a social element, information technology as well as its user characteristics. The outcome shows that job characteristics, virtual competence and media characteristics have a significant influence on task-media fit, whereas virtual competence and SNS characteristics variables have a significant influence on SNS usage. Besides, task-media fit has a significant influence on SNS usage and work performance while SNS usage has a significant influence on work performance. The study suggests that strategic use of SNS helps improve work performance and these individual characteristics should be considered in planning of SNS utilizing strategy.

• 대한공업교육학회지
• /
• v.35 no.2
• /
• pp.124-139
• /
• 2010

This study has its purpose of researching on the relevant variables which affect the attitude toward engineering science and brain dominance for the department of engineering students. The results of this study are as follows: First, the department of engineering students' attitude toward engineering science has shown the order of cognitive element (3.73), definitional element (3.05) and behavioral element (2.86), and in the actual context it is considered that it is necessary to establish a teaching-learning strategy which can reinforce the behavioral elements such as experiments and practices as well as can improve engineering-related cognitive ability. Second, the attitudes toward engineering science according to their brain dominance thinking (Type A: analyst, Type B: Administrator, Type C: Cooperator, and Type D: Jointer) have no significant difference, but the students of Type A who have the characteristics of 7 analyzing thinking have shown high academic accomplishment. Based on these results of study, it is necessary to make a change of the current teaching-learning stratery in accordance with the types of thinking of the students from the teaching-learning perspective. In particular, in order to develop the weak dominance properties and thinking type of individual learners, the change in teacher's recognition that the teacher's teaching-learning strategy and practice is important has to take precedence.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.2
• /
• pp.497-507
• /
• 2018

Objectives: The purpose of this article was to evaluate the health related quality of life (HRQoL) of cancer survivors and to identify its predictors according to gender. Methods: The research was conducted with the data for 203 (cancer survivors?) taken from the 6th wave of the Korea National Health and Nutrition Examination Survey and the EQ-5D index score was used for the measurement of the health-related quality of life (HRQoL). The independent variables inluded socio-demographic data, health related factors (survival duration, disability, subjective health recognition), and psychosocial factors (stress, unmet medical needs). The data were analyzed by the t-test, ANOVA, and hierarchical multiple regression analysis. Results: the HRQoL of the female cancer survivors was significantly worse than that of the males in terms of their mobility, usual activities, pain/discomfort and anxiety/depression quality of life. The only statistically significant factor affecting the HRQoL of the male cancer survivors was their subjective health recognition. In the case of the female cancer survivors, the statistically significant factors were their age, subjective health recognition and unmet medical needs. Conclusions: the results of this study showed a different pattern of predictors according to the gender of the cancer survivors. Therefore, gender should be considered when assessing and addressing the individual care needs of cancer survivors, in order to obtain optimal treatment outcomes.

• Management & Information Systems Review
• /
• v.37 no.2
• /
• pp.283-297
• /
• 2018

This research focuses on the perceived marketplace influence(PMI: A belief that recognizes the effect that an individual's actions will have on the behavior of other consumers in the market and thus drives them to act on fair trade consumption) of consumers who may act as a more fundamental explanatory alternative to the gap in attitudes and behaviors of fair trade products. The purpose of this study is to investigate the relationship between consumer's self - determination psychological needs (autonomy, competence, relevance), influence (personal influence, market influence), and the assets of fair trade products. As a result of the empirical analysis, it was found that among the major psychological needs related to self-determination, the variables other than competence and the perceived influence relations of consumers can be directly formed, and the perceived consumer effectiveness(PCE) has a positive influence on perceived marketplace influence(PMI). It is also found that the perceived influence of consumers(PCE, PMI) has an influence on the consumers' perceived equity of Fair Trade products. The results of this study will provide an opportunity to theoretically explain the gap between consumers' attitudes and behaviors of Fair Trade products, which is a part of ethical consumption, and provide important implications for the establishment of marketing strategies.

• Journal of Digital Convergence
• /
• v.14 no.2
• /
• pp.377-388
• /
• 2016

The purposes of this study are; first, to supply useful suggestions for the market segmentation of the Chinese market according to individual psychological variables(self-congruence) of customers. Second, it figures out the relative importance of actual self-congruence and ideal self-congruence. Lastly, it reveals whether there are any differences in the preference of attributes according to the popular cultural involvement. According to the results, actual self-congruence had a positive influence on the contents factor evaluation while ideal self-congruence had positive effect on the human and cultural factors evaluation. Also, the human and cultural factor had a positive influence on the purchase intention, as well as content factor and cultural factor had the influence on the word-of-mouth. In addition, the group of highly interested in the involvement at the popular culture was significantly higher in the evaluation on the human and contents factor than the low group.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.6
• /
• pp.9-19
• /
• 2016

In finance literature, stock liquidity showing how stocks can be cashed out in the market has received rich attentions from both academicians and practitioners. The reasons are plenty. First, it is known that stock liquidity affects significantly asset pricing. Second, macroeconomic announcements influence liquidity in the stock market. Therefore, stock liquidity itself affects investors' decision and managers' decision as well. Though there exist a great deal of literature about stock liquidity in finance literature, it is quite clear that there are no studies attempting to investigate the stock liquidity issue as one of decision making problems. In finance literature, most of stock liquidity studies had dealt with limited views such as how much it influences stock price, which variables are associated with describing the stock liquidity significantly, etc. However, this paper posits that stock liquidity issue may become a serious decision-making problem, and then be handled by using data mining techniques to estimate its future extent with statistical validity. In this sense, we collected financial data set from a number of manufacturing companies listed in KRX (Korea Exchange) during the period of 2010 to 2013. The reason why we selected dataset from 2010 was to avoid the after-shocks of financial crisis that occurred in 2008. We used Fn-GuidPro system to gather total 5,700 financial data set. Stock liquidity measure was computed by the procedures proposed by Amihud (2002) which is known to show best metrics for showing relationship with daily return. We applied five data mining techniques (or classifiers) such as Bayesian network, support vector machine (SVM), decision tree, neural network, and ensemble method. Bayesian networks include GBN (General Bayesian Network), NBN (Naive BN), TAN (Tree Augmented NBN). Decision tree uses CART and C4.5. Regression result was used as a benchmarking performance. Ensemble method uses two types-integration of two classifiers, and three classifiers. Ensemble method is based on voting for the sake of integrating classifiers. Among the single classifiers, CART showed best performance with 48.2%, compared with 37.18% by regression. Among the ensemble methods, the result from integrating TAN, CART, and SVM was best with 49.25%. Through the additional analysis in individual industries, those relatively stabilized industries like electronic appliances, wholesale & retailing, woods, leather-bags-shoes showed better performance over 50%.