• Journal of Digital Convergence
• /
• v.17 no.7
• /
• pp.285-292
• /
• 2019

With the popularization of PC, SNS and IoT, a lot of data is generated and the amount is increasing exponentially. Artificial neural network learning is a topic that attracts attention in many fields in recent years by using huge amounts of data. Artificial neural network learning has shown tremendous potential in speech recognition and image recognition, and is widely applied to a variety of complex areas such as medical diagnosis, artificial intelligence games, and face recognition. The results of artificial neural networks are accurate enough to surpass real human beings. Despite these many advantages, privacy problems still exist in artificial neural network learning. Learning data for artificial neural network learning includes various information including personal sensitive information, so that privacy can be exposed due to malicious attackers. There is a privacy risk that occurs when an attacker interferes with learning and degrades learning or attacks a model that has completed learning. In this paper, we analyze the attack method of the recently proposed neural network model and its privacy protection method.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.123-135
• /
• 2018

The objective of this paper is to investigate the issues related to the supply chain management in plant engineering industry, and propose the framework to improve the project efficiency. The preliminary case study shows that EPC's fragmented nature, lack of coordination and information sharing, and lack of proper risk and change management contribute to project delay and cost overrun. To examine the level of informatization and information sharing in supply chain, survey responses from the suppliers and subcontractors have been collected. The statistical results show that information sharing, early involvement in design process and awareness in SCM have influenced the level of collaboration, but supplier assessment and informatization have no impact on the collaboration. A conceptual model is proposed in order to facilitate the integration of design, procurement and construction functions. Implications from the study are also provided.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.383-393
• /
• 2018

The purpose of this study was to examine impact of multi-cultural family on subjective health status, mental health and internet addiction tendency compared to general family in Korean adolescent. The data were derived from the 13th Korea youth risk behavior web-based survey 2017 in Korea and analyzed considering complex samples analysis. The subjects were general families 61,320(98.5%) and multi-cultural families 956(1.5%). Multi-cultural youth had higher rates of unhealthy and unhappy and the percentage of depression, suicidal ideation, weekday and weekend smartphone overdependence, experience problems with using smartphone in friend than general youth. In addition, suicidal ideation 1.270 times, weekday and weekend smartphone overdependence 1.359 times and 1.297 times respectively and experience problems with using smartphone in friend 1.603 times was increased in multi-cultural youth compared to general youth. Therefore, it is very meaningful that this study provided basic data of intervention program to improve mental health and internet addiction tendency of multi-cultural youth.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.221-226
• /
• 2019

The characteristic of the beta wave among the EEG waves corresponds to the stress area of human perception. The over-bandwidth of the stress is extracted by analyzing the beta-wave correlation between the low-bandwidth and high-bandwidth. We present a KMeans clustering analysis model for unsupervised machine learning to construct an analytical model for analyzing and extracting the beta-wave correlation. The proposed model classifies the beta wave region into clusters of similar regions and identifies anomalous waveforms in the corresponding clustering category. The abnormal group of waveform clusters and the normal category leaving region are discriminated from the stress risk group. Using this model, it is possible to discriminate the degree of stress of the cognitive state through the EEG waveform, and it is possible to manage and apply the cognitive state of the individual.

• Journal of Digital Convergence
• /
• v.17 no.3
• /
• pp.191-204
• /
• 2019

This study empirically confirmed whether individual characteristics and social capital have distinctive influence on entrepreneurship and entrepreneurship, and whether entrepreneurship consulting has a moderating effect in the context of high interest in entrepreneurship with 223 data. All of the personal characteristics, network, trust, and consulting experience had a significant influence on the entrepreneurial intention, while the external control and reciprocity norms had a significant influence on the entrepreneurial anxiety. The experience of consulting revealed that it has a moderating effect of weakening influence of risk-taking tendency and network on the entrepreneurial will and strengthening the influence of external control on the entrepreneurial anxiety. This research has significance in terms of distinguishing effects of entrepreneurial intention and anxiety and the moderating effect of consulting. In future research, it is expected that verification of entrepreneurial anxiety should be done.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.561-569
• /
• 2018

The aim of this study was to examine the association between daily stress and smartphone overdependence among multicultural adolescents, focusing on the moderating roles of gender and age. This study performed a series of multiple linear regressions with a sample of 794 multicultural adolescents living with a foreign-born parent or parents from the 13th Korea Youth Risk Behavior Web-Based Survey. The main regression analysis showed that daily stress was associated with higher levels of smartphone overdependence among multicultural adolescents. In addition, interaction analyses showed that the association between daily stress and smartphone overdependence was more pronounced for male adolescents compared to female adolescents, and for middle school students compared to high school students. This study concluded with some suggestions to address smartphone overdependence among multicultural adolescents.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.953-958
• /
• 2018

In this study, a portable detection system was developed that can detect harmful gas and signals simultaneously in an enclosed space of industrial sites and underground facilities. The developed system is a sensor module for gas detection, a patch type 1 channel small ECG sensor, a module for three-axial acceleration detection sensor, and a system for statistics. In order to verify the performance of the system modules, the digital resolution, signal frequency, output voltage, and ultra-small modules were evaluated. As a result of the performance of the developed system, the digital resolution was 300 (rps) and the signal amplification gain was 500 dB or more, and the ECG module was manufactured with $50mm{\times}10mm{\times}10mm$ to increase patch utilization. It is believed that the product of this research will be valuable if it is used as an IoT-based management system for real-time monitoring of industrial workers.

• Journal of Digital Convergence
• /
• v.16 no.11
• /
• pp.303-312
• /
• 2018

The purpose of this study is to design the easy payment service research model and to find the influencing effect on the intention for the reuse of easy payment service by analysing the factors such as the social influence, the promotion condition, the security and the convenience as UTAUT model has. Also the research model employs the trust and the user satisfaction as parameters. The result shows that even though people feel the trust due to the convenience by the social influence, it has a negative influence on the user satisfaction if the risk recognized in the easy payment service and the weakness in the security are anticipated. The results of this study are academically meaningful as they established the research model for the easy payment service and the theoretical basis of the easy payment service area; they have provided the various practical implications.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.193-198
• /
• 2019

In smart cities around the world, urban environments have become more convenient due to information and communication technology(ICT). However, extant studies reveal that the level of life satisfaction of citizens has not improved compared to that of the pre-smart city and citizens are skeptical about the role of the smart city. This is largely because local culture and needs were neglected during the planing and development of the smart city. The research was conducted on Cambodia as a pilot site and our findings indicate that middle age group's population is significantly small and the society is at risk of losing its culture. Therefore, this paper opens up various ways of embedding cultural programs using technology in order to pass down cultural heritage to young generation, provide an emotional attachment to the inhabitants and further build up a new phase of cultural legacy. This will engender cultural uniqueness to the city and intrigue tourists around the world resulting in the growth of the tourist industry. This research will contribute locally by providing a sense of community to the public and globally by suggesting applicable methodology to other cities that are under the similar context.

• Journal of Digital Convergence
• /
• v.17 no.9
• /
• pp.127-133
• /
• 2019

A callable product is one of service derivatives using options to generate demand and reduce risk. This paper compares two booking admission controls for callable products, the online and the batch admission controls. To this end, the paper computes the optimal booking policy by using the backward dynamic programming and the stochastic optimization method. Intuitively, the provider should outperform under the batch control by utilizing demand information. The contribution of the paper is to show that the two controls are equivalent in terms of the booking strategy and the expected profit, which enables the provider to keep its current control method. The paper develops the closed-form solutions for the three fare classes. The future work is to extend the result to the model with complicated fare structures.