• Journal of the Korea Society of Computer and Information
• /
• v.29 no.4
• /
• pp.161-175
• /
• 2024

In this paper, we examined the causes of privacy concern and related factors in personalized recommendation service of OTT. On the basis of the 'Big Five Personality model,' we established factors such as agreeableness, neuroticism, conscientiousness, extraversion, and openness to experience. Additionally, we established factors such as accuracy, diversity, and novelty of OTT recommendation's services, and perceived transparency. we analyzed the relationship between privacy concern, service benefit, and intention to give personal information. Finally, we analyzed the mediating effect of service benefits on the relationship between privacy concern and intention to give personal information. The results of this study showed that (1) neuroticism, extraversion and openness to experience had the significant effects on privacy concerns, (2) perceived transparency had the significant effects on privacy concern, 3) privacy concern and service benefit had the significant effect on intention to give personal information, and (4) as a result of multi-group analysis towards low and high groups to verify the moderating effect by service benefits, a significant difference was observed between privacy concern and intention to give personal information. The findings of the study are expected to help the OTT firms' understanding towards users' privacy protection behaviors.

• Journal of Service Research and Studies
• /
• v.9 no.2
• /
• pp.55-76
• /
• 2019

This study conducted empirical analyses to investigate the factors affecting the intention to use smart home services. Based on the previous relevant studies, the characteristics of smart home service were found to influence on the intention to use smart home service, and four variables(ubiquitous connectivity, reliability, context awareness, and security) concerning the service characteristics could be derived. And referring to the technology acceptance model(TAM), the updated TAM, IS success model, and the theory of reasoned action(TRA), three variables such as perceived ease of use, perceived usefulness and subjective norm were also likely to affect the intention to use smart home service, and the user innovativeness was inferred to play a role of moderating variable. In order to examine the research model and the hypotheses which could describe the relationship of the above mentioned variables, this study surveyed 447 people who were currently using or would use the smart home services, and then tested the hypotheses for 436 valid responses. The results of hypotheses testing showed that reliability, context awareness, and security have a significant effect on perceived usefulness and on perceived ease of use. However, it was found that ubiquitous connectivity significantly affected perceived usefulness but did not affect perceived ease of use. And perceived ease of use, perceived usefulness and subjective norm had significant effect on the intention to use smart home services. Also, user innovativeness as moderating variable was found to significantly influence on the magnitude of the relationship between ubiquitous connectivity and perceived usefulness and on that between reliability and perceived ease of use. This can be interpreted as the findings implying that innovative smart home-service users are likely to feel the smart home-services more useful than ordinary users when the degree of ubiquitous connectivity is higher, and are likely to perceive the use of smart home-services to be easier than ordinary ones when the degree of reliability is higher.

• CRM연구
• /
• v.2 no.2
• /
• pp.53-70
• /
• 2009

Understanding consumer behavior based on the analysis of the customer data is one essential part of analytic CRM. To do this, the analytic skills for data extraction and data processing are required to users. As a user has various kinds of questions for the consumer data analysis, the user should use database language such as SQL. However, for the firm's user, to generate SQL statements is not easy because the accuracy of the query result is hugely influenced by the knowledge of work-site operation and the firm's database. This paper proposes a natural language based database search framework finding relevant database elements. Specifically, we describe how our TableRank method can understand the user's natural query language and provide proper relations and attributes of data records to the user. Through several experiments, it is supported that the TableRank provides accurate database elements related to the user's natural query. We also show that the close distance among relations in the database represents the high data connectivity which guarantees matching with a search query from a user.

• Journal of Digital Convergence
• /
• v.19 no.7
• /
• pp.57-70
• /
• 2021

As COVID-19 spreads, people's interest in smart learning that can do non-face-to-face learning is increasing nowadays. In this study, we aim to empirically analyze how users' thoughts on COVID-19 and the information quality and system quality of smart learning systems affect users' acceptance of smart learning and examine the effect of perceived sensitivity and severity of COVID-19 on the satisfaction and use of smart learning through concerns about the risk of transmission. In addition, we examined the influence of information quality composed of content quality and interaction quality and system quality composed of system accessibility and functionality on the use of smart learning through user satisfaction. To verify the validity of the proposed model, we conducted a survey on 334 users with experience in using smart learning, and performed the analysis using Smart PLS 3.0. According to the analysis results, among information quality and system quality, only functionality has a positive (+) effect on the satisfaction of smart learning, and satisfaction has a positive (+) effect on the usage behavior. However, it is found that accessibility among system quality do not affect satisfaction, and concern about the risk of transmission has a negative effect on satisfaction. This study can provide meaningful guidelines to researchers when researching smart learning to support students' learning in a pandemic situation of a new infectious disease, such as COVID-19. It will also be able to provide useful implications for educational institutions and companies related to smart learning.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.5
• /
• pp.95-101
• /
• 2021

In this study, we present how to improve the current seismic disaster information service by utilizing Shake, which can express the effects of earthquakes in the form of isolines. Using ShakeMap software provided by the U.S. Geological Survey, an automated rapid ShakeMap generation system was implemented, and based on this, an earthquake disaster information service improvement model was presented to identify earthquake risk in the form of intensity or peak ground acceleration. In order to verify the feasibility and effectiveness of the improved model, the seismic disaster information service app. was developed and operated on a trial basis in Pohang, Gyeongsangbuk-do. As a result of the operation, it was found that more detailed seismic risk information could be provided by providing information using rapid ShakeMap to induce users' safety behavior more effectively.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.575-577
• /
• 2013

The research was aimed at the hotel industry's employees in order to test the efficiency of e-Learning, which is emerging as the alternative training system to the conventional one. The independent variables are the quality of e-Learning, including the qualities of the system, contents, and service of e-Learning, and the learning characteristic factor, including the quality factor of e-Learning, the self-efficacy of the user, learning motivation, and the flow of learning. Furthermore, the intervening variables are its perceived usefulness and the satisfaction factor of the user known as the so-called utility of e-Learning, continuous intention to use in terms of efficaciousness, and the spread of education and training. The dependent variable is customer orientation, known as the ultimate efficaciousness of corporate e-Learning.

• Journal of Korea Port Economic Association
• /
• v.27 no.4
• /
• pp.13-35
• /
• 2011

The advancement of the information technology provides a wide range of corporate to cope with new business environments that are different in size, life and operation conditions. The Research methodology used in this study is Technology Acceptance Model. The Study Method are mainly survey and questionnaire. The major result of article can be summarized. Its are as the follows: This paper ware investigated the determinants of 'port service quality', 'perceived usefulness', 'perceived ease of use', 'utilization intention', 'practice use'. There are 400 sended samples and 150 returns, 173 of them are analyzed on a port utilization using TAM model. 1. The Port service quality are found to have a positive effect to 'perceived usefulness', 'perceived ease of use', 'utilization intention' 2. The perceived ease of use are found to have a positive effect to 'perceived usefulness', 'utilization intention' 3. The perceived usefulness is found to be positively related to 'utilization intention' 4. The utilization intention is found to have a positive effect to ''practice use' we hove to provide useful contribution to increase the Korea ports' competitiveness in introduction of port information system. In addition, in order to port development offer some insight in further research.

• Journal of the Society of Disaster Information
• /
• v.17 no.3
• /
• pp.465-486
• /
• 2021

Purpose: Since most disaster information systems are centered on non-disabled people, the reality is that there is a lack of disaster information delivery systems for the vulnerable, such as the disabled, the elderly, and children, who are relatively vulnerable to disasters. The purpose of the service is to improve the safety of the disabled and the elderly by eliminating blind spots of informatization and establishing customized disaster information services to respond to disasters through IoT-based integrated control technology. Method: The model at the core of this study is the disaster alert propagation model and evacuation support model, and it shall be developed by reflecting the behavioral characteristics of the disabled and the elderly in the event of a disaster. The disaster alert propagation model spreads disaster situations collected using IoT technology, and the evacuation support model uses geomagnetic field-based measuring technology to identify the user's indoor location and help the disabled and the elderly evacuate safely. Results: Demonstration model demonstration resulted in an efficient qualitative evaluation of indoor location accuracy, such as the suitability of evacuation route guidance and satisfaction of services from the user's perspective. Conclusion: Disaster information and evacuation support services were established for the safety vulnerable groups of mobile app for model verification. The disaster situation was demonstrated through experts in the related fields and the disabled by limiting it to the fire situation. It was evaluated as "satisfaction" in the adequacy of disaster information delivery and evacuation support, and its functional satisfaction and user UI were evaluated as "normal" due to the nature of the pilot model. Through this, the disaster information and evacuation support services presented in this study were evaluated to support the safety vulnerable groups to a faster disaster evacuation without missing the golden time of disaster evacuation.

• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1081-1090
• /
• 2018

The study has been derived through the empirical analysis so as to find the Continuous Usage of Electronic Official Document 24 System. Total of 236 questionnaires were analysis to users who used or experienced the Electronic Official Document 24 System. As a result of the analysis First Accuracy, Convenience, and Security have a positive(+) effect on Ease of Use. However, Compatibility and Innovation were not effect on Ease of Use Second, Accuracy, Convenience, Security, and Innovation have a positive(+) effect on Perceived Usefulness. However, Compatibility was not effect on Perceived Usefulness. Third, Behavioral Costs have a positive(+) effect Continuous Intention and perceived ease of use positively affects perceived usefulness and Continuous Intention. Finally, perceived usefulness also has a positive effect on the Continuous Intention.