• The Korean Journal of Franchise Management
• /
• v.11 no.2
• /
• pp.23-39
• /
• 2020

Purpose: Social Network Sites(SNS) have been grown up as a public communication channel consumer frequently participate in. Most of food service brands are utilizing social media for advertising recently. As a result of SNS marketing, food service brands anticipate positive outputs from SNS engagement and consumer brand engagement so that we need to verify structural relationship among SNS characteristics, SNS engagement and consumer brand engagement. Research design, data, and methodology: This study identifies that SNS characteristics have effects on SNS engagement and examines relationship between SNS engagement and behavioral engagement. We conceptualize SNS characteristics as information quality, hedonic level and interaction. Furthermore, SNS engagement is composed of SNS participation, positive word of mouth(WOM). In order to verify the purposes of this research, research model and hypotheses were developed. All constructs were measured with multiple items developed and tested in the previous studies. Sample data were collected from 433 online survey panels and analyzed by using SmartPLS 3.2.9. Result: The findings of this research are as follows. First, information quality is positively related with SNS participation. Hedonic level and interaction have impacts on SNS participation and positive WOM respectively. Second, SNS participation has positive effects on positive WOM. Third, both SNS participation and WOM influence behavioral engagement respectively. Conclusions: The implications demonstrate that SNS characteristics such as information quality and hedonic level and interaction exert effects for consumer to participate in SNS brand page. Meanwhile, hedonic level and interaction influence on positive WOM but information quality doesn't. SNS participation and positive WOM affect consumer to engage in specific brand behaviorally as well. Therefore, food service brand marketer is required to manage SNS information quality and hedonic level and interaction among members to encourage SNS participation and positive WOM. As SNS participation and positive WOM increases behavioral engagement of consumer, marketer needs to incentivize SNS participation and look after situation of positive WOM and respond swiftly.

• Journal of Internet of Things and Convergence
• /
• v.7 no.2
• /
• pp.7-12
• /
• 2021

Wisdom Contents are created with experiences and ideas of multiple authors, and consumed in Internet based Social Network Services that are not subjected to regional restrictions. Existing copyright management systems are designed for the protection of professional authors' rights, and effective in domestic area. On the contrary, the blockchain protocol is subjected to the service and the block is added by the consensus of participating nodes. If the data is stored to the blockchain, it cannot be modified or deleted. In this paper, we propose the blockchain based undeniable multi-signature scheme for the protection of multiple authorship on Wizdom Contents. The proposed scheme is consisted of co-authors' common public key generation, multi-signature generation and verification protocols. In the undeniable signature scheme, the signature cannot be verified without help of the signer. The proposed scheme is best suited to the contents purchase protocol. All co-authors cannot deny the fairness of the automated profit distribution through the verification of multiple authorship on Wizdom Contents.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.1
• /
• pp.29-37
• /
• 2020

This paper implements a method of extracting an object about a dog through real-time image analysis and classifying dog behaviors from the extracted images. The Darknet YOLO was used to detect dog objects, and the Teachable Machine provided by Google was used to classify behavior patterns from the extracted images. The trained Teachable Machine is saved in Google Drive and can be used by ml5.js implemented on a node.js server. By implementing an interactive web server using a socket.io module on the node.js server, the classified results are transmitted to the user's smart phone or PC in real time so that it can be checked anytime, anywhere.

• Journal of the Korea Convergence Society
• /
• v.12 no.2
• /
• pp.21-28
• /
• 2021

In this study, we propose a deep learning-based NILM technique using actual measured power data for 5 kinds of home appliances and verify its effectiveness. For about 3 weeks, the active power of the central power measuring device and five kinds of home appliances (refrigerator, induction, TV, washing machine, air cleaner) was individually measured. The preprocessing method of the measured data was introduced, and characteristics of each household appliance were analyzed through spectogram analysis. The characteristics of each household appliance are organized into a learning data set. All the power data measured by the central power measuring device and 5 kinds of home appliances were time-series mapping, and training was performed using a LSTM neural network, which is excellent for time series data prediction. An algorithm that can disaggregate five types of energies using only the power data of the main central power measuring device is proposed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.1
• /
• pp.57-64
• /
• 2020

Recently, due to the proliferation of IoT sensors, the development of big data and artificial intelligence, time series prediction research on fine dust pollution is actively conducted. However, because the data representing fine dust contamination changes rapidly, traditional time series prediction methods do not provide a level of accuracy that can be used in the field. In this paper, we propose a method that reflects the classification results of environmental conditions through CNN when predicting micro dust contamination using LSTM. Although LSTM and CNN are independent, they are integrated into one network through the interface, so this method is easier to understand than the application LSTM. In the verification experiments of the proposed method using Beijing PM2.5 data, the prediction accuracy and predictive power for the timing of change were consistently improved in various experimental cases.

• International Journal of Contents
• /
• v.17 no.1
• /
• pp.37-53
• /
• 2021

With the advent of the 5G era, smart phones and communications network technology have progressed, and mobile short video of people's life can be made, Of the new tools of communication, at present, China's social short video industry has shown rapid development, and the most representative of the short video app is Douyin (international version: Tiktok). Under the background of Uses and Gratifications Theory, this study discusse the relationship between Douyin users' preference degree, use motivation, use satisfaction and attention intention. This study divides the content of Douyin video into 10 categories, selects the form of an online questionnaire survey, uses SPSS software to conduct quantitative analysis of 202 questionnaires after screening, and finally draws the following conclusions: (1) The content preference degree of Douyin short video (the high group and low group) is different in users' use motivation, users' satisfaction degree and users' attention intention. ALL results are within the range of statistical significance.(2) Douyin users' video content preference degree has a positive impact on users' use motivation, users' satisfaction degree, and users' attention intention. (3) Douyin users' motivation has a positive impact on users' satisfaction and user' attention intention. (4) Douyin users' satisfaction degree has a positive impact on users' attention intention. Based on the research results, we suggest that Douyin platform pushes videos according to users' preferences. In addition, as the preference degree has an impact on users' motivation, satisfaction degree and attention intention of using the platform, it is important that the platform's focus should to pay attention to the preference degree of users. Collecting users' preferences at the early stage of users' entering the platform is a good way to learn from, and doing a good job of big data collection and management in the later operation.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.2
• /
• pp.165-170
• /
• 2021

Machine learning has recently been applied to research in most areas. This is because the results of machine learning are not determined, but the learning of input data creates the objective function, which enables the determination of new data. In addition, the increase in accumulated data affects the accuracy of machine learning results. The data collected here is an important factor in machine learning. The proposed system is a convergence system of cloud systems and local fog systems for service delivery. Thus, the cloud system provides machine learning and infrastructure for services, while the fog system is located in the middle of the cloud and the user to collect and refine data. The data for this application shall be based on the Sensitive data generated by smart devices. The machine learning technique applied to this system uses SVM algorithm for classification and RNN algorithm for status recognition.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.4
• /
• pp.109-116
• /
• 2021

In this paper, we propose a non-intrusive load monitoring(NILM) system which can find the power of each home appliance from the aggregated total power as the activation in the trading market of the distributed resource and the increasing importance of energy management. We transform the amount of appliances' power into a power on-off state by preprocessing. We use LSTM as a model for predicting states based on these data. Accuracy is measured by comparing predicted states with real ones after postprocessing. In this paper, the accuracy is measured with the different number of electronic products, data postprocessing method, and Time step size. When the number of electronic products is 6, the data postprocessing method using the Round function is used, and Time step size is set to 6, the maximum accuracy can be obtained.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1213-1222
• /
• 2021

This study is a digitalization study based on ICT technology as part of the development of innovative technologies in the new energy industry as a 2050 carbon-neutral policy. It is the development of an oneM2M-based IoT server platform that can be integrated and managed in conjunction with the external interface of each energy facility. It analyzes KEPCO's e-IoT standard specifications through the Power Research Institute's 'SPIN' and develops representative standards, LWM2M and oneM gateway platforms. OneM2M secures and analyzes the recently announced standard for Release 2 instead of the existing Release 1. In addition, the e-IoT standard oneM2M platform is developed based on R2. In addition, it selects the specifications for e-IoT gateway devices that can sufficiently implement KEPCO's e-IoT standards. In addition, a technology and system for developing a high-performance gateway device that considers future scalability were proposed.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1037-1044
• /
• 2021

In this paper, we propose DLP(Dual Linear Polarization) array antenna for 3.5 GHz band. The proposed antenna has 1×4 array antenna and design two port network. A cross shape is inserted at the bottom of the patch for impedance matching. The size of each patch antenna is 18.85 mm(W1)×18.85 mm(L1), array antenna is designed on the FR-4 substrate, which is 236.0 mm(W)×60.2 mm(L), thickness (h) 1.6 mm, and the dielectric constant is 4.3. From the fabrication and measurement results, bandwidths of 70 MHz (3.54 to 3.61 GHz) for input port 1, 75 MHz (3.55 to 3.625 GHz) for input port 2 are obtained on the basis of -10 dB return loss and transmission coefficient S21 is under the -20 dB. Also, cross polarization between two port obtained.