• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.3
• /
• pp.657-662
• /
• 2017

Recently, according to the development of the smart home field, it provides a service to install and keep the smart home appliance in a user's residential environment pleasantly. However, the conventional system method has a problem in that it is not convenient because the user selects a device or manually operates the device. In this paper, we propose a system to set the priority of the devices selected by the user and proceed with the work. When a user selects a device, it recommends a device associated with the device. Compare and set the priority of each device. And it is a system that carries out work according to the set priority. Therefore the proposed system is expected to provide users with increased convenience and efficiency of work management.

• Journal of Internet of Things and Convergence
• /
• v.2 no.3
• /
• pp.7-15
• /
• 2016

These days, a lot of research has been in progress for a home automation system. In this study, the intelligent home automation system is developed for automatically controlling the temperature and illumination of the house. The difference with other research can be adjusted individually according to your taste and lifestyle of each individual, it is that it provides a more comfortable living environment through the accumulated lifestyle database. In addition, proposed system can use the mobile app to easily control the lighting devices, a electric fans, and heaters. Moreover the mobile app of proposed system offers function that allows you to search for residential environments statistics on their lifestyle.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.487-490
• /
• 2018

As the fourth industrial revolution 4.0 era arrives, the role of smart factory is emerging, which establishes a communication system between production devices and products through the Internet of Things and optimizes the entire production process. Germany wants to use smart factory technologies and data to upgrade and standardize the industry as a whole to create factories around the world, and the United States is aiming to create new business models and revenue streams by analyzing big data and improving productivity based on the technological prowess and innovation across ICT. In addition, Japan and China are also working to change and upgrade their manufacturing industries through smart factories. Accordingly, Korea is attempting to introduce smart factory based on the production industry 3.0. Therefore, this study describes the industrial trends of the fourth industrial revolution and smart factory and compares the major underlying technologies and introduction cases of smart factory.

• The Korean Journal of Applied Statistics
• /
• v.31 no.5
• /
• pp.539-554
• /
• 2018

Effective interaction between user and device is considered an important ability of IoT devices. For some applications, it is necessary to recognize human facial expressions in real time and make accurate judgments in order to respond to situations correctly. Therefore, many researches on facial image analysis have been preceded in order to construct a more accurate and faster recognition system. In this study, we constructed an automatic recognition system for facial expressions through two steps - a facial recognition step and a classification step. We compared various models with different sets of data with pixel information, landmark coordinates, Euclidean distances among landmark points, and arctangent angles. We found a fast and efficient prediction model with only 30 principal components of face landmark information. We applied several prediction models, that included linear discriminant analysis (LDA), random forests, support vector machine (SVM), and bagging; consequently, an SVM model gives the best result. The LDA model gives the second best prediction accuracy but it can fit and predict data faster than SVM and other methods. Finally, we compared our method to Microsoft Azure Emotion API and Convolution Neural Network (CNN). Our method gives a very competitive result.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.143-150
• /
• 2020

Recently, many companies are interested in smart factory services. Because various smart factory services are provided by the combination of mobile devices, cloud computing, and IoT services. However, many workers turn away from these systems because most of them are not implemented from the worker's point of view. To solve this, we implemented a development tool that allows field workers to produce their own services so that workers can easily create smart factory services. Manufacturing data is collected in real time from sensors which are connected to manufacturing facilities and stored within smart factory platforms. Implemented development tools can produce services such as monitoring, processing, analysis, and control of manufacturing data in drag-and-drop. The implemented system is effective for small manufacturing companies because of their environment: making various services quickly according to the company's purpose. In addition, it is assumed that this also will help workers' improve operation skills on running smart factories and fostering smart factory capable personnel.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.1
• /
• pp.23-28
• /
• 2018

In this work, we developed a platform that can monitor status and manage events of factory workplaces by providing events and data collected from various types of multi-touch technology based sensors installed in the workplace. By using the image recognition technology, faces of the people in the factory workplace are recognized and the customized contents for each worker are provided, and security of contents is enhanced by the authenticating an individual worker through face recognition. Contents control function through gesture recognition is constructed, so that workers can easily search documents. Also, it is possible to provide contents for workers by implementing face recognition function in mobile devices. The result of this work can be used to improve workplace safety, convenience of workers, contents security and can be utilized as a base technology for future smart factory construction.

• Journal of the Korea Convergence Society
• /
• v.9 no.6
• /
• pp.61-68
• /
• 2018

This paper propose the remote monitoring system using LoRa networks about storm overflow chamber, which is a device designed to discharge rainwater directly to a sewage treatment plant when it reaches a certain amount of rainfall during precipitation. In this system, when the information produced by the sensor is transmitted to the LoRa network server and updated, the application server can automatically receive data through the implemented communication interface. The application server carries out management functions of storm overflow chamber devices and subscription information, collects measured flow rate and opening-closing information, and provides statistical information using the collected data. The android app performs a firebase-based notification function to prompt the user of malfunctioning of the storm overflow chamber device.

• Journal of Digital Contents Society
• /
• v.19 no.9
• /
• pp.1779-1785
• /
• 2018

In this paper, we propose an error correction method to improve the accuracy of human activity recognition using sensor event data obtained by smart devices such as wearable and smartphone. In the context awareness through the smart device, errors inevitably occur in sensing the necessary context information due to the characteristics of the device, which degrades the prediction performance. In order to solve this problem, we apply Kalman filter's error correction algorithm to compensate the signal values obtained from 3-axis acceleration sensor of smart device. As a result, it was possible to effectively eliminate the error generated in the process of the data which is detected and reported by the 3-axis acceleration sensor constituting the time series data through the Kalman filter. It is expected that this research will improve the performance of the real-time context-aware system to be developed in the future.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.39 no.1
• /
• pp.47-55
• /
• 2016

As one of recent issues in the information and communication industry, internet of things has attracted attention to provide intelligent infrastructure services which connect and share data and information between real and virtual world. According to the development of these internet of things technologies, types of machines, telecommunication devices, and terminals are increasing tremendously. In this situation, connectivity and interoperability between internet of things components are important issues to build a hyper connected society. To visualize this society, it is important to set up and develop information and communication technology (ICT) standards among stakeholders. However, under limited budget and human resources, it is essential to rank standardization work items for setting standards with respect to efficiency. The purpose of this study is to provide a method for setting standardization strategies within group decision making. As a multi-criteria group decision making tool, analytic hierarchy process (AHP) is adopted and applied to determine the priorities of setting work items. The proposed method first defines decision making problem with objective, criteria, and alternatives which produces a hierarchy consisting of upper and lower criteria. Then, pairwise comparisons of academy and public sector experts are performed with respect to their relative meaning and importance. Individual surveys of expert groups are collected and summarized to determine relative criteria importance measures. Furthermore, to deliver reliable importance criteria measures, differences between academy and public sector expert groups are compared and tested using Mann-Whitney non-parametric test. The results are illustrated for useful guidelines to practical group decision making in standardization strategy establishments.

• Journal of Advanced Navigation Technology
• /
• v.19 no.1
• /
• pp.66-73
• /
• 2015

In this paper, an architecture of a perpetual smart video device and its energy control model for the internet of things (IoT) are proposed. The smart video device consists of a processor, an image sensor, a video codec, and a network controller. In the proposed energy control model, energy consumed by image sensing, video encoding, and transmission and energy harvested by solar panels are defined as an input and an output of a battery, an energy buffer. Frame rate, quantization parameter, and operating frequency of processor are defined as the energy control parameters, and these parameters control the input and the output energy of the energy buffer, finally control the energy left in the battery. The proposed energy control model is validated by the energy consumption measurement of the smart phone based platform for various combinations of energy control parameters, and can be used for the design of perpetual smart video device.