• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.8
• /
• pp.171-180
• /
• 2020

Smart Factory consists of digital automation solutions throughout the production process, including design, development, manufacturing and distribution, and it is an intelligent factory that installs IoT in its internal facilities and machines to collect process data in real time and analyze them so that it can control itself. The smart factory's equipment works in a physical combination of numerous hardware, rather than a virtual character being driven by a single object, such as a game. In other words, for a specific common goal, multiple devices must perform individual actions simultaneously. By taking advantage of the smart factory, which can collect process data in real time, if reinforcement learning is used instead of general machine learning, behavior control can be performed without the required training data. However, in the real world, it is impossible to learn more than tens of millions of iterations due to physical wear and time. Thus, this paper uses simulators to develop grid sortation systems focusing on transport facilities, one of the complex environments in smart factory field, and design cooperative multi-agent-based reinforcement learning to demonstrate efficient behavior control.

• Journal of Broadcast Engineering
• /
• v.26 no.2
• /
• pp.125-131
• /
• 2021

In recent years, Convolutional Neural Networks (CNNs) have achieved outstanding performance in the fields of computer vision such as image classification, object detection, visual quality enhancement, etc. However, as huge amount of computation and memory are required in CNN models, there is a limitation in the application of CNN to low-power environments such as mobile or IoT devices. Therefore, the need for neural network compression to reduce the model size while keeping the task performance as much as possible has been emerging. In this paper, we propose a method to compress CNN models by combining matrix decomposition methods of LR (Low-Rank) approximation and CP (Canonical Polyadic) decomposition. Unlike conventional methods that apply one matrix decomposition method to CNN models, we selectively apply two decomposition methods depending on the layer types of CNN to enhance the compression performance. To evaluate the performance of the proposed method, we use the models for image classification such as VGG-16, RestNet50 and MobileNetV2 models. The experimental results show that the proposed method gives improved classification performance at the same range of 1.5 to 12.1 times compression ratio than the existing method that applies only the LR approximation.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.597-603
• /
• 2023

The paradigm of military operations has evolved from platform-centric warfare to network-centric warfare and further to information-centric warfare, driven by advancements in information technology. In recent years, with the development of cutting-edge technologies such as big data, artificial intelligence, and the Internet of Things (IoT), military operations are transitioning towards knowledge-centric warfare (KCW), based on artificial intelligence. Consequently, the military places significant emphasis on integrating advanced information and communication technologies (ICT) to establish reliable C4I (Command, Control, Communication, Computer, Intelligence) systems. This research emphasizes the need to apply data mining techniques to analyze and evaluate various aspects of C4I systems, including enhancing combat capabilities, optimizing utilization in network-based environments, efficiently distributing information flow, facilitating smooth communication, and effectively implementing knowledge sharing. Data mining serves as a fundamental technology in modern big data analysis, and this study utilizes it to analyze real-world cases and propose practical strategies to maximize the efficiency of military command and control systems. The research outcomes are expected to provide valuable insights into the performance of C4I systems and reinforce knowledge-centric warfare in contemporary military operations.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.5
• /
• pp.353-358
• /
• 2018

We herein analyze the service traffic characteristics and spectrum of the 5G mobile communication and suggest the effective 5G network deployment method for 5G mobile communication services. The data rates of the 5G mobile communication are from several kbps (voice and IoT) up to 1 Gbps (hologram, among others). The 5G mobile communication services show the diverse cell coverage environments owing to the use of diverse service data rates and multiple spectrum bands. To effectively support the 5G mobile communication services, the network deployment requires the optimization of the service coverages for new service environments and multiple spectrum bands. Considering the 5G spectrum bandwidth debated at present, if the 5G services of 100 Mbps can be supported in the 200 m cell edge using the 3.5 GHz spectrum bands, the 5G services of the 1 Gbps hologram and 500-Mbps 4k UHD can be supported in the cell edges of 50 m and 100 m using the 28 GHz spectrum bands. Therefore, the 5G services can be supported effectively by the 5G network deployment using spectrum portfolio configurations to match the diverse 5G services and multiple bands.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.6
• /
• pp.1077-1082
• /
• 2019

The development of computing technology and networking has developed into a fundamental technology of the Fourth Industrial Revolution, which provides a ubiquitous environment. In the ubiquitous environment, the IoT environment has become an issue so that various devices and the things can be actively accessed and connected. Also, the RFID system using the wireless identification code attaches an RFID tag to the object, such as the production and distribution of products. It is applied to the management very efficiently. EPCglobal is conducting a research on RFID system standardization and various security studies. Since RFID systems use wireless environment technology, there are more security threats than wire problems. In particular, failure to provide confidentiality, indistinguishability, and forward safety could expose them to various threats in the Fourth Industrial Revolution. Therefore, this study analyzes the standard method of EPCgolbal and proposes RFID security method using hash code that can consider the amount of computation.

• KIISE Transactions on Computing Practices
• /
• v.22 no.11
• /
• pp.583-590
• /
• 2016

Recently, the rapidly increasing interest in IoT in almost all areas of casual human life has led to wide acceptance of speech recognition as a means of HCI. Simultaneously, the demand for speech recognition systems for mobile environments is increasing rapidly. The server-based speech recognition systems are typically fast and show high recognition rates; however, an internet connection is necessary, and complicated server computation is required since a voice is recognized by units of words that are stored in server databases. In this paper, we present a novel method for recognizing the Korean vowel 'ㅗ', as a part of a phoneme based Korean speech recognition system. The proposed method involves analyses of waveform patterns in the time domain instead of the frequency domain, with consequent reduction in computational cost. Elementary algorithms for detecting typical waveform patterns of 'ㅗ' are presented and combined to make final decisions. The experimental results show that the proposed method can achieve 89.9% recognition accuracy.

• 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.

• Journal of the Korea Computer Graphics Society
• /
• v.23 no.3
• /
• pp.77-85
• /
• 2017

Tangible Space is a new emerging interaction space with mobile AR/VR computing and ubiquitous computing environment with IoT. Tangible Space spans from a physical environment augmented with virtual entities to immersive virtual environments mirroring the physical environment. Interacting with Tangible Space is logged just like interacting with the Web. By webizing Tangible Space, we can gain persistence as a by-product so that human life experience in the physical environment can be logged and shared just like the information being created and shared in the current Web. The result is a powerful future direction of the web from a World Wide Web of Information to World Wide Web of Life experiences.

• International journal of advanced smart convergence
• /
• v.6 no.1
• /
• pp.82-88
• /
• 2017

Emergency lights and exit signs are an indispensable part of safety precautions for effective evacuation in case of emergency in public buildings. These emergency sign indicates safe escape routes and emergency doors, using an internationally recognizable sign. However visibility of those signs drops drastically in case of emergency situations like fire smoke, etc. and loss of visibility causes serious problems for safety evacuation. This paper propose a novel emergency light and exit sign built-in with Bluetooth Low Energy (BLE) Beacon to assist the emergency self-guiding evacuation using devices for crisis and emergency management to avoid panic condition inside the buildings. In this approach, the emergency light and exit sign with the BLE beacons deployed in the indoor environments and the smart devices detect their indoor positions, direction to move, and next exit sign position from beacon messages and interact with map server in the Internet / Intranet over the available LTE and/or Wi-Fi network connectivity. The map server generate an optimal emergency exit path according to the nearest emergency exit based on a novel graph generation method for less route computation for each smart device. All emergency exit path data interfaces among three system components, the emergency exit signs, map server, and smart devices, have been defined for modular implementation of our emergency evacuation system. The proposed exit sign experimental system has been deployed and evaluated in real-time building environment thoroughly and gives a good evidence that the modular design of the proposed exit sign system and a novel approach to compute emergency exit path route based on the BLE beacon message, map server, and smart devices is competitive and viable.

• Journal of Korea Multimedia Society
• /
• v.17 no.12
• /
• pp.1473-1483
• /
• 2014

A public restroom is different from a household toilet in terms of location and a large number of sharing users. In addition, public restroom is usually messy and filthy. Recently, public toilet tends to be clearly managed than before, but it still has hygienic and clear problems. In this paper, we propose a machine-to-machine (M2M)-based public restroom management system to solve these problems, in which the system with a wireless communication device sends the status information of the toilet, such as blockage or trouble detected by a sensor, to the manager of the restroom at a remote location. In particular, we have developed a prototype management system for public restroom taking into account several system requirements, and verified the basic operations and performance of the management system. With the application of the system to public facilities, it will furnish users with more pleasant environments by restroom administrators who can respond effectively to the troubled toilet.