• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.9
• /
• pp.745-752
• /
• 2016

In the era of the Internet of Things, where all physical objects are connected to the Internet, we suggest a remote control system using a Raspberry Pi single-board computer with ZigBee, which can turn an indoor light-emitting diode (LED) and a multiple-tap on and off, and with a smart phone can control the brightness of the LED as well as an electronic door lock. By connecting an infrared (IR) transmitter module to the Raspberry Pi, we can control home appliances, such as an air conditioner, and we can also monitor indoor images, indoor temperatures, and illumination by using a smart phone app. We developed a method of finding out IR transmission codes required for remote-controllable appliances with an AVR micro-controller. We suggest a method to remotely open and shut an office door by novating the door lock. The brightness level of an LED (between 0 and 10) can be controlled through a PWM signal generated by an ATmega88 microcontroller. A mutiple-tap is controlled using an ATmega32, a photo-coupler, and a TRIAC. The signals for measured temperature and illumination are converted from analog to digital by using the ATtiny44A microcontroller transmitting to a Raspberry Pi through SPI communication. Then, we connect a camera to the CSI head of the Raspberry Pi. We can turn on the smart multiple-tap for a certain period of time, or we can schedule the multi-tap to turn on at a specific time. To reduce standby power, people usually pull out a power code from multiple-taps or turn off a switch. Our method helps people do the same thing with a smart phone, if they are away from home.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.3
• /
• pp.193-198
• /
• 2016

Lane change is an important issue in microscopic traffic flow simulations and active safety. Overtaking and changing lanes are dangerous driving maneuvers. This approach presents a lane-changing system based on speed and a minimum gap between vehicles in a vehicular ad hoc network (VANET). This paper proposes a solution to ensure the safety of drivers while changing lanes on highways. Efficient routing protocols could play a crucial role in VANET applications, safeguarding both drivers and passengers, and thus, maintaining a safe on-road environment. This paper focuses on the development of an intelligent transportation system that provides timely, reliable information to drivers and the concerned authorities. A test bed is created for the techniques used in the proposed system, where analysis takes place in an on-board embedded system designed for vehicle navigation. The designed system was tested on a four-lane road in Neemrana, India. Successful simulations were conducted with real-time network parameters to maximize quality of service and performance using Simulation of Urban Mobility and Network Simulator 2 (NS-2). The system implementation, together with the findings, is presented in this paper. Illustrating the approach are results from simulation using NS-2.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.23 no.7
• /
• pp.164-171
• /
• 2019

Focusing on the bridge facilities, which occupy the largest proportion among SOC public facilities in Korea, it is possible to reduce the cost compared to existing wired measurement systems or wireless measurement systems developed by domestic telecommunications companies, and to increase the technical perfection to be applied to many bridges. We developed a wireless measurement system for bridges. Using LoRa, one of the unlicensed LPWAN technologies, we have developed an optimized MEMS-based LoRa smart sensor node considering the domestic ISM band and the existing wired sensor LoRa DAQ sensor node that can communicate with the LoRa network. Application server was developed for the test bed performance verification and efficient management of the developed sensor node.

• Journal of the Korea Convergence Society
• /
• v.8 no.12
• /
• pp.63-69
• /
• 2017

This study is about the development of a smart bed control system to be able to detect the human position and body signal on bed. The main control board in the bed control system consists of the human sensing part, motor driving part and MCU. Here, to increase the credibility to check the human presence on bed, the human sensing part is combined with the human position part by membrane sensor and the body-signal detecting part of EMFI sensor. Also, remotely connecting the two detected signal to the application program of the app mode makes it possible to monitor human information on bed. In this paper, the remote function monitoring of the on-bed human information by bluetooth communication will be abe to make it applicable to the technical prevention method of the bed fall and absence accident in hospital and care facilities.

• The Journal of the Convergence on Culture Technology
• /
• v.4 no.3
• /
• pp.293-298
• /
• 2018

In the fourth industrial revolution era triggered by the popularization of smart phones, Human daily life and all industrial sites are becoming software and intelligent. With the universal software education for all students nationwide from 2018, Demand is surging, and hardware is interlocked using software technology and Arduino. However, expensive control boards and dozens of different electronic components have to be prepared separately and problems are occurring. In addition, if the same training is repeated, Significantly many parts are lost or destroyed. Being prepared to start a new class is also becoming a very serious problem. In this study, we implement VR technology based on virtualization technology of Arduino board and various electronic parts. In addition, 3D graphics realistic Arduino kit and various electronic components are provided in API form. In this paper, we propose a method of interworking software and virtual hardware on virtualization base.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.1
• /
• pp.107-113
• /
• 2018

In this paper, we design and implement a contest application that enables artists to participate in contest activities, manpower, and job information using smart-phone, and to share and systematically manage the information. While the competition is very important for the artists, it is not easy for them to search the competition information due to lack of time. Therefore, it is effective to provide them with contest information suitable for their interests and to be more immersed in creative activities by sharing them. The core function is to provide a space where artists can share contests in real time through the contest bulletin board and aims to provide a variety of functions for convenient convenience, such as buying and selling of works by artists and spoon market for purchasing materials and art tools do.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.1
• /
• pp.709-714
• /
• 2017

Structures like bridges or buildings need to be checked continuously to diagnose their safety. However, it is extremely difficult for the people who access such structures to check all areas directly. To overcome this problem, there is a lot of active research into structural health monitoring (SHM) with wireless sensor nodes (WSNs). In this paper, for more accurate checking of SHM with WSNs, we experimentally compare and evaluate the performance of Xenomai, which provides real-time processing under the traditional Linux kernel. For this purpose, we patch Xenomai into the traditional Linux kernel of a commercial embedded board, Raspberry Pi, and implement a task that periodically reads vibration data of the z-axis from an accelerometer in order to analyze the natural frequency of cantilever beams. Reading the data from the traditional Linux kernel with the same method, we analyze the natural frequency of the cantilever beams using Smart Office Analyzer. Finally, to review the validity of Xenomai for WSNs, we obtain vibration data on the z-axis from the accelerometer via wired network and compared and analyzed them the same way.

• Journal of the Korea Convergence Society
• /
• v.9 no.5
• /
• pp.21-26
• /
• 2018

In this study, HRD-NET (http://hrd.go.kr), a vocational and training integrated computer network operated by the Ministry of Employment and Labor, is used to confirm whether job training information required by job seekers is being provided smoothly The question bulletin board was extracted using 'R' program which is optimized for big data technique. Therefore, the effectiveness, appropriateness, visualization, frequency analysis and association analysis of the vocational training system were conducted through this, The results of the study are as follows. First, the issue of vocational training card, video viewing, certificate issue, registration error, Second, management and processing procedures of learning cards for tomorrow 's learning cards are complicated and difficult. In addition, it was analyzed that the training cost system and the refund structure differentiated according to the training occupation, the process, and the training institution in the course of the training. Based on this paper, we will study not only the training system of the Ministry of Employment and Labor but also the improvement of the various training computer system of the government department through the analysis of big data.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.10
• /
• pp.983-988
• /
• 2016

Internet of Things Iranian people and things, things and things are connected through the Cloud. It can significantly save energy through a combination of LED lighting as a new ICT technologies and industry-to provide a human-centric, eco-friendly, and the content is embedded multifunction solutions that meet your needs, environment, implementation time according to user requirements, technology It can be systematized as converged next-generation lighting. In this paper, we have developed regarding whether the building in relation to the LED lighting control system using smart devices and Cloud-based user as a human connection through the board to the Arduino Yun lit LED lighting, wireless smart device or to the Cloud or off. After the Arduino Yun is connected to the Internet, taking the current date and time information from the Linux shell command used the way coming across the bridge (BRIDGE) its value.