• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.99-104
• /
• 2022

In this paper, we first intend to develop and introduce a smart laundry drying system for verandas that controls the drying rack by actively responding to climate change. The developed smart laundry drying system receives laundry location information through the app, then detects climate change in real time through data from the Korea Meteorological Administration such as temperature and humidity according to the location information, and automatically controls the laundry on the drying rack in case of rain. It acquires weather information through the Arduino humidity sensor and the Korea Meteorological Administration Open-API, which is used to control the switch bot by the Raspberry Pi. The user interface uses Blynk, and the switch bot controls the laundry. Our proposed system can detect bad weather and automatically control the laundry at a remote location to prevent damage to the laundry.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.4
• /
• pp.92-98
• /
• 2022

This paper proposes a new method of the traffic signal detection and the recognition in an HSI color model. The proposed method firstly converts a ROI image in the RGB model to in the HSI model to segment the color of a traffic signal. Secondly, the segmented colors are dilated by the morphological processing to connect the traffic signal light and the signal light case and finally, it extracts the traffic signal light and the case by the aspect ratio using the connected component analysis. The extracted components show the detection and the recognition of the traffic signal lights. The proposed method is implemented using C language in Raspberry Pi 4 system with a camera module for a real-time image processing. The system was fixedly installed in a moving vehicle, and it recorded a video like a vehicle black box. Each frame of the recorded video was extracted, and then the proposed method was tested. The results show that the proposed method is successful for the detection and the recognition of traffic signals.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.44-49
• /
• 2022

The number of single-person households is increasing worldwide, and among them, the proportion of elderly single-person households is increasing. In the case of elderly single-person households, a significant portion of their leisure time is devoted to watching TV. However, if they fall asleep while watching TV without turning it off, it may be difficult to sleep well due to lights and sounds of TV, which can cause health problems such as depression and reduced immunity. Therefore, in this paper, we propose a system that automatically turns off the TV when a person watching TV falls asleep. Images are collected using the camera installed in front of the TV. Since the posture of a person watching TV varies from a sitting posture to a lying posture, the system is designed to determine whether or not to fall asleep regardless of the posture. In addition, since it becomes difficult to judge eye movements as a person moves away from the TV, a method for extending the judgmentable distance is proposed. The system model was implemented and tested using a Raspberry Pi, a monitor, an infrared sensor, and a camera. Eye movements were judged regardless of sitting or lying position, and the distance between a user and a TV was extended by about 200 cm.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.6
• /
• pp.1271-1278
• /
• 2021

In this paper, we implemented smart mirrors that virtually select and experience eyeglasses and hair styles on user faces through face recognition and recommend weather-specific clothes to guide various styles. In addition, makeup is possible while watching the video while looking at the screen. Raspberry Pi, acrylic plate and half mirror film were used to reduce the cost of conventional smart mirrors. It also added basic information such as weather, dates, calendars, and news, and increased user convenience by using a touchscreen.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.4
• /
• pp.165-172
• /
• 2023

Heterogeneous computing is a technology that utilizes different types of processors to perform parallel processing. It maximizes task processing and energy efficiency by leveraging various computing resources such as CPUs, GPUs, and FPGAs. On the other hand, edge computing has developed with IoT and 5G technologies. It is a distributed computing that utilizes computing resources close to clients, thereby offloading the central server. It has evolved to intelligent edge computing combined with artificial intelligence. Intelligent edge computing enables total data processing, such as context awareness, prediction, control, and simple processing for the data collected on the edge. If heterogeneous computing can be successfully applied in the edge, it is expected to maximize job processing efficiency while minimizing dependence on the central server. In this paper, experiments were conducted to verify the feasibility of various parallel programming models on high-end and low-end edge devices by using benchmark applications. We analyzed the performance of five parallel programming models on the Raspberry Pi 4 and Jetson Orin Nano as low-end and high-end devices, respectively. In the experiment, OpenACC showed the best performance on the low-end edge device and OpenSYCL on the high-end device due to the stability and optimization of system libraries.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.209-209
• /
• 2023

본 연구에서는 강우 시 발생하는 음향 및 진동 신호를 기반으로 강우강도를 산정하기 위한 방법론을 제안하였다. 먼저, Raspberry Pi, 콘덴서 마이크 및 가속도 센서로 구성된 관측 기기로부터 실제 비가 내리는 환경에서의 음향 및 진동 신호를 수집하였다. 가속도 센서로부터 계측된 진동 신호를 활용하여 강우 유무에 대한 이진 분류를 수행하고, 강우가 발생한 것으로 판단된 기간에 해당하는 음향 신호에 Short-Time Fourier Transform 기술을 적용하여 주파수 영역에서 나타나는 magnitude의 평균과 표준 편차, 최고 주파수 등의 특징을 기반으로 강우강도를 산정하였다. 이를 위해 앙상블 기반의 머신러닝 학습 모델인 XGBoost 알고리즘을 사용하였으며, 광학 우적계를 통해 관측한 강우강도와 산정 결과를 비교·평가하였다. 강우강도 산정 과정에서 사용된 음향 신호의 길이를 1초, 10초, 1분으로 구분하였으며, 무강우 기간 내 음향 정보로부터 배경 음향에 의한 노이즈를 제거하고자 하였다. 최종적으로 강우 유무 이진 분류 과정의 선행 여부, 음향 신호의 길이 및 노이즈 제거 방법에 따른 강우강도 산정 결과들에 대한 성능 비교를 통해 본 연구에서 제안하고자 하는 방법론의 실효성을 평가하였다.

• The Plant Pathology Journal
• /
• v.17 no.2
• /
• pp.77-82
• /
• 2001

Erwinia amylovora causes a devastating disease called fire blight in rosaceous trees and shrubs such as apple, pear, and raspberry. To successfully infect its hosts, the pathogen requires a set of clustered genes termed hrp. Studies on the hrp system of E. amylovora indicated that it consists of three functional classes of genes. Regulation genes including hrpS, hrpS, hrpXY, and hrpL produce proteins that control the expression of other genes in the cluster. Secretion genes, many of which named hrc, encode proteins that may form a transmembrane complex, which is devoted to type III protein secretion. Finally, several genes encode the proteins that are delivered by the protein secretion apparatus. They include harpins, DspE, and other potential effector proteins that may contribute to proliferation of E. amylovora inside the hosts. Harpins are glycine-rich heat-stable elicitors of the hypersensitive response, and induce systemic acquired resistance. The pathogenicity protein DseE is homologous and functionally similar to an avirulence protein of Pseudomonas syringae. The region encompassing the hrpldsp gene cluster of E. amylovora shows features characteristic of a genomic island : a cryptic recombinase/integrase gene and a tRNA gene are present at one end and genes corresponding to those of the Escherichia coli K-12 chromosome are found beyond the region. This island, designated the Hrp pathogenicity island, is more than 60 kilobases in size and carries as many as 60 genes.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.1
• /
• pp.119-127
• /
• 2023

Recently, deep learning has been used in the development of various institutional devices and services to help the visually impaired people in their daily lives. This is because not only are there few products and facility guides written in braille, but less than 10% of the visually impaired can use braille. In this paper, we propose a system that recognizes beverage cans in real time and outputs the beverage can name with sound for the convenience of the visually impaired. Five commercially available beverage cans were selected, and a CNN model and a YOLO model were designed to recognize the beverage cans. After augmenting the image data, model training was performed. The accuracy of the proposed CNN model and YOLO model is 91.2% and 90.8%, respectively. For practical verification, a system was built by attaching a camera and speaker to a Raspberry Pi. In the system, the YOLO model was applied. It was confirmed that beverage cans were recognized and output as sound in real time in various environments.

• Nuclear Engineering and Technology
• /
• v.55 no.2
• /
• pp.493-505
• /
• 2023

Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.277-279
• /
• 2020

최근 무선통신기술의 발달로 텍스트나 이미지 등 적은 양의 데이터를 송출하는 것을 넘어 동영상과 같은 많은 양의 데이터 전송이 가능해졌다. 이에 본 논문은 실시간으로 사고의 상황을 효과적으로 구조기관에 전달하기 위해 GPS와 각종 센서를 활용한 GPS 데이터 및 비디오를 실시간으로 전송하는 무선 네트워크 상황 전파 시스템을 제안한다. Raspberry pi module의 카메라와 GPS 데이터는 ffmpeg와 ffserver를 사용하여 서버와 구조기관으로 실시간 송출 및 전송된다. 제안된 시스템은 실제 프로토타입으로 구현되었으며, 실험 결과 제안한 시스템은 즉각적으로 구조기관에 영상 및 GPS 좌표를 송출함으로써 조기에 사고상황을 파악하고 빠른 구조에 이바지함을 보여준다.