• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.115-126
• /
• 2023

Due to the fluctuating random and periodical nature of renewable energy generation power quality disturbances occurred more frequently in power generation transformation transmission and distribution. Various power quality disturbances may lead to equipment damage or even power outages. Therefore it is essential to detect and classify different power quality disturbances in real time automatically. The traditional PQD identification method consists of three steps: feature extraction feature selection and classification. However, the handcrafted features are imprecise in the feature selection stage, resulting in low classification accuracy. This paper proposes a deep neural architecture based on Convolution Neural Network and Long Short Term Memory combining the time and frequency domain features to recognize 16 types of Power Quality signals. The frequency-domain data were obtained from the Fast Fourier Transform which could efficiently extract the frequency-domain features. The performance in synthetic data and real 6kV power system data indicate that our proposed method generalizes well compared with other deep learning methods.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.111-118
• /
• 2023

For the implementation of a smart factory, it is necessary to collect data by connecting various sensors and devices in the manufacturing environment and to diagnose or predict failures in production facilities through data analysis. In this paper, to predict the residual useful lifetime of milling insert used for machining products in CNC machine, weight k-NN algorithm, Decision Tree, SVR, XGBoost, Random forest, 1D-CNN, and frequency spectrum based on vibration signal are investigated. As the results of the paper, the frequency spectrum does not provide a reliable criterion for an accurate prediction of the residual useful lifetime of an insert. And the weighted k-nearest neighbor algorithm performed best with an MAE of 0.0013, MSE of 0.004, and RMSE of 0.0192. This is an error of 0.001 seconds of the remaining useful lifetime of the insert predicted by the weighted-nearest neighbor algorithm, and it is considered to be a level that can be applied to actual industrial sites.

• Journal of Adhesion and Interface
• /
• v.23 no.4
• /
• pp.130-136
• /
• 2022

Recently, organic semiconductor based indoor photovoltaics have gained attention since they exhibit excellent photovoltaic performance than that of conventional Si-based photovoltaics. In this study, we synthesize the medium bandgap polymer of PTBT and optimize PTBT:PC₇₁BM blend films by introducing solvent additives. To this end, we select DIO and CN solvent additives and vary their contents from 0 to 3 vol%. As a result, we produce the highest power conversion efficiency of 11.31% under LED 1000 lx conditions with DIO (1.5 vol%) + CN (0.5 vol%)

• Journal of Practical Agriculture & Fisheries Research
• /
• v.14 no.1
• /
• pp.195-209
• /
• 2012

1) 버섯종균 생산 시스템 개선 버섯의 품질과 수량을 좌우하는 주요 요인은 종균의 활력이다. 그러나 말라위에서는 종균의 활력이 낮아 조그마한 350cc 음료수 병에 배양 완성하는데 20일이 소요되는 등 노동력의 비효율성을 개선하였다. 따라서 350cc 병을 3500cc 비닐봉지로 개선하여 입봉하는데 소요되는 시간을 10배 이상으로 단축 개선하였다. 또한 곡립종균을 액체종균으로 대처한 결과 균사생장 속도가 빨랐으며 작업속도가 빨라졌다. 곡립 수수를 밀로 대체하여 종균제조 노동력을 효율적으로 전환하였다. 2) 버섯재배사 환경관리 개선 버섯재배의 4대 환경조건은 온도, 습도, 환기, 광이다. 그러나 말라위의 버섯재배사는 4대 환경조건 조절을 자연상태에 의존하고 있다. 그럼에도 불구하고 비닐로 커버된 상태에서 문을 닫아두어 과습이 되고 환기가 되지않았다. 이를 개선하기 위하여 직경 5cm 환기공을 버섯재배사 당 4개씩 만들도록 지도하였다. 3) 버섯배지 개선 말라위에서는 옥수수 대를 잘라 버섯배지로 주로 이용하고 있다. 이를 개선하여 말라위 북부지역(다광)에 대규모 사탕수수 공장을 방문하여 사탕수수 박을 이용하여 버섯재배 기술을 교육하였다. 이를 이용함으로서 버섯 균사생장속도를 빠르게 하고 균사량의 축적을 높이도록 하여 고품질 다수확하는데 교육을 하고 컨설팅을 실시하여 개선하였다. 4) 버섯 배지 야외발효 후 지면재배 시도로 시간 단축과 비용절감 말라위 버섯배지 혼합제조법은 옥수수대 한가지로서 영양원이 없다. 이를 개선하여 배지를 수분을 흡수시킨 후 야외 퇴적하므로서 배지의 물리성을 개선하고 야외발효 과정 중 양분이 합성되어 양질의 배지를 만드는 방법이다. 야외발효한 배지를 봉지에 담아 균상에 입상하는 불편함과 나무로 만들어진 균상대의 과습으로 인한 곰팡이 발생과 개미 침입으로 썩는 것 등을 방지하기 위하여 지면재배 방법으로 개선하였다. 이 지면재배는 균상 만드는 나무재료와 인건비 절감. 병해충 발생 방제 뿐만아니라 고품질 다수확할 수 있는 방법으로 개선 교육과 시범 시연을 실시하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.535-538
• /
• 2022

For Plug & Play of IoT devices, we develop a module that recognizes the type of USB, which is a typical wired interface of IoT devices, through image recognition. In order to drive an IoT device, a driver for communication and device hardware is required. The wired interface for connecting to the IoT device is recognized by using the image obtained through the camera of smartphone shooting to recognize the corresponding communication interface. For USB, which is a most popular wired interface, types of USB are classified through artificial neural network-based machine learning. In order to secure sufficient data set of artificial neural networks, USB images are collected through the Internet, and additional image data sets are secured through image processing. In addition to the convolution neural networks, recognizers are implemented with various deep artificial neural networks, and their performance is compared and evaluated.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.150-159
• /
• 2022

This paper presents an implementation of detecting whether a helmet is worn and there is a fall accident through individual image analysis in real-time from extracting the image objects of several workers active in the industrial field. In order to detect image objects of workers, YOLO, a deep learning-based computer vision model, was used, and for whether a helmet is worn or not, the extracted images with 5,000 different helmet learning data images were applied. For whether a fall accident occurred, the position of the head was checked using the Pose real-time body tracking algorithm of Mediapipe, and the movement speed was calculated to determine whether the person fell. In addition, to give reliability to the result of a falling accident, a method to infer the posture of an object by obtaining the size of YOLO's bounding box was proposed and implemented. Finally, Telegram API Bot and Firebase DB server were implemented for notification service to administrators.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.374-376
• /
• 2021

For the diagnosis of cancer-related diseases in clinical practice, pathological examination using biopsy is essential after basic diagnosis using imaging equipment. In order to proceed with such a biopsy, the assistance of an oncologist, clinical pathologist, etc. with specialized knowledge and the minimum required time are essential for confirmation. In recent years, research related to the establishment of a system capable of automatic classification of cancer cells using artificial intelligence is being actively conducted. However, previous studies show limitations in the type and accuracy of cells based on a limited algorithm. In this study, we propose a method to identify a total of 4 cancer cells through a convolutional neural network, a kind of deep learning. The optical images obtained through cell culture were learned through EfficientNet after performing pre-processing such as identification of the location of cells and image segmentation using OpenCV. The model used various hyper parameters based on EfficientNet, and trained InceptionV3 to compare and analyze the performance. As a result, cells were classified with a high accuracy of 96.8%, and this analysis method is expected to be helpful in confirming cancer.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.39-39
• /
• 2021

기상재해를 극소화하기 위해서는 그 원인이 되는 기상현상의 규모와 거동을 명확히 감시하고 분석하여 신뢰성 있는 예측정보가 제공되어야 한다. 최근 위험기상 발생빈도가 증가하여 초단기 및 위험기상 예보의 정확도 향상을 위한 고품질 레이더 정보 활용 연구가 활발하게 진행되고 있다. 레이더는 전자파를 이용하여 강우의 양과 분포, 이동특성을 관측하는 장비로써 우리나라는 초단기적 위험기상 대응능력 향상을 추진하기 위한 목적으로 첨단 성능의 이중편파레이더 관측망을 구축하고 있다. 국내 기상관측용 레이더는 기상예보(기상청), 홍수예보(환경부), 군 작전 기상지원(국방부) 등으로 각 기관이 개별적으로 설치운영 하고 있다. 본 연구에서는 관계부처에서 운영하고 있는 레이더의 합성장을 이용하여 강수장의 상관성을 기반으로 이류(advection) 특성을 도출하였다. 정확도 있는 이류특성을 도출하기 위하여 시간해상도는 10분을 적용하였으며 가우시안 필터링 기법을 적용하여 강수장 상관분석을 수행하였다. 호우와 태풍을 대상으로 강수장의 이류패턴을 추출하여 강수장의 이동방향 및 속도를 고려한 강수량 예측기법의 적용성을 평가하였다. 본 연구 결과는 격자형 강수예측정보를 제공하여 AI 홍수예보 및 수치예보 모델의 초기조건 입력 등에 활용되어 기후변동성에 따른 대국민 안전 실현을 확보하는데 기후변화 대응전략의 핵심기술로 활용될 수 있을 것으로 판단된다. 덧붙어, 4차 산업혁명에 따른 수문기상 빅 데이터(big data) 통합 플랫폼을 구축하여 고해상도 홍수대응 기술 및 GIS 및 모바일 시스템을 연계한 실시간 기후재해 예·경보가 가능할 것으로 사료된다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.5D
• /
• pp.739-746
• /
• 2006

The bus probe-based link travel times were more readily available due to bus' fixed route schedule and it was different from that of taxi-based one in its value for the same link. At the same time, the bus-based one showed less accurate information than the taxi-based link travel time, in terms of reliability expressed by 1-RMSE(%) measure. The purpose of this thesis is to develop a heuristic algorithm for mixing both sources-based link travel times. The algorithm used both real-time and historical profile travel times. Real-time source used 4 consecutive periods' average and historical source used average value of link travel time for various congestion levels. The algorithm was evaluated for Seoul urban arterial network 3 corridors and 20 links. The results based on the developed algorithm were superior than the mere fusion based link travel times and the reliability amounted up to 71.45%. Some limitation and future research agenda have also been discussed.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.459-461
• /
• 2022

One of the big differences between Network-on-Chip (NoC) and the existing parallel processing system based on an off-chip network is that data packet routing is performed using a centralized control scheme. In such an environment, the best-effort packet routing problem becomes a real-time assignment problem in which data packet arriving time and processing time is the cost. In this paper, the Hungarian algorithm, a representative computational complexity reduction algorithm for the linear algebraic equation of the allocation problem, is implemented in the form of a hardware accelerator. As a result of logic synthesis using the TSMC 0.18um standard cell library, the area of the circuit designed through case analysis for the cost distribution is reduced by about 16% and the propagation delay of it is reduced by about 52%, compared to the circuit implementing the original operation sequence of the Hungarian algorithm.