• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.89-89
• /
• 2019

수환경으로 유출되는 유해화학물질은 독성을 가지고 직접 유출되거나 다양한 매체와 반응하여 화재 및 폭발 등의 사고가 발생한다. 실제로 낙동강 유역에서는 1991년 페놀 유출사고를 시작으로 2009년 구미공단 '1,4-다이옥산' 유출사고, 2014년 11월 경북 봉화군의 황산유출사고 등 크고 작은 사고가 빈번히 발생하고 있으며 작년 6월에는 대구와 부산의 수돗물에서 과불화화합물이 검출되기도 하였다. 이러한 대규모 사고를 방지하기 위해 신속한 오염물의 거동 예측이 가능한 추적모델이 필요하며, 본 연구에서는 수환경으로 유출된 유해화학물질의 추적을 위한 1차원 저장대 모형을 개발하였다. 일반적으로 저장대 모형은 복잡한 하천 구조를 하천의 주 흐름이 존재하는 본류대와 하천 흐름이 정체되는 저장대, 그리고 하상구조로 단순화 하여 나타낸다. 본류대에서는 하천흐름에 의한 이송 및 횡방향 유속차로 발생하는 전단류에 의한 확산이 일어나며, 저장대와의 물질교환으로 발생하는 저장효과와, 하상구조와의 흡착 및 탈착, 그리고 생물화학적 반응 및 휘발이 발생한다고 가정한다. 본류대와 저장대간의 질량교환은 난류유속변동과 농도차에 의해서만 발생한다고 가정하고 오염물질의 이송과 분산과정을 해석한다. 저장대에서는 이송 및 전단류에 의한 확산은 일어나지 않으며, 본류대와의 물질교환으로 발생하는 저장효과와 하상구조로의 흡착, 그리고 생물화학적 반응 및 휘발이 발생한다고 가정하며, 하상구조에서는 본류대 및 저장대와의 흡착 및 탈착만 발생한다고 가정한다. 저장대 모형의 해석을 위해서는 리치(Reach) 별로 본류대 분산계수($K_F$), 본류대 면적($A_F$), 저장대 면적($A_S$), 그리고 저장대 교환계수(${\alpha}$)의 네 가지 저장대 매개변수가 필요하며 본 연구에서 개발된 저장대 모형은 흡탈착, 생물화학적 반응 및 휘발 과정을 모두 고려하여 유해화학물질의 확산 거동을 모의한다. 최적의 리치길이, 흡탈착, 반응 및 휘발 계수를 산정하여 모형의 정확도를 향상시켰으며, 신속하고 정확하게 오염물의 거동을 예측할 수 있었다.

• Journal of the Korean Society of Radiology
• /
• v.12 no.7
• /
• pp.919-927
• /
• 2018

The purpose of this study was to present simulation training model for general X-ray examinations and to analyze the errors that occur during the simulation training. From 2012 to 2018, a total of 183 students (77 men and 106 women) participated. The simulated X-ray system used computed radiography (CR) system. The contents of simulation training were patient's care, X-ray examinations accuracy, images stability, etc. As a result, it were found that the patient's position setting error, the accuracy error of the X-ray beam central ray, the image receptor's size and setting error, the error of the grid use, the marking error, and the error of X-ray exposure technical factors. It is expected that improved practical general X-ray examinations training of radiographer will be needed, focusing on these errors, so that we could contribute to the health care of the people by providing precise examinations and high quality medical service.

• Convergence Security Journal
• /
• v.19 no.1
• /
• pp.11-17
• /
• 2019

Recently, the abuse of Internet technology has caused economic and mental harm to society as a whole. Especially, malicious code that is newly created or modified is used as a basic means of various application hacking and cyber security threats by bypassing the existing information protection system. However, research on small-capacity executable files that occupy a large portion of actual malicious code is rather limited. In this paper, we propose a model that can analyze the characteristics of known small capacity executable files by using data mining techniques and to use them for detecting unknown malicious codes. Data mining analysis techniques were performed in various ways such as Naive Bayesian, SVM, decision tree, random forest, artificial neural network, and the accuracy was compared according to the detection level of virustotal. As a result, more than 80% classification accuracy was verified for 34,646 analysis files.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.18 no.5
• /
• pp.112-125
• /
• 2019

An acoustic signal-based, tunnel-incident detection system was developed and evaluated. The system was comprised of three components: algorithm, acoustic signal collector, and server system. The algorithm, which was based on nonnegative tensor factorization and a hidden Markov model, processes the acoustic signals to attenuate noise and detect incident-related signals. The acoustic signal collector gathers the tunnel sounds, digitalizes them, and transmits the digitalized acoustic signals to the center server. The server system issues an alert once the algorithm identifies an incident. The performance of the system was evaluated thoroughly in two steps: first, in a controlled tunnel environment using the recorded incident sounds, and second, in an uncontrolled tunnel environment using real-world incident sounds. As a result, the detection rates ranged from 80 to 95% at distances from 50 to 10 m in the controlled environment, and 94 % in the uncontrolled environment. The superiority of the developed system to the existing video image and loop detector-based systems lies in its instantaneous detection capability with less than 2 s.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.29-35
• /
• 2019

As the fourth industrial revolution is emerging, many companies are increasingly interested in smart factories and the importance of sensors is being emphasized. In the case that sensors for collecting sensing data fail, the plant could not be optimized and further it could not be operated properly, which may incur a financial loss. For this purpose, it is necessary to diagnose the status of sensors to prevent sensor' fault. In the paper, we propose a scheme to diagnose digital-sensor' fault by analyzing the rising time and falling time of digital sensors through the LSTM(Long Short Term Memory) of Deep Learning RNN algorithm. Experimental results of the proposed scheme are compared with those of rule-based fault diagnosis algorithm in terms of AUC(Area Under the Curve) of accuracy and ROC(Receiver Operating Characteristic) curve. Experimental results show that the proposed system has better and more stable performance than the rule-based fault diagnosis algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1341-1347
• /
• 2020

Legacy studies for classifying arrhythmia have been studied in order to improve the accuracy of classification, Neural Network, Fuzzy, Machine Learning, etc. In particular, deep learning is most frequently used for arrhythmia classification using error backpropagation algorithm by solving the limit of hidden layer number, which is a problem of neural network. In order to apply a deep learning model to an ECG signal, it is necessary to select an optimal model and parameters. In this paper, we propose parameter extraction based on AR and arrhythmia classification through a deep learning. For this purpose, the R-wave is detected in the ECG signal from which noise has been removed, QRS and RR interval is modelled. And then, the weights were learned by supervised learning method through deep learning and the model was evaluated by the verification data. The classification rate of PVC is evaluated through MIT-BIH arrhythmia database. The achieved scores indicate arrhythmia classification rate of over 97%.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1141-1147
• /
• 2020

The hornet species are so similar in shape that they are difficult for non-experts to classify, and because the size of the objects is small and move fast, it is more difficult to detect and classify the species in real time. In this paper, we developed a system that classifies hornets species in real time based on a deep learning algorithm using a boundary box. In order to minimize the background area included in the bounding box when labeling the training image, we propose a method of selecting only the head and body of the hornet. It also experimentally compares existing boundary box-based object recognition algorithms to find the best algorithms that can detect wasps in real time and classify their species. As a result of the experiment, when the mish function was applied as the activation function of the convolution layer and the hornet images were tested using the YOLOv4 model with the Spatial Attention Module (SAM) applied before the object detection block, the average precision was 97.89% and the average recall was 98.69%.

• Journal of the Institute of Convergence Signal Processing
• /
• v.21 no.3
• /
• pp.121-126
• /
• 2020

Sound-based machine fault diagnosis is the automatic detection of abnormal sound in the acoustic emission signals of the machines. Conventional methods of using mathematical models were difficult to diagnose machine failure due to the complexity of the industry machinery system and the existence of nonlinear factors such as noises. Therefore, we want to solve the problem of machine fault diagnosis as a deep learning-based image classification problem. In the paper, we propose a CNN-based automatic machine fault diagnosis method using Spectrogram images. The proposed method uses STFT to effectively extract feature vectors from frequencies generated by machine defects, and the feature vectors detected by STFT were converted into spectrogram images and classified by CNN by machine status. The results show that the proposed method can be effectively used not only to detect defects but also to various automatic diagnosis system based on sound.

• Journal of Platform Technology
• /
• v.9 no.4
• /
• pp.3-9
• /
• 2021

In this paper, a graph data model is introduced to effectively recognize the situation between each object on the road detected by vehicles or road infrastructure sensors. The proposed method builds a graph database by modeling each object on the road as a node of the graph and the relationship between objects as an edge of the graph, and updates object properties and edge properties in real time. In this case, the relationship between objects represented as edges is set when there is a possibility of approach between objects in consideration of the position, direction, and speed of each object. Finally, we propose a spatial indexing technique for graph nodes and edges to update the road object graph database represented through the proposed graph modeling method continuously in real time. To show the superiority of the proposed indexing technique, we compare the proposed indexing based database update method to the non-indexing update method through simulation. The results of the simulation show the proposed method outperforms more than 10 times to the non-indexing method.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.859-864
• /
• 2022

Drowsy driving, one of the biggest causes of traffic accidents every year, is accompanied by various factors. As a general method to check whether or not there is drowsiness, a method of identifying a driver's expression and driving pattern, and a method of analyzing bio-signals are being studied. This paper proposes a driver fatigue detection system using deep learning technology and bio-signal measurement technology. As the first step in the proposed method, deep learning is used to detect the driver's eye shape, yawning presence, and body movement to detect drowsiness. In the second stage, it was designed to increase the accuracy of the system by identifying the driver's fatigue state using the pulse wave signal and body temperature. As a result of the experiment, it was possible to reliably determine the driver's drowsiness and fatigue in real-time images.