• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.387-387
• /
• 2022

기존 홍수기시 댐 운영은 예측 강우와 실시간 관측 강우를 이용하여 댐 운영 모형을 수행하며, 예측 결과에 따라 의사결정 및 댐 운영을 실시하게 된다. 하지만 이 과정에서 반복적인 분석이 필요하며, 댐 운영 모형 수행자의 경험에 따라 예측 결과가 달라져서 반복작업에 대한 자동화, 모형 수행자에 따라 달라지지 않는 예측 결과의 일반화가 필요한 상황이다. 이에 댐 운영 모형에 AI 기법을 적용하여, 다양한 강우 상황에 따른 자동 예측 및 모형 결과의 일반화를 구현하고자 하였다. 이를 위해 수자원 분야에 적용된 국내외 129개 연구논문에서 사용된 딥러닝 기법의 활용성을 분석하였으며, 다양한 수자원 분야 AI 적용 사례 중에서 댐 운영 예측 모형에 적용한 사례는 없었지만 유사한 분야로는 장기 저수지 운영 예측과 댐 상·하류 수위, 유량 예측이 있었다. 수자원의 시계열 자료 활용을 위해서는 Long-Short Term Memory(LSTM) 기법의 적용 활용성이 높은 것으로 분석되었다. 댐 운영 모형에서 AI 적용은 2개 분야에서 진행하였다. 기존 강우관측소의 관측 강우를 활용하여 강우의 패턴분석을 수행하는 과정과, 강우에서 댐 유입량 산정시 매개변수 최적화 분야에 적용하였다. 강우 패턴분석에서는 유사한 표본끼리 묶음을 생성하는 K-means 클러스터링 알고리즘과 시계열 데이터의 유사도 분석 방법인 Dynamic Time Warping을 결합하여 적용하였다. 강우 패턴분석을 통해서 지점별로 월별, 태풍 및 장마기간에 가장 많이 관측되었던 강우 패턴을 제시하며, 이를 모형에서 직접적으로 활용할 수 있도록 구성하였다. 강우에서 댐 유입량을 산정시 활용되는 매개변수 최적화를 위해서는 3층의 Multi-Layer LSTM 기법과 경사하강법을 적용하였다. 매개변수 최적화에 적용되는 매개변수는 중권역별 8개이며, 매개변수 최적화 과정을 통해 산정되는 결과물은 실측값과 오차가 제일 적은 유량(유입량)이 된다. 댐 운영 모형에 AI 기법을 적용한 결과 기존 반복작업에 대한 자동화는 이뤘으며, 댐 운영에 따른 상·하류 제약사항 표출 기능을 추가하여 의사결정에 소요되는 시간도 많이 줄일 수 있었다. 하지만, 매개변수 최적화 부분에서 기존 댐운영 모형에 적용되어 있는 고전적인 매개변수 추정기법보다 추정시간이 오래 소요되며, 매개변수 추정결과의 일반화가 이뤄지지 않아 이 부분에 대한 추가적인 연구가 필요하다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.1
• /
• pp.649-654
• /
• 2023

This paper proposes the design of a neural network structure search model using graph convolutional neural networks. Deep learning has a problem of not being able to verify whether the designed model has a structure with optimized performance due to the nature of learning as a black box. The neural network structure search model is composed of a recurrent neural network that creates a model and a convolutional neural network that is the generated network. Conventional neural network structure search models use recurrent neural networks, but in this paper, we propose GC-NAS, which uses graph convolutional neural networks instead of recurrent neural networks to create convolutional neural network models. The proposed GC-NAS uses the Layer Extraction Block to explore depth, and the Hyper Parameter Prediction Block to explore spatial and temporal information (hyper parameters) based on depth information in parallel. Therefore, since the depth information is reflected, the search area is wider, and the purpose of the search area of the model is clear by conducting a parallel search with depth information, so it is judged to be superior in theoretical structure compared to GC-NAS. GC-NAS is expected to solve the problem of the high-dimensional time axis and the range of spatial search of recurrent neural networks in the existing neural network structure search model through the graph convolutional neural network block and graph generation algorithm. In addition, we hope that the GC-NAS proposed in this paper will serve as an opportunity for active research on the application of graph convolutional neural networks to neural network structure search.

• Journal of the Korean Geotechnical Society
• /
• v.22 no.6
• /
• pp.15-26
• /
• 2006

Although numerous investigations have been performed over the years to predict the behavior and bearing capacity of piles, the mechanisms are not yet entirely understood. The prediction of bearing capacity is a difficult task, because large numbers of factors affect the capacity and also have complex relationship one another. Therefore, it is extremely difficult to search the essential factors among many factors, which are related with ground condition, pile type, driving condition and others, and then appropriately consider complicated relationship among the searched factors. The present paper describes the application of Artificial Neural Network (ANN) in predicting the capacity including its components at the tip and along the shaft from dynamic load test of the driven piles. Firstly, the effect of each factor on the value of bearing capacity is investigated on the basis of sensitivity analysis using ANN modeling. Secondly, the authors use the design methodology composed of ANN and genetic algorithm (GA) to find optimal neural network model to predict the bearing capacity. The authors allow this methodology to find the appropriate combination of input parameters, the number of hidden units and the transfer structure among the input, the hidden and the out layers. The results of this study indicate that the neural network model serves as a reliable and simple predictive tool for the bearing capacity of driven piles.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.119-125
• /
• 2023

IT infrastructure operation has advanced, and the methods for managing systems have become widely adopted. Recently, research has focused on improving system management using Syslog. However, utilizing log data collected through these methods presents challenges, as logs are extracted in various formats that require expert analysis. This paper proposes a system that utilizes edge computing to distribute the collection of Syslog data and preprocesses duplicate data before storing it in a central database. Additionally, the system constructs a data dictionary to classify and count data in real-time, with restrictions on transmitting registered data to the central database. This approach ensures the maintenance of predefined patterns in the data dictionary, controls duplicate data and temporal duplicates, and enables the storage of refined data in the central database, thereby securing fundamental data for big data analysis. The proposed algorithms and procedures are demonstrated through simulations and examples. Real syslog data, including extracted examples, is used to accurately extract necessary information from log data and verify the successful execution of the classification and storage processes. This system can serve as an efficient solution for collecting and managing log data in edge environments, offering potential benefits in terms of technology diffusion.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.104-123
• /
• 2022

Style transfer based on neural network provides very high quality results by reflecting the high level structural characteristics of images, and thereby has recently attracted great attention. This paper deals with the problem of resolution limitation due to GPU memory in performing such neural style transfer. We can expect that the gradient operation for style transfer based on partial image, with the aid of the fixed size of receptive field, can produce the same result as the gradient operation using the entire image. Based on this idea, each component of the style transfer loss function is analyzed in this paper to obtain the necessary conditions for partitioning and padding, and to identify, among the information required for gradient calculation, the one that depends on the entire input. By structuring such information for using it as auxiliary constant input for partition-based gradient calculation, this paper develops a recursive algorithm for super high-resolution image style transfer. Since the proposed method performs style transfer by partitioning input image into the size that a GPU can handle, it can perform style transfer without the limit of the input image resolution accompanied by the GPU memory size. With the aid of such super high-resolution support, the proposed method can provide a unique style characteristics of detailed area which can only be appreciated in super high-resolution style transfer.

• Journal of agriculture & life science
• /
• v.50 no.2
• /
• pp.175-185
• /
• 2016

In this study, manufactured experimental pig house (two pig house) and compared the changes in internal temperature and energy depending on the application of UTC control system for their utilizing of them as basic data for maintaining proper conditions for feeding environment and reducing heating energy depending on the UTC control system and program development, prior to applying the UTC system into pig house, representative agricultural facility. The control system ranges T1~T4 which is made to control a total of five output signals O1~O5 in the way of On/Off by using the algorithms of the program after measuring temperature scored 4 of total. Temperature setting was controlled with 28.0℃ in experimental pig house and 34.0℃ in UTC plenum, and output signal was controlled by comparing it with the measured temperature. During 3 days, the maximum temperature were measured at an average 31.8℃ when operated the control system in pig house. At the same time, the maximum temperature were measured 36.6℃ in comparison pig house, it was low temperature at 4.8℃ in experimental pig house than comparison pig house. Also, UTC plenum temperature was showed that rose at an average 50.5℃ by operation of the control program.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.6
• /
• pp.709-718
• /
• 2017

The installation of the elevator ARD(Automatic Rescue Device) system has been forced into law in these days in order to safely rescue passengers during power failure. The configuration of the ARD system consists of energy storage device, power converter and control systems. The EDLC(Electric Double Layer Capacitor) are used as energy storage device for rapid charge/discharge purposes. The power conditioning system (PCS) consists of bi-directional converter, 3-phase converter and control system. The dead-beat control system is adopted for most systems however it requires complex mathematical calculations, the high performance microprocessors are mandatory and thus it can be a cause of high manufacturing cost. In this paper the new control method for average current mode control is presented for simple structure. The control algorithm is applied to the single phase system and then expands to three phase system to meet the sysem requirements. The mathematical modeling using average modeling method is presented and analysed by PSIM computer simulation to verifie the validity of the proposed control methods.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.365-368
• /
• 2021

In this study, a plastic bottle recycling bin system that utilizes an infrared sensor was implemented. The proposed system consists of a recognition unit, a control unit, an alarm unit, and a driving unit. The recognition unit detects the plastic bottle, measures the distance between the plastic bottle and the infrared sensor, extracts the value of the bottle, compares the extracted value with a standard range, and then transmits the control value to the control unit if the extracted value of the bottle is outside the standard range. In this case, the result of the presence or absence of a brand label or bottle cap is transmitted to the controller. The control unit opens the entrance of the recycling bin or alerts the alarm unit according to the result value transmitted from the sensor unit. In order to implement the proposed system, the recognition unit was implemented with an infrared sensor, and the control unit was made with an Arduino IDE controller, based on the C programming language. Additionally, the recognition unit and the control unit are able to communicate using analog signals. The proposed system accurately judges the presence or absence of a brand label and bottle cap of plastic bottles according to a predetermined algorithm. It then blocks the entrance of the recycling bin when a brand label or bottle cap is still attached. As the amount of waste discharged per person is relatively high and the majority of such waste is incinerated rather than recycled, the system proposed in this study is expected to increase the recycling rate of plastic bottles.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.21 no.1
• /
• pp.105-122
• /
• 2022

According to the statistics about the fatal crashes that have occurred on the expressways for the last 5 years, those who died on the shoulders of the road has been as 3 times high as the others who died on the expressways. It suggests that the crashes on the shoulders of the road should be fatal, and that it would be important to prevent the traffic crashes by cracking down on the vehicles intruding the shoulders of the road. Therefore, this study proposed a method to detect a vehicle that violates the shoulder lane by using the Faster R-CNN. The vehicle was detected based on the Faster R-CNN, and an additional reading module was configured to determine whether there was a shoulder violation. For experiments and evaluations, GTAV, a simulation game that can reproduce situations similar to the real world, was used. 1,800 images of training data and 800 evaluation data were processed and generated, and the performance according to the change of the threshold value was measured in ZFNet and VGG16. As a result, the detection rate of ZFNet was 99.2% based on Threshold 0.8 and VGG16 93.9% based on Threshold 0.7, and the average detection speed for each model was 0.0468 seconds for ZFNet and 0.16 seconds for VGG16, so the detection rate of ZFNet was about 7% higher. The speed was also confirmed to be about 3.4 times faster. These results show that even in a relatively uncomplicated network, it is possible to detect a vehicle that violates the shoulder lane at a high speed without pre-processing the input image. It suggests that this algorithm can be used to detect violations of designated lanes if sufficient training datasets based on actual video data are obtained.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.42-42
• /
• 2022

지금까지도 유역에서의 녹조 모니터링은 현장채수를 통한 점 단위 모니터링에 크게 의존하고 있어 기후, 유속, 수온조건 등에 따라 수체에 광범위하게 발생하는 녹조를 효율적으로 모니터링하고 대응하기에는 어려운 점들이 있어왔다. 또한, 그동안 제한된 관측 데이터로 인해 현장 측정된 실측 데이터 보다는 녹조와 관련이 높은 NDVI, FGAI, SEI 등의 파생적인 지수를 산정하여 원격탐사자료와 매핑하는 방식의 분석연구 등이 선행되었다. 본 연구는 녹조의 모니터링시 정확도와 효율성을 향상을 목표로 하여, 우선은 녹조 측정장비를 활용, 7000개 이상의 녹조 관측 데이터를 확보하였으며, 이를 바탕으로 동기간의 고해상도 위성 자료와 실측자료를 매핑하기 위해 다양한Machine Learning기법을 적용함으로써 그 효과성을 검토하고자 하였다. 연구대상지는 낙동강 내성천 상류에 위치한 영주댐 유역으로서 데이터 수집단계에서는 면단위 현장(in-situ) 관측을 위해 2020년 2~9월까지 4회에 걸쳐 7291개의 녹조를 측정하고, 동일 시간 및 공간의 Sentinel-2자료 중 Band 1~12까지 총 13개(Band 8은 8과 8A로 2개)의 분광특성자료를 추출하였다. 다음으로 Machine Learning 분석기법의 적용을 위해 algae_monitoring Python library를 구축하였다. 개발된 library는 1) Training Set과 Test Set의 구분을 위한 Data 준비단계, 2) Random Forest, Gradient Boosting Regression, XGBoosting 알고리즘 중 선택하여 적용할 수 있는 모델적용단계, 3) 모델적용결과를 확인하는 Performance test단계(R², MSE, MAE, RMSE, NSE, KGE 등), 4) 모델결과의 Visualization단계, 5) 선정된 모델을 활용 위성자료를 녹조값으로 변환하는 적용단계로 구분하여 영주댐뿐만 아니라 다양한 유역에 범용적으로 적용할 수 있도록 구성하였다. 본 연구의 사례에서는 Sentinel-2위성의 12개 밴드, 기상자료(대기온도, 구름비율) 총 14개자료를 활용하여 Machine Learning기법 중 Random Forest를 적용하였을 경우에, 전반적으로 가장 높은 적합도를 나타내었으며, 적용결과 Test Set을 기준으로 NSE(Nash Sutcliffe Efficiency)가 0.96(Training Set의 경우에는 0.99) 수준의 성능을 나타내어, 광역적인 위성자료와 충분히 확보된 현장실측 자료간의 데이터 학습을 통해서 조류 모니터링 분석의 효율성이 획기적으로 증대될 수 있음을 확인하였다.