• 한국측량학회지
• /
• 제37권3호
• /
• pp.199-208
• /
• 2019

운용 가능한 위성의 수가 증가하고 기술이 진보함에 따라 영상정보의 성과물이 다양해지고 많은 양의 자료가 축적되고 있다. 본 연구에서는 기구축된 영상정보를 활용하여 부족한 훈련자료의 문제를 극복하고 딥러닝(deep learning) 기법의 장점을 활용하고자 전이학습과 변화탐지 네트워크를 활용한 고해상도 위성영상의 변화탐지를 수행하였다. 본 연구에서 활용한 딥러닝 네트워크는 공간 및 분광 정보를 추출하는 합성곱 레이어(convolutional layer)와 시계열 정보를 분석하는 합성곱 장단기 메모리 레이어(convolutional long short term memory layer)로 구성되었으며, 고해상도 다중분광 영상에 최적화된 정보를 추출하기 위하여 커널(kernel)의 차원에 따른 정확도를 비교하였다. 또한, 학습된 커널 정보를 활용하기 위하여 변화탐지 네트워크의 초기 합성곱 레이어를 고해상도 항공영상인 ISPRS (International Society for Photogrammetry and Remote Sensing) 데이터셋에서 추출된 40,000개의 패치로 학습된 값으로 초기화하였다. 다시기 KOMPSAT-3A (KOrean Multi-Purpose SATllite-3A) 영상에 대한 실험 결과, 전이학습과 딥러닝 네트워크를 활용할 경우 기복 변위 및 그림자 등으로 인한 변화에 덜 민감하게 반응하며 분류 항목이 달라진 지역의 변화를 보다 효과적으로 추출할 수 있었으며, 2차원 커널보다 3차원 커널을 사용할 때 변화탐지의 정확도가 높았다. 3차원 커널은 공간 및 분광정보를 모두 고려하여 특징 맵(feature map)을 추출하기 때문에 고해상도 영상의 분류뿐만 아니라 변화탐지에도 효과적인 것을 확인하였다. 본 연구에서는 고해상도 위성영상의 변화탐지를 위한 전이학습과 딥러닝 기법의 활용 가능성을 제시하였으며, 추후 훈련된 변화탐지 네트워크를 새롭게 취득된 영상에 적용하는 연구를 수행하여 제안기법의 활용범위를 확장할 예정이다.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제10권3호
• /
• pp.91-98
• /
• 2021

오늘날 정보통신 기술이 급격하게 발달하면서 IT 인프라에서 보안의 중요성이 높아졌고 동시에 지능형 지속 공격(Advanced Persistent Threat)처럼 고도화되고 다양한 형태의 사이버 공격이 증가하고 있다. 점점 더 고도화되는 사이버 공격을 조기에 방어하거나 예측하는 것은 매우 중요한 사안으로, NIDS(Network-based Intrusion Detection System) 관련 데이터 분석만으로는 빠르게 변형하는 사이버 공격을 방어하지 못하는 경우가 많이 보고되고 있다. 따라서 현재는 HIDS(Host-based Intrusion Detection System) 데이터 분석을 통해서 위와 같은 사이버 공격을 방어하는데 침입 탐지 시스템에서 생성된 데이터를 이용하고 있다. 본 논문에서는 기존에 사용되었던 데이터 세트에서 결여된 스레드 정보, 메타 데이터 및 버퍼 데이터를 포함한 LID-DS(Leipzig Intrusion Detection-Data Set) 호스트 기반 침입 탐지 데이터를 이용하여 기계학습 알고리즘에 관한 비교 연구를 진행했다. 사용한 알고리즘은 Decision Tree, Naive Bayes, MLP(Multi-Layer Perceptron), Logistic Regression, LSTM(Long Short-Term Memory model), RNN(Recurrent Neural Network)을 사용했다. 평가를 위해 Accuracy, Precision, Recall, F1-Score 지표와 오류율을 측정했다. 그 결과 LSTM 알고리즘의 정확성이 가장 높았다.

• Journal of Information Processing Systems
• /
• 제19권5호
• /
• pp.688-701
• /
• 2023

The conventional methods of network intrusion detection system (NIDS) cannot measure the trend of intrusiondetection targets effectively, which lead to low detection accuracy. In this study, a NIDS method which based on a deep neural network in a big-data environment is proposed. Firstly, the entire framework of the NIDS model is constructed in two stages. Feature reduction and anomaly probability output are used at the core of the two stages. Subsequently, a convolutional neural network, which encompasses a down sampling layer and a characteristic extractor consist of a convolution layer, the correlation of inputs is realized by introducing bidirectional long short-term memory. Finally, after the convolution layer, a pooling layer is added to sample the required features according to different sampling rules, which promotes the overall performance of the NIDS model. The proposed NIDS method and three other methods are compared, and it is broken down under the conditions of the two databases through simulation experiments. The results demonstrate that the proposed model is superior to the other three methods of NIDS in two databases, in terms of precision, accuracy, F1- score, and recall, which are 91.64%, 93.35%, 92.25%, and 91.87%, respectively. The proposed algorithm is significant for improving the accuracy of NIDS.

• 한국지반신소재학회논문집
• /
• 제21권2호
• /
• pp.11-19
• /
• 2022

본 연구에서는 하수관거 내부에서 촬영된 균열 데이터를 활용하여 균열검출에 대한 시계열 예측 성능을 개선하기 위해 GoogleNet의 전이학습과 CNN- LSTM(Long Short-Term Memory) 결합 방법을 제안하였다. LSTM은 합성곱방법(CNN)의 장기의존성 문제를 해결할 수 있으며 공간 및 시간적 특징을 동시에 모델링 할 수 있다. 제안 방법의 성능을 검증하기 위해 하수관거 내부 균열 데이터를 활용하여 학습데이터, 초기학습률 및 최대 Epochs를 변화하면서 RMSE를 비교한 결과 모든 시험 구간에서 제안 방법의 예측 성능이 우수함을 알 수 있다. 또한 데이터가 발생하는 시점에 대한 예측 성능을 살펴본 결과 역시 제안방법이 우수하게 나타나 균열검출의 예측에서 제안 방법이 효율적인 것을 검증하였다. 기존 합성곱방법(CNN) 단독 모델과 비교함으로써 본 연구를 통해 확보된 제안 방법과 실험 결과를 활용할 경우 콘크리트 구조물의 균열데이터뿐만 아니라 시계열 데이터가 많이 발생하는 환경, 인문과학 등 다양한 영역에서 응용이 가능하다.

• 한국물환경학회지
• /
• 제39권1호
• /
• pp.46-60
• /
• 2023

Climate change causes fluctuations in water quality in the aquatic environment, which can cause changes in water circulation patterns and severe adverse effects on aquatic ecosystems in the future. Therefore, research is needed to predict and respond to water quality changes caused by climate change in advance. In this study, we tried to predict the dissolved oxygen (DO), chlorophyll-a, and turbidity of the Paldang reservoir for about two weeks using long short-term memory (LSTM) and gated recurrent units (GRU), which are deep learning algorithms based on recurrent neural networks. The model was built based on real-time water quality data and meteorological data. The observation period was set from July to September in the summer of 2021 (Period 1) and from March to May in the spring of 2022 (Period 2). We tried to select an algorithm with optimal predictive power for each water quality parameter. In addition, to improve the predictive power of the model, an important variable extraction technique using random forest was used to select only the important variables as input variables. In both Periods 1 and 2, the predictive power after extracting important variables was further improved. Except for DO in Period 2, GRU was selected as the best model in all water quality parameters. This methodology can be useful for preventive water quality management by identifying the variability of water quality in advance and predicting water quality in a short period.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1419-1436
• /
• 2020

For an energy harvesting sensor network, when the network lifetime is not the only primary goal, maximizing the network performance under environmental energy harvesting becomes a more critical issue. However, clustering protocols that aim at providing maximum information throughput have not been thoroughly explored in Energy Harvesting Wireless Sensor Networks (EH-WSNs). In this paper, clustering protocols are studied for maximizing the data transmission in the whole network. Based on a long short-term memory (LSTM) energy predictor and node energy consumption and supplement models, an uneven clustering protocol is proposed where the cluster head selection and cluster size control are thoroughly designed for this purpose. Simulations and results verify that the proposed scheme can outperform some classic schemes by having more data packets received by the cluster heads (CHs) and the base station (BS) under these energy constraints. The outcomes of this paper also provide some insights for choosing clustering routing protocols in EH-WSNs, by exploiting the factors such as uneven clustering size, number of clusters, multiple CHs, multihop routing strategy, and energy supplementing period.

• 농업과학연구
• /
• 제46권4호
• /
• pp.843-856
• /
• 2019

Real-time flood prediction has an important role in significantly reducing potential damage caused by floods for urban residential areas located downstream of river basins. This paper presents an effective approach for flood forecasting based on the construction of a deep neural network (DNN) model. In addition, this research depends closely on the open-source software library, TensorFlow, which was developed by Google for machine and deep learning applications and research. The proposed model was applied to forecast the flowrate one, two, and three days in advance at the Son Tay hydrological station on the Red River, Vietnam. The input data of the model was a series of discharge data observed at five gauge stations on the Red River system, without requiring rainfall data, water levels and topographic characteristics. The research results indicate that the DNN model achieved a high performance for flood forecasting even though only a modest amount of data is required. When forecasting one and two days in advance, the Nash-Sutcliffe Efficiency (NSE) reached 0.993 and 0.938, respectively. The findings of this study suggest that the DNN model can be used to construct a real-time flood warning system on the Red River and for other river basins in Vietnam.

• Computers and Concrete
• /
• 제24권6호
• /
• pp.555-560
• /
• 2019

During the application of shotcrete, a part of the concrete bounces back after hitting to the surface, the reinforcement or previously sprayed concrete. This rebound material is definitely not added to the mixture and considered as waste. In this study, a deep neural network model was developed to predict the rebound material during shotcrete application. The factors affecting rebound and the datasets of these parameters were obtained from previous experiments. The Long Short-Term Memory (LSTM) architecture of the proposed deep neural network model was used in accordance with this data set. In the development of the proposed four-tier prediction model, the dataset was divided into 90% training and 10% test. The deep neural network was modeled with 11 dependents 1 independent data by determining the most appropriate hyper parameter values for prediction. Accuracy and error performance in success performance of LSTM model were evaluated over MSE and RMSE. A success of 93.2% was achieved at the end of training of the model and a success of 85.6% in the test. There was a difference of 7.6% between training and test. In the following stage, it is aimed to increase the success rate of the model by increasing the number of data in the data set with synthetic and experimental data. In addition, it is thought that prediction of the amount of rebound during dry-mix shotcrete application will provide economic gain as well as contributing to environmental protection.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2018년도 학술발표회
• /
• pp.147-147
• /
• 2018

In this article, we use an open source software library: TensorFlow, developed for the purposes of conducting very complex machine learning and deep neural network applications. However, the system is general enough to be applicable in a wide variety of other domains as well. The proposed model based on a deep neural network model, LSTM (Long Short-Term Memory) to predict the river water level at Okcheon Station of the Guem River without utilization of rainfall - forecast information. For LSTM modeling, the input data is hourly water level data for 15 years from 2002 to 2016 at 4 stations includes 3 upstream stations (Sutong, Hotan, and Songcheon) and the forecasting-target station (Okcheon). The data are subdivided into three purposes: a training data set, a testing data set and a validation data set. The model was formulated to predict Okcheon Station water level for many cases from 3 hours to 12 hours of lead time. Although the model does not require many input data such as climate, geography, land-use for rainfall-runoff simulation, the prediction is very stable and reliable up to 9 hours of lead time with the Nash - Sutcliffe efficiency (NSE) is higher than 0.90 and the root mean square error (RMSE) is lower than 12cm. The result indicated that the method is able to produce the river water level time series and be applicable to the practical flood forecasting instead of hydrologic modeling approaches.

• ETRI Journal
• /
• 제41권3호
• /
• pp.371-382
• /
• 2019

Machine reading comprehension is the task of understanding a given context and finding the correct response in that context. A simple recurrent unit (SRU) is a model that solves the vanishing gradient problem in a recurrent neural network (RNN) using a neural gate, such as a gated recurrent unit (GRU) and long short-term memory (LSTM); moreover, it removes the previous hidden state from the input gate to improve the speed compared to GRU and LSTM. A self-matching network, used in R-Net, can have a similar effect to coreference resolution because the self-matching network can obtain context information of a similar meaning by calculating the attention weight for its own RNN sequence. In this paper, we construct a dataset for Korean machine reading comprehension and propose an $S^2-Net$ model that adds a self-matching layer to an encoder RNN using multilayer SRU. The experimental results show that the proposed $S^2-Net$ model has performance of single 68.82% EM and 81.25% F1, and ensemble 70.81% EM, 82.48% F1 in the Korean machine reading comprehension test dataset, and has single 71.30% EM and 80.37% F1 and ensemble 73.29% EM and 81.54% F1 performance in the SQuAD dev dataset.