• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.131-131
• /
• 2021

Deep learning models, especially those based on long short-term memory (LSTM), have presented their superiority in addressing time series data issues recently. This study aims to comprehensively evaluate the performance of deep learning models that belong to the supervised learning category in streamflow prediction. Therefore, six deep learning models-standard LSTM, standard gated recurrent unit (GRU), stacked LSTM, bidirectional LSTM (BiLSTM), feed-forward neural network (FFNN), and convolutional neural network (CNN) models-were of interest in this study. The Red River system, one of the largest river basins in Vietnam, was adopted as a case study. In addition, deep learning models were designed to forecast flowrate for one- and two-day ahead at Son Tay hydrological station on the Red River using a series of observed flowrate data at seven hydrological stations on three major river branches of the Red River system-Thao River, Da River, and Lo River-as the input data for training, validation, and testing. The comparison results have indicated that the four LSTM-based models exhibit significantly better performance and maintain stability than the FFNN and CNN models. Moreover, LSTM-based models may reach impressive predictions even in the presence of upstream reservoirs and dams. In the case of the stacked LSTM and BiLSTM models, the complexity of these models is not accompanied by performance improvement because their respective performance is not higher than the two standard models (LSTM and GRU). As a result, we realized that in the context of hydrological forecasting problems, simple architectural models such as LSTM and GRU (with one hidden layer) are sufficient to produce highly reliable forecasts while minimizing computation time because of the sequential data nature.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.793-810
• /
• 2022

Synthetic Aperture Radar (SAR) is considered to be suitable for near real-time inundation monitoring. The distinctly different intensity between water and land makes it adequate for waterbody detection, but the intrinsic speckle noise and variable intensity of SAR images decrease the accuracy of waterbody detection. In this study, we suggest two modules, named 'morphology module' and 'edge-enhanced module', which are the combinations of pooling layers and convolutional layers, improving the accuracy of waterbody detection. The morphology module is composed of min-pooling layers and max-pooling layers, which shows the effect of morphological transformation. The edge-enhanced module is composed of convolution layers, which has the fixed weights of the traditional edge detection algorithm. After comparing the accuracy of various versions of each module for U-Net, we found that the optimal combination is the case that the morphology module of min-pooling and successive layers of min-pooling and max-pooling, and the edge-enhanced module of Scharr filter were the inputs of conv9. This morphologic and edge-enhanced U-Net improved the F1-score by 9.81% than the original U-Net. Qualitative inspection showed that our model has capability of detecting small-sized waterbody and detailed edge of water, which are the distinct advancement of the model presented in this research, compared to the original U-Net.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1047-1056
• /
• 2022

Sea ice, frozen sea water, in the Artic is a primary indicator of global warming. Due to its importance to the climate system, shipping-route navigation, and fisheries, Arctic sea ice prediction has gained increased attention in various disciplines. Recent advances in artificial intelligence (AI), motivated by a desire to develop more autonomous and efficient future predictions, have led to the development of new sea ice prediction models as alternatives to conventional numerical and statistical prediction models. This study aims to evaluate the performance of the two-stream convolutional long-and short-term memory (TS-ConvLSTM) AI model, which is designed for learning both global and local characteristics of the Arctic sea ice changes, for the minimum September Arctic sea ice from 2001 to 2021, and to show the possibility for an operational prediction system. Although the TS-ConvLSTM model generally increased the prediction performance as training data increased, predictability for the marginal ice zone, 5-50% concentration, showed a negative trend due to increasing first-year sea ice and warming. Additionally, a comparison of sea ice extent predicted by the TS-ConvLSTM with the median Sea Ice Outlooks (SIOs) submitted to the Sea Ice Prediction Network has been carried out. Unlike the TS-ConvLSTM, the median SIOs did not show notable improvements as time passed (i.e., the amount of training data increased). Although the TS-ConvLSTM model has shown the potential for the operational sea ice prediction system, learning more spatio-temporal patterns in the difficult-to-predict natural environment for the robust prediction system should be considered in future work.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1282-1290
• /
• 2017

Since the mitigation of fear of crime significantly enhances the consumptions in a city, studies focusing on urban safety analysis have received much attention as means of revitalizing the local economy. In addition, with the development of computer vision and machine learning technologies, efficient and automated analysis methods have been developed. Previous studies have used global features to predict the safety of cities, yet this method has limited ability in accurately predicting abstract information such as safety assessments. Therefore we used a Convolutional Context Neural Network (CCNN) that considered "context" as a decision criterion to accurately predict safety of cities. CCNN model is constructed by combining a stacked auto encoder with a fully connected network to find the context and use it in the CNN model to predict the score. We analyzed the RMSE and correlation of SVR, Alexnet, and Sharing models to compare with the performance of CCNN model. Our results indicate that our model has much better RMSE and Pearson/Spearman correlation coefficient.

• Journal of Advanced Research in Ocean Engineering
• /
• v.3 no.3
• /
• pp.136-148
• /
• 2017

The paper presents dual arm ROV manipulation using deep reinforcement learning. The purpose of this underwater manipulator is to investigate and excavate natural resources in ocean, finding lost aircraft blackboxes and for performing other extremely dangerous tasks without endangering humans. This research work emphasizes on a self-learning approach using Deep Reinforcement Learning (DRL). DRL technique allows ROV to learn the policy of performing manipulation task directly, from raw image data. Our proposed architecture maps the visual inputs (images) to control actions (output) and get reward after each action, which allows an agent to learn manipulation skill through trial and error method. We have trained our network in simulation. The raw images and rewards are directly provided by our simple Lua simulator. Our simulator achieve accuracy by considering underwater dynamic environmental conditions. Major goal of this research is to provide a smart self-learning way to achieve manipulation in highly dynamic underwater environment. The results showed that a dual robotic arm trained for a 3DOF movement successfully achieved target reaching task in a 2D space by considering real environmental factor.

• Journal of radiological science and technology
• /
• v.43 no.3
• /
• pp.195-208
• /
• 2020

Artificial intelligence(AI) is a field of computer science that is defined as allowing computers to imitate human intellectual behavior, even though AI's performance is to imitate humans. It is grafted across software-based fields with the advantages of high accuracy and speed of processing that surpasses humans. Indeed, the AI based technology has become a key technology in the medical field that will lead the development of medical image analysis. Therefore, this article introduces and discusses the concept of deep learning-based medical imaging analysis using the principle of algorithms for convolutional neural network(CNN) and back propagation. The research cases application of the AI based medical imaging analysis is used to classify the various disease(such as chest disease, coronary artery disease, and cerebrovascular disease), and the performance estimation comparing between AI based medical imaging classifier and human experts.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.476-478
• /
• 2018

현대 사회의 발전으로 인해 사람들의 삶의 질이 향상됨에 따라 사람들은 다양한 방식으로 자신 및 자신의 개성을 표출하려는 시도를 한다. 특히 IT 기술의 발전은 가상현실 및 3D 기술의 성장을 이끌어냈다. 본 논문은 다가올 4차 산업혁명에 발맞추어 사용자의 개성을 표출할 실용적이고 개성 있는 3D 모델링 아이디어를 제안하고자 한다. 스마트폰 사진 촬영과 동시에 사용자가 선택한 다른 캐릭터 사진과의 합성 사진을 Convolutional Neural Network (CNN)과 Generative Adversarial Network (GAN) 기반 딥러닝 기술을 통해 생성한다. 생성된 이미지는 사용자의 모습과 합성의 대상이 되는 캐릭터의 모습을 동시에 담고 있다. 본 연구의 결과물로 생성된 합성 사진을 3D 프린터를 이용하여 자신만의 모습이 담긴 굿즈를 생산 혹은 이모티콘을 생성하는 등 다양한 실용적인 응용분야에 적용 가능하다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.7
• /
• pp.3599-3619
• /
• 2019

In human activity recognition system both static and motion information play crucial role for efficient and competitive results. Most of the existing methods are insufficient to extract video features and unable to investigate the level of contribution of both (Static and Motion) components. Our work highlights this problem and proposes Static-Motion fused features descriptor (SMFD), which intelligently leverages both static and motion features in the form of descriptor. First, static features are learned by two-stream 3D convolutional neural network. Second, trajectories are extracted by tracking key points and only those trajectories have been selected which are located in central region of the original video frame in order to to reduce irrelevant background trajectories as well computational complexity. Then, shape and motion descriptors are obtained along with key points by using SIFT flow. Next, cholesky transformation is introduced to fuse static and motion feature vectors to guarantee the equal contribution of all descriptors. Finally, Long Short-Term Memory (LSTM) network is utilized to discover long-term temporal dependencies and final prediction. To confirm the effectiveness of the proposed approach, extensive experiments have been conducted on three well-known datasets i.e. UCF101, HMDB51 and YouTube. Findings shows that the resulting recognition system is on par with state-of-the-art methods.

• International Journal of Computer Science & Network Security
• /
• v.22 no.5
• /
• pp.73-78
• /
• 2022

The aim of this paper is to investigate the prevalence of Deep Learning in the literature on Fire & Rescue Service. It is found that deep learning techniques are only beginning to benefit the firefighters. The popular areas where deep learning techniques are making an impact are situational awareness, decision making, mental stress, injuries, well-being of the firefighter such as his sudden fall, inability to move and breathlessness, path planning by the firefighters while getting to an fire scene, wayfinding, tracking firefighters, firefighter physical fitness, employment, prediction of firefighter intervention, firefighter operations such as object recognition in smoky areas, firefighter efficacy, smart firefighting using edge computing, firefighting in teams, and firefighter clothing and safety. The techniques that were found applied in firefighting were Deep learning, Traditional K-Means clustering with engineered time and frequency domain features, Convolutional autoencoders, Long Short-Term Memory (LSTM), Deep Neural Networks, Simulation, VR, ANN, Deep Q Learning, Deep learning based on conditional generative adversarial networks, Decision Trees, Kalman Filters, Computational models, Partial Least Squares, Logistic Regression, Random Forest, Edge computing, C5 Decision Tree, Restricted Boltzmann Machine, Reinforcement Learning, and Recurrent LSTM. The literature review is centered on Firefighters/firemen not involved in wildland fires. The focus was also not on the fire itself. It must also be noted that several deep learning techniques such as CNN were mostly used in fire behavior, fire imaging and identification as well. Those papers that deal with fire behavior were also not part of this literature review.