• Journal of Korean Society of Water and Wastewater
• /
• v.35 no.1
• /
• pp.83-91
• /
• 2021

The increased turbidity in rivers during flood events has various effects on water environmental management, including drinking water supply systems. Thus, prediction of turbid water is essential for water environmental management. Recently, various advanced machine learning algorithms have been increasingly used in water environmental management. Ensemble machine learning algorithms such as random forest (RF) and gradient boosting decision tree (GBDT) are some of the most popular machine learning algorithms used for water environmental management, along with deep learning algorithms such as recurrent neural networks. In this study GBDT, an ensemble machine learning algorithm, and gated recurrent unit (GRU), a recurrent neural networks algorithm, are used for model development to predict turbidity in a river. The observation frequencies of input data used for the model were 2, 4, 8, 24, 48, 120 and 168 h. The root-mean-square error-observations standard deviation ratio (RSR) of GRU and GBDT ranges between 0.182~0.766 and 0.400~0.683, respectively. Both models show similar prediction accuracy with RSR of 0.682 for GRU and 0.683 for GBDT. The GRU shows better prediction accuracy when the observation frequency is relatively short (i.e., 2, 4, and 8 h) where GBDT shows better prediction accuracy when the observation frequency is relatively long (i.e. 48, 120, 160 h). The results suggest that the characteristics of input data should be considered to develop an appropriate model to predict turbidity.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.11
• /
• pp.1500-1506
• /
• 2020

In this paper, we study a scheduling problem based on reinforcement learning for overlay device-to-device (D2D) communication networks. Even though various technologies for D2D communication networks using Q-learning, which is one of reinforcement learning models, have been studied, Q-learning causes a tremendous complexity as the number of states and actions increases. In order to solve this problem, D2D communication technologies based on Deep Q Network (DQN) have been studied. In this paper, we thus design a DQN model by considering the characteristics of wireless communication systems, and propose a distributed scheduling scheme based on the DQN model that can reduce feedback and signaling overhead. The proposed model trains all parameters in a centralized manner, and transfers the final trained parameters to all mobiles. All mobiles individually determine their actions by using the transferred parameters. We analyze the performance of the proposed scheme by computer simulation and compare it with optimal scheme, opportunistic selection scheme and full transmission scheme.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.195-206
• /
• 2022

Crack detection is essential for inspection of existing structures and crack segmentation based on deep learning is a significant solution. However, datasets are usually one of the key issues. When building a new dataset for deep learning, laborious and time-consuming annotation of a large number of crack images is an obstacle. The aim of this study is to develop an approach that can automatically select a small portion of the most informative crack images from a large pool in order to annotate them, not to label all crack images. An active learning method with difficulty learning mechanism for crack segmentation tasks is proposed. Experiments are carried out on a crack image dataset of a steel box girder, which contains 500 images of 320×320 size for training, 100 for validation, and 190 for testing. In active learning experiments, the 500 images for training are acted as unlabeled image. The acquisition function in our method is compared with traditional acquisition functions, i.e., Query-By-Committee (QBC), Entropy, and Core-set. Further, comparisons are made on four common segmentation networks: U-Net, DeepLabV3, Feature Pyramid Network (FPN), and PSPNet. The results show that when training occurs with 200 (40%) of the most informative crack images that are selected by our method, the four segmentation networks can achieve 92%-95% of the obtained performance when training takes place with 500 (100%) crack images. The acquisition function in our method shows more accurate measurements of informativeness for unlabeled crack images compared to the four traditional acquisition functions at most active learning stages. Our method can select the most informative images for annotation from many unlabeled crack images automatically and accurately. Additionally, the dataset built after selecting 40% of all crack images can support crack segmentation networks that perform more than 92% when all the images are used.

• Journal of the Korean Institute of Educational Facilities
• /
• v.25 no.6
• /
• pp.35-44
• /
• 2018

The purpose of this study is to predict more accurate construction costs and to support efficient decision making in the planning and design stages of smart education facilities. The higher the error in the projected cost, the more risk a project manager takes. If the manager can predict a more accurate construction cost in the early stages of a project, he/she can secure a decision period and support a more rational decision. During the planning and design stages, there is a limited amount of variables that can be selected for the estimating model. Moreover, since the number of completed smart schools is limited, there is little data. In this study, various artificial intelligence models were used to accurately predict the construction cost in the planning and design phase with limited variables and lack of performance data. A theoretical study on an artificial neural network and deep learning was carried out. As the artificial neural network has frequent problems of overfitting, it is found that there is a problem in practical application. In order to overcome the problem, this study suggests that the improved models of Deep Neural Network and Deep Belief Network are more effective in making accurate predictions. Deep Neural Network (DNN) and Deep Belief Network (DBN) models were constructed for the prediction of construction cost. Average Error Rate and Root Mean Square Error (RMSE) were calculated to compare the error and accuracy of those models. This study proposes a cost prediction model that can be used practically in the planning and design stages.

• Electronics and Telecommunications Trends
• /
• v.35 no.4
• /
• pp.81-90
• /
• 2020

The use of machine learning technologies such as deep and reinforcement learning has proliferated in various domains with the advancement of deep neural network studies. To make the learning successful, both big data acquisition and fast processing are required. However, for some physical world applications such as autonomous drone flight, it is difficult to achieve efficient learning because learning with a premature A.I. is dangerous, cost-ineffective, and time-consuming. To solve these problems, simulation-based approaches can be considered. In this study, we analyze recent trends in drone simulation technologies and compare their features. Subsequently, we introduce Octopus, which is a highly precise and scalable drone simulator being developed by ETRI.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.750-759
• /
• 2019

Presently, the extraction of hand-crafted features is still the dominant method in radar emitter recognition. To solve the complicated problems of selection and updation of empirical features, we present a novel automatic feature extraction structure based on deep learning. In particular, a convolutional neural network (CNN) is adopted to extract high-level abstract representations from the time-frequency images of emitter signals. Thus, the redundant process of designing discriminative features can be avoided. Furthermore, to address the performance degradation of a single platform, we propose the construction of an ensemble learning-based architecture for multi-platform fusion recognition. Experimental results indicate that the proposed algorithms are feasible and effective, and they outperform other typical feature extraction and fusion recognition methods in terms of accuracy. Moreover, the proposed structure could be extended to other prevalent ensemble learning alternatives.

• Journal of KIBIM
• /
• v.9 no.1
• /
• pp.22-31
• /
• 2019

In this paper, we construct a prototype model for city data prediction by using time series data of floating population, and use machine learning to analyze urban data of complex structure. A correlation prediction model was constructed using three of the 10 data (total flow population, male flow population, and Monday flow population), and the result was compared with the actual data. The results of the accuracy were evaluated. The results of this study show that the predicted model of the floating population predicts the correlation between the predicted floating population and the current state of commerce. It is expected that it will help efficient and objective design in the planning stages of architecture, landscape, and urban areas such as tree environment design and layout of trails. Also, it is expected that the dynamic population prediction using multivariate time series data and collected location data will be able to perform integrated simulation with time series data of various fields.

• Transactions of Materials Processing
• /
• v.30 no.4
• /
• pp.186-194
• /
• 2021

Finite element simulation is a widely applied method for practical purpose in various metal forming process. However, in the simulation of elasto-plastic behavior of porous material or in crystal plasticity coupled multi-scale simulation, it requires much calculation time, which is a limitation in its application in practical situations. A machine learning model that directly outputs the constitutive equation without iterative calculations would greatly reduce the calculation time of the simulation. In this study, we examined the possibility of artificial intelligence based constitutive equation with the input of existing state variables and current velocity filed. To introduce the methodology, we described the process of obtaining the training data, machine learning process and the coupling of machine learning model with commercial software DEFROM^TM, as a preliminary study, via rigid plastic finite element simulation.

• Journal of Semiconductor Engineering
• /
• v.2 no.1
• /
• pp.125-129
• /
• 2021

As the interest of deep learning, techniques to control the color of images in image processing field are evolving together. However, there is no clear standard for color, and it is not easy to find a way to represent only the color itself like the color-palette. In this paper, we propose a novel color palette extraction system by chroma fine-tuning with reinforcement learning. It helps to recognize the color combination to represent an input image. First, we use RGBY images to create feature maps by transferring the backbone network with well-trained model-weight which is verified at super resolution convolutional neural networks. Second, feature maps are trained to 3 fully connected layers for the color-palette generation with a generative adversarial network (GAN). Third, we use the reinforcement learning method which only changes chroma information of the GAN-output by slightly moving each Y component of YCbCr color gamut of pixel values up and down. The proposed method outperforms existing color palette extraction methods as given the accuracy of 0.9140.

• Journal of IKEEE
• /
• v.25 no.4
• /
• pp.728-734
• /
• 2021

In recent years, there has been a strong interest in the end-to-end autonomous driving based on deep reinforcement learning. In this paper, we present a reward function of latent SAC deep reinforcement learning to improve the longitudinal driving performance of an agent vehicle. While the existing reward function significantly degrades the driving safety and efficiency, the proposed reward function is shown to maintain an appropriate headway distance while avoiding the front vehicle collision.