• Journal of Advanced Navigation Technology
• /
• v.22 no.5
• /
• pp.478-484
• /
• 2018

This study predicts solar radiation, solar radiation, and solar power generation using hourly weather data such as temperature, precipitation, wind direction, wind speed, humidity, cloudiness, sunshine and solar radiation. I/O pattern in supervised learning is the most important factor in prediction, but it must be determined by repeated experiments because humans have to decide. This study proposed four input and output patterns for solar and sunrise prediction. In addition, we predicted solar power generation using the predicted solar and solar radiation data and power generation data of Youngam solar power plant in Jeollanamdo. As a experiment result, the model 4 showed the best prediction results in the sunshine and solar radiation prediction, and the RMSE of sunshine was 1.5 times and the sunshine RMSE was 3 times less than that of model 1. As a experiment result of solar power generation prediction, the best prediction result was obtained for model 4 as well as sunshine and solar radiation, and the RMSE was reduced by 2.7 times less than that of model 1.

• Journal of Broadcast Engineering
• /
• v.25 no.1
• /
• pp.83-93
• /
• 2020

With the rapid increase of vehicles, various traffic problems, e.g., car crashes, traffic congestions, etc, frequently occur in the road environment of the urban area. To overcome such traffic problems, intelligent transportation systems have been developed with a traffic flow analysis. The traffic flow, which can be estimated by the vehicle counting scheme, plays an important role to manage and control the urban traffic. In this paper, we propose a novel vehicle counting method based on predicted centers of each lane. Specifically, the centers of each lane are detected by using the accumulated movement of vehicles and its filtered responses. The number of vehicles, which pass through extracted centers, is counted by checking the closest trajectories of the corresponding vehicles. Various experimental results on road CCTV videos demonstrate that the proposed method is effective for vehicle counting.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.776-788
• /
• 2020

In this paper, a vehicle type recognition system using deep learning and a license plate recognition system are proposed. In the existing system, the number plate area extraction through image processing and the character recognition method using DNN were used. These systems have the problem of declining recognition rates as the environment changes. Therefore, the proposed system used the one-stage object detection method YOLO v3, focusing on real-time detection and decreasing accuracy due to environmental changes, enabling real-time vehicle type and license plate character recognition with one RGB camera. Training data consists of actual data for vehicle type recognition and license plate area detection, and synthetic data for license plate character recognition. The accuracy of each module was 96.39% for detection of car model, 99.94% for detection of license plates, and 79.06% for recognition of license plates. In addition, accuracy was measured using YOLO v3 tiny, a lightweight network of YOLO v3.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.3
• /
• pp.525-532
• /
• 2013

Recently. smartphones have been popularized rapidly and now located deep in our daily life, providing a variety of services from banking, SNS (Social Network Service), and entertainment to smart-work mobile office through apps. Such smartphone apps can be easily downloaded from what is known as app store which, however, bears many security issues as software developers can just as easily upload to it. Military apps will be exposed to a myriad of security threats if distributed through internet-basis commercial app store. In order to mitigate such security concerns, this paper suggests a security guidelines for establishing a military-excusive app store and security verification system which prevent the security hazards that can occur during the process of development and distribution of military-use mobile apps.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.5
• /
• pp.592-601
• /
• 2016

The recurrent neural network (RNN) is a deep learning model which is suitable to sequential or length-variable data. The Long Short-Term Memory (LSTM) mitigates the vanishing gradient problem of RNNs so that LSTM can maintain the long-term dependency among the constituents of the given input sequence. In this paper, we propose a LSTM based language model which can predict following words of a given incomplete sentence to generate a complete sentence. To evaluate our method, we trained our model using multiple Korean corpora then generated the incomplete part of Korean sentences. The result shows that our language model was able to generate the fluent Korean sentences. We also show that the word based model generated better sentences compared to the other settings.

• KIPS Transactions on Computer and Communication Systems
• /
• v.9 no.1
• /
• pp.9-16
• /
• 2020

The k-anonymity scheme has been widely used to protect private information when Big Data are distributed to a third party for research purposes. When the scheme is applied, an optimal k value determination is one of difficult problems to be resolved because many factors should be considered. Currently, the determination has been done almost manually by human experts with their intuition. This leads to degrade performance of the anonymization, and it takes much time and cost for them to do a task. To overcome this problem, a simple idea has been proposed that is based on machine learning. This paper describes implementations and experiments to realize the proposed idea. In thi work, a deep neural network (DNN) is implemented using tensorflow libraries, and it is trained and tested using input dataset. The experiment results show that a trend of training errors follows a typical pattern in DNN, but for validation errors, our model represents a different pattern from one shown in typical training process. The advantage of the proposed approach is that it can reduce time and cost for experts to determine k value because it can be done semi-automatically.

• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.137-148
• /
• 2017

Researches on the Artificial Intelligence has been explosively activated in various fields since the advent of AlphaGo. Particularly, researchers on the application of multi-layer neural network such as deep learning, and various machine learning algorithms are being focused actively. In this paper, we described a development of an artificial intelligence Janggi game based on reinforcement learning algorithm and MCTS (Monte Carlo Tree Search) algorithm with accumulated game data. The previous artificial intelligence games are mostly developed based on mini-max algorithm, which depends only on the results of the tree search algorithms. They cannot use of the real data from the games experts, nor cannot enhance the performance by learning. In this paper, we suggest our approach to overcome those limitations as follows. First, we collects Janggi expert's game data, which can reflect abundant real game results. Second, we create a graph structure by using the game data, which can remove redundant movement. And third, we apply the reinforcement learning algorithm and MCTS algorithm to select the best next move. In addition, the learned graph is stored by object serialization method to provide continuity of the game. The experiment of this study is done with two different types as follows. First, our system is confronted with other AI based system that is currently being served on the internet. Second, our system confronted with some Janggi experts who have winning records of more than 50%. Experimental results show that the rate of our system is significantly higher.

• Korean System Dynamics Review
• /
• v.14 no.3
• /
• pp.25-49
• /
• 2013

As global competition for green car, that is environmentally friendly car, is getting tougher, the governments and the related industries are putting their core efforts in its diffusion. However, the green car sales are disappointing so far. To overcome the gridlock, it is necessary to develop concrete analytical framework to understand the diffusion process. Based on causal loop analysis from the previous work, we have identified main variables and relationships of them in the diffusion process and developed a stock-flow diagram and mathematical formula for the main components. The model would be applied for further quantitative simulation on the diffusion process of green car and other innovative goods as well. Also, we have suggested constructive insights for the policy makers and for the related industries. First, it is important to increase consumers' willingness to consider through marketing and word of mouth to accelerate the diffusion process. Second, in the perspective of the industry, the market share of green car should be increased at the earliest possible stage and this could be done by enhancing each components of green car attractiveness(e.g. price, driving range, social infra). Third, companies should develop a balanced investment between consumer and technology sector through a flexible financial policy. Fourth, the government continuously has the role of investing in the related R&D and social infra building. We expect the green car diffusion model and related formula from the research can provide meaningful tools to analyze the diffusion process of other new and innovative goods based on its deep researched literature review.

• Analytical Science and Technology
• /
• v.33 no.2
• /
• pp.98-107
• /
• 2020

Methamphetamine (MA) is currently the most abused illicit drug in Korea. MA is produced by chemical synthesis, and the final target drug that is produced contains small amounts of the precursor chemicals, intermediates, and by-products. To identify and quantify these trace compounds in MA seizures, a practical and feasible approach for conducting chromatographic fingerprinting with a suite of traditional chemometric methods and recently introduced machine learning approaches was examined. This was achieved using gas chromatography (GC) coupled with a flame ionization detector (FID) and mass spectrometry (MS). Following appropriate examination of all the peaks in 71 samples, 166 impurities were selected as the characteristic components. Unsupervised (principal component analysis (PCA), hierarchical cluster analysis (HCA), and K-means clustering) and supervised (partial least squares-discriminant analysis (PLS-DA), orthogonal partial least squares-discriminant analysis (OPLS-DA), support vector machines (SVM), and deep neural network (DNN) with Keras) chemometric techniques were employed for classifying the 71 MA seizures. The results of the PCA, HCA, K-means clustering, PLS-DA, OPLS-DA, SVM, and DNN methods for quality evaluation were in good agreement. However, the tested MA seizures possessed distinct features, such as chirality, cutting agents, and boiling points. The study indicated that the established qualitative and semi-quantitative methods will be practical and useful analytical tools for characterizing trace compounds in illicit MA seizures. Moreover, they will provide a statistical basis for identifying the synthesis route, sources of supply, trafficking routes, and connections between seizures, which will support drug law enforcement agencies in their effort to eliminate organized MA crime.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.5
• /
• pp.37-46
• /
• 2020

Recently, studies of facial attribute editing have obtained realistic results using generative adversarial net (GAN) and encoder-decoder structure. Spatial attention GAN (SaGAN), one of the latest researches, is the method that can change only desired attribute in a face image by spatial attention mechanism. However, sometimes unnatural results are obtained due to insufficient information on face areas. In this paper, we propose an improved SaGAN (MSaGAN) using a guide mask for learning and applying multitask learning approach to improve the limitations of the existing methods. Through extensive experiments, we evaluated the results of the facial attribute editing in therms of the mask loss function and the neural network structure. It has been shown that the proposed method can efficiently produce more natural results compared to the previous methods.