• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.

• 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.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.4
• /
• pp.226-231
• /
• 2019

A WTCI is an important criteria for evaluating an mount of patient's tongue coating in tongue diagnosis. However, Previous WTCI tongue coating evaluation methods is a most of quantitatively measuring ration of the extracted tongue coating region and tongue body region, which has a non-objective measurement problem occurring by exposure conditions of tongue image or the recognition performance of tongue coating. Therefore, a WTCI based on deep learning is proposed for classifying an amount of tonger coating in this paper. This is applying the AI deep learning method using big data. to WTCI for evaluating an amount of tonger coating. In order to verify the effectiveness performance of the deep learning in tongue coating evaluating method, we classify the 3 types class(no coating, some coating, intense coating) of an amount of tongue coating by using CNN model. As a results by testing a building the tongue coating sample images for learning and verification of CNN model, proposed method is showed 96.7% with respect to the accuracy of classifying an amount of tongue coating.

• ETRI Journal
• /
• v.40 no.1
• /
• pp.39-50
• /
• 2018

More people prefer using rail traffic for travel or for commuting owing to its convenience and flexibility. The railway scenario has become an important communication scenario in the fifth generation era. The communication system should be designed to support high-data-rate demands with seamless connectivity at a high mobility. In this paper, the channel characteristics are studied and modeled for the railway tunnel scenario with straight and curved route shapes. On the basis of measurements using the "Mobile Hotspot Network" system, a three-dimensional ray tracer (RT) is calibrated and validated for the target scenarios. More channel characteristics are explored via RT simulations at 25.25 GHz with a 500-MHz bandwidth. The key channel parameters are extracted, provided, and incorporated into a 3rd-Generation-Partnership-Project-like stochastic channel generator. The necessary channel information can be practically realized, which can support the link-level and system-level design of the communication system in similar scenarios.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.6
• /
• pp.730-736
• /
• 2011

In this paper, we designed the models for pattern classification which can reflect the latest trend in time series. It has been shown that fusion models based on statistical and AI methods are superior to traditional ones for the pattern classification model supporting decision making. Especially, the hit rates of pattern classification models combined with fuzzy theory are relatively increased. The statistical SVM models combined with fuzzy membership function, or the models combining neural network and FCM has shown good performance. BPN, PNN, FNN, FCM, SVM, FSVM, Decision Tree, Time Series Analysis, and Regression Analysis were used for pattern classification models in the experiments of this paper. The economical indices DB with time series properties of the financial market(Korea, KOSPI200 DB) and the electrocardiogram DB of arrhythmia patients in hospital emergencies(USA, MIT-BIH DB) were used for data base.

• IMMUNE NETWORK
• /
• v.11 no.6
• /
• pp.368-375
• /
• 2011

Background: Recent clinical observation reported that there was a significant correlation between change in circulating vascular endothelial growth factor (VEGF) levels and the occurrence of severe acute graft-versus-host disease (GVHD) following allogeneic hematopoietic stem cell transplantation (allo-HSCT), but the action mechanisms of VEGF in GVHD have not been demonstrated. Methods: This study investigated whether or not blockade of VEGF has an effect on acute GVHD in a lethally irradiated murine allo-HSCT model of $B6\;(H-2^b)\;{\rightarrow}B6D2F1\;(H-2^{b/d})$. Syngeneic or allogeneic recipient mice were injected subcutaneously with anti-VEGF peptides, dRK6 ($50{\mu}g/dose$) or control diluent every other day for 2 weeks (total 7 doses). Results: Administration of the dRK6 peptide after allo-HSCT significantly reduced survival with greaterclinical GVHD scores and body weight loss. Allogeneic recipients injected with the dRK6 peptide exhibited significantly increased circulating levels of VEGF and expansion of donor $CD3^+$ T cells on day +7 compared to control treated animals. The donor $CD4^+$ and $CD8^+$ T-cell subsets have differential expansion caused by the dRK6 injection. The circulating VEGF levels were reduced on day +14 regardless of blockade of VEGF. Conclusion: Together these findings demonstrate that the allo-reactive responses after allo-HSCT are exaggerated by the blockade of VEGF. VEGF seems to be consumed during the progression of acute GVHD in this murine allo-HSCT model.

• Ecology and Resilient Infrastructure
• /
• v.1 no.2
• /
• pp.94-101
• /
• 2014

This is the urban design master plan for the Public Administration Town. The project proposes a newly configured city, where environmental and democratic principles are expressed in the shape of the urban fabric. To achieve the goal, the concepts of 'Flat City, Link City, and Zero City' were introduced. These concept show "Space fabric arrange, connection and material circulation and flow from ecological landscape". 'Flat City' shaped the government buildings into an iconic plane, and democratic society. The iconic plane's surface extends across the whole city, creating an expansive public park, which is easily accessible, and open to nature. 'Link City' connects governmental agencies to enhance their function and interactions. Government facilities, parks and green spaces, cultural facilities, commercial zones, and residential districts areas create an interconnecting network. 'Zero City' has integrated infrastructure systems to reuse waste, reduce pollution, and provide essential city functions. It creates a new wildlife habitat, making 'Zero City' a good neighborhood. This proposal was made to integrate historical, regional, nature experiences with various approaches in architecture, city, and landscape architecture.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.53 no.1
• /
• pp.29-36
• /
• 2011

HPAI (High pathogenic avian influenza) which is a disease legally designated as an epidemic generally shows rapid spread of disease resulting in high mortality rate as well as severe economic damages. Because Korea is contiguous with China and southeast Asia where HPAI have occurred frequently, there is a high risk for HPAI outbreak. A prompt treatment against epidemics is most important for prevention of disease spread. The spread of HPAI should be considered by both direct and indirect contact as well as various spread factors including airborne spread. There are high risk of rapid propagation of HPAI flowing through the air because of collective farms mostly in Korea. Field experiments for the mechanism of disease spread have limitations such as unstable weather condition and difficulties in maintaining experimental conditions. In this study, therefore, computational fluid dynamics which has been actively used for mass transfer modeling were adapted. Korea has complex terrains and many livestock farms are located in the mountain regions. GIS numerical map was used to estimate spreads of virus attached aerosol by means of designing three dimensional complicated geometry including farm location, road network, related facilities. This can be used as back data in order to take preventive measures against HPAI occurrence and spread.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.4
• /
• pp.445-450
• /
• 2018

AIS is the most important navigation equipment for the identification of other ships, etc. However, the AIS overload problem has been raised recently due to an increase in AIS equipped vessels. The government is planning to introduce the wireless LTE network at 100 km offshore as part of the SMART-Navigation project. Continuous development and dissemination of the services available through such platforms will be necessary to achieve major goals such as marine accident prevention and environmental protection. In this study, we applied a WAVE communication system, which could be the basis for the development of such services. As a result, reliable data transmission was confirmed for a range of communication of approx. 5 miles, although the service was limited to 1 km in road traffic. Therefore, it is expected that WAVE communication technology will be used to prevent marine accidents through such efforts as collision avoidance and the transfer of marine safety information between ships.

• Journal of the Korea Convergence Society
• /
• v.12 no.12
• /
• pp.65-74
• /
• 2021

Recently, studies on Korean spelling correction have been actively conducted based on machine translation and automatic noise generation. These methods generate noise and use as train and data set. This has limitation in that it is difficult to accurately measure performance because it is unlikely that noise other than the noise used for learning is included in the test set In addition, there is no practical error type standard, so the type of error used in each study is different, making qualitative analysis difficult. This paper proposes new 'error type classification' for deep learning-based Korean spelling correction research, and error analysis perform on existing commercialized Korean spelling correctors (System A, B, C). As a result of analysis, it was found the three correction systems did not perform well in correcting other error types presented in this paper other than spacing, and hardly recognized errors in word order or tense.