• Journal of Digital Convergence
• /
• v.17 no.10
• /
• pp.259-264
• /
• 2019

This paper proposes an image prediction system architecture for deep running in enterprise environment. Easily transform into an artificial intelligence platform for an enterprise environment, and allow sufficient deep-running services to be developed and modified even in Java-centric architectures to improve the shortcomings of Java-centric enterprise development because artificial intelligence platforms are concentrated in the pipeline. In addition, based on the proposed environment, we propose a more accurate prediction system in the deep running architecture environment that has been previously learned through image forecasting experiments. Experiments show 95.23% accuracy in the image example provided for deep running to be performed, and the proposed model shows 96.54% accuracy compared to other similar models.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.35 no.6
• /
• pp.375-380
• /
• 2022

High-speed railway bridges carry a risk of dynamic response amplification due to resonance caused by train loads, and running safety and riding comfort must therefore be reviewed through dynamic analysis in accordance with design codes. The running safety and ride comfort calculation procedure, however, is time consuming and expensive because dynamic analyses must be performed for every 10 km/h interval up to 110% of the design speed, including the critical speed for each train type. In this paper, a deep-learning-based prediction system that can predict the running safety and ride comfort in advance is proposed. The system does not use dynamic analysis but employs a deep learning algorithm. The proposed system is based on a neural network trained on the dynamic analysis results of each train and speed of the railway bridge and can predict the running safety and ride comfort according to input parameters such as train speed and bridge characteristics. To confirm the performance of the proposed system, running safety and riding comfort are predicted for a single span, straight simple beam bridge. Our results confirm that the deck vertical displacement and deck vertical acceleration for calculating running safety and riding comfort can be predicted with high accuracy.

• International Journal of Advanced Culture Technology
• /
• v.7 no.2
• /
• pp.195-200
• /
• 2019

Media art, which is a combination of media technology and art, is making a lot of progress in combination with AI, IoT and VR. This paper aims to meet people's needs by creating a video that simulates the dance moves of an object that users admire by using media art that features interactive interactions between users and works. The project proposed a universal image synthesis system that minimizes equipment constraints by utilizing a deep running-based Skeleton estimation system and one of the deep-running neural network structures, rather than a Kinect-based Skeleton image. The results of the experiment showed that the images implemented through the deep learning system were successful in generating the same results as the user did when they actually danced through inference and synthesis of motion that they did not actually behave.

• KIISE Transactions on Computing Practices
• /
• v.23 no.5
• /
• pp.299-303
• /
• 2017

By piling up hidden layers in artificial neural networks, deep learning is delivering outstanding performances for high-level abstraction problems such as object/speech recognition and natural language processing. Alternatively, deep-learning users often struggle with the tremendous amounts of time and resources that are required to train deep neural networks. To alleviate this computational challenge, many approaches have been proposed in a diversity of areas. In this work, two of the existing Apache Spark-based acceleration frameworks for deep learning (SparkNet and DeepSpark) are compared and analyzed in terms of the training accuracy and the time demands. In the authors' experiments with the CIFAR-10 and CIFAR-100 benchmark datasets, SparkNet showed a more stable convergence behavior than DeepSpark; but in terms of the training accuracy, DeepSpark delivered a higher classification accuracy of approximately 15%. For some of the cases, DeepSpark also outperformed the sequential implementation running on a single machine in terms of both the accuracy and the running time.

• International Journal of Railway
• /
• v.3 no.2
• /
• pp.54-59
• /
• 2010

In order to develop the deep-underground GTX (Great Train eXpress) in domestic, the running performance analysis of the propulsion system by a variety of route condition must be carried out before studying the specification and the development of the high-speed propulsion system with inverter and traction motor. Then it is necessary to study the running resistance properties of the high-speed traction system for the variety of tunnel type and vehicle organization method at first. In addition, the properties of the power requirement of the traction motors needed to maintain the balanced speed of the high-speed traction system are next studied. We need to study properties of the emergency braking distance caused by the highest operation speed of the high-speed traction system and present the fundamental design technologies to develop the high-speed traction system for the deep-underground GTX. Finally, the paper analyzes the applicability of the conventional Korean Tilting Train eXpress (TTX) propulsion system on the high-speed propulsion system for the deep-underground GTX.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2021.11a
• /
• pp.8-9
• /
• 2021

The unit-water content of concrete is one of the important factors in determining the quality of concrete and is directly related to the durability of the construction structure, and the current method of measuring the unit-water content of concrete is applied by the Air Meta Act and the Electrostatic Capacity Act. However, there are complex and time-consuming problems with measurement methods. Therefore, high frequency moisture sensor was used for quick and high measurement, and unit-water content of mortar was evaluated through machine running and deep running based on measurement big data. The multi-input deep learning model is as accurate as 24.25% higher than the OLS linear regression model, which shows that deep learning can more effectively identify the nonlinear relationship between high-frequency moisture sensor data and unit quantity than linear regression.

• Journal of information and communication convergence engineering
• /
• v.19 no.1
• /
• pp.61-66
• /
• 2021

An underwater remotely operated vehicle (ROV) has been implemented. It can inspect foreign substances through a CCD camera while the ROV is running in water. The maximum thrust of the ROV's running thruster is 139.3 N, allowing the ROV to move forward and backward at a running speed of 1.03 m/s underwater. The structural strength of the guard frame was analyzed when the ROV collided with a wall while traveling at a speed of 1.03 m/s underwater, and found to be safe. The maximum running speed of the ROV is 1.08 m/s and the working speed is 0.2 m/s in a 5.8-m deep-water wave pool, which satisfies the target performance. As the ROV traveled underwater at a speed of 0.2 m/s, the inspection camera was able to read characters that were 3 mm in width at a depth of 1.5 m, which meant it could sufficiently identify foreign objects in the water.

• Structural Engineering and Mechanics
• /
• v.76 no.2
• /
• pp.207-222
• /
• 2020

Due to the rugged terrain, metro lines in mountain city across numerous wide rivers and deep valleys, resulting in instability of high-pier bridge and insecurity of metro train subjected to fluctuating crosswind. To ensure the safe operation in metro lines in mountain cities, running safety of the metro train over the high-pier bridge under crosswind is analyzed in this paper. Firstly, the dynamic model of the wind-train-bridge (WTB) system is built, in which the speed-up effect of crosswind is fully considered. On the basis of time domain analysis, the basic characteristics of the WTB system with high-pier are analyzed. Afterwards, the dynamic responses varies with train speed and wind speed are calculated, and the safety zone of metro train over a high-pier bridge subjected to fluctuating crosswind in mountain city is determined. The results indicate that, fluctuating crosswind triggers drastic vibration to the metro train and high-pier bridges, which in turn causes running instability of the train. For this reason, the corresponding safety zone for metro train running on the high-pier is proposed, and the metro traffic on the high-pier bridge should be closed as the mean wind speed of standard height reaches 9 m/s (15.6 m/s for the train).

• Journal of Electrical Engineering and Technology
• /
• v.7 no.2
• /
• pp.200-206
• /
• 2012

In order to develop a deep-underground great train express (GTX) in South Korea, the specifications decision and development of a traction control system (including an inverter and a traction motor), which considers a variety of route conditions, must be advanced. In this study, we examined the running resistance properties of a high-speed traction system based on a variety of tunnel types and vehicle organization methods. Then, we studied the power requirements necessary for the traction motor to maintain balanced speed in the high-speed traction system. From this, we determined the design criteria for the development of a high-speed traction system for use in the deep-underground GTX. Finally, we designed a linear induction motor (LIM) for a propulsion system, and we used the finite element method (FEM) to analyze its performance as it travelled through deep-underground tunnels.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.9 no.11
• /
• pp.1133-1144
• /
• 2019

Recently, the amount of image on the Internet has rapidly increased, due to the advancement of smart devices and various approaches to effective image retrieval have been researched under these situation. Existing image retrieval methods simply detect the objects in a image and carry out image retrieval based on the label of each object. Therefore, the semantic gap occurs between the image desired by a user and the image obtained from the retrieval result. To reduce the semantic gap in image retrievals, we connect the module for multiple objects classification based on deep learning with the module for human behavior classification. And we combine the connected modules with a behavior ontology. That is to say, we propose an image retrieval system considering the relationship between objects by using the combination of deep learning and behavior ontology. We analyzed the experiment results using walking and running data to take into account dynamic behaviors in images. The proposed method can be extended to the study of automatic annotation generation of images that can improve the accuracy of image retrieval results.