• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.6
• /
• pp.834-841
• /
• 2022

Recently, applying artificial intelligence technologies in various fields of production has drawn an upsurge of research interest due to the increase for smart factory and artificial intelligence technologies. A great deal of effort is being made to introduce artificial intelligence algorithms into the defect detection task. Particularly, detection of defects on the surface of metal has a higher level of research interest compared to other materials (wood, plastics, fibers, etc.). In this paper, we compare and analyze the speed and performance of defect classification by combining machine learning techniques (Support Vector Machine, Softmax Regression, Decision Tree) with dimensionality reduction algorithms (Principal Component Analysis, AutoEncoders) and two convolutional neural networks (proposed method, ResNet). To validate and compare the performance and speed of the algorithms, we have adopted two datasets ((i) public dataset, (ii) actual dataset), and on the basis of the results, the most efficient algorithm is determined.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.3
• /
• pp.207-215
• /
• 2022

This research has been focused on accessing precision and accuracy of UAV (Unmanned Aerial Vehicle)-derived 3-D surveying coordinates. To this end, a highly precise and accurate testing control network had been established by GNSS (Global Navigation Satellite Systems) campaign and its network adjustment. The coordinates of the ground control points and the check points were estimated within 1cm accuracy for 95% of the confidence level. FC330 camera mounted on DJI Phantom 4 repeatedly took aerial photos of an experimental area seven times, and then processed them by two widely used software packages. To evaluate the precision and accuracy of the aerial surveys, 3-D coordinates of the ten check points which automatically extracted by software were compared with GNSS solutions. For the 95% confidence level, the standard deviation of two software's result is within 1cm, 2cm, and 4cm for the north-south, east-west, and height direction, and RMSE (Root Mean Square Error) is within 9cm and 8cm for the horizontal, vertical component, respectively. The interest is that the standard deviation is much smaller than RMSE. The F-ratio test was performed to confirm the statistical difference between the two software processing results. For the standard deviation and RMSE of most positional components, exception of RMSE of the height, the null hypothesis of the one-tailed tests was rejected. It indicates that the result of UAV photogrammetry can be different statistically based on the processing software.

• Journal of the Korea Institute of Building Construction
• /
• v.21 no.3
• /
• pp.231-239
• /
• 2021

Entering the era of the fourth industrial revolution, information and communication technologies such as CCTV, home network systems and equipment are being used in the construction industry. In particular, in order to increase the autonomy of information and communication technologies in apartments, the government has announced an administrative revision of information and communication-related laws, and companies are focusing on developing technologies such as smart home services. In addition, most domestic and foreign studies on the information and communication work were mainly conducted on technology and management. However there is a lack of research on physical defects affecting the quality of ICT. Therefore, this study collected the defect data registered in the project management system of three domestic construction companies and classified them according to the standards of the Enforcement Decree of the Apartment House Management Act. According to the analysis of the frequency of defects work type, 88.10% of defects occurred in home network equipment work. In addition, analysis of defects type in the four detailed works showed the highest number of operation error. The cause was analyzed and prevention measures and countermeasures were presented in parts of design, construction, and maintenance. The results of this study will improve the quality of apartment housing and be used as basic data for future research on practical defect minimization and prevention measures.

• Journal of the Society of Disaster Information
• /
• v.17 no.1
• /
• pp.165-175
• /
• 2021

Purpose: The purpose of this study is to quantitatively present the carbon dioxide(CO₂) emission change according to the application of autonomous driving technology at the network level for waste vehicles in the metropolitan area. Method: The target year was set to 2030, and the analysis method estimated the carbon dioxide (CO₂) emissions for each road link through user equilibrium assignment when unapplied scenario. The application scenario performed traffic assignment using route data on the premise that the group was running in accordance with the application of autonomous driving technology to waste vehicles. In addition, the other means estimated the carbon dioxide emissions through user balance allocation by reflecting the results of the waste vehicle allocation. Result: As a result of the analysis, carbon dioxide(CO₂) emissions were found to be reduced by about 56.9ton/day from the national network level, and the Seoul metropolitan area was analyzed to be reduced by about 54.7ton/day. Conclusion: This study quantitatively presented environmental impacts among various social effects that autonomous driving technology will bring, and in the future, development of various analytical methodologies and related studies should be continuously conducted.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.221-228
• /
• 2021

This study was conducted to improve the convenience of design of mobile VR devices use in a way binds smart phones. Research on traditional mobile VR devices is insufficient. So the first survey was conducted on users 100 to understand the current status and status of mobile VR devices. As a result, it was found that the satisfaction with the convenience of use was significantly lowered, and countermeasures were needed. Then, a second survey of 30 Heavy Users was conducted to find out specific usability and problems of mobile VR devices. Through this, problems, ease of use, and other opinions of mobile VR devices were found. The survey results were analyzed through the Descriptive Statistics Act, and it was found that improvement was urgent due to low satisfaction with wearing and network. In-depth interviews were conducted with the same respondents. As with the problems derived first, problems such as wearing satisfaction, excessive head weight for long-term use, and lack of content could be found. Based on the previous studies, the focus group interview consisting of 6 experts derived the ease of use evaluation element. It consists of elements that can satisfy the convenience of use of mobile VR devices for creation, wearing satisfaction, network, morphology, learning, and spatiality, and has a total of 26. Using this evaluation elements, it is intended to provide better ease of use to users who will use the mobile VR device.

• Journal of Internet Computing and Services
• /
• v.24 no.1
• /
• pp.1-7
• /
• 2023

Recently, the technology of device-to-device(D2D) communication has been receiving big attention to improve the system performance since the amount of high quality/large capacity data traffic from smart phones and various devices of Internet of Things increase rapidly in 5G/6G based next generation cellular networks. However, even though the system performance of macro cells increase by reusing the frequency, the performance of macro user equipments(MUEs) decrease because of the strong interference from D2D user equipments(DUEs). Therefore, this paper proposes a dynamic channel management(DCM) scheme for DUEs to guarantee the performance of MUEs as the number of DUEs increases in next generation downlink cellular networks. In the proposed D2D DCM scheme, macro base stations dynamically assign subchannels to DUEs based on the interference information and signal to interference and noise ratio(SINR) of MUEs. Simulation results show that the proposed D2D DCM scheme outperforms other schemes in terms of the mean MUE capacity as the threshold of the SINR of MUEs incareases.

• Journal of Korean Society of Coastal and Ocean Engineers
• /
• v.34 no.6
• /
• pp.315-324
• /
• 2022

The experimental data obtained in a wave flume were analyzed using machine learning techniques to establish a model that predicts the input wave height of the wavemaker based on the waves that have experienced wave shoaling and to verify the performance of the established model. For this purpose, artificial neural network (NN), the most representative machine learning technique, and Gaussian process regression (GPR), one of the non-parametric regression analysis methods, were applied respectively. Then, the predictive performance of the two models was compared. The analysis was performed independently for the case of using all the data at once and for the case by classifying the data with a criterion related to the occurrence of wave breaking. When the data were not classified, the error between the input wave height at the wavemaker and the measured value was relatively large for both the NN and GPR models. On the other hand, if the data were divided into non-breaking and breaking conditions, the accuracy of predicting the input wave height was greatly improved. Among the two models, the overall performance of the GPR model was better than that of the NN model.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.29 no.6
• /
• pp.653-658
• /
• 2023

In systems like the combat management system of a naval ship or smart city of civilians, where many sensors and actuators are connected, the middle-ware DDS (Data Distribution Service) is mainly used to transmit large amounts of data. It is scalable and can effectively respond to the increase in sensors or equipment connected to the system in the future. The engineering control system (ECS), which plays an important role similar to the combat management system of a naval ship, still uses Server-Client model with industrial protocols such as Modbus and CAN (Controller Area Network) bus, to transmit data, which is unfavorable in terms of scalability. However, as automation and unmanned systems advance, more sensors and actuators are expected to be added, necessitating substantial program modification. DDS can effectively address such situations. The purpose of this study is to confirm the development possibility of an integrated monitoring and control system of a ship by using OpenDDS, which follows the OMG (Object Management Group) standard among the middle-ware DDS used in the combat management system. To achieve this goal, field equipment simulators and an ECS server were configured to perform field equipment data input/output and simulation using DDS was performed. The ECS prototype successfully handled data transmission, confirming that DDS is capable of serving as the middle-ware for the ECS of a ship.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1321-1330
• /
• 2023

This study attempts to address the problem of 3D pose estimation for multiple human objects through a single image generated during the character development process that can be used in augmented reality. In the existing top-down method, all objects in the image are first detected, and then each is reconstructed independently. The problem is that inconsistent results may occur due to overlap or depth order mismatch between the reconstructed objects. The goal of this study is to solve these problems and develop a single network that provides consistent 3D reconstruction of all humans in a scene. Integrating a human body model based on the SMPL parametric system into a top-down framework became an important choice. Through this, two types of collision loss based on distance field and loss that considers depth order were introduced. The first loss prevents overlap between reconstructed people, and the second loss adjusts the depth ordering of people to render occlusion inference and annotated instance segmentation consistently. This method allows depth information to be provided to the network without explicit 3D annotation of the image. Experimental results show that this study's methodology performs better than existing methods on standard 3D pose benchmarks, and the proposed losses enable more consistent reconstruction from natural images.

• The KIPS Transactions:PartC
• /
• v.11C no.4
• /
• pp.439-446
• /
• 2004

In the Internet, user authentication is the most important service in secure communications. Although password-based mechanism is the most widely used method of the user authentication in the network, people are used to choose easy-to-remember passwords, and thus suffers from some Innate weaknesses. Therefore, using a memorable password it vulnerable to the dictionary attacks. The techniques used to prevent dictionary attacks bring about a heavy computational workload. In this paper, we describe a recent solution, the Optimal Strong-Password Authentication (OSPA) protocol, and that it is vulnerable to the stolen-verifier attack and an impersonation attack. Then, we propose an Improved Optimal Strong-Password Authentication (I-OSPA) protocol, which is secure against stolen-verifier attack and impersonation attack. Also, since the cryptographic operations are computed by the processor in the smart card, the proposed I-OSPA needs relatively low computational workload and communicational workload for user.