• Wind and Structures
• /
• v.39 no.4
• /
• pp.271-285
• /
• 2024

The multiple-fan wind tunnel is an important facility for reproducing target wind field. Existing control methods for the multiple-fan wind tunnel can generate wind speeds that satisfy the target statistical characteristics of a wind field (e.g., power spectrum). However, the frequency-domain features cannot well represent the nonstationary winds of extreme storms (e.g., downburst). Therefore, this study proposes a multiple-fan wind tunnel control scheme based on Deep Reinforcement Learning (DRL), which will completely transform into a data-driven closed-loop control problem, to reproduce the target wind field in the time domain. Specifically, the control scheme adopts the Deep Deterministic Policy Gradient (DDPG) paradigm in which the strong fitting ability of Deep Neural Networks (DNN) is utilized. It can establish the complex relationship between the target wind speed time series and the current control strategy in the DRL-agent. To address the fluid memory effect of the wind field, this study innovatively designs the system state and control reward to improve the reproduction performance based on historical data. To validate the performance of the model, we established a simplified flow field based on Navier Stokes equations to simulate a two-dimensional numerical multiple-fan wind tunnel environment. Using the strategy of DRL decision maker, we generated a wind speed time series with minor error from the target under low Reynolds number conditions. This is the first time that the AI methods have been used to generate target wind speed time series in a multiple-fan wind tunnel environment. The hyperparameters in the DDPG paradigm are analyzed to identify a set of optimal parameters. With these efforts, the trained DRL-agent can simultaneously reproduce the wind speed time series in multiple positions.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_3
• /
• pp.1789-1803
• /
• 2022

With the increase of data and the development of AI technology, the strategies and policies related to integrated data are being actively established to increase the usability of data all over the world. Recently, in the research field, infrastructure projects and management systems are being prepared to utilize research data at the initiative of the government. Also, in Korea, platforms for searching and sharing research data are being actively developed. The National Disaster Management Research Institute (NDMI) has been conducting extensive research on disaster & safety as a national institute, but data-oriented management and utilization are insufficient. Because it still lacks consistent data management systems, metadata for outcomes of research, experts on data and policies for utilization of data to research. In order to move to the data-based research paradigm, we defined the master plans and verified a target model for the integrated management and utilization of disaster & safety research data. In this study, we found out the need to establish differentiated data governance, such as data standardization and unification of the data management system, and dedicated organization for managing data, based on the necessity and actual demands of NDMI. In order to verify the effectiveness of the target model reflecting the derived implications, we intend to establish a pilot mode. In the future, major improvement measures to establish a disaster & safety research data management system will be implement.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.4
• /
• pp.765-776
• /
• 2018

Artificial Intelligence is a rapidly growing technology with the latest developments in computing technology and is considered as one of the next major technologies. Chat-Bot is a system that is designed to respond to user's input according to the rules that are set up in advance and it provides more services through simple and repetitive tasks such as counseling, ordering and others. Accordingly, the study aims to present a model of a celeb-bot using Artificial Intelligence. Celeb-Bot is a combination of Celeb, which are short for Celebrity and Chat-bot. Celeb-Bot provides a Chat-Bot service that allows people to talk to a celebrity. The celeb is the best thing to build a relationship and has the advantages of being accessible to anyone. At the same time, Artificial Intelligence is a technology that can be seen as a person, not a product. Based on this, we believe that Celeb's Characteristic and Chat-bot based on artificial intelligence technologies need to be combined, so variety of products can generate synergy. It is predicted that there will be variety of derivatives that utilize this technology, and it is going to present a celeb-bot model accordingly.

• Strategy21
• /
• s.44
• /
• pp.5-27
• /
• 2018

The purpose of this paper is to look at USN's efforts to rebuild its combat power in the face of a reemergence of great powers competition, and to propose some recommendations for the ROKN. In addition to the plan to augment its fleet towards a 355-ships capacity, the USN is pursuing to improve exponentially combat lethality(quality) of its existing fleet by means of innovative science and technology. In other words, the USN is putting its utmost efforts to improve readiness of current forces, to modernize maintenance facilities such as naval shipyards, and simultaneously to invest in innovative weapons system R&D for the future. After all, the USN seems to pursue innovations in advanced military Science & Technology as the best way to ensure continued supremacy in the coming strategic competition between great powers. However, it is to be seen whether the USN can smoothly continue these efforts to rebuild combat strength vis-a-vis its new competition peers, namely China and Russian navy, due to the stringent fiscal constraints, originating, among others, from the 2011 Budget Control Act effective yet. Then, it seems to be China's unilateral and assertive behaviors to expand its maritime jurisdiction in the South China Sea that drives the USN's rebuild-up efforts of the future. Now, some changes began to be perceived in the basic framework of the hitherto regional maritime security, in the name of declining sea control of the USN as well as withering maritime order based on international law and norms. However, the ROK-US alliance system is the most excellent security mechanism upon which the ROK, as a trading power, depends for its survival and prosperity. In addition, as denuclearization of North Korea seems to take significant time and efforts to accomplish in the years to come, nuclear umbrella and extended deterrence by the US is still noting but indispensible for the security of the ROK. In this connection, the naval cooperation between ROKN and USN should be seen and strengthened as the most important deterrents to North Korean nuclear and missile threats, as well as to potential maritime provocation by neighboring countries. Based on these observations, this paper argues that the ROK Navy should try to expand its own deterrent capability by pursuing selective technological innovation in order to prevent this country's destiny from being dictated by other powers. In doing so, however, it may be too risky for the ROK to pursue the emerging, disruptive innovative technologies such as rail gun, hypersonic weapon... etc., due to enormous budget, time, and very thin chance of success. This paper recommends, therefore, to carefully select and extensively invest on the most cost-effective technological innovations, suitable in the operational environments of the ROK. In particular, this paper stresses the following six areas as most potential naval innovations for the ROK Navy: long range precision strike; air and missile defense at sea; ASW with various unmanned maritime system (UMS) such as USV, UUV based on advanced hydraulic acoustic sensor (Sonar) technology; network; digitalization for the use of AI and big data; and nuclear-powered attack submarines as a strategic deterrent.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.1
• /
• pp.25-32
• /
• 2020

In the context-aware system, rule-based AI technology has been used in the abstraction process for getting context information. However, the rules are complicated by the diversification of user requirements for the service and also data usage is increased. Therefore, there are some technical limitations to maintain rule-based models and to process unstructured data. To overcome these limitations, many studies have applied machine learning techniques to Context-aware systems. In order to utilize this machine learning-based model in the context-aware system, a management process of periodically injecting training data is required. In the previous study on the machine learning based context awareness system, a series of management processes such as the generation and provision of learning data for operating several machine learning models were considered, but the method was limited to the applied system. In this paper, we propose a training data generating method of a machine learning model to extend the machine learning based context-aware system. The proposed method define the training data generating model that can reflect the requirements of the machine learning models and generate the training data for each machine learning model. In the experiment, the training data generating model is defined based on the training data generating schema of the cardiac status analysis model for older in health status notification service, and the training data is generated by applying the model defined in the real environment of the software. In addition, it shows the process of comparing the accuracy by learning the training data generated in the machine learning model, and applied to verify the validity of the generated learning data.

• Journal of Advanced Navigation Technology
• /
• v.14 no.3
• /
• pp.297-302
• /
• 2010

The AtoN is subsidiary navigation facilities for ship to navigate safely. AtoN includes signs of visual, sound, special and radio. Receltly as GNSS and AIS are developed rapidly, AtoN has been considered as a promising candidate technique for ensuring fairway safety of ship. However, present AtoN systems are not adopted to ship fully, but are adopted to ship partly, and total management systems are not installed. In this study, AtoN Monitoring system based on AIS is developed. It consists of AIS system and AIS viewer program. In the system AIS gathers data of AtoN and ship information and AIS viewer is a program that plots AIS data on ECDIS.

• The Journal of the Convergence on Culture Technology
• /
• v.8 no.2
• /
• pp.385-391
• /
• 2022

Quality evaluation of beef carcasses is an important issue in the livestock industry. Recently, through the AI monitor system based on artificial intelligence, the quality manager can receive help in making accurate decisions based on the analysis of beef carcass images or result information. This artificial intelligence dataset is an important factor in judging performance. Existing datasets may have different surface orientation or resolution. In this paper, we proposed a two-stage classification model that can efficiently manage the grades of beef carcass image using deep learning. And to overcome the problem of the various conditions of the image, a new dataset of 1,300 images was constructed. The recognition rate of deep network for 5-grade classification using the new dataset was 72.5%. Two-stage evaluation is a method to increase reliability by taking advantage of the large difference between grades 1++, 1+, and grades 1 and 2 and 3. With two experiments using the proposed two stage model, the recognition rates of 73.7% and 77.2% were obtained. As this, The proposed method will be an efficient method if we have a dataset with 100% recognition rate in the first stage.

• ETRI Journal
• /
• v.41 no.6
• /
• pp.760-770
• /
• 2019

Based on the growing demand for neural network technologies, various neural network inference engines are being developed. However, each inference engine has its own neural network storage format. There is a growing demand for standardization to solve this problem. This study presents interworking techniques for ensuring the compatibility of neural networks and data among the various deep learning frameworks. The proposed technique standardizes the graphic expression grammar and learning data storage format using the Neural Network Exchange Format (NNEF) of Khronos. The proposed converter includes a lexical, syntax, and parser. This NNEF parser converts neural network information into a parsing tree and quantizes data. To validate the proposed system, we verified that MNIST is immediately executed by importing AlexNet's neural network and learned data. Therefore, this study contributes an efficient design technique for a converter that can execute a neural network and learned data in various frameworks regardless of the storage format of each framework.

• Steel and Composite Structures
• /
• v.49 no.2
• /
• pp.231-244
• /
• 2023

Many of the recent investigations in the field of geotechnical engineering focused on the bearing capacity theories of multilayered soil. A number of factors affect the bearing capacity of the soil, such as soil properties, applied overburden stress, soil layer thickness beneath the footing, and type of design analysis. An extensive number of finite element model (FEM) simulation was performed on a prototype slope with various abovementioned terms. Furthermore, several non-linear artificial intelligence (AI) models are developed, and the best possible neural network system is presented. The data set is from 3443 measured full-scale finite element modeling (FEM) results of a circular shallow footing analysis placed on layered cohesionless soil. The result is used for both training (75% selected randomly) and testing (25% selected randomly) the models. The results from the predicted models are evaluated and compared using different statistical indices (R² and RMSE) and the most accurate model BBO (R²=0.9481, RMSE=4.71878 for training and R²=0.94355, RMSE=5.1338 for testing) and TLBO (R²=0.948, RMSE=4.70822 for training and R²=0.94341, RMSE=5.13991 for testing) are presented as a simple, applicable formula.

• Journal of Korea Water Resources Association
• /
• v.55 no.spc1
• /
• pp.1177-1185
• /
• 2022

The water and sewage system is an infrastructure that provides safe and clean water to people. In particular, since the water and sewage pipelines are buried underground, it is very difficult to detect system defects. For this reason, the diagnosis of pipelines is limited to post-defect detection, such as system diagnosis based on the images taken after taking pictures and videos with cameras and drones inside the pipelines. Therefore, real-time detection technology of pipelines is required. Recently, pipeline diagnosis technology using advanced equipment and artificial intelligence techniques is being developed, but AI-based defect detection technology requires a variety of learning data because the types and numbers of defect data affect the detection performance. Therefore, in this study, various defect scenarios are implemented using 3D printing model to improve the detection performance when detecting defects in pipelines. Afterwards, the collected images are performed to pre-processing such as classification according to the degree of risk and labeling of objects, and real-time defect detection is performed. The proposed technique can provide real-time feedback in the pipeline defect detection process, and it would be minimizing the possibility of missing diagnoses and improve the existing water and sewerage pipe diagnosis processing capability.