• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.47-49
• /
• 2022

Robot navigation has seen a major improvement since the the rediscovery of the potential of Artificial Intelligence (AI) and the attention it has garnered in research circles. A notable achievement in the area was Deep Learning (DL) application in computer vision with outstanding daily life applications such as face-recognition, object detection, and more. However, robotics in general still depend on human inputs in certain areas such as localization, navigation, etc. In this paper, we propose a study case of robot navigation based on deep reinforcement technology. We look into the benefits of switching from traditional ROS-based navigation algorithms towards machine learning approaches and methods. We describe the state-of-the-art technology by introducing the concepts of Reinforcement Learning (RL), Deep Learning (DL) and DRL before before focusing on visual navigation based on DRL. The case study preludes further real life deployment in which mobile navigational agent learns to navigate unbeknownst areas.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.6
• /
• pp.873-879
• /
• 2013

In this paper, high-quality business-type communications(UC) capabilities of the communication activities overlap, waste, reducing rework process improvement provides for high efficiency. Messages sent via UC app development, FMC calling features, schedule management organization for the development and deployment DataBase UC server deployment, the search for the JSP implementation, XMPP is using the messaging system. IP-PBX running on the IP network, on the basis of UC applications in real life, improve utilization of the infrastructure necessary to provide services to the system design and implementation.

• Smart Structures and Systems
• /
• v.10 no.3
• /
• pp.209-228
• /
• 2012

Structural health monitoring with wireless sensor networks has received much attention in recent years due to the ease of sensor installation and low deployment and maintenance costs. However, sensor network technology needs to solve numerous challenges in order to substitute conventional systems: large amounts of data, remote configuration of measurement parameters, on-site calibration of sensors and robust networking functionality for long-term deployments. We present a structural health monitoring network that addresses these challenges and is used in several deployments for monitoring of bridges and buildings. Our system supports a diverse set of sensors, a library of highly optimized processing algorithms and a lightweight solution to support a wide range of network runtime configurations. This allows flexible partitioning of the application between the sensor network and the backend software. We present an analysis of this partitioning and evaluate the performance of our system in three experimental network deployments on civil structures.

• Journal of Korean Society for Quality Management
• /
• v.47 no.1
• /
• pp.1-15
• /
• 2019

Purpose: The purpose of this study is to support SMEs' introduction of smart factories during the $4^{th}$ Industrial Revolution era. Through this study, we developed the readiness assessment framework for SMEs. This study draws practical implications for improving the readiness of SMEs to introduce smart factories. Methods: Readiness Assessment Framework Design method, Case Studies Analysis Results: This study identified SMEs suitable for smart factories and identified key issues for nonconforming companies. And the diagnostic framework has been determined whether it works in a real-life SME environment. Conclusion: In order to succeed in the smart factory deployment, readiness assessment for SMEs should be performed as necessary. Prior to the introduction of smart factories, quality innovation activities should be carried out according to factory level.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.145-145
• /
• 2022

Availability of abundant water resources data in developing countries is a great concern that has hindered the adoption of deep learning techniques (DL) for disaster prevention and mitigation. On the contrary, over the last two decades, a sizeable amount of DL publication in disaster management emanated from developed countries with efficient data management systems. To understand the current state of DL adoption for solving water-related disaster management in developing countries, an extensive bibliometric review coupled with a theory-based analysis of related research documents is conducted from 2003 - 2022 using Web of Science, Scopus, VOSviewer software and PRISMA model. Results show that four major disasters - pluvial / fluvial flooding, land subsidence, drought and snow avalanche are the most prevalent. Also, recurrent flash floods and landslides caused by irregular rainfall pattern, abundant freshwater and mountainous terrains made India the only developing country with an impressive DL adoption rate of 50% publication count, thereby setting the pace for other developing countries. Further analysis indicates that economically-disadvantaged countries will experience a delay in DL implementation based on their Human Development Index (HDI) because DL implementation is capital-intensive. COVID-19 among other factors is identified as a driver of DL. Although, the Long Short Term Model (LSTM) model is the most frequently used, but optimal model performance is not limited to a certain model. Each DL model performs based on defined modelling objectives. Furthermore, effect of input data size shows no clear relationship with model performance while final model deployment in solving disaster problems in real-life scenarios is lacking. Therefore, data augmentation and transfer learning are recommended to solve data management problems. Intensive research, training, innovation, deployment using cheap web-based servers, APIs and nature-based solutions are encouraged to enhance disaster preparedness.

• Advances in Computational Design
• /
• v.3 no.4
• /
• pp.385-404
• /
• 2018

The study investigated an area of sustainable structural design that is often overlooked in practical engineering applications. Specifically, a novel method to simultaneously optimise the cost and embodied carbon performance of steel building structures was explored in this paper. To achieve this, a parametric design model was developed to analyse code compliant structural configurations based on project specific constraints and rigorous testing of various steel beam sections, floor construction typologies (precast or composite) and column layouts that could not be performed manually by engineering practitioners. Detailed objective functions were embedded in the model to compute the cost and life cycle carbon emissions of the different material types used in the structure. Results from a comparative numerical analysis of a real case study illustrated that the proposed optimisation approach could guide structural engineers towards areas of the solution space with realistic design configurations, enabling them to effectively evaluate trade-offs between cost and carbon performance. This significant contribution implied that the optimisation model could reduce the time required for the design and analysis of multiple structural configurations especially during the early stages of a project. Overall, the paper suggested that the deployment of automated design procedures can enhance the quality as well as the efficiency of the optimisation analysis.

• Journal of Communications and Networks
• /
• v.11 no.1
• /
• pp.57-71
• /
• 2009

Networking together hundreds or thousands of cheap sensor nodes allows users to accurately monitor a remote environment by intelligently combining the data from the individual nodes. As sensor nodes are typically battery operated, it is important to efficiently use the limited energy of the nodes to extend the lifetime of the wireless sensor network (WSN). One of the fundamental issues in WSNs is the coverage problem. In this paper, the border coverage problem in WSNs is rigorously analyzed. Most existing results related to the coverage problem in wireless sensor networks focused on planar networks; however, three dimensional (3D) modeling of the sensor network would reflect more accurately real-life situations. Unlike previous works in this area, we provide distributed algorithms that allow the selection and activation of an optimal border cover for both 2D and 3D regions of interest. We also provide self-healing algorithms as an optimization to our border coverage algorithms which allow the sensor network to adaptively reconfigure and repair itself in order to improve its own performance. Border coverage is crucial for optimizing sensor placement for intrusion detection and a number of other practical applications.

• Smart Structures and Systems
• /
• v.6 no.3
• /
• pp.263-275
• /
• 2010

In the last decade, wireless sensor networks have emerged as a promising technology that could accelerate progress in the field of structural monitoring. The main advantages of wireless sensor networks compared to conventional monitoring technologies are fast deployment, small interference with the surroundings, self-organization, flexibility and scalability. These features could enable mass application of monitoring systems, even on smaller structures. However, since wireless sensor network nodes are battery powered and data communication is the most energy consuming task, transferring all the acquired raw data through the network would dramatically limit system lifetime. Hence, data reduction has to be achieved at the node level in order to meet the system lifetime requirements of real life applications. The objective of this paper is to discuss some general aspects of data processing and management in monitoring systems based on wireless sensor networks, to present a prototype monitoring system for civil engineering structures, and to illustrate long-term field test results.

• Journal of the Institute of Convergence Signal Processing
• /
• v.10 no.3
• /
• pp.181-185
• /
• 2009

Recently, much attention to a self-organizing mobile ad-hoc network is escalating along with progressive deployment of wireless networks in our everyday life. Being readily deployable, the MANET (mobile ad hoc network) can find its applications to emergency medical service, customized calling service, group-based communications, and military purposes. In this paper we investigate a time slot exchange problem found in the time slot based MAC, that is designed for IEEE 802.11b interfaces composing a MANET. The paper provides a method to maintain the quality of voice call by providing a new time slot when the channel assigned for that time slot gets noisy with interferences induced from other nodes, which belong to the same and/or other subgroups. In order to assess the performance of the proposed algorithm, a set of simulations using the OPNET modeler has been performed assuming that the IEEE 802.11b interfaces are operating under a modified MAC, which is a time slot based reservation MAC implemented in the PCF part of the superframe. In a real-time voice call service over a MANET of a size 500 ${\times}$ 500 meter squares with the number of nodes up to 100, the simulation results are collected and analyzed with respect to the packet loss rate and packet delay. The results show us that the proposed time slot exchange protocol improves the quality of voice call over that of plain DCF.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.38 no.2
• /
• pp.49-58
• /
• 2024

The rapid advancement of generative large language models has revolutionized various real-life domains, emphasizing the importance of exploring their applications in healthcare. This study aims to examine how generative large language models are implemented in the medical domain, with the specific objective of searching for the possibility and potential of integration between generative large language models and East Asian medicine. Through a comprehensive current state analysis, we identified limitations in the deployment of generative large language models within East Asian medicine and proposed directions for future research. Our findings highlight the essential need for accumulating and generating structured data to improve the capabilities of generative large language models in East Asian medicine. Additionally, we tackle the issue of hallucination and the necessity for a robust model evaluation framework. Despite these challenges, the application of generative large language models in East Asian medicine has demonstrated promising results. Techniques such as model augmentation, multimodal structures, and knowledge distillation have the potential to significantly enhance accuracy, efficiency, and accessibility. In conclusion, we expect generative large language models to play a pivotal role in facilitating precise diagnostics, personalized treatment in clinical fields, and fostering innovation in education and research within East Asian medicine.