• KIPS Transactions on Computer and Communication Systems
• /
• v.8 no.1
• /
• pp.17-28
• /
• 2019

In the financial investment management strategy, the distributed investment selecting and combining various financial assets is called portfolio management theory. In recent years, the blockchain based financial assets, such as cryptocurrencies, have been traded on several well-known exchanges, and an efficient portfolio management approach is required in order for investors to steadily raise their return on investment in cryptocurrencies. On the other hand, deep learning has shown remarkable results in various fields, and research on application of deep reinforcement learning algorithm to portfolio management has begun. In this paper, we propose an efficient financial portfolio investment management method based on Asynchronous Advantage Actor-Critic (A3C), which is a representative asynchronous reinforcement learning algorithm. In addition, since the conventional cross-entropy function can not be applied to portfolio management, we propose a proper method where the existing cross-entropy is modified to fit the portfolio investment method. Finally, we compare the proposed A3C model with the existing reinforcement learning based cryptography portfolio investment algorithm, and prove that the performance of the proposed A3C model is better than the existing one.

• Smart Media Journal
• /
• v.13 no.3
• /
• pp.9-17
• /
• 2024

Due to the recent pandemic and the development of ICT technology, the use of non-face-to-face and unmanned systems is expanding, and it is very important to understand emotions in communication in non-face-to-face situations. As emotion recognition methods for various facial expressions are required to understand emotions, artificial intelligence-based research is being conducted to improve facial expression emotion recognition in image data. However, existing research on facial expression emotion recognition requires high computing power and a lot of learning time because it utilizes a large amount of data to improve accuracy. To improve these limitations, this paper proposes a method of recognizing facial expressions using age and gender, which are image meta information, as a method of recognizing facial expressions with even a small amount of data. For facial expression emotion recognition, a face was detected using the Yolo Face model from the original image data, and age and gender were classified through the VGG model based on image meta information, and then seven emotions were recognized using the EfficientNet model. The accuracy of the proposed data classification learning model was higher as a result of comparing the meta-information-based data classification model with the model trained with all data.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.133-140
• /
• 2012

This study starts from interests on an endeavor of each economy unit, especially the enterprises, for the survival and sustainability of themselves. Competition, how to get it, maintain it and advance it! Agreeing the perceivedness of industries, scholars and public; what the core competition of manufacturer is an competitiveness of product, this study focuses on the PLM system as the key solution for obtaining the competitiveness of product with reviewing the contents and studies of PLM formulated. PLM is highlighted as the one of top tier ICT solution for the product development domain of manufacturing industry today. First of all, this study deals with the opinion of actual work-site and management of our small&medium business for the benefits of PLM based on product development; the impact on the performances of management, which is the key objective of the existence of enterprises. In conclusion, the answers for these questionnaires shows positive perception of actual work-sites and managers for the PLM system. They agree some useful effects on shortening the term and downsizing the cost of product development due to Data integration and Process management, even if they have not full confidence on the effectiveness of the individual functionality of the PLM system.

• Journal of Convergence for Information Technology
• /
• v.9 no.4
• /
• pp.1-7
• /
• 2019

The medical environment, combined with IT technology, is changing the paradigm for medical services from treatment to prevention. In particular, as ICT convergence digital healthcare technology is applied to hospital medical systems, infrastructure technologies such as big data, Internet of Things, and artificial intelligence are being used in conjunction with the cloud. In particular, as medical services are used with IT devices, the quality of medical services is increasingly improving to make them easier for users to access. Medical institutions seeking to incorporate IoT services into cloud health care environment services are trying to reduce hospital operating costs and improve service quality, but have not yet been fully supported. In this paper, a patient information collection model from hospital IoT system, which has established a cloud environment, is proposed. The proposed model prevents third parties from illegally eavesdropping and interfering with patients' biometric information through IoT devices attached to the patient's body at hospitals in cloud environments that have established hospital IoT systems. The proposed model allows clinicians to analyze patients' disease information so that they can collect and treat diseases associated with their eating habits through IoT devices. The analyzed disease information minimizes hospital work to facilitate the handling of prescriptions and care according to the patient's degree of illness.

• Journal of Wetlands Research
• /
• v.24 no.1
• /
• pp.38-43
• /
• 2022

Smart sewage treatment plant means creating a safe and clean water environment by establishing an ICT-based real-time monitoring, remote control management and intelligent system for the entire sewage treatment process. The core technology of such a smart sewage treatment plant can be operation control technology using measuring instruments. This research team analyzed and suggested the operation control technologies necessary for the establishment of the intelligent business by referring to the intelligent research projects of the sewage treatment plant in progress in Korea. As a result of the analysis, a total of six removal technologies were presented, including control by scale, reflow water control, linked treated water control, chemical quantity control, winter operation control, and total organic carbon control. By size, standards that can be classified into small and medium-sized large-scale are presented, and in the case of reflow water control, the location of water quality and flow sensors capable of managing reflow water is suggested. In the case of the linked treated water control, the influence and control points of the linked treated water on the sewage treatment plant were presented, and in the case of the chemical injection volume control, a system capable of optimizing the amount of chemical injection according to the introduction of an intelligent sewage treatment plant was presented. In the case of winter operation, the sensors and pumps to be controlled are suggested when considering the decrease in nitrification due to the decrease in water temperature. In the case of total organic carbon control, an interlocking system considering the total amount of pollution in the future was proposed. These operation control scenarios are expected to be used as basic data to be used in intelligent sewage treatment algorithms and scenarios in the future.

• Journal of Appropriate Technology
• /
• v.6 no.1
• /
• pp.56-64
• /
• 2020

Recently, major manufacturers are focusing their efforts on securing global competitiveness through smart factory, but developing countries have many difficulties in applying smart factory due to financial and technical conditions. This study is a preliminary study on the development of an ICT-based power monitoring system applicable to developing countries. The questionnaire surveyed and analyzed workers' perceptions of smart factory in a garment manufacturing factory in developing countries, Indonesia. Before and after the installation of the power monitoring system, the survey was conducted for 126 local managers and workers, and the correlation was analyzed using SPSS. As a result of analysis, factory workers in developing countries such as Indonesia are also positively aware of the necessity of introducing smart factory technology, and it is expected that the introduction of these technologies will affect job satisfaction and improve the factory environment. In addition, the result of the survey conducted after the installation of the power monitoring system increased the job satisfaction score by 5.5% compared to before the installation, and the scores on the perception of the necessity of the power monitoring system and the positive effect of the application of the system on the factory environment were increased 13% and 5.9%, respectively. It was also confirmed that managers rather than workers and female rather than male showed positive perception for the introduction of smart factory technology. The result of this study is expected to be an important reference in the direction of development of appropriate smart factory technology applicable to developing countries and the introduction of smart factory by manufacturers operating factories in developing countries.

• Journal of Practical Engineering Education
• /
• v.14 no.2
• /
• pp.387-392
• /
• 2022

To participate in global carbon neutrality, the Korean government is also planning to carry out zero-energy building certification for all buildings by 2030 through the enforcement decree of the 'Green Building Support Act'. Accordingly, the government is providing various projects related to solar power generation, which are relatively close to life. In particular, roof-mounted photovoltaic power generation systems are attracting attention in terms of using unused space to produce energy without destroying the environment, but low power generation efficiency compared to other photovoltaic power generation facilities is pointed out as a disadvantage. Therefore, in this paper, to solve this problem, we propose an efficient solar panel angle variable system through research on the solar panel structure for single-axial solar tracking, and also consider the application environment of the roof-mounted solar power generation system. Suggests measures to prevent damage and secondary damage. In addition, it is judged that it is possible to control the solar panel based on ICT convergence and configure the accident prediction safety system to link the project-based education program.

• Journal of Korea Water Resources Association
• /
• v.56 no.6
• /
• pp.403-417
• /
• 2023

In this research, a methodology was developed for constructing an appropriate rainfall image database for estimating rainfall intensity based on CCTV video. The database was constructed in the Large-Scale Climate Environment Chamber of the Korea Conformity Laboratories, which can control variables with high irregularity and variability in real environments. 1,728 scenarios were designed under five different experimental conditions. 36 scenarios and a total of 97,200 frames were selected. Rain streaks were extracted using the k-nearest neighbor algorithm by calculating the difference between each image and the background. To prevent overfitting, data with pixel values greater than set threshold, compared to the average pixel value for each image, were selected. The area with maximum pixel variability was determined by shifting with every 10 pixels and set as a representative area (180×180) for the original image. After re-transforming to 120×120 size as an input data for convolutional neural networks model, image augmentation was progressed under unified shooting conditions. 92% of the data showed within the 10% absolute range of PBIAS. It is clear that the final results in this study have the potential to enhance the accuracy and efficacy of existing real-world CCTV systems with transfer learning.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.11a
• /
• pp.8-10
• /
• 2017

지상파 UHD 방송은 시청자에게 기존 HD 방송화면보다 4배 더 선명한 영상 서비스를 제공하며, 광대역 통신망과 결합한 홈포탈(Home Portal) 서비스를 통해서 다양한 부가서비스를 지상파 방송과 함께 제공할 수 있다. 본 논문에서는 지상파 UHD TV 방송과 연계된 360도 가상현실(VR; Virtual Reality) 부가서비스 시스템과 이를 효과적으로 시청하기 위한 사용자환경을 제안한다. 방송의 ESG(Electronic Service Guide)를 통해 시청자는 VR 부가서비스임을 확인하고 스마트 단말기 또는 HMD(Head Mount Display) 등을 이용하여 마치 현장에 있는 듯한 체험을 즐길 수 있다. 제안한 부가서비스는 앱 형태로 스마트 단말기에 설치하여 실행하며 지상파 UHD TV의 ESG 정보로부터 프로그램 편성과 VR 지원여부를 확인한다. 이를 통해, 실시간 방송 뿐 아니라 VOD 형태로 제공되는 다양한 비디오 및 오디오 콘텐츠를 극장에서 보는 것과 같은 빅스크린 모드, 360도 VR 모드, 오디오 청취모드 등 다양한 시청환경에서 감상할 수 있다. 제안한 사용자 환경은 게임엔진을 기반으로 개발되어 가상의 시청 공간에서 장소를 이동하며 영상, 음향 등 미디어 콘텐츠를 감상할 수 있다. 전용컨트롤러를 이용하면 다양한 인터액티브 콘텐츠를 효과적으로 운용하여 감상할 수 있으며, 일반적으로 통용되는 VR 기기 제어 모드도 지원하여 HMD나 일반 스마트 단말기 어느 것을 이용해서도 용이하게 사용자 메뉴를 선택할 수 있다. 제안된 시스템의 시제품은 IBC 2017 및 평창 ICT 체험관을 통해 발표되었다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.3
• /
• pp.365-369
• /
• 2015

In this paper, geographic information system(GIS) for an intelligent power distribution network was implemented with location informations acquired from automatic meter reading system, where the location informations of power line communication(PLC) modems installed at customer side were collected at data concentration units(DCUs) of headend equipment via PLC and then were transmitted to front end processor server. By displaying the connection status of the power distribution network on GIS map, operation of advanced metering infrastructure(AMI) or management of power grid system could be performed intuitionally and in real time, because the configuration state of the power grid could be easily monitored. The feasibility of the proposed system was confirmed with the especially constructed laboratory-level test bed and the verification test of the system will be carried out for a real power distribution network.