• Journal of Integrative Natural Science
• /
• v.11 no.4
• /
• pp.167-183
• /
• 2018

Electroencephalogram (EEG) recording provides a new way to support human-machine communication. It gives us an opportunity to analyze the neuro-dynamics of human cognition. Machine learning is a powerful for the EEG classification. In addition, machine learning can compensate for high variability of EEG when analyzing data in real time. However, the optimal EEG electrode location must be prioritized in order to extract the most relevant features from brain wave data. In this paper, we propose an intelligent system model for the extraction of EEG data by training the optimal electrode location of EEG in a specific problem. The proposed system is basically a fuzzy system and uses a neural network structurally. The fuzzy clustering method is used to determine the optimal number of fuzzy rules using the features extracted from the EEG data. The parameters and weight values found in the process of determining the number of rules determined here must be tuned for optimization in the learning process. Genetic algorithms are used to obtain optimized parameters. We present useful results by using optimal rule numbers and non - symmetric membership function using EEG data for four movements with the right arm through various experiments.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2019.05a
• /
• pp.15-17
• /
• 2019

Some blind spots of information were occurring because important information such as school events, employment information, attendance information, and major school schedules were currently communicated through home communication messages only. To address this problem, an e-Board prototype was designed to incorporate P2P-based Internet of Things technology in a wired and wireless network based on a survey of data on smart education based on the Internet of Things. In each classroom, necessary information, such as school events, was received in real time from the classroom and shared in the classroom. They also want to design an e-Board prototype for Internet of Things-based smart education because they are easily accessible to anyone even if they do not know how to use e-Board.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2018.11a
• /
• pp.110-113
• /
• 2018

최근 인터넷 미디어 스트리밍 수요의 증가로 인해 CDN(Content Delivery Network) 서버 비용이 크게 증가하였으며 이를 절감하기 위한 방안의 필요성이 날로 증가하고 있다. 이러한 상황에 맞춰 최근 CDN 서버 비용을 절감할 수 있는 WebRTC(Web Real-Time Communication) 표준 기반의 P2P(Peer-to-Peer) 통신을 병용하는 DASH(Dynamic Adaptive Streaming over HTTP) 기술이 등장하였다. 본 논문에서는 이 기술의 CDN 서버 부하 절감 효과를 크게 개선할 수 있는 알고리듬을 제안한다. 또한 실제 모바일 네트워크 환경과 유사하게 실험 조건을 설정한 후, 이 알고리듬을 구현하여 그 성능을 측정한 결과, 기존과 비교하여 더 높은 절감 효과를 달성할 수 있음을 실험실 내 실험을 통해 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.12
• /
• pp.5654-5668
• /
• 2018

Driven by security and real-time demands of Internet of Things (IoT), the timing of fog computing and edge computing have gradually come into place. Gateways bear more nearby computing, storage, analysis and as an intelligent broker of the whole computing lifecycle in between local devices and the remote cloud. In fog computing, the edge broker requires X-aware capabilities that combines software programmability, stream processing, hardware optimization and various connectivity to deal with such as security, data abstraction, network latency, service classification and workload allocation strategy. The prosperous of Field Programmable Gate Array (FPGA) pushes the possibility of gateway capabilities further landed. In this paper, we propose a software-defined gateway (SDG) scheme for fog computing paradigm termed as Fog Computing Zero-Knowledge Gateway that strengthens data protection and resilience merits designed for industrial internet of things or highly privacy concerned hybrid cloud scenarios. It is a proxy for fog nodes and able to integrate with existing commodity gateways. The contribution is that it converts Privacy-Enhancing Technologies rules into provable statements without knowing original sensitive data and guarantees privacy rules applied to the sensitive data before being propagated while preventing potential leakage threats. Some logical functions can be offloaded to any programmable micro-controller embedded to achieve higher computing efficiency.

• Journal of Information Technology Services
• /
• v.18 no.1
• /
• pp.187-200
• /
• 2019

Bankruptcy prediction model is an issue that has consistently interested in various fields. Recently, as technology for dealing with unstructured data has been developed, researches applied to business model prediction through text mining have been activated, and studies using this method are also increasing in bankruptcy prediction. Especially, it is actively trying to improve bankruptcy prediction by analyzing news data dealing with the external environment of the corporation. However, there has been a lack of study on which news is effective in bankruptcy prediction in real-time mass-produced news. The purpose of this study was to evaluate the high impact news on bankruptcy prediction. Therefore, we classify news according to type, collection period, and analyzed the impact on bankruptcy prediction based on sentiment analysis. As a result, artificial neural network was most effective among the algorithms used, and commentary news type was most effective in bankruptcy prediction. Column and straight type news were also significant, but photo type news was not significant. In the news by collection period, news for 4 months before the bankruptcy was most effective in bankruptcy prediction. In this study, we propose a news classification methods for sentiment analysis that is effective for bankruptcy prediction model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.135-138
• /
• 2009

G-Sensor is being used for controlling motion of smart-phone and robot. G-Sensor can control motion to several direction, because it is composed of X, Y, and Z axis and also can be used on many mobile-phone by using Wi-Fi communication and RS-232C communication on the Bluetooth module. In this research, we suggest the application that realize and develop visual-vehicle-remote-control-system by using mobile-phone with G-Sensor so that drivers can more easily remote control and manage their vehicle with mobile-phone in real-time visual.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.2
• /
• pp.19-25
• /
• 2021

In this paper proposes a method of finding missing persons based on face-recognition technology and deep learning. In this paper, a real-time face-recognition technology was developed, which performs face verification and improves the accuracy of face identification through data fortification for face recognition and convolutional neural network(CNN)-based image learning after the pre-processing of images transmitted from a mobile device. In identifying a missing person's image using the system implemented in this paper, the model that learned both original and blur-processed data performed the best. Further, a model using the pre-learned Noisy Student outperformed the one not using the same, but it has had a limitation of producing high levels of deflection and dispersion.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.4
• /
• pp.251-261
• /
• 2022

The Centimeter Level Augmentation Service (CLAS) is the Precise Point Positioning (PPP) - Real Time Kinematic (RTK) correction service utilizing the Quasi-Zenith Satellite System (QZSS) L6 (1278.65 MHz) signal to broadcast the Global Navigation Satellite System (GNSS) error corrections. Compact State-Space Representation (CSSR) corrections for mitigating GNSS measurement error sources such as satellite orbit, clock, code and phase biases, tropospheric error, ionospheric error are estimated from the ground segment of QZSS CLAS using the code and carrier-phase measurements collected in the Japan's GNSS Earth Observation Network (GEONET). Since the CLAS service begun on November 1, 2018, users with dedicated receivers can perform cm-level precise positioning using CSSR corrections. In this paper, CLAS-based VRS-RTK performance evaluation was performed using Global Positioning System (GPS) observables collected from the refence station, TSK2, located in Japan. As a result of performing GPS-only RTK positioning using the open-source software CLASLIB and RTKLIB, it took about 15 minutes to resolve the carrier-phase ambiguities, and the RTK fix rate was only about 41%. Also, the Root Mean Squares (RMS) values of position errors (fixed only) are about 4cm horizontally and 7 cm vertically.

• Journal of Information Processing Systems
• /
• v.17 no.3
• /
• pp.599-614
• /
• 2021

This paper proposes a digital signage system based on an intelligent recommendation model. The proposed system consists of a server and an edge. The server manages the data, learns the advertisement recommendation model, and uses the trained advertisement recommendation model to determine the advertisements to be promoted in real time. The advertisement recommendation model provides predictions for various products and probabilities. The purchase index between the product and weather data was extracted and reflected using correlation analysis to improve the accuracy of predicting the probability of purchasing a product. First, the user information and product information are input to a deep neural network as a vector through an embedding process. With this information, the product candidate group generation model reduces the product candidates that can be purchased by a certain user. The advertisement recommendation model uses a wide and deep recommendation model to derive the recommendation list by predicting the probability of purchase for the selected products. Finally, the most suitable advertisements are selected using the predicted probability of purchase for all the users within the advertisement range. The proposed system does not communicate with the server. Therefore, it determines the advertisements using a model trained at the edge. It can also be applied to digital signage that requires immediate response from several users.

• Korean Journal of Optics and Photonics
• /
• v.32 no.3
• /
• pp.108-113
• /
• 2021

We propose and experimentally demonstrate a method of remote sound extraction using laser Doppler interferometry. The output frequency of a laser Doppler interferometer changes to be the same as the frequency of the acoustic wave from than object vibrated by the sound due to the Doppler effect. Based on this phenomenon, we measure the vibrational frequency of a remote target affected by a sound wave in real time, via laser Doppler interferometry. We track the peak frequency of the interferometer's output via appropriate signal processing, which confirms that the characteristics of the so detected wave are the same as that of the original sound source. We also confirm that the same method can retrieve the sound waves not only from remote sources of single tones, but from those of any sound.