• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.10a
• /
• pp.671-673
• /
• 2016

기술의 발전에 따라 소형 디바이스에서도 데이터를 수집하고 전송하는 것이 가능해졌다. 따라서 최근 IoT와 헬스케어가 부각되고 있으며 여기서 발생한 데이터에 대한 많은 연구가 진행되고 있다. 그 중에서도 헬스케어 장비에 내장된 심전도 센서를 이용하여 시계열 데이터를 수집할 수 있고, 여기서 수집한 데이터는 부정맥 등의 심장질환 진단의 중요한 지표로서 사용될 수 있다. 시계열 데이터는 시계열 분석 방법을 사용하여 정상 패턴과 비정상 패턴으로 분류할 수 있지만, 대량의 시계열 분석 방법은 수행시간이 많이 소요되기 때문에 이를 단축 할 필요성이 있다. 본 논문에서는 시계열 데이터 분석 기법 중 하나인 Shapelet을 사용하여 심전도 데이터의 패턴을 정상 및 비정상으로 분류하였고, 병렬처리 기법을 적용하여 수행시간을 단축하였다. 실험 결과, 각각의 심전도 데이터는 87%의 정확도로 분류되었고, Shapelets을 탐색하는 구간의 병렬처리를 통하여 수행 시간이 약 60%로 감소하였음을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.11a
• /
• pp.764-767
• /
• 2017

최근 개인정보 활용에서 보안 및 인증에 대한 중요성이 대두되고 있으며, IoT 기반의 바이오 디바이스를 접목한 생체인식 기술은 사용자의 식별과 인증을 위해 다양한 분야에서 많은 발전을 보이고 있다. 본 논문에서는 대규모 뇌파신호를 효과적으로 처리하기 위한 방안으로 Deep Learning 기법을 적용한 뇌파 데이터 식별과 이를 분석한 사용자 인증이 가능한 스마트 자물쇠 모델을 제안한다. 제안한 뇌파신호를 활용한 Deep Learning 기반 사용자 식별 및 인증 모델은 보안 시스템에서의 활용뿐만 아니라 다양한 사물인터넷과 접목 시킬 수 있으며, 뇌성마비 또는 신체 활동이 제한적인 환자의 경우 일상생활의 제약을 줄이고 삶의 질적 향상에 도움이 될 것으로 기대한다.

• Journal of the Korea Convergence Society
• /
• v.8 no.9
• /
• pp.25-30
• /
• 2017

The Connected House is a new type of IT convergence service that combines new communication services with existing IT systems such as M2M, NFC, smart home, and smart grid. It is a future connected life service that connects to any device anytime, anywhere. In this paper, we designed an intelligent gateway, a connected office solution for the Internet of things, which provides a connected life service for the future, and can control various sensors, ZigBee/Z-Wave/NFC and terminal devices. In addition, IP/SIP/IMS cameras and video door phones that are linked to the gateway have been developed to satisfy the quality standards of domestic communication service providers in terms of voice quality, jitter, and frame rate.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.05a
• /
• pp.724-727
• /
• 2014

This paper is analyzing the situation of the Internet of Things Industry and draw the policy implications to promote Internet of Things industry. Major IT companies as Apple, Google, IBM, Sony, and Samsung have developed various smart glass and smart watch as a Iot products. In order to promote Iot Industry, we should take the build up of eco system between IT makers and the various contents provider, protection of personal information and data, development of killer applications and business models, and the conversion from IPv4 to IPv6 as a next internet address infra, build up of international standard platform on IoT.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.4
• /
• pp.165-172
• /
• 2023

Heterogeneous computing is a technology that utilizes different types of processors to perform parallel processing. It maximizes task processing and energy efficiency by leveraging various computing resources such as CPUs, GPUs, and FPGAs. On the other hand, edge computing has developed with IoT and 5G technologies. It is a distributed computing that utilizes computing resources close to clients, thereby offloading the central server. It has evolved to intelligent edge computing combined with artificial intelligence. Intelligent edge computing enables total data processing, such as context awareness, prediction, control, and simple processing for the data collected on the edge. If heterogeneous computing can be successfully applied in the edge, it is expected to maximize job processing efficiency while minimizing dependence on the central server. In this paper, experiments were conducted to verify the feasibility of various parallel programming models on high-end and low-end edge devices by using benchmark applications. We analyzed the performance of five parallel programming models on the Raspberry Pi 4 and Jetson Orin Nano as low-end and high-end devices, respectively. In the experiment, OpenACC showed the best performance on the low-end edge device and OpenSYCL on the high-end device due to the stability and optimization of system libraries.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.178-180
• /
• 2021

In this paper, we design a system to monitor environmental data in fish farms in real-time and provide machine learning-based prediction services to prevent damage on fish farms caused by changes in the sea environment. The proposed system will install an IoT device module consisting of sensors that can measure hydrogen concentration, salinity, dissolved oxygen, and water temperature, which can be transferred to Cloud DB using LTE or LoRa communication technology and then monitor the real-time condition through a web or mobile application. In addition, it has a function to prepare for changes within the environment of fish farms by applying machine learning-based prediction technology using collected data.

• Smart Media Journal
• /
• v.6 no.4
• /
• pp.58-64
• /
• 2017

Modern society is characterized by rapid increase in world population, aging of the rural population, decrease of cultivation area due to industrialization. The food problem is becoming an important issue with the farmers and becomes rural. Recently, the researches about the field of the smart farm are actively carried out to increase the profit of the rural area. The existing smart farm researches mainly monitor the cultivation environment of the crops in the greenhouse, another way like in the case of poor quality t is being studied that the system to control cultivation environmental factors is automatically activated to keep the cultivation environment of crops in optimum conditions. The researches focus on the crops cultivated indoors, and there are not many studies applied to the cultivation environment of crops grown outside. In this paper, we propose a method to improve the harvestability of poor areas by monitoring the areas with bad harvests by using big data analysis, by precisely predicting the harvest timing of fruit trees growing in orchards. Factors besides for harvesting include fruit color information and fruit weight information We suggest that a harvest correlation factor data collected in real time. It is analyzed using the Apache Spark engine. The Apache Spark engine has excellent performance in real-time data analysis as well as high capacity batch data analysis. User device receiving service supports PC user and smartphone users. A sensing data receiving device purpose Arduino, because it requires only simple processing to receive a sensed data and transmit it to the server. It regulates a harvest time of fruit which produces a good quality fruit, it is needful to determine a poor harvest area or concentrate a bad area. In this paper, we also present an architectural model to determine the bad areas of fruit harvest using strong data analysis.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.25-31
• /
• 2016

With the development of IOT technology and the expansion of ICT services recently, a variety of home network services have been advanced based on wired and wireless high speed telecommunication. Domestic and global companies have been studying on the innovative technology for the users using IOT based technology and the environment for the smart home services has been gradually developed. The users live their lives with more convenience due to the expansions and developments of smart phones. However, the threatening on the security of the smart home network had occurred by various attacks with the connection to the smart environment telecommunication, lack of applications on low powered and light weight telecommunication, and the problems of security guideline. In addition, the solutions are required for the new and variant attacking cases such as data forgery and alteration of the device for disguising approach with ill will. In this article, the safe communication protocol was designed using certification management technique based on AKI which supplemented the weakness of PKI, the existing certification system in the smart environment. Utilizing the signature technique based on ECDSA, the efficiency on the communication performance was improved, and the security and the safety were analyzed on the security threat under the smart home environment.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.5
• /
• pp.143-149
• /
• 2016

Recent accidents caused by toxic chemicals and the social problems caused by frequent. As of 2010, there are more than 100,000 types of deadly toxic chemicals being distributed throughout Korea, and severely intoxicated patients along with an enormous number of patients can be induced at the time of an accident involving deadly toxic chemicals. Internationally, the seriousness of large-scale disasters due to a NBC disaster (nuclear, biologic and chemical disaster) is being highlighted as well. So, we obtain the information of the RFID tag attached to a glass bottle with containing the toxic chemical to transfer the data to the smart device has been studied a system that can monitor the status of the toxic chemical in real time. The proposed system is the information was sent to the main system using a zigbee communication by recognizing the tag vial containing the toxic chemical with the 13.56MHz bandwidths good permeability. User may check the information in real time by utilizing the smart device. However, the error of the system for managing the toxic chemical generates a result that can not be predicted. Failure of the system was detecting the error by using a comparator as this can cause an error. And the detected error proposed a duplex system so that they do not affect the overall system.

• Smart Media Journal
• /
• v.9 no.2
• /
• pp.16-21
• /
• 2020

Recently, mobile traffic is increasing exponentially as major traffic is transferred to IoT and visual media data in the dissemination of mobile communication terminals and contents use. In order to overcome the limitations of the existing LTE system, 5G mobile communication technology (5G) is a technology that meets 1000 times data traffic capacity, 4G LTE system acceptance, low latency, high energy efficiency, and high cost compared to 4G LTE system. The path loss due to the use of the frequency domain is very high, so it may be difficult to provide a service compared to the existing 4G LTE system. To overcome these shortcomings, various techniques are under study. In this paper, small cell technology is introduced to improve the system performance of 5G mobile communication systems. The performance is analyzed by comparing the results of small cell technology application, macro communication and small cell communication, and the results of the proposed algorithm application for power control. The analysis results show that the use of small cell technology in the 5th generation mobile communication system can significantly reduce the shadow area and reduce the millimeter wave path loss problem.