• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.503-505
• /
• 2021

정보통신 기술(ICT)의 발달로 이루어진 4 차 산업혁명으로 '빅데이터'의 시대가 도래하고 있다. 소셜 네트워크 서비스(SNS), 사물인터넷(IOT), 인공지능(AI) 등 다양한 장소에서 다양한 형태로 데이터들이 쌓이고 있다. 그중 MBTI 성격유형 검사를 통한 다양한 분석 시스템이 많아지고 있다. 사람들은 재미를 위해 자신의 성향을 입력하고 정해진 MBTI 검사 기준을 통해 결과를 받는다. 이러한 개개인의 성향 데이터를 모으면 거대한 빅데이터 플랫폼을 만들 수 있을 것이라 기대한다. 이에 본 논문은 구체적인 방안을 제시하고자 한다.

• The Proceeding of the Korean Institute of Electromagnetic Engineering and Science
• /
• v.27 no.4
• /
• pp.19-28
• /
• 2016

최근 RFID와 같은 무선 센싱 네트워크 기술과 객체 추적을 위한 센싱 디바이스 및 다양한 컴퓨팅 자원들이 빠르게 발전함에 따라, 기존 웹의 형태는 소셜 웹에서 유비쿼터스 컴퓨팅 웹으로 자연스럽게 진화되고 있다. 유비쿼터스 컴퓨팅 웹에서 사물인터넷(IoT)은 기존의 컴퓨터를 대체할 수 있는데, 이것은 곧 한 사람과 주변 사물들 간에 연결되는 네트워크가 확장되는 것과 동시에 네트워크 안에서 생성되는 데이터의 수가 기하급수적으로 증가되는 것을 의미한다. 따라서 보다 지능적인 IoT 서비스를 위해서는, 수많은 미가공 데이터들 사이에서 사람의 의도와 상황을 실시간으로 정확히 파악할 수 있어야 한다. 이때 사물과의 상호작용을 위한 동작 인식 기술(Gesture recognition)은 집적적인 접촉을 필요로 하지 않기 때문에, 미래의 사람-사물 간 상호작용에 응용될 수 있는 잠재력을 갖고 있다. 한편, 기계학습 분야의 최신 알고리즘들은 다양한 문제에서 사람의 인지능력을 종종 뛰어넘는 성능을 보이고 있는데, 그 중에서도 의사결정나무(Decision Tree)를 기반으로 한 Decision Forest는 분류(Classification)와 회귀(Regression)를 포함한 전 영역에 걸쳐 우월한 성능을 보이고 있다. 따라서 본 논문에서는 지능형 IoT 서비스를 위한 다양한 동작 인식 기술들을 알아보고, 동작 인식을 위한 Decision Forest의 기본 개념과 구현을 위한 학습, 테스팅에 대해 구체적으로 소개한다. 특히 대표적으로 사용되는 3가지 학습방법인 배깅(Bagging), 부스팅(Boosting) 그리고 Random Forest에 대해 소개하고, 이것들이 동작 인식을 위해 어떠한 특징을 갖는지 기존의 연구결과를 토대로 알아보았다.

• KIPS Transactions on Computer and Communication Systems
• /
• v.5 no.11
• /
• pp.403-410
• /
• 2016

IoT(Internet of Things) has purpose for providing new kind of service though interaction with everything. With development of IoT, computer model which is based on internet is changed to distributed connection model between heterogeneous things. There is a problem that it is impossible to connect between each other different protocols. To solve this problem, we should abstract each of things of data through using adaptor of middleware structure in order to make consistent data unit. In this paper, we propose BLE(Bluetooth Low Energy) adaptor, which is interaction with things, based on DDS(Data Distribution Service) that is real-time standard middleware. It is possible to data interaction between BLE Devices as well as two-way data interaction with different protocol devices. Also existing BLE Devices and study have a problem that Data exchange without using a standard data format of a profile defined by the Bluetooth SIG. Using the data formats defined independently by a problem that should not exchange data according to the type and manufacturer of the device BLE. The BLE adapter to solve this problem, the classification and analysis of the 12 stand profile was applied to create a profile based on the standard data format. It is possible to get wide interoperability of not affected on the BLE devices type and manufacturer of the device because it is applied a profile that standard data format.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.10a
• /
• pp.947-948
• /
• 2015

IOT(Internet of things) is a technology to embed various sensors and communication features on diverse things such as home appliances, mobile devices, wearable computers and connect to the Internet and through this technology, the status of things connected to the network can be analyzed and controlled with various data. On the other hand, this paper suggests to develop a merchandise management app using Android-based barcode to systematically manage expiry date of various goods that we purchase in our daily life. Therefore, individual goods are recognized with mobile-based barcode and divided under each category. By additionally supporting the notification service to let us know about expire date, goods can be efficiently managed.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.709-710
• /
• 2019

제안 시스템은 모바일 사용자를 공공 인터넷 환경에서 사용 유형별로 분류 및 관리 가능한 서비스를 제공한다. 비콘을 이용하여 시스템 사용자의 위치와 서비스공간의 근접성을 확인한다. 또한 사용자의 서비스 사용 형태 및 성향에 따라 서비스 제공 장소에서 네트워크에 연결된 사물 인터넷 기기 및 기타 기기에 대한 접근 권한을 미리 정의하고 이를 제공할 수 있다. 본 연구는 이러한 시스템을 제안하고 구현된 결과를 바탕으로 시스템의 기능을 분석한다.

• Journal of Convergence for Information Technology
• /
• v.7 no.1
• /
• pp.55-60
• /
• 2017

In order to provide intelligent services without human intervention in the Internet of Things environment, it is necessary to analyze the big data generated by the IoT device and learn the normal pattern, and to predict the abnormal symptoms such as faulty or malfunction based on the learned normal pattern. The purpose of this study is to implement a machine learning model that can predict product failure by analyzing big data generated in various devices of product process. The machine learning model uses the big data analysis tool R because it needs to analyze based on existing data with a large volume. The data collected in the product process include the information about product faulty, so supervised learning model is used. As a result of the study, I classify the variables and variable conditions affecting the product failure, and proposed a prediction model for the product failure based on the decision tree. In addition, the predictive power of the model was significantly higher in the conformity and performance evaluation analysis of the model using the ROC curve.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.297-299
• /
• 2016

기술의 발달과 융합으로 사물인터넷(Internet of Things; IoT)의 시대가 열렸다. 빅 데이터와 센서의 발달로 인해 정보는 전과 달리 더욱 사용자와 밀접해졌고 다양해졌으며 양 또한 많아졌다. 이와 더불어 IoT 환경은 다양한 기술들이 융합된 구조로 기존 기술들이 가지고 있는 보안 취약점뿐만 아니라 보다 복잡한 보안 문제점들이 발생할 수 있다. 본 논문에서는 IoT 환경에서 서비스나 IoT 기기들이 갖춰야할 보안 요구사항들을 확장성(scalability), 상호운용성(interoperability), 최소 자원 필요성(minimum resource necessity)으로 분류 하고 정의하였으며, IoT 서비스를 제공하기 위해 사용하는 대표적 프로토콜인 MQTT(Message Queue Telemetry Transfer)와 CoAP(Constrained Application Protocol)에 초점을 맞춰 각각의 표준 문서에서 권고하고 있는 보안 기술에 대해 살펴본다. 또한 그런 기술들에 있어서 발생 가능한 보안 취약점들을 분석하고 이를 해결하기 위한 방법을 제시한다.

• Journal of Internet Computing and Services
• /
• v.16 no.5
• /
• pp.75-86
• /
• 2015

Internet of Thing (IoT) computing is an environment where various devices with sensors and actuators are connect, and interact together to acquire contexts and provide useful services. With the advances of IoT technologies, its usability becomes an in important issue. However, there exist various types of faults in IoT computing which are not conventionally addressed in software research community. Providing reliable IoT services is challenging. In this paper, we present a hierarchy of IoT faults and analyze causes and symptoms of the faults. Based on the analysis, we define effective methods for managing IoT faults. We believe that our proposed framework for managing IoT faults can be utilized in reducing the development cost of IoT applications and enhancing the quality of the applications.

• Smart Media Journal
• /
• v.6 no.2
• /
• pp.42-49
• /
• 2017

It is important to realize automation services by communicating in IoT with humans, objects & objects, and forming a common network. People used web like the most powerful network way to sharing things and communication. Therefore the efficiency method communication between each device and the web in IoT could be different from ones. The best method for high quality software product in web applications is software reuse ; Modules, classes, patterns, frameworks, and business components are reusable elements of various perspectives. Components is plugged with others through well-defined interfaces, which can overcome the operation and complexity of application development. A web-based distributed environment for IoT applications is a standard architecture use information collected from various devices for developing and using applications. For that reason, the network management which manages the constituent resources for the best service control in IoT application is required as a sub-layer support service in most applications as well as individual applications. In this paper, we measure to develop a network management system based not only by components but on heterogeneous internetworks. For procedure this, we clarify a component architecture for classifying and classify also the component needed in the IOT and network domain or order the type of real network management system.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.26 no.3
• /
• pp.667-678
• /
• 2016

Due to a development of the cable/wireless network infra, the traffic as big as unable to compare with the past is being served through the internet, the traffic is increasing every year following the change of the network paradigm such as the object internet, especially the traffic of about 1.6 zettabyte is expected to be distributed through the network in 2018. As the network traffic increases, the performance of the security infra is developing together to deal with the bulk terabyte traffic in the security equipment, and is generating hundreds of thousands of security events every day such as hacking attempt and the malignant code. Efficiently analyzing and responding to an event on the attack attempt detected by various kinds of security equipment of company is one of very important assignments for providing a stable internet service. This study attempts to overcome the limit of study such as the detection of Tor network traffic using the existing low-latency by classifying the anonymous network by means of the suggested algorithm about the event detected in the security infra.