• Journal of the Korea Society of Computer and Information
• /
• v.19 no.6
• /
• pp.1-10
• /
• 2014

In this paper, we propose a real-time video playback scheme for the N-Screen service based on Windows Azure. This scheme creates several playback blocks based on the performance of each node by non-uniform splitting of the original video. To reduce transcoding-time, it allocates the playback blocks to a corresponding node by transcoding the playback blocks. Through the simulation, we show that it is more effective to use real-time video playback for the N-screen service than the previous method. The proposed scheme splits an AVI format 300MB source video with non-uniform playback blocks. It allocates the playback blocks to the heterogeneous node of Windows Azure, the commercial cloud system and measures of transcoding-time by transcoding non-uniform playback blocks to mp4 and Flv format. As a result, the proposed scheme improves the performance of the N-screen service based on Windows Azure compared to the previous uniform split strategy.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.6
• /
• pp.37-46
• /
• 2021

In this paper, we designed and implemented a program to measure and to judge the accuracy of yoga postures using Azure Kinect. The program measures all joint positions of the user through Azure Kinect Camera and sensors. The measured values of joints are used as data to determine accuracy in two ways. The measured joint data are determined by trigonometry and Pythagoras theorem to determine the angle of the joint. In addition, the measured joint value is changed to relative position value. The calculated and obtained values are compared to the joint values and relative position values of the desired posture to determine the accuracy. Azure Kinect Camera organizes the screen so that users can check their posture and gives feedback on the user's posture accuracy to improve their posture.

• Biotechnology and Bioprocess Engineering:BBE
• /
• v.10 no.1
• /
• pp.47-51
• /
• 2005

The bioelectrochemical reduction of nitrate in the presence of various mediators including methyl viologen and azure A was studied using a 3-electrode voltammetric system. The catalytic potential for the reduction of the mediators was observed in the reactor, which for methyl viologen and azure A were -0.74 V and -0.32 V, respectively, with respect to the potential of Ag/AgCl reference electrode. This potential was then applied to a working electrode to reduce each mediator for enzymatic nitrate reduction. Nitrite, the product of the reaction, was measured to observe the enzymatic nitrate reduction in the reaction media. Methyl viologen was observed as the most efficient mediator among those tested, while azure A showed the highest electron efficiency at the intrinsic reduction potential when the mediated enzyme reactions were carried out with the freely solubilized mediator. The electron transfer of azure A with respect to time was due to the adhesion of azure A to the hydrophilic surface during the reduction. In addition, the use of the adsorbed mediator on conductive activated carbon was proposed to inhibit the change in the electron transfer rate during the reaction by maintaining a constant mediator concentration and active surface area of the electrode. Azure A showed better than nitrite formation than methyl viologen when used with activated carbon.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.329-330
• /
• 2020

본 논문에서는 Azure 클라우드 플랫폼의 가상서버 호스팅을 이용해 데이터 수집 환경을 구축하고, Azure에서 제공하는 자동화된 기계학습(Automated Machine Learning, AutoML)을 기반으로 데이터 분석 방법에 관한 연구를 수행했다. 가상 서버 호스팅 환경에 LAMP(Linux, Apache, MySQL, PHP)를 설치하여 데이터 수집환경을 구축했으며, 수집된 데이터를 Azure AutoML에 적용하여 자동화된 기계학습을 수행했다. Azure AutoML은 소모적이고 반복적인 기계학습 모델 개발을 자동화하는 프로세스로써 기계학습 솔루션 구현하는데 시간과 자원(Resource)를 절약할 수 있다. 특히, AutoML은 수집된 데이터를 분류와 회귀 및 예측하는데 있어서 학습점수(Training Score)를 기반으로 보유한 데이터에 가장 적합한 기계학습 모델의 순위를 제공한다. 이는 데이터 분석에 필요한 기계학습 모델을 개발하는데 있어서 개발 초기 단계부터 코드를 설계하지 않아도 되며, 전체 기계학습 시스템을 개발 및 구현하기 전에 모델의 구성과 시스템을 설계해볼 수 있기 때문에 매우 효율적으로 활용될 수 있다. 본 논문에서는 NPU(Neural Processing Unit) 학습에 필요한 데이터 수집 환경에 관한 연구를 수행했으며, Azure AutoML을 기반으로 데이터 분류와 회귀 등 가장 효율적인 알고리즘 선정에 관한 연구를 수행했다.

• Journal of Engineering Education Research
• /
• v.22 no.1
• /
• pp.55-60
• /
• 2019

This paper deals with the process and requirements of a capstone design project performed by undergraduate students. We discuss about the preliminary study for the capstone design, the derivation of a subject, the level descriptor of the subject, and the system requirements. And then, we summarize the results of the capstone design project entitled as Microsoft Azure based IoT (Internet of Things) system which is performed by 4 undergraduate students during 10 months. This system is composed of a Zigbee sensor network, the TCP/IP Internet, an IoT server, and a smartphone application program, with which we can gather the sensor data and control actuators at the far away area.

• Asia pacific journal of information systems
• /
• v.28 no.4
• /
• pp.308-319
• /
• 2018

This paper aims at providing valuable insights on Financial Fraud Detection on a mobile money transactional activity. We have predicted and classified the transaction as normal or fraud with a small sample and massive data set using Azure and Spark ML, which are traditional systems and Big Data respectively. Experimenting with sample dataset in Azure, we found that the Decision Forest model is the most accurate to proceed in terms of the recall value. For the massive data set using Spark ML, it is found that the Random Forest classifier algorithm of the classification model proves to be the best algorithm. It is presented that the Spark cluster gets much faster to build and evaluate models as adding more servers to the cluster with the same accuracy, which proves that the large scale data set can be predictable using Big Data platform. Finally, we reached a recall score with 0.73, which implies a satisfying prediction quality in predicting fraudulent transactions.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.20 no.3
• /
• pp.12-26
• /
• 2017

The objective of this study was to develop a runoff analysis system of the Nakdong River watershed using the GRM (Grid-based Rainfall-runoff Model), a physically-based distributed rainfall-runoff model, and to assess the system run time performance according to Microsoft Azure VM (Virtual Machine) settings. Nakdong River watershed was divided into 20 sub-watersheds, and GRM model was constructed for each subwatershed. Runoff analysis of each watershed was calculated in separated CPU process that maintained the upstream and downstream topology. MoLIT (Ministry of Land, Infrastructure and Transport) real-time radar rainfall and dam discharge data were applied to the analysis. Runoff analysis system was run in Azure environment, and simulation results were displayed through web page. Based on this study, the Nakdong River real-time runoff analysis system, which consisted of a real-time data server, calculation node (Azure), and user PC, could be developed. The system performance was more dependent on the CPU than RAM. Disk I/O and calculation bottlenecks could be resolved by distributing disk I/O and calculation processes, respectively, and simulation runtime could thereby be decreased. The study results could be referenced to construct a large watershed runoff analysis system using a distributed model with high resolution spatial and hydrological data.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.07a
• /
• pp.31-32
• /
• 2019

본 논문에서는 Microsoft Azure 기반의 운동 방법 안내 챗봇을 설계하고 구현한다. 이 챗봇은 자동 추천과 부위 선택 기능을 제공한다. 자동 추천은 본 프로그램을 처음 접하거나 편리하게 사용하고 싶은 사용자에게 권장하는 기능을 제공한다. 이 챗봇은 사용자에게 맞춤 운동법을 효과적으로 제시하기 위해 키, 몸무게, 나이, 성별 같은 사용자 정보를 입력시킨다. 그리고 운동 부위 선택 기능은 사용자가 운동하고 싶은 특정 부위를 명확하게 인식하고 있을 때 사용한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.425-428
• /
• 2013

최근 서버 구축 및 유지 비용을 절검하고, 용량이 큰 동영상과 클라이언트의 수가 점차 증가함에 따라 서버의 용량과 성능을 용이하게 향상시킬 수 있는 클라우드 컴퓨팅을 이용한 개발이 증가하고 있다. 이에 본 논문은 Windows Azure 클라우드 컴퓨팅에 기반한 모바일 학습 시스템을 제시한다. 제시된 시스템은 학생이 강사의 비디오, 오디오, 슬라이드 그리고 애노테이션을 실시간으로 받을 수 있으며, 텍스트 형태로 질문을 실시간으로 할 수 있게 해준다. 그리고 강의내용을 저장하여 학생이 나중에 원하는 강의를 경험하게 할 수 있게 해주는 비동기식 기능도 제공한다. 그리고 본 시스템은 클라우드를 이용함으로써, 서비스 제공자가 별도의 서버를 구축할 필요가 없으며 나중에 저장되는 동영상데이터의 크기 및 클라이언트의 수가 증가하더라도 그에 대응한 서버의 확장이 용이하다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.425-426
• /
• 2022

본 논문에서는 사용자가 원하는 주제를 통해 전시장을 추천, 등록, 조회하는 Microsoft Bot Framework, Microsoft Azure 기반의 챗봇을 설계하고 구현한다. 이 챗봇은 사용자가 원하는 주제를 입력하면, 해당하는 주제의 전시장을 추천하게 된다. 주제는 알고리즘으로 단어를 지정한 것이 아닌, Azure Luis로 단어를 학습시켜서 비슷한 주제의 단어를 도출하는 알고리즘을 선택한다. 등록 부분은 Form 형식이 아닌 대화형으로 사용자 정보를 수집하게 된다. 사용자 정보는 Microsoft SQL Database 서버에 저장이 되고, 구현한 챗봇은 애뮬레이터 형식이 아닌 Channel 연동으로 Line 서비스로 배포한다.