• 한국인터넷방송통신학회논문지
• /
• 제17권2호
• /
• pp.271-277
• /
• 2017

현대에 들어서면서 대기오염 물질이 심각하게 국민의 건강을 위협하는 단계에 이르렀기 때문에 이에 대한 예보의 중요성은 점점 높아지고 있다. 대기질을 예보하는데 있어서 예보 모델에 입력되는 초기장은 예보의 정확성에 영향을 미치는 요소이기 때문에 신뢰도 높은 초기장을 생성하는 것이 매우 중요하며, 이때 필요한 기법 중 하나가 자료동화이다. 자료동화는 대상 지역이 넓어지고, 관측소의 수가 증가될수록 더 많은 연산이 필요하기 때문에 그 수행시간이 길어진다. 때문에 예보 규모가 커질수록 기존의 순차처리 방식으로는 빠른 처리속도를 요구하는 현업에 적용하기 어렵다. 이에 본 논문에서는 자료동화 기법 중의 하나인 크레스만 방법을 CUDA를 이용하여 실시간으로 처리할 수 있는 방법을 제안하였다. 그 결과, 제안한 CUDA를 이용한 병렬처리 방법이 최소 35배 이상 속도가 향상되었다.

• 한국인터넷방송통신학회논문지
• /
• 제20권6호
• /
• pp.1-6
• /
• 2020

도로이동 오염원 대기환경 빅데이터는 상시 교통량 조사장비인 AVC, VDS, WIM, DTG를 활용한 차종, 속도, 하중 등 실시간 교통류 데이터와 GIS를 활용한 도로형상(오르막, 내리막, 회전구간) 데이터를 연계한 교통류 데이터로 구성되어 있다. 또한, 일반적인 데이터와 달리 단위시간 당 데이터가 많이 발생하고, 다양한 포맷을 가지고 있다. 특히, 이들 상세 교통류 정보로 수집되는 대용량의 실시간 데이터들은 약 총 740만 건/시간 이상이 수집되어 저장 및 가공되기 때문에 효율적으로 데이터를 처리할 수 있는 시스템이 필요하다. 따라서 본 연구에서는 도로이동 오염뭔 대기환경 빅데이터 시각화를 위한 오픈소스 기반의 데이터 병렬처리 성능 최적화 연구를 수행한다.

• 한국인터넷방송통신학회논문지
• /
• 제22권6호
• /
• pp.63-68
• /
• 2022

현재 대한민국의 서울특별시를 기준으로 응급실은 총 68개가 있으며, 응급실의 위치를 조회할 수 있는 포털 사이트가 존재하지만, 구와 자치동을 선택하는 방법으로 구성되어 실제 응급 상황에서는 활용하기가 어렵다. 또한, 119 구조대를 요청하고, 기다리는 상황에서 생존에 필요한 골든타임을 놓칠 수 있기 때문에 직접 응급실로 이동하는 방안이 더 효율적일 수도 있다. 따라서 본 논문에서는 MongoDB에서 지원되는 다양한 기능을 통해 특정 위치를 기준으로 빠르게 응급실의 위치를 조회할 수 있는 서비스를 제안한다. 서울특별시를 기준으로 응급실 위치 데이터를 다운로드하고, MongoDB에 저장한 후 다양한 처리 기술을 통해 데이터를 처리하고, 공간 인덱스를 적용하여 특정 위치에서 거리를 기준으로 응급실을 실시간으로 조회할 수 있다.

• 해양환경안전학회:학술대회논문집
• /
• 해양환경안전학회 1999년도 춘계학술발표회논문집
• /
• pp.93-105
• /
• 1999

In Vessel Traffic Service, the management information on marine traffic control is almost transported by VHF. It is so difficult to exchange a lot of the related information necessary for marine traffic control exactly and in real time. Aiming at improved visualized data transporting network, we examine the methods for transporting and displaying the data on marine traffic controls. In this paper, we design the information networks established by broadcasting method and by internet method using home page in order to manage marine traffics in Masan port.

• International journal of advanced smart convergence
• /
• 제6권3호
• /
• pp.29-37
• /
• 2017

The current behavior recognition system don't match data formats between sensor data measured by user's sensor module or device. Therefore, it is necessary to support data processing, sharing and collaboration services between users and behavior recognition system in order to process sensor data of a large capacity, which is another formats. It is also necessary for real time interaction with users and behavior recognition system. To solve this problem, we propose fog cloud based behavior recognition system for human body sensor data processing. Fog cloud based behavior recognition system solve data standard formats in DbaaS (Database as a System) cloud by servicing fog cloud to solve heterogeneity of sensor data measured in user's sensor module or device. In addition, by placing fog cloud between users and cloud, proximity between users and servers is increased, allowing for real time interaction. Based on this, we propose behavior recognition system for user's behavior recognition and service to observers in collaborative environment. Based on the proposed system, it solves the problem of servers overload due to large sensor data and the inability of real time interaction due to non-proximity between users and servers. This shows the process of delivering behavior recognition services that are consistent and capable of real time interaction.

• International journal of advanced smart convergence
• /
• 제9권1호
• /
• pp.113-120
• /
• 2020

Recently, the license plate OCR system has been commercialized in a variety of fields and preferred utilizing low-cost embedded systems using only cameras. This system has a high recognition rate of about 98% or more for the environments such as parking lots where non-vehicle is restricted; however, the environments where non-vehicle objects are not restricted, the recognition rate is about 50% to 70%. This low performance is due to the changes in the environment by non-vehicle objects in real-time situations that occur anomaly data which is similar to the license plates. In this paper, we implement the appropriate anomaly detection based on semi-supervised learning for the license plate OCR system in the real-time environment where the appearance of non-vehicle objects is not restricted. In the experiment, we compare systems which anomaly detection is not implemented in the preceding research with the proposed system in this paper. As a result, the systems which anomaly detection is not implemented had a recognition rate of 77%; however, the systems with the semi-supervised learning based on anomaly detection had 88% of recognition rate. Using the techniques of anomaly detection based on the semi-supervised learning was effective in detecting anomaly data and it was helpful to improve the recognition rate of real-time situations.

• International journal of advanced smart convergence
• /
• 제12권4호
• /
• pp.75-87
• /
• 2023

We designed to employ an Artificial Intelligence learning model to predict real estate prices and determine the reasons behind their changes, with the goal of using the results as a guide for policy. Numerous studies have already been conducted in an effort to develop a real estate price prediction model. The price prediction power of conventional time series analysis techniques (such as the widely-used ARIMA and VAR models for univariate time series analysis) and the more recently-discussed LSTM techniques is compared and analyzed in this study in order to forecast real estate prices. There is currently a period of rising volatility in the real estate market as a result of both internal and external factors. Predicting the movement of real estate values during times of heightened volatility is more challenging than it is during times of persistent general trends. According to the real estate market cycle, this study focuses on the three times of extreme volatility. It was established that the LSTM, VAR, and ARIMA models have strong predictive capacity by successfully forecasting the trading price index during a period of unusually high volatility. We explores potential synergies between the hybrid artificial intelligence learning model and the conventional statistical prediction model.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2010년도 추계학술대회
• /
• pp.643-645
• /
• 2010

인터넷 기반 멀티미디어 서비스가 확대되고 IPTV 기술의 발달로 방송과 통신의 융합을 지원하기 위한 제어 기술이 더욱 발전할 것으로 보인다. 특히 실시간 TV 방송을 위한 멀티캐스트 제어 기술을 지원하기 위한 인증 및 자원 제어 기술 그 외에 서비스의 가치를 높이기 위한 다양한 양방향 서비스 제공 기술이 개발될 것으로 보인다. 그리고 인터넷 기반 전송환경에서 비디오 콘텐츠 전송을 할 때 비디오 콘텐츠 전송을 위해 RTP(Real Time Transport Protocol)를 사용한다. 따라서 표준화 기구인 IETF(Internet Engineering Task Force)에서는 RTP 내에서 다양한 오디오 및 비디오 포맷에 따라 전용 전송포맷(RTP Payload Format)을 별도의 표준으로 정하고 있으며, 스케일러블 비디오 콘텐츠는 "RTP Payload Format for SVC(Switched Virtual Connection) Video"로 표준화가 현재 진행 중이다. 이에 본 논문에서는 방송 통신 융합 시스템의 질적 향상을 위하여, 상위 계층 응용이 적응적으로 반응하도록 함으로써 기존의 MPEG2-TS로 제공되는 다양한 콘텐츠를 RTP를 이용하여 다양한 장치에 적용하여 소비자의 ETE(End-to-End) QoS(Quality of Service)를 향상하기 위한 시스템을 설계 및 구현하였다.

• International journal of advanced smart convergence
• /
• 제6권4호
• /
• pp.80-87
• /
• 2017

Mixed Reality (MR) shows a composite image of a virtual object in the real world. It has been applied to various fields by the introduction of head mounted display (HMD) such as Microsoft's Hololens [1-3]. The virtual studio in broadcasting combines the contents created by computer graphics with the actual set to reproduce the 3D image screen. This requires physical space such as a set of chroma keys. It also requires professional knowledge and manpower and costly equipment to post-process the graphics and information for long periods of time. Therefore, in this paper, we aim to study the implementation of virtual studio based on Mixed Reality using Microsoft Hololens. Through the implementation of 'Holo-studio' application, realistic and virtual objects of broadcasting camera viewpoint were acquired at the same time. Using Microsoft's spectator view library, the frame rate is degraded in objects with high polygons (100,000 polygons). The proposed method maintains 60 fps image transmission in high polygon objects. The results of this paper show the possibility of using virtual studio at low cost which does not need separate physical space.

• International journal of advanced smart convergence
• /
• 제8권4호
• /
• pp.154-160
• /
• 2019

In this paper, we propose the miniaturization size of wearable Range of Motion(ROM) and a system that can be connected with smart devices in real-time to measure the joint movement range dynamically. Currently, the ROM of the joint is directly measured by a person using a goniometer. Conventional methods are different depending on the measurement method and location of the measurement person, which makes it difficult to measure consistently and may cause errors. Also, it is impossible to measure the ROM of joints in real-life situations. Therefore, the wearable sensor is attached to the joint to be measured to develop a miniaturize size ROM device that can measure the range of motion of the joint in real-time. The sensor measured the resistance value changed according to the movement of the joint using a load cell. Also, the sensed analog values were converted to digital values using an Analog to Digital Converter(ADC). The converted amount can be transmitted wireless to the smart device through the wearable sensor node. As a result, the developed device can be measured more consistently than the measurement using the goniometer, communication with IoT-based smart devices, and wearable enables dynamic observation. The developed wearable sensor node will be able to monitor the dynamic state of rehabilitation patients in real-time and improve the rapid change of treatment method and customized treatment.