• 한국BIM학회 논문집
• /
• 제8권3호
• /
• pp.12-19
• /
• 2018

The research aims to find implications of machine learning and urban big data as a way to construct the flexible transportation network system of smart city by responding the urban context changes. This research deals with a problem that existing a bus headway model is difficult to respond urban situations in real-time. Therefore, utilizing the urban big data and machine learning prototyping tool in weathers, traffics, and bus statues, this research presents a flexible headway model to predict bus delay and analyze the result. The prototyping model is composed by real-time data of buses. The data is gathered through public data portals and real time Application Program Interface (API) by the government. These data are fundamental resources to organize interval pattern models of bus operations as traffic environment factors (road speeds, station conditions, weathers, and bus information of operating in real-time). The prototyping model is implemented by the machine learning tool (RapidMiner Studio) and conducted several tests for bus delays prediction according to specific circumstances. As a result, possibilities of transportation system are discussed for promoting the urban efficiency and the citizens' convenience by responding to urban conditions.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.705-708
• /
• 2005

Mobile Mapping Systems using the vehicle equipped the GPS, IMU, CCD Cameras is the effective system for the management of the road facilities, update of the digital map, and etc. They must provide users with the sensor data which is acquired by Mobile Mapping Systems in real-time so that users can process what they want by using the latest data. But it' s not an easy process because the amount of sensor data is very large, particularly image data to be transmitted. So it is necessary to reduce the amount of image data so that it is transmitted effectively. In this study, the effective method was suggested for the compression/decompression image data using the Wavelet Transformation and Huffman Coding. This technique will be possible to transmit of the geographic information effectively such as position data, attitude data, and image data acquired by Mobile Mapping Systems in the wireless internet environment when data is transmitted in real-time.

• 대한임베디드공학회논문지
• /
• 제19권3호
• /
• pp.151-158
• /
• 2024

Although on-device artificial intelligence (AI) has gained attention to diagnosing machine faults in real time, most previous studies did not consider the model retraining and redeployment processes that must be performed in real-world industrial environments. Our study addresses this challenge by proposing an on-device AI-based real-time machine fault diagnosis system that utilizes continual learning. Our proposed system includes a lightweight convolutional neural network (CNN) model, a continual learning algorithm, and a real-time monitoring service. First, we developed a lightweight 1D CNN model to reduce the cost of model deployment and enable real-time inference on the target edge device with limited computing resources. We then compared the performance of five continual learning algorithms with three public bearing fault datasets and selected the most effective algorithm for our system. Finally, we implemented a real-time monitoring service using an open-source data visualization framework. In the performance comparison results between continual learning algorithms, we found that the replay-based algorithms outperformed the regularization-based algorithms, and the experience replay (ER) algorithm had the best diagnostic accuracy. We further tuned the number and length of data samples used for a memory buffer of the ER algorithm to maximize its performance. We confirmed that the performance of the ER algorithm becomes higher when a longer data length is used. Consequently, the proposed system showed an accuracy of 98.7%, while only 16.5% of the previous data was stored in memory buffer. Our lightweight CNN model was also able to diagnose a fault type of one data sample within 3.76 ms on the Raspberry Pi 4B device.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 하계종합학술대회 논문집(3)
• /
• pp.47-50
• /
• 2002

In this paper, the efficient transmission technique of real time video data over 3G wireless networks is presented. To understand the transmission characteristic of 3G networks on real time video data, we implemented the data transport structure of 3G wireless networks. Also this research is based on current 3G wireless network specification of 3GPP, 3GPP2 standard organization to evaluate the result over real 3G wireless network environment. The retransmission by radio link layer results in the delay factor. To implement video data transmission efficiently, we Propose to use both no-retransmission and forward error correction method.

• 한국정보처리학회논문지
• /
• 제4권10호
• /
• pp.2581-2595
• /
• 1997

본 논문에서는 주문형 비디오 서버가 필요로 하는 운영체제의 실시간 스케쥴링 기능을 분석 및 구현하였다. 실시간 스케쥴링 요구 조건은 비디오 데이타 전달 경로에 대한 모델 분석을 통하여 수집되었다. 특히, 병목 현상을 일으키는 하부 시스템이 전체 시스템의 실시간 스케쥴링에 미치는 영향을 분석함으로써 비디오 데이타 처리에 적합한 실시간 스케쥴러 및 프리미티브를 구현하였다. 성능 측정에서는 구현된 실시간 스케쥴러의 보장성을 실험하였다. 측정된 데이타는 프로세스가 가진 대부분의 시간 제약 조건이 만족됨을 보였다. 그러나 인터럽터 방식의 네트워크 프로토콜 처리는 실시간 스케쥴링의 가장 큰 장애 요소이다. 또한, 프로세스 수행 시간 간격을 측정함으로써 비실시간 스케쥴러와 실시간 스케쥴러의 차이점을 비교하였다. 측정된 결과에 의하면 비실시간 스케쥴러을 사용하면 프로세스에 할당되는 프로세서 시간을 예측하기 어렵기 때문에 효율적인 비디오 서비스를 위해서는 반드시 실시간 스케쥴러가 사용되어야 함을 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.35.4-35
• /
• 2001

Image detection system for road traffic data analysis is a real time detection system using image processing techniques to get the real-time traffic information which is used for traffic control and analysis. One of the most important functions in this system is to match the coordinates of real world and that of image on video camera. When there in no way to know the exact position of camera and it´s height from the object. If some points on the road of real world are known it is possible to calculate the coordinates of real world from image.

• 한국정보전자통신기술학회논문지
• /
• 제11권4호
• /
• pp.421-429
• /
• 2018

IoT device 측정 데이터 또는 거래 데이터는 관측 정보가 실시간으로 전송되고 이를 처리하는 과정에서 많은 트래픽이 발생한다. 이를 실시간 무 손실 압축 기법인 universal code를 이용하면 효과적으로 압축 또는 전송할 수 있다. 본 논문은 측정 수치의 최대 범위를 예측하기 어렵고, 매우 짧은 시간 마다 비교적 일정한 범위 내에서 데이터가 발생하는 주식 거래량 데이터의 압축 전송을 위해, 본 연구진의 새롭게 개발한 유니버설 코드 BL-beta를 이용하여 압축 전송에 적용해보니, 고정 길이 비트 전송에 비해 최소 49.5%이상의 높은 압축 효율을 보였으며, 기존 유니버설 코드인 Exponential Golomb 코드 보다 16.6% 더 우수한 압축 전송 성능을 나타내었다.

• Spatial Information Research
• /
• 제9권2호
• /
• pp.309-324
• /
• 2001

본 연구에서는 실시간 동적 GPS 측량의 응용을 위해 우선 전국에 분포된 상시관측점들의 공경기준계 성과를 도출하고, 후처리에 의한 연속 동적 GPS 방법과 실시간 동적 GPS 방법을 적용하여 육상과 해상지역에 대한 지형 해석을 시도하였다. 실시간 동적 GPS 측량을 위한 초기 조건과 관측 시간대를 고려한 다음, 후처리에 의한 연속 동적 GPS 측량과 실시간 동적 GPS 측량을 수행하였으며, 본 연구를 의해 실시간으로 GPS 관측자료를 저장할 수 있는 프로그램을 개발하여 결과값을 동시에 저장하고 controller를 통해 관측 당시의 위성 상태를 모니터링 할 수 있는 시스템을 제안하였다. 실시간으로 관측된 GPS관측값의 위치 정확도는 후처리에 의한 정확도와 같은 정도로 획득할 수 있었으며, 항만의 매립, 준설공사나 하천에서의 유사량 변화 탐지등에 매우 높은 정확도로 수치지형모형을 구축할 수 있었고, 해안 지형의 특성해석에 유용하게 응용될 것으로 기대된다.

• 제어로봇시스템학회논문지
• /
• 제5권6호
• /
• pp.734-743
• /
• 1999

In this paper, a real-time communication method using a PICNET-NP(Plant instrumentation and Control Network for Nuclear Power plant) is proposed with an analysis of the control network requirements of DCS(Distributed Control System) in nuclear power plants. The method satisfies deadline in case of worst data traffics by considering aperiodic and periodic real-time data and others. In addition, the method was used to analyze the data characteristics of the DCS in existing nuclear power plant. The result shows that use of this method meets the response time requirement(100ms).

• 한국지반공학회지:지반
• /
• 제26권9호
• /
• pp.33-47
• /
• 2010

Underground constructions continue to provide challenges to Geotechnical Engineers yet they pose the best opportunities for development and deployment of advance technologies for analysis, design and construction. The reason for this is that, by virtue of the nature of underground constructions, more data and information on ground characteristics and response become available as the construction progresses. However, due to several barriers, these data and information are rarely, if ever, utilized to modify and improve project design and construction during the construction stage. To enable the use of evolving realtime data and information, and adaptively modify and improve design and construction, the paper presents an analysis and design system, called AMADEUS, for underground projects. AMADEUS stands for Adaptive, real-time and geologic Mapping, Analysis and Design of Underground Space. AMADEUS relies on recent advances in IT (Information Technology), particularly in digital imaging, data management, visualization and computation to significantly improve analysis, design and construction of underground projects. Using IT and remote sensors, real-time data on geology and excavation response are gathered during the construction using non-intrusive techniques which do not require expensive and time-consuming monitoring. The real-time data are then used to update geological and geomechanical models of the excavation, and to determine the optimal, construction sequences and stages, and structural support. Virtual environment (VE) systems are employed to allow virtual walk-throughs inside an excavation, observe geologic conditions, perform virtual construction operations, and investigate stability of the excavation via computer simulation to steer the next stages of construction.