• 센서학회지
• /
• 제24권5호
• /
• pp.331-341
• /
• 2015

In this paper, real-time water quality monitoring system of small water supply facilities based on IEEE 802.15.4e-2012 DSME MAC and IEEE 802.15.4g-2012 PHY standard is presented, which is capable to acquire for highly reliable water quality information in the wide outdoor areas for effective water quality management of small water quality facilities is distributed in the long distance and remote areas. Previously, Long distance transmission is difficult in most water quality sensor module is using RS-485 protocol. But with this system, even in harsh outdoor environment, it is possible to establish a radio wave sensor in a wide area network, and not only water quality sensor shall be connected to the wireless system, but also wireless integrated management system shall provide more effective way of management of the numerous small water supply facilities spread throughout the community, so that the administrator can remotely monitor the data of water turbidity, pH, residual chlorine in the water-supply, water-level, and generate alarm to cope with risks. The management of small water facilities is done by residents will be very effective to notice water quality information of small water facilities to residents.

• 한국ITS학회 논문지
• /
• 제7권5호
• /
• pp.139-146
• /
• 2008

무선 센서 네트워크 관련 응용 시스템은 환경오염, 건물통제, 홈 오토메이션 등의 역할을 수행할 것으로 예상된다. 본 논문에서는 지하철 역사 내 인명 및 화재 피해 등을 줄이기 위한 무선 센서 네트워크 기반의 지하철 응급 상황 조치 시스템에 대해 기술한다. 본 시스템의 센서 노드는 온도, 조도, 연기, 인체 감지 등을 통해 지하철 역사내 발생 할 수 있는 사고를 실시간 감지한다. 이러한 실시간 센서 감지와 무선 네트워킹을 통해 인명과 재산의 피해를 최소화 하고자 한다.

• 한국멀티미디어학회논문지
• /
• 제23권10호
• /
• pp.1236-1249
• /
• 2020

In a most recent object tracking research work, applying Convolutional Neural Network and Recurrent Neural Network-based strategies become relevant for resolving the noticeable challenges in it, like, occlusion, motion, object, and camera viewpoint variations, changing several targets, lighting variations. In this paper, the LSTM Network-based Tracking association method has proposed where the technique capable of real-time multi-object tracking by creating one of the useful LSTM networks that associated with tracking, which supports the long term tracking along with solving challenges. The LSTM network is a different neural network defined in Keras as a sequence of layers, where the Sequential classes would be a container for these layers. This purposing network structure builds with the integration of tracking association on Keras neural-network library. The tracking process has been associated with the LSTM Network feature learning output and obtained outstanding real-time detection and tracking performance. In this work, the main focus was learning trackable objects locations, appearance, and motion details, then predicting the feature location of objects on boxes according to their initial position. The performance of the joint object tracking system has shown that the LSTM network is more powerful and capable of working on a real-time multi-object tracking process.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1527-1534
• /
• 2016

Online voltage stability monitoring using real-time measurements is one of the most important tasks in a smart grid system to maintain the grid stability. Loading margin is a good indicator for assessing the voltage stability level. This paper presents an Extreme Learning Machine (ELM) approach for estimation of voltage stability level under credible contingencies using real-time measurements from Phasor Measurement Units (PMUs). PMUs enable a much higher data sampling rate and provide synchronized measurements of real-time phasors of voltages and currents. Depth First (DF) algorithm is used for optimally placing the PMUs. To make the ELM approach applicable for a large scale power system problem, Mutual information (MI)-based feature selection is proposed to achieve the dimensionality reduction. MI-based feature selection reduces the number of network input features which reduces the network training time and improves the generalization capability. Voltage magnitudes and phase angles received from PMUs are fed as inputs to the ELM model. IEEE 30-bus test system is considered for demonstrating the effectiveness of the proposed methodology for estimating the voltage stability level under various loading conditions considering single line contingencies. Simulation results validate the suitability of the technique for fast and accurate online voltage stability assessment using PMU data.

• 정보보호학회논문지
• /
• 제28권2호
• /
• pp.485-500
• /
• 2018

시스템 및 네트워크 환경의 규모가 확대되고, 네트워크 구조 및 시스템 구성이 빈번하게 변화함에 따라 네트워크 관리자가 현황을 수동으로 관리하고 실시간 변동사항을 식별하는 데에 많은 어려움이 발생하고 있다. 본 논문에서는 동적인 네트워크 정보를 실시간으로 스캔하고, 사전에 수집한 취약점 정보를 바탕으로 네트워크 내 장치의 취약성 정도를 점수화하고 최종적으로 공격자의 입장에서 공격 가능한 모든 경로를 도출하여 네트워크 관리자에게 공격 가능성이 높은 경로 목록을 제공하는 알고리즘을 제안하였다. 또한 제안하는 알고리즘을 토대로 한 Attack Graph를 실제로 구현하였으며, Software Defined Networking (SDN) 환경이 포함된 동적으로 변화하는 가상 네트워크 환경을 구축한 후 시뮬레이션을 진행하여 Moving Target Defense (MTD) 개념이 반영된 시스템에도 적용이 가능함을 입증하였다.

• 한국전기전자재료학회논문지
• /
• 제35권5호
• /
• pp.459-465
• /
• 2022

This paper reports a method to use a wireless sensor network deployed in the field to real-time monitor soil moisture, warning when the moisture level reaches a specific value, and wirelessly controlling an additional device (LED or water supply system, etc.). In addition, we report all processes related to wireless irrigation system, including field deployment of sensors, real-time monitoring using a smartphone, data calibration, and control of additional devices deployed in the field by smartphone. A commercially available open-source Internet of Things (IoT) platform, NodeMCU, was used, which was combined with a 9V battery, LED and soil humidity sensor to be integrated into a portable prototype. The IoT-based soil humidity sensor prototype deployed in the field was installed next to a tree for on-site demonstration for the measurement of soil humidity in real-time for about 30 hours, and the measured data was successfully transmitted to a smartphone via Wifi. The measurement data were automatically transmitted via e-mail in the form of a text file, stored on the web, followed by analyses and calibrations. The user can check the humidity of the soil real-time through a personal smartphone. When the humidity of a soil reached a specific value, an additional device, an LED device, placed in the field was successfully controlled through the smartphone. This LED can be easily replaced by other electronic devices such as water supplies, which can also be controlled by smartphones. These results show that farmers can not only monitor the condition of the field real-time through a sensor monitoring system manufactured simply at a low cost but also control additional devices such as irrigation facilities from a distance, thereby reducing unnecessary energy consumption and helping improve agricultural productivity.

• 디지털융복합연구
• /
• 제17권5호
• /
• pp.217-223
• /
• 2019

자동차 분야에서 저항 점용접의 결함 및 품질을 실시간으로 예측할 수 있는 연구는 원가절감과 고품질 생산을 위한 필수 불가결한 연구 분야라 할 수 있다. 용접 품질은 전단강도와 너깃의 크기에 의해서 결정되며 여러 가지 독립변수에 따라 결과가 달라진다. 실시간 예측시스템을 개발하기 위하여 다중 회귀분석을 실시하여 3개의 독립변수로 두 가지 종속변수를 충분한 통계적 결과로 구하였으나 회귀식에 의한 품질 예측은 정확도를 보장할 수 없었다. 본 연구에서는 다층 신경망 회로를 구축하였다. 10가지의 동저항 변수에 의한 신경망은 3개의 은닉층을 구축하여 실행 함수와 가중치 행렬을 구하였다. 그러나 이 경우, 입력 변수가 너무 많아 실시간 제어에 어려움이 있을 수 있으므로 회귀분석에 의한 3개의 독립변수로 신경망을 구축하였다. 그 결과 모든 시험데이터를 불량, 부분 불량, 양품으로 구분하는데 성공하였다. 따라서 다중 회귀분석에 의해서 구한 3개의 독립변수에 의한 실시간 용접 품질 판정 시스템을 완성할 수 있었다.

• 한국통신학회논문지
• /
• 제31권1A호
• /
• pp.30-37
• /
• 2006

본 논문에서는 차세대 이동통신 수송망에서 트래픽 클래스별 서비스 품질 요구 사항을 고려한 효율적인 대역폭 재할당 기법을 제안한다. 제안 기법은 유선망 트래픽 클래스를 실시간 클래스와 비시실시간 클래스로 구분하여 무선망 계층에서 정의된 서비스 품질 클래스를 유선망 트래픽 클래스로 매핑시킨 후 실시간 트래픽 클래스가 비실시간 트래픽 클래스의 유휴 자원을 동적으로 사용하도록 한다. 제안 기법은 운영자가 지정한 패킷 손실율과 Auto-Regressive(AR) 시계열 모델을 이용하여 주기적으로 비실시간 트래픽 클래스의 향후 필요 대역폭을 예측하며 유휴 대역폭이 발생하는 경우에만 이를 실시간 트래픽 클래스에 동적으로 할당함으로써 비실시간 트래픽 클래스의 패킷 손실율을 보장함과 동시에 시스템의 대역폭 이용율을 향상시킨다. 본 논문에서는 실제 측정된 인터넷 트래픽을 비실시간 트래픽 클래스로 이용하여 제안 기법은 링크 대역폭의 효율을 증가시켜 실시간 트래픽의 수용량을 증가시킴과 동시에 모든 시 구간에서 비실시간 트래픽 클래스에 원하는 패킷 손실율을 보장할 수 있음을 검증하였다.

• 한국정보통신학회논문지
• /
• 제23권11호
• /
• pp.1482-1484
• /
• 2019

We present a method for transmitting 3D object information in real time in a telepresence system. Three-dimensional object information consists of a large amount of point cloud data, which requires high performance computing power and ultra-wideband network transmission environment to process and transmit such a large amount of data in real time. In this paper, multiple users can transmit object motion and facial expression information in real time even in small network bands by using GANs (Generative Adversarial Networks), a non-supervised learning machine learning algorithm, for real-time transmission of 3D point cloud data. In particular, we propose the creation of an object similar to the original using only the feature information of 3D objects using conditional GANs.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.657-659
• /
• 2004

CAN is a serial communication bus for real-time controls and automations in distributed control systems. In distributed control systems, occasionally a sensor module and a controller are not in the same node and physically separated. In order for the signal from a sensor node to reach the controller node, the signal must travel through network. CAN has a certain capabilities to deal with real-time data. However, when many nodes on the networks try to send data on the same network, the arbitration mechanism to solve the data collision problem is necessary. This situation causes the time delay which has detrimental effects on the performance of the control systems. This paper proposes a method to solve the problem due to the time delay in distributed control system using CAN. Time delay is approximated to an element with a rational transfer function using Pade approximation and Mu~synthesis method is applied. Since time delay in the network is not constant, the time delay element is considered to be an uncertainty block with a bound. The proposed method is applied to the experimental system with CAN and proved to be effective.