• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.28 no.1
• /
• pp.88-95
• /
• 2014

The infrared, flame detector uses to detect fire situation from the characteristics of fire sources radiant energy. But it is able to malfunction on account of susceptible to interference of various surrounding waves. This paper is designed 6 independent PCB-boards to minimize the closed loops of siginal circuit. Also considering the interaction of electric and magnetic fields, this paper is designed protecting circuit of current and voltage output to reduced electromagnetic interference. And this paper is improving electromagnetic susceptibility by ferrite bid, capacitor filter and grounding circuits.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2011.06a
• /
• pp.159-163
• /
• 2011

U-City의 안전을 위하여 안전한 전기공급과 전기안전 점검과 전송에 필요한 전기IT 인프라는 중대한 요소이다. U-City의 건설에 필요한 전기IT기기의 설계와 개발 및 제조를 하고 Test-bed에 설치하여 성능 평가를 한 후에 검증을 맡은 전기IT기기를 U-City 설치하여야 한다. 본 논문에서는 U-City 안전을 위한 전기IT기기에 대한 절연저항, 누설전류에 따르는 고온, 연기, Co2, 불꽃, 화재 등을 감지하는 센서를 부착하고, 발생할 수 있는 재난을 사전에 예방하기 위해 전기안전보호기술, 전기설비를 상시 감시할 수 있는 기반기술, 설비를 원격으로 관리할 수 있는 제품에 대한 성능평가와 시뮬레이션을 통해 U-City에 구축되려는 종합적인 전력통합감시시스템을 연구한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.652-655
• /
• 2023

우리나라에서는 지난 10년간 매년 4만 건 내외의 화재가 발생하여 많은 인명 피해와 경제적 손실이 발생하고 있다. 화재가 발생했을 때는 화재를 신속히 진압하여 인명 피해와 경제적 손실을 최소화하여야 한다. 또한, 화재 사고를 예방하기 위해 화재의 발화 원인이 무엇인지 알아내야 한다. 기존의 화재 경보 시스템에서는 온도, 연기, 불꽃 센서 등으로 화재를 감지하였으나 오경보나 화재를 인식하지 못하는 문제, 화재 원인을 구분하지 못하는 문제 등이 있었다. 또한, 사람이 화재 발생을 인지하기까지 시간이 많이 소요될 수 있고 부재로 인해 화재 상황인식이 늦어질 수도 있는 문제가 있었다. 이러한 문제를 해결하기 위해 본 논문에서는 GCN(Graph Convolutional Network) 모델을 이용하여 화재 상황에서의 복합 센서 상황을 학습해서 실제 화재 사고가 발생했을 때 화재의 원인을 구분할 수 있는 모델을 제안한다.

• Journal of Convergence for Information Technology
• /
• v.7 no.4
• /
• pp.91-96
• /
• 2017

In this paper, we aim to respond efficiently to crime by using Arduino and smartphone apps in response to increasing number of house-breaking crimes. It receives the signal of the sensor installed in the house and connects it with the app of the smartphone. To use the app, you can download the app from the user's smartphone, launch the app, and operate the operation outside the home, not only inside the house, by linking the executed app. Among the sensors installed in the house, the movement detection sensor is used to enhance the security, and the gas leakage sensor and the flame detection sensor can be used to easily detect the risk of fire and to prevent the fire early. Security is further enhanced by the ability to remotely control the front door with a smartphone. After that, various sensors can be added and it can be developed as a WiFi module in addition to the Bluetooth module.

• Fire Science and Engineering
• /
• v.26 no.6
• /
• pp.24-30
• /
• 2012

This study is on the method of the detection for flame and series arc which can be happened at poor contact point added a vibration in part of contact point of low voltage line. In general, the causes of electric fire are over current, short circuit, poor contact, ect. The over-current or short circuit among those causes is detected by measuring a instant current value, but poor contact is difficult to detect by measuring a excessive value of the voltage and current and a distortion of waveforms. And therefore, in this paper, it is studied on the optimal technique of the arc judgement using fuzzy logic and MDET (Multi Dimension Estimation Technique). And it carries out the simulation for arc detection and the experiment for controller and load test. In result, the controller and detection algoristhm, is classified with normal wave and abnormal arc wave without relation with each loads and so the controller can detect a series arc successfully.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.4
• /
• pp.753-762
• /
• 2024

Tunnels have limited evacuation areas, and It is difficult for cars coming from behind to recognize the accident situation in front. Since an accident is very likely to lead to a serious secondary accident, a IoT-based smart tunnel accident warning system was studied to prepare for traffic accidents that occur in tunnels. If the measured values from the flame detection sensor, gas detection sensor, and shock detection sensor in the tunnel exceed the standard, it is judged to be an emergency situation and an alert system is designed to operate. The accident information message was designed to be displayed on the LCD and transmitted to drivers inside and outside the tunnel through a Wi-Fi communication network. A performance test system was established and performance evaluation was performed for several accident scenarios. As a result of the test, it was confirmed that the accident alert system can accurately detect accidents based on given reference values, perform alert procedures, and transmit alert messages to smart phones through Wi-Fi wireless communication. And through this, its effectiveness could be confirmed.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.534-539
• /
• 2008

This paper is about intelligent hexapod robot for the support walking of the aged person. The robot using various sensors and small camera has various abilities of forward backward walking, turing left or right, control the speed of walking, avoiding the obstacles and detecting risky situation of fire or gas. To let the aged feel soft and safe walking, we used special servo motor and developed hexapod walking mechanism and effective algorithm.

• Proceedings of the Korea Contents Association Conference
• /
• 2007.11a
• /
• pp.201-205
• /
• 2007

This thesis aims to realize an intelligent home service robot that alerts the user to dangerous situations such as fires and gas leaks by utilizing wireless internet platforms in a cellular phone. The intelligent home service robot is composed of the following parts: The robot part consists of a gas sensor, a fire detector, a smoke sensor, ultrasonic sensors, motors, a camera and a Blue-tooth module and perceives various danger circumstances; The middleware part connects the robot part with the mobile part through the middleware applications, monitors the robot and notifies an emergency situation using SMS modules; The mobile part communicates with the middleware using TCP/IP protocol and controls the robot through various commands; The proposed scheme is to control the sensors of the robot part through and Atmega128 processor, and the mobile part was developed based on the WIPI platform. The robot and middleware parts will be installed in the household, and will be controled by mobile part from the outside.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.397-399
• /
• 2021

The increase in single-person households and the development of Home IoT technology make it important to improve the convenience of the residential environment. In addition, the increase in indoor activities caused by COVID-19 calls for the development of products to make life more convenient for single-person households. This trend of increased indoor activity has made it easier to interact with the current residential environment than before, and as a result, the need to develop technology for Home IoT is emerging. Therefore, the Home IoT system will be developed to monitor the information needed to maintain an ideal indoor environment such as temperature, humidity, and fine dust. The system will also interact with users, and propose a system that improves safety in indoor activities by equipping the home with IoT sensors for preventing safety accidents such as gas leakage and fire.

• Journal of the Society of Disaster Information
• /
• v.19 no.4
• /
• pp.968-975
• /
• 2023

Purpose: We would like to confirm that the false positive rate of flames/smoke is high when detecting fires. Propose a method and dataset to recognize and classify fire situations to reduce the false detection rate. Method: Using the video as learning data, the characteristics of the fire situation were extracted and applied to the classification model. For evaluation, the model performance of Yolov8 and Slowfast were compared and analyzed using the fire dataset conducted by the National Information Society Agency (NIA). Result: YOLO's detection performance varies sensitively depending on the influence of the background, and it was unable to properly detect fires even when the fire scale was too large or too small. Since SlowFast learns the time axis of the video, we confirmed that detects fire excellently even in situations where the shape of an atypical object cannot be clearly inferred because the surrounding area is blurry or bright. Conclusion: It was confirmed that the fire detection rate was more appropriate when using a video-based artificial intelligence detection model rather than using image data.