• Journal of the Korean Society for Railway
• /
• v.11 no.4
• /
• pp.364-370
• /
• 2008

In this paper, we proposed new sensor network architecture with autonomous robots based on beacon mode and implemented real time monitoring system in real test-bed environment. The proposed scheme offers beacon based real-time scheduling for reliable association process with parent nodes and dynamically assigns network address by using NAA (Next Address Assignment) mechanism. For the large scale multi-sensor processing, our real-time monitoring system accomplished the intelligent database processing, which can generate not only the alert messages to the civilians but also process various sensing data such as fire, air, temperature and etc. Moreover, we also developed mobile robot which can support network mobility. Though the performance evaluation by using real test-bed system, we illustrate that our proposed system demonstrates promising performance for emergence monitoring systems.

• Journal of Advanced Marine Engineering and Technology
• /
• v.39 no.9
• /
• pp.953-958
• /
• 2015

Raspberry Pi is a credit card-sized computer with support for a large number of input and output peripherals. This makes it the perfect platform for interaction with many different devices and for usage in a wide range of applications. When combined with Wi-Fi, it can communicate remotely, therefore increasing its suitability for the construction of wireless sensor nodes. In addition, data processing and decision-making can be based on artificial intelligence, what is performed in developed testbed on the example of monitoring and determining the confidence of fire. In this paper, we demonstrated the usage of Raspberry Pi as a sensor web node for fire-safety monitoring in a building. When the UV-flame sensors detect a flame as thin as that of a candle, the Raspberry Pi sends a push-message to notify the assigned smartphone of the on-site situation through the GCM server. A mobile app was developed to provide a real-time video streaming service in order to determine a false alarm. If an emergency occurs, one can immediately call for help.

• Proceedings of the Korean Society of Surveying, Geodesy, Photogrammetry, and Cartography Conference
• /
• 2006.04a
• /
• pp.319-326
• /
• 2006

All around tile world there has been great human and economical damage continuously by disasters like the earthquakes and storms(Tsunami) in eastern asia which recently occurred, and like the New Orleams hurricane in USA. The situation is our countries damage from natural disasters due to heavy snow, storms, forest fires have been increasing In this research we obtained GSIS data of the 05' Yang-yang forest fire disaster area using multi-sensors like airborne laser data, GPS/INS, aerial photograph surveying. In result we produced digital topographical maps, digital elevation models, digital external models, digital images, infrared images. By, analyzing and comparing with past aerial photography we obtained the exact damage area, amount of damage, estimated tile areas where a landslide might occur, and we analyzed vegetations amount of damage and possibility of recovery.

• Journal of KIISE:Information Networking
• /
• v.35 no.3
• /
• pp.207-214
• /
• 2008

There are lots of studies on application systems using wireless sensor networks. As the application systems are adapted to industrial field, the reliability of these systems becomes new key feature. The lack of reliability is an obstacle to extension of wireless sensor networks. In this paper, we propose the monitoring system framework that can offer the reliability of wireless sensor networks using a micro camera module and wireless sensor network nodes. And also we propose the efficient transfer method for image information over low rate wireless networks. Using these system framework and transfer method, we implement WiSN(Wireless image Sensor Network) based fire monitoring system.

• Fire Science and Engineering
• /
• v.33 no.4
• /
• pp.140-151
• /
• 2019

It is to assess the indoor air quality of the chemical hazardous materials exposed to the fire after firefighters returned to the fire scene. The research subject randomly selected four fire stations located in Seoul, Korea. Two fire stations were set up as control groups after the return of the firefighting activities at the actual fire scene, and two other fire stations were set up as control groups to measure the air quality of the room at normal levels regardless of the action. We conducted 24-hour monitoring for all fire accidents that occurred in Seoul Metropolitan using fire safety map computer system. Also, indoor air quality was measured immediately after homecoming if the experiment group was to be dispatched due to an accident of intermediate or larger scale. 11 hazardous substance items such as fine dust, formaldehyde, volatile organic compounds, PAH, VCM, acidity, asbestos, CO₂, NO₂, O₃ were measured according to the process test method. Three of 11 types of harmful substances exceeded domestic and foreign standards, and one of them was found to be close to foreign standards. In particular, total volatile organic compounds, carbon dioxide and sulfuric acids were 2.5 times, 2.2 times and 1.1 times higher than the standard. Also, for formaldehyde and sulfuric acid, it was measured higher in the control group than in the case group. This findings could be used in policies to improve indoor air quality in the fire station of the Seoul Metropolitan Government.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_3
• /
• pp.967-977
• /
• 2022

The occurrence and intensity of wildfires are increasing with climate change. Emissions from forest fire smoke are recognized as one of the major causes affecting air quality and the greenhouse effect. The use of satellite product and machine learning is essential for detection of forest fire smoke. Until now, research on forest fire smoke detection has had difficulties due to difficulties in cloud identification and vague standards of boundaries. The purpose of this study is to detect forest fire smoke using Level 1 and Level 2 data of Geostationary Environment Monitoring Spectrometer (GEMS), a Korean environmental satellite sensor, and machine learning. In March 2022, the forest fire in Gangwon-do was selected as a case. Smoke pixel classification modeling was performed by producing wildfire smoke label images and inputting GEMS Level 1 and Level 2 data to the random forest model. In the trained model, the importance of input variables is Aerosol Optical Depth (AOD), 380 nm and 340 nm radiance difference, Ultra-Violet Aerosol Index (UVAI), Visible Aerosol Index (VisAI), Single Scattering Albedo (SSA), formaldehyde (HCHO), nitrogen dioxide (NO₂), 380 nm radiance, and 340 nm radiance were shown in that order. In addition, in the estimation of the forest fire smoke probability (0 ≤ p ≤ 1) for 2,704 pixels, Mean Bias Error (MBE) is -0.002, Mean Absolute Error (MAE) is 0.026, Root Mean Square Error (RMSE) is 0.087, and Correlation Coefficient (CC) showed an accuracy of 0.981.

• Journal of Digital Convergence
• /
• v.7 no.3
• /
• pp.103-111
• /
• 2009

In this paper, we introduce automatic meter reading system for tap water. The system is composed of automatic meter, router using RF and CDMA network, and data server. This system will easily extend to fire detect, gas, and electric charge meter system. In addition, this system will be used to monitoring a water leak and human which live in solitude. Proposed system is installed at Gimhae-City and Gijang-gun. As a result of the automatic meter reading system for tap water, The leak of water and complain of user is decreased. But The building cost is still an obstacle to expand into entire city.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.24 no.5
• /
• pp.519-526
• /
• 2018

In this study, an algorithm to predict evacuation routes in support of shipboard lifesaving activities is presented. As the first step of algorithm development, the feasibility and necessity of an evacuation route prediction algorithm are shown numerically. The proposed algorithm can be explained in brief as follows. This system continuously obtains and analyzes passenger movement data from the ship's monitoring system during non-disaster conditions. In case of a disaster, evacuation route prediction information is derived using the previously acquired data and a prediction tool, with the results provided to rescuers to minimize casualties. In this study, evacuation-related data obtained through fire evacuation trials was filtered and analyzed using a statistical method. In a simulation using the conventional evacuation prediction tool, it was found that reliable prediction results were obtained only in the SN1 trial because of the conceptual and structural nature of the tool itself. In order to verify the validity of the algorithm proposed in this study, an industrial engineering tool was adapted for evacuation characteristics prediction. When the proposed algorithm was implemented, the predicted values for average evacuation time and route were very similar to the measured values with error ranges of 0.6-6.9 % and 0.6-3.6 %, respectively. In the future, development of a high-performance evacuation route prediction algorithm is planned based on shipboard data monitoring and analysis.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.3
• /
• pp.583-589
• /
• 2016

Volatile organic compounds(VOCs) are regarded as a harmful cause substance not only causing air pollutions but also causing global warming phenomenon. For this reason, VOCs are managed politically to reduce emissions by each country. In particular, the vapor from the gas station contains VOCs which is harmful to the human body such as carcinogens benzene and pollute the atmosphere, the Ministry of Environment defined every gas station must install vapor recovery equipment to recover volatile organic compounds. Recently, there are many accidents caused by existing vapor treatment methods, the liquefaction recovery technology is getting the spotlight to cool the vapor at the field. However, because the liquefaction recovery technology have risks of fire or explosion in accordance with temperature, the real time monitoring is critical factor. In this paper, we implement an Android-based monitoring application for liquified vapor recovery device which attached sensor module for temperature and power to monitoring real time information.

• 한국태양에너지학회:학술대회논문집
• /
• 2009.11a
• /
• pp.259-264
• /
• 2009

Most of the fossil power plants firing lower grade coals are challenged with maintaining good combustion conditions while maximizing generation and minimizing emissions. In many cases significant derate, availability losses and increase in unburned carbon levels can be attributed to poor combustion conditions as a result of poorly controlled local fuel and air distribution within the boiler furnace. The poor combustion conditions are directly related to the gas flow deviation in upper furnace and convection tube-bank but a less reported issue related to in large-scale oppose wall fired boilers. In order to develop a on-line combustion monitoring system and suggest an alternative heat flux estimation method at tube bank, which is very useful information for boiler design tool and blower optimizing system, field test was conducted at operating power boiler. During the field test the exhaust gases' temperature and tube metal temperature were monitored by using a spatially distributed sensors grid which located in the boiler's high temperature vestibule region. At these locations. the flue gas flow is still significantly stratified, and air in-leakage is minimal which enables tracing of poor combustion zones to specific burners and over-fire air ports. Test results showed that the flue gas monitoring method is more proper than metal temperature distribution monitoring for real time combustion monitoring because tube metal temp. distribution monitoring method is related to so many variables such as flue gas, internal flow unbalance, spray etc., Heat flux estimation at the tube bank with flue gas temp. and metal temp. data can be alternative method when tube drilling type sensor can't able to use.