• Journal of the Korean Institute of Gas
• /
• 제24권6호
• /
• pp.91-97
• /
• 2020

Lithium-ion batteries (LIBs) have a longer lifespan, higher energy density, and lower self-discharge rates than other batteries, therefore, they are preferred as an Energy Storage System (ESS). However, during years 2017-2019, 28 ESS fire accidents occurred in Korea, and accurate capacity estimation of LIB is essential to ensure safety and reliability during operations. In this study, data-driven modeling that predicts capacity changes according to the charging cycle of LIB was conducted, and developed models were compared their performance for the selection of the optimal machine learning model, which includes the Decision Tree, Ensemble Learning Method, Support Vector Regression, and Gaussian Process Regression (GPR). For model training, lithium battery test data provided by NASA was used, and GPR showed the best prediction performance. Based on this study, we will develop an enhanced LIB capacity prediction and remaining useful life estimation model through additional data training, and improve the performance of anomaly detection and monitoring during operations, enabling safe and stable ESS operations.

• Journal of the Korea Society of Computer and Information
• /
• 제28권1호
• /
• pp.65-70
• /
• 2023

In this paper, we propose a CCTV storage space securing model using YOLO v3. CCTV is installed and operated in various parts of society for disasters, disasters and safety such as crime prevention, fire prevention, and monitoring, and the number of CCTV is increasing and the quality of the video quality is improving. Due to this, as the number and size of image files increase, it is difficult to cope with the existing storage space. In order to solve this problem, we propose a model that detects specific objects in CCTV images using YOLO v3 library and deletes unnecessary frames by saving only the corresponding frames, thereby securing storage space by reducing the size of the image file, and thereby Periodic images can be stored and managed. After applying the proposed model, it was confirmed that the average image file size was reduced by 94.9%, and it was confirmed that the storage period was increased by about 20 times compared to before the application of the proposed model.

• Journal of Auto-vehicle Safety Association
• /
• 제14권1호
• /
• pp.26-31
• /
• 2022

Changwon City has the second highest accident rate with 79.6 according to the city bus accident rate. In fact, 250,000 people use the city bus a day in Changwon, The number of accidents is increasing gradually. In addition, a recent fire accident occurred in the engine room of a city bus (CNG) in Changwon, which has gradually expanded the public's anxiety. In the case of business vehicles, the government conducts inspections with a short inspection cycle for the purpose of periodic safety inspections, etc., but it is not in the monitoring stage. In the case of city buses, the operation records are monitored using Digital Tacho Graph (DTG). As such, driving records, methods, etc. are continuously monitored, but inspections are conducted every six months to ascertain the safety and performance of automobiles. It is difficult to identify real-time information on automobile safety. Therefore, in this study, individual automobile management solutions are presented through machine learning techniques of inspection results based on driving records or habits by linking DTG data and Vehicle Inspection Management System (VIMS) data for city buses in Changwon from 2019 to 2020.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.351-353
• /
• 2021

In recent years, while the demand for electricity is rapidly increasing, fire accidents due to negligence in management of switchboards. In particular, switchboards for industrial and electrical resource control can cause serious problems. Thus, for the safety management of power switchboard, a secondary response is conducted to control firing when a specific condition value is satisfied, but in this case, it is highly likely that a considerable amount of time has elapsed after firing. In this paper, we propose a method to acquire big data for the development of a switchboard temperature and power control system that can actively respond to the current situation by monitoring and learning the temperature of the switchboard's busbar connection in real time. Specifically, a method for periodically acquiring and managing data such as temperature and power from various scattered sensors is proposed.

• Korean Journal of Remote Sensing
• /
• 제39권6_1호
• /
• pp.1413-1425
• /
• 2023

The increasing frequency of wildfires due to climate change is causing extreme loss of life and property. They cause loss of vegetation and affect ecosystem changes depending on their intensity and occurrence. Ecosystem changes, in turn, affect wildfire occurrence, causing secondary damage. Thus, accurate estimation of the areas affected by wildfires is fundamental. Satellite remote sensing is used for forest fire detection because it can rapidly acquire topographic and meteorological information about the affected area after forest fires. In addition, deep learning algorithms such as convolutional neural networks (CNN) and transformer models show high performance for more accurate monitoring of fire-burnt regions. To date, the application of deep learning models has been limited, and there is a scarcity of reports providing quantitative performance evaluations for practical field utilization. Hence, this study emphasizes a comparative analysis, exploring performance enhancements achieved through both model selection and data design. This study examined deep learning models for detecting wildfire-damaged areas using Landsat 8 satellite images in California. Also, we conducted a comprehensive comparison and analysis of the detection performance of multiple models, such as U-Net and High-Resolution Network-Object Contextual Representation (HRNet-OCR). Wildfire-related spectral indices such as normalized difference vegetation index (NDVI) and normalized burn ratio (NBR) were used as input channels for the deep learning models to reflect the degree of vegetation cover and surface moisture content. As a result, the mean intersection over union (mIoU) was 0.831 for U-Net and 0.848 for HRNet-OCR, showing high segmentation performance. The inclusion of spectral indices alongside the base wavelength bands resulted in increased metric values for all combinations, affirming that the augmentation of input data with spectral indices contributes to the refinement of pixels. This study can be applied to other satellite images to build a recovery strategy for fire-burnt areas.

• The Korean Journal of Air & Space Law and Policy
• /
• 제28권1호
• /
• pp.3-54
• /
• 2013

Nowadays, major advanced countries in aviation technology are putting their effort to develop commercial and civil Unmanned Aircraft System(UAS) due to its highly promising market demand in the future. The market scale of commercial and civil UAS is expected to increase up to approximately 8.8 billon U.S. dollars by the year 2020. The usage of commercial and civil UAS covers various areas such as remote sensing, relaying communications, pollution monitoring, fire detection, aerial reconnaissance and photography, coastline monitoring, traffic monitoring and control, disaster control, search and rescue, etc. With the introduction of UAS, changes need to be made on current Air Traffic Management Systems which are focused mainly manned aircrafts to support the operation of UAS. Accordingly, the legislation for the UAS operation should be followed. Currently, ICAO's Unmanned Aircraft System Study Group(UASSG) is leading the standardization process of legislation for UAS operation internationally. However, some advanced countries such as United States, United Kingdom, Australia have adopted its own legislation. Among these countries, United States is most forth going with President Obama signing a bill to integrate UAS into U.S. national airspace by 2015. In case of Korea, legislation for the unmanned aircraft system is just in the beginning stage. There are no regulations regarding the operation of unmanned aircraft in Korea's domestic aviation law except some clauses regarding definition and permission of the unmanned aircraft flight. However, the unmanned aircrafts are currently being used in military and under development for commercial use. In addition, the Ministry of Land, Infrastructure and Transport has a ambitious plan to develop commercial and civil UAS as Korea's most competitive area in aircraft production and export. Thus, Korea is in need of the legislation for the UAS operation domestically. In this regards, I personally think that Korea's domestic legislation for UAS operation will be enacted focusing on following 12 areas : (1)use of airspace, (2)licenses of personnel, (3)certification of airworthiness, (4)definition, (5)classification, (6)equipments and documents, (7)communication, (8)rules of air, (9)training, (10)security, (11)insurance, (12)others. Im parallel with enacting domestic legislation, korea should contribute to the development of international standards for UAS operation by actively participating ICAO's UASSG.

• Journal of Cadastre & Land InformatiX
• /
• 제46권2호
• /
• pp.27-42
• /
• 2016

Forest accounts for almost 64 percents of total land cover in South Korea. For inventorying, monitoring, and managing such large area of forest, application of remote sensing and geographic information system (RS/GIS) technology is essential. On the basis of spectral characteristics of satellite imagery, forest cover and tree species can be classified, and forest cover map can be prepared. Using three dimensional data of LiDAR(Light Detection and Ranging), tree location and tree height can be measured, and biomass and carbon stocks can be also estimated. In addition, many indices can be extracted using reflection characteristics of land cover. For example, the level of vegetation vitality and forest degradation can be analyzed with VI (vegetation Index) and TGSI (Top Grain Soil Index), respectively. Also, pine wilt disease and o ak w ilt d isease c an b e e arly detected and controled through understanding of change in vegetation indices. RS and GIS take an important role in assessing carbon storage in climate change related projects such as A/R CDM, REDD+ as well. In the field of climate change adaptation, impact and vulnerability can be spatio-temporally assessed for national and local level with the help of spatio-temporal data of GIS. Forest growth, tree mortality, land slide, forest fire can be spatio-temporally estimated using the models in which spatio-temporal data of GIS are added as influence variables.

• Environmental and Resource Economics Review
• /
• 제27권2호
• /
• pp.315-337
• /
• 2018

Korean government temporarily shut down the coal-fired power plants built before 30 years and more from 6/1/2017 to 6/31/2017. This treatment provides a credible natural experiment regarding the regional $PM_{2.5}$ concentration and coal-fired generators. Based on this feature of the treatment, this study analyzed the causality between the old coal-fired power plants and regional $PM_{2.5}$ concentration. To be specific, we categorized two pollution monitoring stations nearby coal-fired power plants in Yeongdong into a treatment station and a control station based on the distance from the power plants. The control station is similar to the treatment station geographically and topographically, but its $PM_{2.5}$ concentration would not be directly affected by coal-fired power plants in Yeongdong. A difference-in-difference method was applied to identify the effects of the old coal-fire power plants on regional $PM_{2.5}$ concentration. The results show that the temporary shutdown would decrease $PM_{2.5}$ concentration nearby coal-fired power plants in Yeongdong by $3.7{\sim}4.4{\mu}g/m^3$.

• Journal of the Ergonomics Society of Korea
• /
• 제34권3호
• /
• pp.199-215
• /
• 2015

Objective: The purpose of this study is to find the level of physical relaxation of individual subject by monitoring psychophysiological biofeedback to different types of mattresses. And, the study also aims to find a protocol to make a selection of the best mattress based on the measured information. Background: In Korea, there are an increasing number of people using western style bed. However, they are often fastidious in choosing the right mattress for them. In fact, people use their past experience with their old mattress as well as the spontaneous experience they encounter in a show room to finally decide to buy a bed. Method: Total five mattresses were tested in this study. After measuring the elasticity of the mattresses, they were sorted into five different classes. Physiological and psychological variables including Electromyography (EMG), heart rates (HR), oxygen saturations (SaO2) were used. In addition, the peak body pressure concentration rate was used to find uncomfortably pressured body part. Finally, the personal factors and subjective satisfaction were also examined. A protocol was made to select the best mattress for individual subject. The selection rule for the protocol considered all the variables tested in this study. Results: The result revealing psychological comfort range of 0.68 to 0.95, dermal comfort range of 3.15 to 6.07, back muscle relaxation range of 0.25 to 1.64 and personal habit range of 2.0 to 3.4 was drawn in this study. Also a regression model was developed to predict biofeedback with the minimal use of biofeedback devices. Moreover results from the proposed protocol with the regression equation and subjective satisfaction were compared with each other for validation. Ten out of twenty subjects recorded the same level of relaxation, and eight subjects showed one-level difference while two subjects showed two-levels difference. Conclusion: The psychophysiological variables and suitability selection process used in this study seem to be used for selecting and assessing ergonomic products mechanically or emotionally. Application: This regression model can be applied to the mattress industry to estimate back muscle relaxation using dermal, psychophysiology and personal habit values.

• Journal of agricultural medicine and community health
• /
• 제34권3호
• /
• pp.346-358
• /
• 2009

Objectives: A study was conducted by analysing the contents and frequency of emergency treatment practiced by emergency medical technicians(EMTs) in emergency situations and contains related factors. Methods: The study subjects included 80 EMTs who participated in ongoing education classes during the period from June 25th to June 26th, 2008. the survey included 53 EMTs employed within 119 first aid teams in fire stations in both a metropolitan city and a medium-sized city. From the survey results relation between frequency of emergency treatment and subjects characteristics explored statistically including t-test, X2 test, Pearson correlation and finally stepwise multiple regression. Results: The most frequent procedure by EMTs checking vital signs. The statistically significant related factors overall of the 23 items of emergency treatment frequency was the working area and the grading of EMT certification. In contrast, significant related factors with frequency of IV linkage were found to be the subjects gender, institution employed and the importance of recognizing the item. The statistically significant related factors of that of ECG monitoring was the gender of respondents. Conclusions: To keep the appropriate frequency of emergency treatment by EMT, active efforts to promote their individual importance and confidence cognition are necessary, especially towards males and persons who have 2nd class certification. Moreover, EMTs who work in small cities must be supported.