• Journal of the Korean Solar Energy Society
• /
• v.37 no.2
• /
• pp.23-33
• /
• 2017

Accurate prediction of stochastic behavior of occupants is a well known problem for improving prediction performance of building energy use. Many researchers have been tried various sensors that have information on the status of occupant such as $CO_2$ sensor, infrared motion detector, RFID etc. to predict occupants, while others have been developed some algorithm to find occupancy probability with those sensors or some indirect monitoring data such as energy consumption in spaces. In this research, various sensor data and energy consumption data are utilized for decision tree algorithms (C4.5 & CART) for estimation of sub-hourly occupancy status. Although the experiment is limited by space (private room) and period (cooling season), the prediction result shows good agreement of above 95% accuracy when energy consumption data are used instead of measured $CO_2$ value. This result indicates potential of IoT data for awareness of indoor environmental status.

• Journal of the Regional Association of Architectural Institute of Korea
• /
• v.20 no.6
• /
• pp.113-119
• /
• 2018

Occupancy-based heating control is effective in reducing heating energy by preventing unnecessary heating during unoccupied period. Various technologies on detecting human occupancy have been developed using complicated machine learning algorithm and stochastic methodologies. This study aims at deriving low-cost and simple algorithm of occupancy inference that can be implemented to residential buildings. The core concept of the algorithm is to combine the occupancy probabilities based on indoor CO2 concentration and PIR(passive infrared) signals. The probability was estimated by applying different levels of decrement ratio depending on CO2 concentration change rate and aggregated PIR signals. The developed algorithm was validated by comparing the inference results with the occupancy schedule in a real residential building. The results showed that the inference algorithm can achieve the accuracy of 75~99%, which would be successfully implemented to the control of residential heating systems.

• Proceedings of the Korean Society of Disaster Information Conference
• /
• 2022.10a
• /
• pp.341-342
• /
• 2022

본 논문에서는 실내 재난 상황에서 재실자의 위치를 판단하기 위한 Frequency Modulated Continuous Wave(FMCW) 레이더 시스템의 정확도 향상을 위한 Generative Adversarial Networks(GAN) 기반의 신호 보간법을 제안한다. 제안된 실내 위치 추정 시스템은 딥러닝 학습 생성 모델을 활용하게 되는데, 학습을 위한 데이터의 수집이 용이하지 않아 부족하게 되는 학습데이터를 GAN 기법을 통해 확보하고자한다.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2008.11a
• /
• pp.356-362
• /
• 2008

This study is intended to evaluate the characteristics of smoke spreading and the appropriateness of evacuation time extended by operation of smoke control system during fire within the underground space of the building structured in compliance with the smoke control system performance criteria from the local fire safety standard in Korea. As a preceding review of this study, the combustibles was categorized and identified their heat release rates. For validate the estimated values, modeling a single underground shop was carried out. And a numerical analysis both in case of smoke control system in operation and the system not in operation was carried out of underground space. From the viewpoint of securing the evacuation time, the results were compared in an attempt to assess the appropriateness of the fire safety criteria.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 2011.04a
• /
• pp.165-169
• /
• 2011

실제 화재의 위험성을 평가하는 가장 좋은 방법은 직접 실재 화재 조건을 모사 또는 구현하여 평가하는 방법이다. 그러나, 비용과 시간 및 환경 문제를 생각한다면 쉬운 일은 아니다. 따라서 단위 재료를 태우거나, 전산 시뮬레이션을 활용하여 화재를 예측하는 방법을 활용한다. 본 연구에서는 콘칼로리미터 실험 결과를 기초 데이터로 실제 화재 실험인 room corner test의 총열방출량을 추정하였다. 그 결과 가연물의 부피 및 밀도와 보정상수를 활용하여 실제 총열방출량에 근접한 결과값을 얻을 수 있었으며, 산출된 총열방출량을 근거로 전산시뮬레이션을 수행, 시뮬레이션 결과값을 통해 재실자의 화재 및 연기에 대한 위험성 평가를 할 수 있었다. 본 결과를 통해 화재 시뮬레이션 수행 시 가연물에 따른 화재에 의한 위험성 평가를 할 수 있을 것으로 보인다.

• Solar Energy
• /
• v.15 no.3
• /
• pp.119-125
• /
• 1995

Since the using of heating energy associated with infiltration is significant in a building, the efforts to minimize the infiltration while ensuring minimum ventilation rates for various types of occupancy will be beneficial. In constrast to that many efforts have been made to reduce heat loss by improving thermal resistance of building envelope, little has been tried to reduce heat loss from infiltration. For achieving such an objective, measurement of air leakage rate will be pre-requisite as a diagnostic tool. A blower door system, a depressurization/pressurization method, was employed and it demonstrated a good potential for measuring airtightness performance of residential buildings. Based on the test results, annual energy savings for residential heating was estimated by reducing infiltration to a level of reasonably airtight or to a level of ASHRAE Standard 62-1989 for minimum ventilation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.661-663
• /
• 2014

Lighting that installed in large buildings detects a movement of passer using human-detecting sensor or occupancy sensor. It can turn on lighting automatically using sensor when there is any movement and turn off when there is no movement to reduce unnecessary power consumption. However, there is a problem of malfunction due to improper location of the sensor. Also the case of passage, even after passing through the passage, lighting is turned on for a long time. It does not reduce the power consumption efficiently. In this paper, we propose a method to control lighting by estimating the position of the passer. According to the result simulated in one passage, it is confirmed that the time of turning on the lighting is reduced about 7 minute compared to existing methods.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.25 no.6
• /
• pp.111-120
• /
• 2021

When a fire occurs in a commercial building, the evacuation route is complicated and the direction of smoke and flame is similar to that of the egress route of occupants, resulting in many casualties. Performance-based evacuation design for buildings is essential to minimize human casualties. In order to apply the performance-based evacuation design to buildings, it requires a complex fire simulation for each building, demanding a large amount of time and manpower. In order to supplement this, it would be very useful to develop an Available Safe Egress Time (ASET) prediction model that can rationally derive the ASET without performing a fire simulation. In this study, the correlations between fire temperature with visibility and toxic gas concentration were investigated through a fire simulation on a commercial building, from which databases for the training of artificial neural networks (ANN) were created. Based on this, an ANN model that can predict the available safe egress time was developed. In order to examine whether the proposed ANN model can be applied to other commercial buildings, it was applied to another commercial building, and the proposed model was found to estimate the available safe egress time of the commercial building very accurately.