• Proceedings of the Korean Society of Computer Information Conference
• /
• 2016.07a
• /
• pp.13-15
• /
• 2016

에너지 소비가 큰 건물은 내부 온/습도, 이산화탄소 농도, 미세먼지 농도 등의 일정 공기 질을 유지하면서 에너지 비용을 최소화할 수 있는 제어계획을 수립하는 것이 필요하다. 기존 건물에서 실내 환경의 운영은 설정된 실내 환경 값을 기준을 벗어나면 설비 기기를 제어하는 방식으로 이루어진다. 이는 단 시간에 고에너지를 투입하여 장비를 가동시키므로 에너지 소모가 크며 peak 전력이 높아 에너지 비용이 크다는 문제가 있다. 따라서 온도를 포함한 환경이 변해가는 상황을 예측하고 사전에 에너지 사용 계획을 수립하여 관리 제어를 수행함으로써 예열부하 등의 불필요한 에너지 손실을 절감하려 한다. 이를 위해 실내 환경이 변화하는 것을 예측하고 후보 제어계획으로 제어를 수행할 때 소요되는 에너지가 어느 정도인지 시뮬레이션하여 제어계획의 적합도를 평가한다. 기존 EnergyPlus와 같은 시뮬레이션 도구는 모델이 복잡하여 시뮬레이션에 많은 시간이 필요하기 때문에 환경 변화를 반영하기 위해 주기적으로 재수립되는 수많은 제어계획 데이터를 단시간에 시뮬레이션하기에 부적합하다. 본 논문에서는 빠른 시뮬레이션을 위해 실제 운영 데이터와 에뮬레이션을 통해 획득한 운영 데이터를 기반으로 학습 알고리즘을 이용하여 제어계획 적용 시의 미래 상황을 예측한다.

• 한국공간정보시스템학회:학술대회논문집
• /
• 2004.12a
• /
• pp.125-131
• /
• 2004

LiDAR 데이터의 필터링은 원 데이터로부터 건물, 수목 등과 같은 비지면점을 제거하는 과정이며, 이러한 필터링을 통해 DEM을 생성할 수 있다. 대표적인 필터링 방법들로는 분산을 이용한 linear prediction 기법, 주변 점들과의 경사관계를 이용한 slope-based 기법, morphology 필터, local maxima 필터 등이 있으며 이러한 기존의 기법들의 단점을 보완하기 위한 연구가 활발히 진행되고 있다. 대부분의 필터링 기법들은 필터의 크기(윈도우의 크기)와 같은 인자를 대상 지역에 적합하게 사용자가 직접 설정해주어야 한다. 더욱이 복잡한 지형, 지물이 존재하는 지역에 적용하기 위해서는 인자를 변형시켜줘야 하며 특히, 다양한 크기의 건물이 존재하는 지역에 대하여 적용하기 위해서는 가변적인 크기의 필터가 필요하다. 이에 본 논문에서는 다양한 크기의 건물이 존재하는 지역에 대하여 필터의 크기를 변화시키지 않고 필터링을 수행할 수 있는 연산기법을 제안하였다. 본 연구에서는 수목이나 자동차 등과 같은 작은 개체의 제거를 위해 고정된 작은 크기의 윈도우를 가지는 모폴로지 필터를 우선 적용한다. 그 후 건물과 같은 큰 개체의 포인트는 이웃 포인트와의 고도차이를 이용하여 인식하고 이웃에 위치하는 지면 포인트로 대체하며, 갱신된 값이 바로 다음 연산에 반영 되도록 한다. 또한 상, 하, 좌, 우 네 방향에 대하여 라인별로 독립된 연산을 수행한 후에 이들을 비교함으로써 오차를 보정한다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.3
• /
• pp.24-33
• /
• 2009

Stream data, gathered from ubiquitous sensor networks, change continuously over time. Because they have quite different characteristics from traditional databases, we need new techniques for storing and querying/analyzing these stream data, which are research issues recently emerging. In this research, we implemented a storage manager gathering stream data and storing them into databases, which are sampled continuously from sensor networks. The storage manager cleans faulty data occurred in mobile sensors and it also reduces the size of stream data by merging repeatedly-sampled values into one and by employing the tilted time frame which stores stream data with several different sampling rates. In this research furthermore, we measured the performance of the storage manager in the context of a sensor network monitoring fires of a building. The experimental results reveal that the storage manager reduces significantly the size of storage spaces and it is effective to manage the data stream for real applications monitoring buildings and their fires.

• Spatial Information Research
• /
• v.23 no.1
• /
• pp.49-57
• /
• 2015

Due to high density of population and progress of high building construction technologies, the number of high buildings has been increasing. Several information services have been provided to figure out complex indoor structures of building such as indoor navigations and indoor map services. The most fundamental information for these services are indoor network information. Indoor network in building provides topological connectivity between spaces unlike geometric information of buildings. In order to make indoor network information, we have to edit network manually or derive network properties based on the geometric data of buildings. This process is not easy for complex buildings. In this paper, we suggest a method to generate indoor network automatically based on crowdsourcing. From the collected individual trajectories, we derive indoor network information with crowdsourcing. We validate our method with a sample set of trajectory data and the result shows that our method is practical if the indoor positioning technology is reasonably accurate.

• The Journal of Bigdata
• /
• v.6 no.1
• /
• pp.133-144
• /
• 2021

This paper derives the fire risk of buildings in Seoul through the prediction of property damage and the occurrence of fires. This study differs from prior research in that it utilizes variables that include not only a building's characteristics but also its affiliated administrative area as well as the accessibility of nearby fire-fighting facilities. We use Ensemble Voting techniques to merge different machine learning algorithms to predict property damage and fire occurrence, and to extract feature importance to produce fire risk. Fire risk prediction was made on 300 buildings in Seoul utilizing the established model, and it has been derived that with buildings at Level 1 for fire risks, there were a high number of households occupying the building, and the buildings had many factors that could contribute to increasing the size of the fire, including the lack of nearby fire-fighting facilities as well as the far location of the 119 Safety Center. On the other hand, in the case of Level 5 buildings, the number of buildings and businesses is large, but the 119 Safety Center in charge are located closest to the building, which can properly respond to fire.

• Journal of Industrial Convergence
• /
• v.21 no.1
• /
• pp.159-165
• /
• 2023

While the frequency of seismic occurrence has been increasing recently, the domestic seismic response system is weak, the objective of this research is to compare and analyze the seismic vulnerability of buildings using statistical analysis and machine learning techniques. As the result of using statistical technique, the prediction accuracy of the developed model through the optimal scaling method showed about 87%. As the result of using machine learning technique, because the accuracy of Random Forest method is 94% in case of Train Set, 76.7% in case of Test Set, which is the highest accuracy among the 4 analyzed methods, Random Forest method was finally chosen. Therefore, Random Forest method was derived as the final machine learning technique. Accordingly, the statistical analysis technique showed higher accuracy of about 87%, whereas the machine learning technique showed the accuracy of about 76.7%. As the final result, among the 22,296 analyzed building data, the seismic vulnerabilities of 1,627(0.1%) buildings are expected as more dangerous when the statistical analysis technique is used, 10,146(49%) buildings showed the same rate, and the remaining 10,523(50%) buildings are expected as more dangerous when the machine learning technique is used. As the comparison of the results of using advanced machine learning techniques in addition to the existing statistical analysis techniques, in spatial analysis decisions, it is hoped that this research results help to prepare more reliable seismic countermeasures.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.24 no.4
• /
• pp.335-341
• /
• 2006

This paper aims at developing an efficient method that extracts building using local spatial association of raw LiDAR data without setting up empirical variables such as a minimum building area, and applying the method to survey data to evaluate the efficiency of that. To do this, LISA(Local Indicatiors of Spatial Association) statistics are used which reflect local variations that can be appeared in the research area. It can be also a preprocess that detects spatial outliers through the significance test of LISA statistics and interpolate using kernel estimation. Boundaries of buildings as well as buildings can be extracted based on quadrant of Moran Scatterplot. Experimental results show that the proposed method is promising in extracting buildings from LiDAR data automatically.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1091-1100
• /
• 2022

As deep learning technology advances and various high-resolution remote sensing images are available, interest in using deep learning technology and remote sensing big data to detect buildings and change in urban areas is increasing significantly. In this paper, for semantic building segmentation of high-resolution remote sensing images, we propose a new building segmentation model, Convolutional Block Attention Module (CBAM)-DRUNet that uses the DeepResUNet model, which has excellent performance in building segmentation, as the basic structure, improves the residual learning unit and combines a CBAM with the basic structure. In the performance evaluation using WHU dataset and INRIA dataset, the proposed building segmentation model showed excellent performance in terms of F1 score, accuracy and recall compared to ResUNet and DeepResUNet including UNet.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.248-250
• /
• 2015

건물 또는 실내에서 사용자의 위치를 찾는 스마트 측위 기술은 비콘 노드에서 발생하는 신호의 세기와 식별자 정보로 위치를 검색한다. 하지만 이러한 측위에 사용되는 데이터의 이동 경로는 비콘 노드의 에너지 량, 거리 및 홉 수를 고려하지 않고 설계된다. 또한, 실외와 달리 건물 내의 비콘 노드가 설치된 상황에 따라 데이터 경로가 사라져 데이터를 유실하는 경우가 많이 발생한다. 본 연구에서는 실시간으로 변하는 환경에서 노드의 에너지양, 노드간의 거리 및 홉 수를 고려해 효율적으로 전달하는 방법을 연구했다. 이로써 기존의 고정된 데이터 경로 모델에서의 발생하는 국부적인 에너지 손실 및 데이터 유실의 문제점을 개선했다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.31 no.2
• /
• pp.111-119
• /
• 2013

It is essential and fundamental to extract boundary information of target object via massive three-dimensional point data acquired from laser scanner. Especially extracting boundary information of manmade features such as buildings is quite important because building is one of the major components consisting complex contemporary urban area, and has artificially defined shape. In this research, extended ${\chi}$-algorithm using geometry information of point data was proposed to extract boundary information of building from three-dimensional point data consisting building. The proposed algorithm begins with composing Delaunay triangulation process for given points and removes edges satisfying specific conditions process. Additionally, to make whole boundary extraction process efficient, we used Sweep-hull algorithm for constructing Delaunay triangulation. To verify the performance of the proposed extended ${\chi}$-algorithm, we compared the proposed algorithm with Encasing Polygon Generating Algorithm and ${\alpha}$-Shape Algorithm, which had been researched in the area of feature extraction. Further, the extracted boundary information from the proposed algorithm was analysed against manually digitized building boundary in order to test accuracy of the result of extracting boundary. The experimental results showed that extended ${\chi}$-algorithm proposed in this research proved to improve the speed of extracting boundary information compared to the existing algorithm with a higher accuracy for detecting boundary information.