• Journal of architectural history
• /
• v.18 no.5
• /
• pp.7-24
• /
• 2009

This stydy investigates H-shaped houses in 1930s and examines the characters and meanigs of Kim, Jong-Ryang's H-shaped houses as a new trial to urban Hanok of those days. He, who was concerned about the housing problem of Seoul, made an attempt to make various types of dwellings. Among them, this study focuses on Japanese-Korean Style H-shaped houses in Samcheong-dong. As the alternative housing type against other urban Hanok of Seoul in 1930s, the H-shaped houses of Kim, Jong Ryang had characters as follows : 1) H-shaped houses has two special characters. First, the whole space of a single house can be divided into a left region and a right region. Second, it can be divided to a front region and a rear region. In his H-shaped houses, the left/right division was expressed as folding of space-layers in parallel with urban streets. The front/rear division was used as classification of main-living space and sub-living space. 2) KJR's H-shaped Japanese-Korean Style houses were proved to be designed as urban housing against the extreme housing shortage of Seoul in 1930s. 3) His houses however were not accepted broadly as a urban house type because the construction cost of those was higher than an average and the element of Japanese style house was not adapted to Korea. Kim, Jong-Ryang's trial is valuable because it was the rare case of realization of many discourses as defects of existing house type. With more rigorous investigations on KJR's experiment in modern house type, we could understand the housing condition of Seoul in 1930s and modern urban houses more than before.

• Spatial Information Research
• /
• v.16 no.3
• /
• pp.373-383
• /
• 2008

LiDAR, unlike satellite imagery and aerial photographs, which provides irregularly distributed three-dimensional coordinates of ground surface, enables three-dimensional modeling. In this study, urban area was classified based on 3D information collected by LiDAR. Morphological and spatial properties are determined by the ratio of ground and non-ground point that are estimated with the number of ground reflected point data of LiDAR raw data. With this information, the residential and forest area could be classified in terms of height and density of trees. The intensity of the signal is distinguished by a statistical method, Jenk's Natural Break. Vegetative area (high or low density) and non-vegetative area (high or low density) are classified with reflective ratio of ground surface.

• Smart Structures and Systems
• /
• v.33 no.2
• /
• pp.93-103
• /
• 2024

Despite the rapid development of sensors, structural health monitoring (SHM) still faces challenges in monitoring due to the degradation of devices and harsh environmental loads. These challenges can lead to measurement errors, missing data, or outliers, which can affect the accuracy and reliability of SHM systems. To address this problem, this study proposes a classification method that detects anomaly patterns in sensor data. The proposed classification method involves several steps. First, data scaling is conducted to adjust the scale of the raw data, which may have different magnitudes and ranges. This step ensures that the data is on the same scale, facilitating the comparison of data across different sensors. Next, informative features in the time and frequency domains are extracted and used as input for a deep neural network model. The model can effectively detect the most probable anomaly pattern, allowing for the timely identification of potential issues. To demonstrate the effectiveness of the proposed method, it was applied to actual data obtained from a long-span cable-stayed bridge in China. The results of the study have successfully verified the proposed method's applicability to practical SHM systems for civil infrastructures. The method has the potential to significantly enhance the safety and reliability of civil infrastructures by detecting potential issues and anomalies at an early stage.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.23 no.4
• /
• pp.77-93
• /
• 2024

The recent development of data collection technology, which conveys various travel data in real-world such as mobile data and probe vehicle data, facilitates transportation planners identifying specified spatio-temporal travel patterns. In this study, an easily implementable travel mode classification methodology was proposed to classify inter-regional trip-modes without modeling by superimposing trajectories generated from mobile phone signaling and transportation infrastructure points into a polygon scale of a shapefile in a GIS system. Each regional mode trip was classified according to the rules such as the presence of transportation infrastructure in the trip trajectory, travel time, and the presence of access trips. An accuracy test generates Type I and Type II error results table to verify the proposed methodology. As a result, it was found that the methodology developed showed the F1-Score of the air mode 1.00, rail mode 0.95, bus mode 0.73.

• Journal of the Society of Disaster Information
• /
• v.14 no.4
• /
• pp.501-509
• /
• 2018

Purpose: UAV-based photo measurements are being researched using UAVs in the space information field as they are not only cost-effective compared to conventional aerial imaging but also easy to obtain high-resolution data on desired time and location. In this study, the UAV-based high-resolution images were used to perform the land cover classification. Method: RGB cameras were used to obtain high-resolution images, and in addition, multi-distribution cameras were used to photograph the same regions in order to accurately classify the feeding areas. Finally, Land cover classification was carried out for a total of seven classes using created ortho image by RGB and multispectral camera, DSM(Digital Surface Model), NDVI(Normalized Difference Vegetation Index), GLCM(Gray-Level Co-occurrence Matrix) using RF (Random Forest), a representative supervisory classification system. Results: To assess the accuracy of the classification, an accuracy assessment based on the error matrix was conducted, and the accuracy assessment results were verified that the proposed method could effectively classify classes in the region by comparing with the supervisory results using RGB images only. Conclusion: In case of adding orthoimage, multispectral image, NDVI and GLCM proposed in this study, accuracy was higher than that of conventional orthoimage. Future research will attempt to improve classification accuracy through the development of additional input data.

• International Journal of Highway Engineering
• /
• v.7 no.3 s.25
• /
• pp.43-52
• /
• 2005

Highway classification is an essential part of defining design criteria of roads. This study is to classify highways by factor analysis. To accomplish the objectives, factor analysis is performed for classifying highways using the traffic data observed at the permanent traffic count points in 2004. A total off variables are applied : AADT, K factor, D factor, heavy vehicle proportion, day time traffic volume proportion, peak hour volume proportion, sunday factor, vacation factor and COV(Coefficient of Variation). The results of factor analysis show that variables are divided into two factors, which are the factor related to the fluctuational characteristics of traffic volume and the factor related to heavy vehicle and directional volume characteristics. According to the results of cluster analysis, 353 permanent traffic count points are categorized into such three groups as type I for urban highway, type II for rural highway, type III for recreational highway, respectively.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.14 no.2
• /
• pp.28-39
• /
• 2011

This study estimates the characteristics of flow loads by classification items of the Ministry of Environment and by land cover change using HyGIS-SWAT. The result of analyzing the land cover change using the classification items shows that the urban area and the farmland area in Mishim-cheon and Gap-cheon are expanding while the forest area is decreasing. The result of analyzing the characteristics of classification items shows that peak discharge increases and total yearly discharge decreases in Mushim-cheon. The result of analyzing the characteristics by data-construction period shows that peak discharge decreases but total discharge increases in Gap-cheon. Three land cover change scenarios are applicable to the expansion of urban area and farmland area. According to the result of application, urbanization influences and Farmland area expansion influences increase peak discharge, total yearly discharge and sediment concentration.

• Korean Journal of Remote Sensing
• /
• v.35 no.2
• /
• pp.279-288
• /
• 2019

We evaluated the land cover classification performance of SegNet, which features semantic segmentation of aerial imagery. We selected four semantic classes, i.e., urban, farmland, forest, and water areas, and created 2,000 datasets using aerial images and land cover maps. The datasets were divided at a 8:2 ratio into training (1,600) and validation datasets (400); we evaluated validation accuracy after tuning the hyperparameters. SegNet performance was optimal at a batch size of five with 100,000 iterations. When 200 test datasets were subjected to semantic segmentation using the trained SegNet model, the accuracies were farmland 87.89%, forest 87.18%, water 83.66%, and urban regions 82.67%; the overall accuracy was 85.48%. Thus, deep learning-based semantic segmentation can be used to classify land cover.

• Land and Housing Review
• /
• v.14 no.4
• /
• pp.95-102
• /
• 2023

Numerous investigations have explored the integration of machine leaning algorithms with high-resolution drone image for object detection in urban settings. However, a prevalent limitation in vehicle extraction studies involves the reliance on bounding boxes rather than instance segmentation. This limitation hinders the precise determination of vehicle direction and exact boundaries. Instance segmentation, while providing detailed object boundaries, necessitates labour intensive labelling for individual objects, prompting the need for research on automating unsupervised instance segmentation in vehicle extraction. In this study, a novel approach was proposed for vehicle extraction utilizing unsupervised SVM classification applied to vehicle bounding boxes in drone images. The method aims to address the challenges associated with bounding box-based approaches and provide a more accurate representation of vehicle boundaries. The study showed promising results, demonstrating an 89% accuracy in vehicle extraction. Notably, the proposed technique proved effective even when dealing with significant variations in spectral characteristics within the vehicles. This research contributes to advancing the field by offering a viable solution for automatic and unsupervised instance segmentation in the context of vehicle extraction from image.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.6
• /
• pp.2748-2760
• /
• 2018

This paper proposes an audio event classification method based on convolutional neural networks (CNNs). CNN has great advantages of distinguishing complex shapes of image. Proposed system uses the features of audio sound as an input image of CNN. Mel scale filter bank features are extracted from each frame, then the features are concatenated over 40 consecutive frames and as a result, the concatenated frames are regarded as an input image. The output layer of CNN generates probabilities of audio event (e.g. dogs bark, siren, forest). The event probabilities for all images in an audio segment are accumulated, then the audio event having the highest accumulated probability is determined to be the classification result. This proposed method classified thirty audio events with the accuracy of 81.5% for the UrbanSound8K, BBC Sound FX, DCASE2016, and FREESOUND dataset.