• 대한원격탐사학회지
• /
• 제27권6호
• /
• pp.637-651
• /
• 2011

This study presents a rule-based urban image classification method for time series analysis of changes in the vicinity of Asan-si and Cheonan-si in Chungcheongnam-do, using Landsat satellite images (1991-2006). The area has been highly developed through the relocation of industrial facilities, land development, construction of a high-speed railroad, and an extension of the subway. To determine the yearly changing pattern of the urban area, eleven classes were made depending on the trend of development. An algorithm was generalized for the rules to be applied as an unsupervised classification, without the need of training area. The analysis results show that the urban zone of the research area has increased by about 1.53 times, and each correlation graph confirmed the distribution of the Built Up Index (BUI) values for each class. To evaluate the rule-based classification, coverage and accuracy were assessed. When Optimal allowable factor=0.36, the coverage of the rule was 98.4%, and for the test using ground data from 1991 to 2006, overall accuracy was 99.49%. It was confirmed that the method suggested to determine the maximum allowable factor correlates to the accuracy test results using ground data. Among the multiple images, available data was used as best as possible and classification accuracy could be improved since optimal classification to suit objectives was possible. The rule-based urban image classification method is expected to be applied to time series image analyses such as thematic mapping for urban development, urban development, and monitoring of environmental changes.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2010년도 춘계학술대회 논문집
• /
• pp.377-378
• /
• 2010

• 수산경영론집
• /
• 제22권2호
• /
• pp.1-17
• /
• 1991

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 춘계 학술발표회
• /
• pp.777-784
• /
• 2010

In the current Korean seismic design guide, the site classification and the corresponding site coefficients were determined based on the UBC-1997 (Uniform Building Code). In order to develop the current site classification system, it is important to compare the local site conditions in Korea to other countries which have similar seismic design guides. In the eastern United States, New York City(40degrees 45minutes north latitude, 73degrees 59minutes west longitude) suggested that current design guidelines are unsuitable to shallow bedrock depth sites. So the 3-parameter methods are performed for new criteria in New York City. In this study, site response analyses were performed at 181 study sites using one-dimensional equivalent linear to evaluate the site-specific earthquake ground motions at inland areas in the Korean peninsula and reclassify the results according to similar ground motions using the 3-parameter methods. It is effective that multi-parameter methods for Korean site characteristics in comparison with single parameter method.

• 로봇학회논문지
• /
• 제11권3호
• /
• pp.115-126
• /
• 2016

This paper suggests the method of the spherical signature description of 3D point clouds taken from the laser range scanner on the ground vehicle. Based on the spherical signature description of each point, the extractor of significant environmental features is learned by the Deep Belief Nets for the urban structure classification. Arbitrary point among the 3D point cloud can represents its signature in its sky surface by using several neighborhood points. The unit spherical surface centered on that point can be considered to accumulate the evidence of each angular tessellation. According to a kind of point area such as wall, ground, tree, car, and so on, the results of spherical signature description look so different each other. These data can be applied into the Deep Belief Nets, which is one of the Deep Neural Networks, for learning the environmental feature extractor. With this learned feature extractor, 3D points can be classified due to its urban structures well. Experimental results prove that the proposed method based on the spherical signature description and the Deep Belief Nets is suitable for the mobile robots in terms of the classification accuracy.

• Geomechanics and Engineering
• /
• 제30권5호
• /
• pp.449-460
• /
• 2022

Safe underground construction in a rock mass requires adequate ground investigation and effective determination of rock conditions. The estimation of rock mass behavior is difficult, because rock masses are innately anisotropic and heterogeneous at different scales and are affected by various environmental factors. Quantitative rock mass classification systems, such as the Q-system and rock mass rating, are widely used for characterization and engineering design. The measurement of rock classification parameters is subjective and can vary among observers, resulting in questionable accuracy. Geophysical investigation methods, such as seismic surveys, have also been used for ground characterization. Torsional shear wave propagation characteristics in cylindrical rods are equal to that in an infinite media. A probabilistic quantitative relationship between the Q-value and shear wave velocity is thus investigated considering long-wavelength wave propagation in equivalent continuum jointed rock masses. Individual Q-system parameters are correlated with stress-dependent shear wave velocities in jointed rocks using experimental and numerical methods. The relationship between the Q-value and the shear wave velocity is normalized using a defined reference condition. This relationship is further improved using probabilistic analysis to remove unrealistic data and to suggest a range of Q-values for a given wave velocity. The proposed probabilistic Q-value estimation is then compared with field measurements and cross-hole seismic test data to verify its applicability.

• 한국군사과학기술학회지
• /
• 제27권2호
• /
• pp.147-155
• /
• 2024

Based on the recently developed deep learning technology, many studies have been conducted on deep learning networks that simultaneously detect and classify targets of interest in synthetic aperture radar(SAR) images. Although numerous research results have been derived mainly with the open SAR ship datasets, there is a lack of work carried out on the deep learning network aimed at detecting and classifying SAR ground targets and trained with the synthetic dataset generated from electromagnetic scattering simulations. In this respect, this paper presents the deep learning network trained with the synthetic dataset and applies it to detecting and classifying real SAR ground targets. With experiment results, this paper also analyzes the network performance according to the composition ratio between the real measured data and the synthetic data involved in network training. Finally, the summary and limitations are discussed to give information on the future research direction.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.193-202
• /
• 2022

The classification of hyperspectral imagery (HSI) is essential in the surface of earth observation. Due to the continuous large number of bands, HSI data provide rich information about the object of study; however, it suffers from the curse of dimensionality. Dimensionality reduction is an essential aspect of Machine learning classification. The algorithms based on feature extraction can overcome the data dimensionality issue, thereby allowing the classifiers to utilize comprehensive models to reduce computational costs. This paper assesses and compares two HSI classification techniques. The first is based on the Joint Spatial-Spectral Stacked Autoencoder (JSSSA) method, the second is based on a shallow Artificial Neural Network (SNN), and the third is used the SVM model. The performance of the JSSSA technique is better than the SNN classification technique based on the overall accuracy and Kappa coefficient values. We observed that the JSSSA based method surpasses the SNN technique with an overall accuracy of 96.13% and Kappa coefficient value of 0.95. SNN also achieved a good accuracy of 92.40% and a Kappa coefficient value of 0.90, and SVM achieved an accuracy of 82.87%. The current study suggests that both JSSSA and SNN based techniques prove to be efficient methods for hyperspectral classification of snow features. This work classified the labeled/ground-truth datasets of snow in multiple classes. The labeled/ground-truth data can be valuable for applying deep neural networks such as CNN, hybrid CNN, RNN for glaciology, and snow-related hazard applications.

• 한국의상디자인학회지
• /
• 제16권4호
• /
• pp.117-136
• /
• 2014

The purpose of this study is to present a classification system of the hand-made and machine-made lace according to the configuration method and re-make the category and definition of lace to consider the emergence and development of major laces techniques. The re-made category and definition of the lace is as follows. The lace usually consists of ground and motifs, however, the techniques of netting and sprang are suitable for making ground than motif, so I think it is appropriate to exclude them from the category of the lace. Many scholars are excluded openwork embroidery fabric from the category of the lace. But, an openwork embroidery fabric is the basis of a needle point lace called true lace and is consist of motif and ground. I think it is appropriate to include it in the category of the lace. I think it is also appropriate to include in the category of the lace that the eyelet embroidery fabric which mimics the openwork embroidery fabric in the machine. Lace is redefined that a fabric with openwork decoration consists of motif and ground, constructed by a variety of ways such as plaiting, twisting, looping, knotting of threads or embroidering by hand or machine. The classification of the lace is presented as follows. Hand-made lace is classified bobbin lace, needle point lace, embroidery lace, knotted lace, crochet lace, and knitting lace. Machine-made lace is classified raschel lace, leaver lace, torchon lace, and machine-made embroidery laces which include tool lace, eyelet embroidery lace, chemical lace, etc.

• 물과 미래
• /
• 제6권1호
• /
• pp.55-58
• /
• 1973