• Asian Journal of Atmospheric Environment
• /
• v.2 no.1
• /
• pp.34-46
• /
• 2008

Emissions inputs for use in air quality modeling of Korea were generated with the emissions inventory data from the National Institute of Environmental Research (NIER), maintained under the Clean Air Policy Support System (CAPSS) database. Source Classification Codes (SCC) in the Korea emissions inventory were adapted to use with the U.S. EPA's Sparse Matrix Operator Kernel Emissions (SMOKE) by finding the best-matching SMOKE default SCCs for the chemical speciation and temporal allocation. A set of 19 surrogate spatial allocation factors for South Korea were developed utilizing the Multi-scale Integrated Modeling System (MIMS) Spatial Allocator and Korean GIS databases. The mobile and area source emissions data, after temporal allocation, show typical sinusoidal diurnal variations with high peaks during daytime, while point source emissions show weak diurnal variations. The model-ready emissions are speciated for the carbon bond version 4 (CB-4) chemical mechanism. Volatile organic carbon (VOC) emissions from painting related industries in area source category significantly contribute to TOL (Toluene) and XYL (Xylene) emissions. ETH (Ethylene) emissions are largely contributed from point industrial incineration facilities and various mobile sources. On the other hand, a large portion of OLE (Olefin) emissions are speciated from mobile sources in addition to those contributed by the polypropylene industry in point source. It was found that FORM (Formaldehyde) is mostly emitted from petroleum industry and heavy duty diesel vehicles. Chemical speciation of PM2.5 emissions shows that PEC (primary fine elemental carbon) and POA (primary fine organic aerosol) are the most abundant species from diesel and gasoline vehicles. To reduce uncertainties in processing the Korea emission inventory due to the mapping of Korean SCCs to those of U.S., it would be practical to develop and use domestic source profiles for the top 10 SCCs for area and point sources and top 5 SCCs for on-road mobile sources when VOC emissions from the sources are more than 90% of the total.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.16 no.2
• /
• pp.93-104
• /
• 2013

The purpose of this study was to develop a list of plants that adapted to the aquatic environment in urban areas based on the list of plants surveyed through literature review and field surveys, and to classify the types of vegetation according to the five categories of plant distributions set by the U.S. Fish and Wildlife Service (1988) in the aspect of the adaptability of plants to the aquatic environment. Results of the classification by category according to the adaptability to the aquatic environment for the plant species surveyed through literature review and field surveys showed that there are 45 species of OBL, 96 species of FACW, 66 species of FAC, and 94 species of FACU, totaling 650 species. In addition, a total of 50 species excluding exotic species, endangered species, and naturally introduced plants are proposed as appropriate plants for the urban aquatic environment that will be artificially constructed. The results of the study can be utilized as the basic information for maintaining diversity and stability of the ecosystem during the restoration of water ecology; they can serve as useful data for the development of an optimum vegetation model when planting in water spaces in the future and preparing proper planting plans for each space. In addition, it is believed that the information will be useful in wetland identification and evaluation by observing plant species that appear only in wetlands.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.750-757
• /
• 2020

One of the basic tasks for robots to interact with humans is to quickly and accurately grasp human behavior. Therefore, it is necessary to increase the accuracy of human pose recognition when the robot is estimating the human pose and to recognize it as quickly as possible. However, when the human pose is estimated using deep learning, which is a representative method of artificial intelligence technology, recognition accuracy and speed are not satisfied at the same time. Therefore, it is common to select one of a top-down method that has high inference accuracy or a bottom-up method that has high processing speed. In this paper, we propose two methods that complement the disadvantages while including both the advantages of the two methods mentioned above. The first is to perform parallel inference on the server using multi GPU, and the second is to mix bottom-up and One-class Classification. As a result of the experiment, both of the methods presented in this paper showed improvement in speed. If these two methods are applied to the entertainment robot, it is expected that a highly reliable interaction with the audience can be performed.

• Current Research on Agriculture and Life Sciences
• /
• v.27
• /
• pp.59-67
• /
• 2009

The purpose of this study is to propose the methodology for introducing green infrastructure that can improve the health of citizens by promoting walkability. The methodology is composed of the following three phases: classification of the types of green spaces, selection of core green spaces with two separate analyses, and introduction of the framework of green infrastructure to promote walkability. In the first phase, the classification of the types of green spaces was carried out in order to understand existing distribution pattern of green spaces in study site. In the second phase, walkable blocks were selected by such methods as walkability value. Through these two analyses, all the blocks were divided into three groups according to the ranking figured up the second analyses' results. The blocks in the first group, the group involved in the top 30% and having the greatest ranking, were defined as walkable blocks. In the last phase, a basic frame of the green infrastructure in study site was introduced by connecting the walkable blocks with using other blocks and the green spaces over 1ha. In case study, 28 important green spaces and 35 walkable blocks were selected through the two analysis process. Then, the basic framework of green infrastructure based on the selected 28 important green spaces and 35 walkable blocks was introduced. The methodology applied to this study can be used to get the best selections of the proper green infrastructure in accordance with the purpose of the ecological and recreational local development. In particular, this study will suggest a specific analysis model to use for the ecological and walkable urban planning with green spaces existing in the city.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.5
• /
• pp.167-178
• /
• 2020

The purpose of this paper is to establish a defect classification system for defects before inspection and to derive the pattern and characteristics of defects before inspection by examining about 3,110 defect items for 133 apartment buildings. The study analysis revealed a relatively high rate of defects before inspection that occurred in finishing work. Second, defects occurred such as cracking of external wall, which is a very important defect. However, defects before inspection were relatively rare on the external wall. Finally, defects before inspection occurred during waterproofing in the common area or garage. It is necessary to establish a reasonable basis or countermeasure to resolve differences between stakeholders as various issues may arise in the course of a dispute, as a result of identifying the details of defects within the top 20 of the defectives.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.6
• /
• pp.1113-1125
• /
• 2013

Corporate bankruptcy prediction has been an important topic in the accounting and finance field for a long time. Several data mining techniques have been used for bankruptcy prediction. However, there are many limits for application to real classification problem with a single model. This study proposes ensemble SVM (support vector machine) model which assembles different SVM models with each different kernel functions. Our ensemble model is made and evaluated by v-fold cross-validation approach. The k top performing models are recruited into the ensemble. The classification is then carried out using the majority voting opinion of the ensemble. In this paper, we investigate the performance of ensemble SVM classifier in terms of accuracy, error rate, sensitivity, specificity, ROC curve, and AUC to compare with single SVM classifiers based on financial ratios dataset and simulation dataset. The results confirmed the advantages of our method: It is robust while providing good performance.

• Korean Journal of Applied Biomechanics
• /
• v.16 no.4
• /
• pp.95-103
• /
• 2006

The purpose of this study was to review the relevant literature about coaching and thereupon, survey the coaching methods used for golf lesson to reinterpret them and thereby, describe in view of kinetics the swing errors committed frequently by amateur golfers and suggest more scientific golf coaching methods. For this purpose, kinetic elements were divided into accuracy and power ones and therewith, the variables affecting such elements were identified. For this study, a total of 60 amateur golfer were sampled, and their swing forms were photographed with two high-speed digital cameras, and the resultant images were analyzed to determine the errors of each form kinetically, which would be analyzed again with the program V1-5000. The kinetic elements could be identified as accuracy, power and accuracy & power. Thus, setup and trajectory were classified into accuracy elements, while differences of inter-joint angles, cocking and delayed hitting. Lastly, timing and axial movement were classified into accuracy & power elements. Three errors were identified in association with setup. The errors related with trajectory elements accounted for most (6) of the 20 errors. Three errors were determined for inter-joint angle differences, and one error was associated with cocking and delayed hitting. Lastly, one error was classified into timing error, while five errors were associated with axial movement. Finally, as a result of arranging the errors into a cross table, it was found that the errors were associated with each other between take-back and back-swing, take-back and follow-through, back-swing and back-swing top, and between back-swing and down-swing. Namely, an error would lead to other error repeatedly. So, it is more effective to identify all the errors for every form and correct them comprehensively rather than single out the errors and correct them one by one.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.43-51
• /
• 2023

As online transactions increase, the image of clothing has a great influence on consumer purchasing decisions. The importance of image information for clothing materials has been emphasized, and it is important for the fashion industry to analyze clothing images and grasp the materials used. Textile materials used for clothing are difficult to identify with the naked eye, and much time and cost are consumed in sorting. This study aims to classify the materials of textiles from clothing images based on deep learning algorithms. Classifying materials can help reduce clothing production costs, increase the efficiency of the manufacturing process, and contribute to the service of recommending products of specific materials to consumers. We used machine vision-based deep learning algorithms ResNet and Vision Transformer to classify clothing images. A total of 760,949 images were collected and preprocessed to detect abnormal images. Finally, a total of 167,299 clothing images, 19 textile labels and 20 fabric labels were used. We used ResNet and Vision Transformer to classify clothing materials and compared the performance of the algorithms with the Top-k Accuracy Score metric. As a result of comparing the performance, the Vision Transformer algorithm outperforms ResNet.

• Journal of the Korea Concrete Institute
• /
• v.26 no.4
• /
• pp.545-553
• /
• 2014

This study suggested an integrated classification method for generalized characteristics of PC beam-column connection according to connection details. Quantifying the failure mode of PC-beam column connection and characteristics of corresponding details, this study suggested to use deformation contribution of each element of beam-column assemblage. According to the expected failure mode of beam-column connection assemblage, PC beam-column connection can be classified into 'equivalent monolithic system' and 'jointed system'. In this study, four test specimens were tested for verification of detailed classification method of PC beam-column connections. Test was carried out with typical beam-column connection test method. Load was applied at the top of test specimen and end of beams were restrained by hinge. In order to verify the deformation contribution of each test specimen, 34-LVDTs were mounted on test specimen. According to test results, deformation contribution of each test specimen have different characteristics. Deformation characteristics of joint and other components which are quantified by test results, equivalent monolithic system can be classified into two categories. Strong connection have extremely small deformation contribution of joint and much larger deformation contribution was shown in flexural behavior of beam. The other type of beam-column connection is ductile connection which allows the larger deformation in joint area compared with strong connection.

• The Journal of Engineering Geology
• /
• v.17 no.1 s.50
• /
• pp.89-99
• /
• 2007

This paper intends to introduce more objective and qualitative rock mass classification method easily applicable to the excavation of gneissic masses showing corestone weathering profiles. It is proven that corestone weathering profile could be divided with reasonable accuracy into digging, ripping and blasting layers using visual and simple mechanical techniques such as Schmidt hammer rebound test on cut slopes, taking into consideration strength and spacial distribution of corestone, workability and work efficiency of excavation. Also, seismic refraction surveys were employed for shallow investigations (down to $20{\sim}30m$ depth) in corestone weathering profile and conducted across the top of vertical exposures where the underlying geology could be directly inspected. Some discrepancies ($3{\sim}4m$ in average and 6 m occasionally) between the actual and assumed materials with respect to seismic velocities were observed. Thus it can be concluded that field geotechnical mapping and field seismic test should be used together in order to get a relatively good accuracy in assessing likely excavation conditions of corestone weather-ing profiles.