• The korean journal of orthodontics
• /
• v.52 no.1
• /
• pp.3-19
• /
• 2022

Objective: The purpose of this study was to investigate the accuracy of one-step automated orthodontic diagnosis of skeletodental discrepancies using a convolutional neural network (CNN) and lateral cephalogram images with different qualities from nationwide multi-hospitals. Methods: Among 2,174 lateral cephalograms, 1,993 cephalograms from two hospitals were used for training and internal test sets and 181 cephalograms from eight other hospitals were used for an external test set. They were divided into three classification groups according to anteroposterior skeletal discrepancies (Class I, II, and III), vertical skeletal discrepancies (normodivergent, hypodivergent, and hyperdivergent patterns), and vertical dental discrepancies (normal overbite, deep bite, and open bite) as a gold standard. Pre-trained DenseNet-169 was used as a CNN classifier model. Diagnostic performance was evaluated by receiver operating characteristic (ROC) analysis, t-stochastic neighbor embedding (t-SNE), and gradient-weighted class activation mapping (Grad-CAM). Results: In the ROC analysis, the mean area under the curve and the mean accuracy of all classifications were high with both internal and external test sets (all, > 0.89 and > 0.80). In the t-SNE analysis, our model succeeded in creating good separation between three classification groups. Grad-CAM figures showed differences in the location and size of the focus areas between three classification groups in each diagnosis. Conclusions: Since the accuracy of our model was validated with both internal and external test sets, it shows the possible usefulness of a one-step automated orthodontic diagnosis tool using a CNN model. However, it still needs technical improvement in terms of classifying vertical dental discrepancies.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.4
• /
• pp.391-396
• /
• 2003

This paper proposes a new approach that converts continuous-valued attributes to categorical-valued ones considering the distribution of target attributes(classes). In this approach, It can be possible to get optimal interval boundaries by considering the distribution of data itself without any requirements of parameters. For each attributes, the distribution of target attributes is projected to one-dimensional space. And this space is clustered according to the criteria like as the density value of each target attributes and the amount of overlapped areas among each density values of target attributes. Clusters which are made in this ways are based on the probabilities that can predict a target attribute of instances. Therefore it has an interval boundaries that minimize a loss of information of original data. An improved performance of proposed discretization method can be validated using C4.5 algorithm and UCI Machine Learning Data Repository data sets.

• Science of Emotion and Sensibility
• /
• v.16 no.3
• /
• pp.363-372
• /
• 2013

When retrieving music with folksonomy tags, internal use of numeric tags (AV tags: tags consisting of Arousal and Valence values ) instead of word tags can partially solve the problem posed by synonyms. However, the two predecessor tasks should be done correctly; the first task is to map word tags to their numeric tags; the second is to get numeric tags of the music pieces to be retrieved. The first task is verified through our prior study and thus, in this paper, its significance is seen for the second task. To this end, we propose the music mapping table defining the relation between AV values and music and ANOVA tests are performed for analysis. The result shows that the arousal values and valence values of music have different distributions for 12 mood tags with or without synonymy and that their type I error values are P<0.001. Consequently, it is checked that the distribution of AV values is different according to music mood.

• Korean Journal of Remote Sensing
• /
• v.27 no.6
• /
• 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.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.4 no.1
• /
• pp.68-75
• /
• 2011

The performance of peripheral devices is improving rapidly to meet the needs of users for multimedia data. Therefore, the peripheral interface with wide bandwidth and high transmission rate becomes necessary to handle large amounts of data in real time for multiple high-performance devices. PCI Express is a fast serial interface with the use of packets that are compatible with previous PCI and PCI-X. In this paper, we design and verify general peripheral interface using serial link. It includes two kinds of traffic class (TC) labels which are mapped to virtual channels (VC). The design adopts TC/VC mapping and the scheme of arbitration by priority. The design uses a packet which can be transmitted through up to four transmission lanes. The design of general peripheral interface is described in Verilog HDL and verified using ModelSim. For FPGA verification, Xilinx ISE and SPARTAN XC3S400 are used.We used Synopsys Design Compiler as a synthesis tool and the used library was MagnaChip 0.35um technology.

• Journal of Korea Multimedia Society
• /
• v.3 no.3
• /
• pp.253-262
• /
• 2000

This paper proposes a new RBF neural network that determines the number and the center of hidden neurons based on the adaptive feature extraction for the input data. The principal component analysis is applied for extracting adaptively the features by reducing the dimension of the given input data. It can simultaneously achieve a superior property of both the principal component analysis by mapping input data into set of statistically independent features and the RBF neural networks. The proposed neural networks has been applied to classify the 200 breast cancer databases by 2-class. The simulation results shows that the proposed neural networks has better performances of the learning time and the classification for test data, in comparison with those using the k-means clustering algorithm. And it is affected less than the k-means clustering algorithm by the initial weight setting and the scope of the smoothing factor.

• Korean Journal of Remote Sensing
• /
• v.29 no.6
• /
• pp.611-619
• /
• 2013

Although the need of crop production has increased in Mongolia, crop cultivation is very limited because of the harsh climatic and topographic conditions. Crop lands are sparsely distributed with relatively small sizes and, therefore, it is difficult to survey the exact area of crop lands. The study aimed to find an easy and effective way of accurate classification to map crop lands in Mongolia using satellite images. To classify the crop lands over the study area in northern Mongolia, four classifications were carried out by using 1) Thematic Mapper (TM) image August 23, 2) TM image of July 6, 3) combined 12 bands of TM images of July and August, and 4) both TM images of July and August by layered classification. Wheat and potato are the major crop types and they show relatively high variation in crop conditions between July and August. On the other hands, other land cover types (forest, riparian vegetation, grassland, water and bare soil) do not show such difference between July and August. The results of four classifications clearly show that the use of multi-temporal images is essential to accurately classify the crop lands. The layered classification method, in which each class is separated by a subset of TM images, shows the highest classification accuracy (93.7%) of the crop lands. The classification accuracies are lower when we use only a single TM image of either July or August. Because of the different planting practice of potato and the growth condition of wheat, the spectral characteristics of potato and wheat cannot be fully separated from other cover types with TM image of either July or August. Further refinements on the spatial characteristics of existing crop lands may enhance the crop mapping method in Mongolia.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.4 no.2
• /
• pp.11-25
• /
• 2001

A wetland is an ecosystem which is the most useful and highly-energetic transition area. This study has been carried out to classify and identify the various types of wetlands in Korea. The main objective of this study are 1) defining and classifying of wetlands, and 2) identifying the wetlands characteristics, and 3) studying cases on the natural wetlands such as Han river, DMZ(Demillitarized Zone), Upo wetland and Yong(Dragon) wetland. The results as follows： 1) Development of the indices for identifying and classifying wetlands in encompassing in such as Ramsar Conference, US NWI(National Wetlands Inventory), Hydrogeomorphic system. 2) Development on the classifying method on the wetlands in the level of supersystem, system, subsystem, class and subclass. The systems include Palustrine and Riverine, and the subsystems are Seasonal, Permanent(Palustrine) and Impersistent, Lower perennial, Impersistent (Riverine). 3) Finally, we find out Young wetland is Palustrine/Permanent/Slope/Persistent, and Upo wetland consists of various types of wetlands, those are, Palustrine/Permanent/Depression/Forest Deciduous, Palustrine/Permanent/Depression/Shrub Deciduous, Palustrine/Permanent/Depression/Persistent, Palustrine /Permanent/Depression/Hydrophytes, and Lacustrine/Permanent/Openwater/Hydrophytes. The taxonomy of this study stems from identifying and classifying wetlands with indices mainly based on hydrologic features and substrates. So, it is needed that consequent studies are to be performed with various viewpoints. And the studying cases were limited because of the restricted entrance into the DMZ, And, we selected only 10 crucial sites in Han river as the subject for wetlands regulation and creation. And, for advanced studies, drawing up inventory and mapping are necessary.

• Journal of KIISE:Software and Applications
• /
• v.34 no.9
• /
• pp.773-784
• /
• 2007

Aspect-Oriented Programming (AOP) has focused on improving the modularity of the crosscutting concerns. The existing AOP methodology has been mainly focused on the implementation method of programs and thus developer-oriented concern extraction and development were performed. Recently, many studies for applying AOP to the entire software development processes ranging from requirement analysis to design and implementation are being conducted. But specification methods having consistency from the initial phase of concern extraction to implementation phase are not sufficient. In this paper, we have presented the specification of crosscutting concerns so as to solve these problems. The specification of crosscutting concerns provides guidelines and specification from the requirement analysis phase to the process of converting extracted crosscutting concerns to codes. This method reduces the gap to the process of mapping extracted crosscutting concerns into a single class and thus enhances program development and understandability. In addition, it raises program reusability, maintenance and extensibility by enhancing traceability.

• Journal of Korean Library and Information Science Society
• /
• v.51 no.1
• /
• pp.1-20
• /
• 2020

This study is to find the methods that BIBFRAME could accept the new concept of representative expression in the RDA Toolkit Beta which has developed in 2019. Research methods were the literature reviews and the mapping between RDA Toolkit Beta and BIBFRAME. BIBFRAME's acceptance of representative expression of RDA Toolkit Beta was suggested as followings. First, the properties of representative expression should be defined in BIBFRAME because the RDA Toolkit Beta defined the expression attributes and representative expression elements apart. Three choices for BIBFRAME's acceptances are (1) to develop the newly devised representative expression properties (2) to specify representative expression properties with using refinement (3) to differentiate representative expression properties with using class. Second, as relationship elements should be defined in BIBFRAME to link work and representative expression which transfer the expression attribute to work. This study will contribute to revise the BIBFRAME because this focusd on BIBFRAME's acceptance of RDA Toolkit Beta in which reflected LRM.