• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.11 no.1
• /
• pp.19-27
• /
• 1993

For the design of a large-scale landfill, the future utilization plan of the landfill ought to precede based on the analysis of existing facility. Analysis for the present condition of reclamation must include accurate assesment of volume and other consideration such as urban scenery. In this study an optimum data interpolation scheme area/volume determination method based on the classification of topography were combined for the correct assessment of sweeping volume. Combined model was compared with the real data of Digital Elevation Model constructed by aero photography. The new model aims at providing basic information for the design and utilization of a new landfill. A a result of this study, we made an algorithm to perform the classification of the topography in the area of interest objectively. In addition, we decided optimal data interpolation scheme and area/volume calculation method for given topography. Finally, we applied the developed methodology to Nangido Landfill to assess current landfill situation and potential capacity when landfilling is resumed.

• Journal of Korean Society of Forest Science
• /
• v.97 no.6
• /
• pp.565-569
• /
• 2008

Geographic variation of characteristics of cone, seed and bract morphology were examined in 8 populations of rare endemic Abies nephrolepis (Trautv.) Maxim and A. koreana Wilson. Additionally we studied classification index to distinguish between the species by the method of discriminant analysis. Nested ANOVA showed that there were statistically significant differences among populations as well as among individuals within populations in all 13 morphological traits. In the seed length, seed index, bract width, and bract index of A. nephrolepis and the bract width and index of A. koreana, variance components among populations were larger than those among individuals within populations. In discriminant analysis, three traits (cone width, length of seed wing, and bract length) were found to be useful in discriminating A. nephrolepis from A. koreana. The optimal classification results of stepwise selection were discriminated length of seed wing and bract length.

• Korean Journal of Cognitive Science
• /
• v.21 no.4
• /
• pp.459-480
• /
• 2010

A dialogue system includes various morphological analyses for recognizing a user's intention from the user's utterances. However, a user can represent various intentions via emotional states in addition to morphological expressions. Thus, a user's emotion recognition can analyze a user's intention in various manners. This paper presents a new method to automatically recognize a user's emotion for a dialogue system. For general emotions, we define nine categories using a psychological approach. For an optimal feature set, we organize a combination of sentential, a priori, and context features. Then, we employ a support vector machine (SVM) that has been widely used in various learning tasks to automatically classify a user's emotions. The experiment results show that our method has a 62.8% F-measure, 15% higher than the reference system.

• The KIPS Transactions:PartB
• /
• v.16B no.1
• /
• pp.7-16
• /
• 2009

Some clustering algorithms have a problem that an image is over-segmented since both the spatial information between the segmented regions is not considered and the number of the clusters is defined in advance. Therefore, they are difficult to be applied to the applicable fields. This paper proposes the new post-processing methods, a reclassification of the inhomogeneous clusters and a region merging using Baysian algorithm, that improve the segmentation results of the clustering algorithms. The inhomogeneous cluster is firstly selected based on variance and between-class distance and it is then reclassified into the other clusters in the reclassification step. This reclassification is repeated until the optimal number determined by the minimum average within-class distance. And the similar regions are merged using Baysian algorithm based on Kullbeck-Leibler distance between the adjacent regions. So we can effectively solve the over-segmentation problem and the result can be applied to the applicable fields. Finally, we design a classification system for the segmented regions to validate the proposed method. The segmented regions are classified by SVM(Support Vector Machine) using the principal colors and the texture information of the segmented regions. In experiment, the proposed method showed the validity for various real-images and was effectively applied to the designed classification system.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.2
• /
• pp.92-97
• /
• 2021

The importance of processes in cryogenic environments is increasing in a way to address problems such as critical dimension (CD) narrow and bottlenecks in micro-processing. Accordingly, in this paper, we proceed with the design and analysis of Electrostatic Chuck(ESC) and Coolant in cryogenic environments, and present optimal model conditions to provide the temperature distribution analysis of ESC in these environments and the appropriate optimal design. The wafer temperature uniformity was selected as the reference model that the operating conditions of the refrigerant of the liquid nitrogen in the doubled aluminum path were excellent. Design of simulation (DOS) was carried out based on the wheel settings within the selected reference model and the classification of three mass flow and diameter case, respectively. The comparison between factors with p-value less than 0.05 indicates that the optimal design point is when five turns of coolant have a flow rate of 0.3 kg/s and a diameter of 12 mm. ANOVA determines the interactions between the above factor, indicating that mass flow is the most significant among the parameters of interests. In variable selection procedure, Case 2 was also determined to be superior through the two-Sample T-Test of the mean and variance values by dividing five coolant wheels into two (Case 1 : 2+3, Case 2: 3+2). Finally, heat transfer analysis processes such as final difference method (FDM) and heat transfer were also performed to demonstrate the feasibility and adequacy of the analysis process.

• The Journal of the Acoustical Society of Korea
• /
• v.14 no.2
• /
• pp.101-112
• /
• 1995

In order to construct a feature map-based phoneme classification system for speech recognition, two procedures are usually required. One is clustering and the other is labeling. In this paper, we present a phoneme classification system based on the Kohonen's Self-Organizing Feature Map (SOFM) for clusterer and labeler. It is known that the SOFM performs self-organizing process by which optimal local topographical mapping of the signal space and yields a reasonably high accuracy in recognition tasks. Consequently, SOFM can effectively be applied to the recognition of phonemes. Besides to improve the performance of the phoneme classification system, we propose the learning algorithm combined with the classical K-mans clustering algorithm in fine-tuning stage. In order to evaluate the performance of the proposed phoneme classification algorithm, we first use totaly 43 phonemes which construct six intra-class feature maps for six different phoneme classes. From the speaker-dependent phoneme classification tests using these six feature maps, we obtain recognition rate of $87.2\%$ and confirm that the proposed algorithm is an efficient method for improvement of recognition performance and convergence speed.

• Journal of the Mineralogical Society of Korea
• /
• v.18 no.1
• /
• pp.19-31
• /
• 2005

A study on the beneficiation of illite occurring in Youngdong province is performed with applying selective grinding and air classification techniques. Quartz and illite are occurred as major components, and sulfide minerals such as pyrite, chalcopyrite are associated as minor components. The result of sieving test shows that contents of Al₂O₃, K₂O and ignition loss are increased, whereas SiO₂ is decreased with particle size decrease. Fe₂O₃ content is almost same in all the particle size range but slightly lower at coarse particles. The yield of fine particles is increased with increasing rotor speed in both grinding stage and air classification stage. When the selective grinding and air classification are carried out at optimal condition, yield of the concentrate is 76.16 wt.%. The chemical compositions of the concentrate are SiO₂70.13%, Al₂O₃ 19.40%, Fe₂O₃ 1.62%, K₂O 5.20%, and ignition loss 2.77%. The beneficiation process developed in the current study is very effective method which purification and particle size control can be achieved simultaneously.

• Journal of the Korean Society of Costume
• /
• v.63 no.3
• /
• pp.95-109
• /
• 2013

This thesis was conducted with the purpose of proposing a systematic and comprehensive system for women's upper garment sizes so that the satisfaction level of women purchasing the upper garment products in Internet shopping malls is enhanced. To achieve this, this study first conducted a survey of women from the ages of 18 to 39 and attempted to discover consumer satisfaction levels and preferences of the clothing product sizing system of Internet shopping malls. While keeping track of the global distribution environment, an optimal clothing sizing system for Korean women that fit recent changes in their body shapes was proposed. The results of this study are as follows. First, A result of studying the satisfaction levels and preferences of consumer's purchase experience and the sizing system showed that 48.6% of the total respondents were dissatisfied with the current sizing system. Second, based on the research of the size classification system of domestic and foreign upper garment for women, unlike domestic Internet shopping malls, overseas generally offer several size classifications. Third, results of studies 1 and 2 was used to propose an optimal clothing products sizing system method. Also, the body and product sizes and the measurement methods should be offered together. In summary of all these results, by establishing globally compatible sizing system, consumers are able to recognize their sizes on their own and by doing this, it will lower perceived risk of the consumers at the time of a Internet shopping mall purchase, and this will raise their level of satisfaction while making purchases.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.2
• /
• pp.369-383
• /
• 2018

User authentication using PIN input or lock pattern is widely used as a user authentication method of smartphones. However, it is vulnerable to shoulder surfing attacks and because of low complexity of PIN and lock pattern, it has low security. To complement these problems, keystroke dynamics have been used as an authentication method for complex authentication and researches on this have been in progress. However, many studies have used imposter data in classifier training and validation. When keystroke dynamics authentications are actually applied in reality, it is realistic to use only legitimate user data for training, and using other people's data as imposter training data may result in problems such as leakage of authentication data and invasion of privacy. In response, in this paper, we experiment and obtain the optimal ratio of the thresholds for distance based classification. By suggesting the optimal ratio, we try to contribute to the real applications of keystroke authentications.

• The Korean Journal of Applied Statistics
• /
• v.30 no.6
• /
• pp.867-876
• /
• 2017

Datasets with small n and large p are often found in various fields and the analysis of the datasets is still a challenge in statistics. Discriminant analysis models for such datasets were recently developed in classification problems. One approach of those models tries to detect dimensions that distinguish between groups well and the number of the detected dimensions is typically smaller than p. In such models, the number of dimensions is important because the prediction and visualization of data and can be usually determined by the K-fold cross-validation (CV). However, in sparse data scenarios, the CV is not reliable for determining the optimal number of dimensions since there can be only a few observations for each fold. Thus, we propose a method to determine the number of dimensions using a measure based on the standardized distance between the mean values of each group in the reduced dimensions. The proposed method is verified through simulations.