• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.207-214
• /
• 2010

A method of the region extraction and recognition of a traffic light and speed sign board in the real road environment is proposed. Traffic light was recognized by using brightness and color information based on HSI color model. Speed sign board was extracted by measuring red intensity from the HSI color information We improve the recognition rate by performing an incline compensation of the speed sign for directions clockwise and counterclockwise. The proposed algorithm shows a robust recognition rate in the image sequence which includes traffic light and speed sign board.

• Phonetics and Speech Sciences
• /
• v.10 no.4
• /
• pp.39-44
• /
• 2018

This study aimed to examine whether preconsonantal vowel shortening, which occurs in many languages, exists in Chinese. To this end, we compared 15 pairs of Chinese bi-syllabic words with intervocalic unaspirated/aspirated stops. The results revealed that (1) the effect of the feature aspiration of the following stop on the preceding vowel (V1) was neither significant nor consistent though V1 tends to be a little longer before an unaspirated stop; (2) the following unaspirated stop closure (C) was similar to or longer than its aspirated cognate; (3) the durational sum of V1 and C was longer when the stop is unaspirated, and V1 and C had no compensatory relationship; (4) Voice Onset Time (VOT) was significantly longer when the stop is aspirated than unaspirated; (5) the vowel (V2) following VOT was significantly longer when the stop is unaspirated, so the differentials in VOT were partially compensated; (6) despite the partial compensation, the sum of VOT and V2 was longer when the stop is aspirated; (7) words with an intervocalic aspirated stop were longer than those with its unaspirated cognate. It is concluded that while VOT is the most important factor for deciding the timing structure of Chinese words with intervocalic stops, closure duration is crucial for Korean and many other languages.

• Structural Monitoring and Maintenance
• /
• v.11 no.3
• /
• pp.203-217
• /
• 2024

Electro-mechanical impedance (EMI) technique is a low-cost structural damage detection method. It reflects structural damage through the change in admittance signal which contains the structural mechanical impedance information. The ambient temperature greatly affects the admittance signal, which hides the changes caused by structural damage and reduces the accuracy of damage identification. This study introduces a convolutional neural network to compensate for the temperature effect. The proposed method uses a framework that consists of a feature extraction network and a decoding network, and the original admittance signal with temperature information is used as the input. The output admittance signal is eliminated from the temperature effect, improving damage identification robustness. The admittance data simulated by the finite element model of the spatial grid structure is used to verify the effectiveness of the proposed method. The results show that the proposed method has advantages in identification accuracy compared with the damage index minimization method and the principal component analysis method.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.19-32
• /
• 2007

This paper present a new face recognition method based on LVQ neural net to construct a real time face recognition system. The previous researches which used PCA, LDA combined neural net usually need much time in training neural net. The supervised LVQ neural net needs much less time in training and can maximize the separability between the classes. In this paper, the proposed method transforms the input face image by PCA and LDA sequentially into low-dimension feature vectors and recognizes the face through LVQ neural net. In order to make the system robust to external light variation, light compensation is performed on the detected face by max-min normalization method as preprocessing. PCA and LDA transformations are applied to the normalized face image to produce low-level feature vectors of the image. In order to determine the initial centers of LVQ and speed up the convergency of the LVQ neural net, the K-Means clustering algorithm is adopted. Subsequently, the class representative vectors can be produced by LVQ2 training using initial center vectors. The face recognition is achieved by using the euclidean distance measure between the center vector of classes and the feature vector of input image. From the experiments, we can prove that the proposed method is more effective in the recognition ratio for the cases of still images from ORL database and sequential images rather than using conventional PCA of a hybrid method with PCA and LDA.

• Korean Security Journal
• /
• no.10
• /
• pp.127-147
• /
• 2005

This study (research) has been done on the job, job-satisfaction and job dedication of body guards from many sectors in Korea. This research is focused on the relationship of job, job-satisfaction and job-dedication in diverse aspects in order to build up a detailed theory, As a result, teams of body guard can enhance their systematic efficiency through the theory. Therefore in this chapter, it will re-examine the result of this research and discuss about the theoretical and practical aspect of the result. This study(research) will be the outset(start) for the organizational behavior study of the body guards in Korea. Especially, this research tries to distinguish the duty aspect and the general feature of the body guards, satisfaction along with the level of dedication. Therefore it will give the persons concerning the bodyguards many theoretical and practical points to consider. But there is a limitation as crossing research that in this research we didn't research in compensation for all internal body guards and accomplishment of research has achieved in a short-time. Though it will be necessary to accomplish in henceforth research, if at all possible, in compensation for all body guards and much more diverse security service classification, also for a long time extended vertical research.

• Journal of KIISE:Software and Applications
• /
• v.31 no.1
• /
• pp.54-60
• /
• 2004

Face recognition is one of the problems to be solved by appearance based matching technique. However, the appearance of face image is very sensitive to variation in illumination. One of the easiest ways for better performance is to collect more training samples acquired under variable lightings but it is not practical in real world. ]:n object recognition, it is desirable to focus on feature extraction or normalization technique rather than focus on classifier. This paper presents a simple approach to normalization of faces subject to directional illumination. This is one of the significant issues that cause error in the face recognition process. The proposed method, ICR(illumination Compensation based on Multiple Linear Regression), is to find the plane that best fits the intensity distribution of the face image using the multiple linear regression, then use this plane to normalize the face image. The advantages of our method are simple and practical. The planar approximation of a face image is mathematically defined by the simple linear model. We provide experimental results to demonstrate the performance of the proposed ICR method on public face databases and our database. The experimental results show a significant improvement of the recognition accuracy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.327-343
• /
• 2020

This study proposes a method to improve the geometric quality of KOMPSAT (Korea Multi-Purpose Satellite)-3/3A Level 1R imagery, particularly for efficient disaster damage analysis. The proposed method applies a novel grid-based SIFT (Scale Invariant Feature Transform) method to the Planetscope ortho-imagery, which solves the inherent limitations in acquiring appropriate optical satellite imagery over disaster areas, and the KOMPSAT-3/3A imagery to extract GCPs (Ground Control Points) required for the RPC (Rational Polynomial Coefficient) bias compensation. In order to validate its effectiveness, the proposed method was applied to the KOMPSAT-3 multispectral image of Gangnueng which includes the April 2019 wildfire, and the KOMPSAT-3A image of Daejeon, which was additionally selected in consideration of the diverse land cover types. The proposed method improved the geometric quality of KOMPSAT-3/3A images by reducing the positioning errors(RMSE: Root Mean Square Error) of the two images from 6.62 pixels to 1.25 pixels for KOMPSAT-3, and from 7.03 pixels to 1.66 pixels for KOMPSAT-3A. Through a visual comparison of the post-disaster KOMPSAT-3 ortho-image of Gangneung and the pre-disaster Planetscope ortho-image, the result showed appropriate geometric quality for wildfire damage analysis. This paper demonstrated the possibility of using Planetscope ortho-images as an alternative to obtain the GCPs for geometric calibration. Furthermore, the proposed method can be applied to various KOMPSAT-3/3A research studies where Planetscope ortho-images can be provided.

• Korean Journal of Remote Sensing
• /
• v.17 no.1
• /
• pp.85-97
• /
• 2001

The KT(Kauth-Thomas) and IHS(Intensity-Hue-Saturation) transformation techniques were introduced and compared to investigate fire-scarred areas with single post-fire Landsat 7 ETM+ image. This study consists of two parts. First, using only geometrically corrected imagery, it was examined whether or not the different level of fire-damaged areas could be detected by simple slicing method within the image enhanced by the IHS transform. As a result, since the spectral distribution of each class on each IHS component was overlaid, the simple slicing method did not seem appropriate for the delineation of the areas of the different level of fire severity. Second, the image rectified by both radiometrically and topographically was enhanced by the KT transformation and the IHS transformation, respectively. Then, the images were classified by the maximum likelihood method. The cross-validation was performed for the compensation of relatively small set of ground truth data. The results showed that KT transformation produced better accuracy than IHS transformation. In addition, the KT feature spaces and the spectral distribution of IHS components were analyzed on the graph. This study has shown that, as for the detection of the different level of fire severity, the KT transformation reflects the ground physical conditions better than the IHS transformation.

• Korea Journal of Hospital Management
• /
• v.17 no.2
• /
• pp.21-33
• /
• 2012

Purpose : This study aims to suggest application of patients DB to hospital marketing by performing market segmentation and selecting target market. Consequently help to establish suited strategy of marketing. Method : 14,072 patients hospitalized in a University Medical Center were recruited into this study. In order to classify the customer groups, cluster analysis was used with RFM(Recency, Frequency, Monetary) model, and 1-way ANOVA verified the differences among groups. And then, sociodemographical status, healthcare utilization and diagnosis(ICD-10) of each group were compared to draw a marketing strategy. Results : Four groups were classified through clustering analysis, and'high use and high profit' and'low use and high profit' groups were selected as a target market. The features of target market were as follows, the female proportion was high; used a private room; hospitalized through the emergency room; had operation; length of stay was long; had many comorbidity and cooperative treatment. There was difference in each feature of target market: as for the'high use and high profit' group, many patients were diagnosed with 'certain infectious and parasitic diseases'; and as for the'low use and high profit'group, the proportion of patients who purchased'industrial accident compensation insurance'and'auto insurance'was relatively high; many patients were diagnosed with'Injury, poisoning and certain other consequences of external causes'. Conclusion : It is needed to establish'positioning' strategy by monitoring and communicating with'high use and high profit' group. And for the case of'low use and high profit' group, it is necessary to make a follow-up management and lead them to have a medical check-up.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.690-693
• /
• 2002

According to the growth of communication biz, embedded market rapidly developing in domestic and overseas. Embedded system can be used in various way such as wire and wireless communication equipment or information products. There are lots of developing performance applying speech recognition to embedded system, for instance, PDA, PCS, CDMA-2000 or IMT-2000. This study implement minimum memory of speech recognition engine and DB for apply real time embedded system. The implement measure of speech recognition equipment to fit on embedded system is like following. At first, DC element is removed from Input voice and then a compensation of high frequency was achieved by pre-emphasis with coefficients value, 0.97 and constitute division data as same size as 256 sample by lapped shift method. Through by Levinson - Durbin Algorithm, these data can get linear predictive coefficient and again, using Cepstrum - Transformer attain feature vectors. During HMM training, We used Baum-Welch reestimation Algorithm for each words training and can get the recognition result from executed likelihood method on each words. The used speech data is using 40 speech command data and 10 digits extracted form each 15 of male and female speaker spoken menu control command of Embedded system. Since, in many times, ARM CPU is adopted in embedded system, it's peformed porting the speech recognition engine on ARM core evaluation board. And do the recognition test with select set 1 and set 3 parameter that has good recognition rate on commander and no digit after the several tests using by 5 proposal recognition parameter sets. The recognition engine of recognition rate shows 95%, speech commander recognizer shows 96% and digits recognizer shows 94%.