• The Journal of the Acoustical Society of Korea
• /
• v.22 no.5
• /
• pp.375-382
• /
• 2003

Lip-reading technique based on bimodal is to enhance speech recognition rate in noisy environment. It is most important to detect the correct lip-image. But it is hard to estimate stable performance in dynamic environment, because of many factors to deteriorate Lip-reading's performance. There are illumination change, speaker's pronunciation habit, versatility of lips shape and rotation or size change of lips etc. In this paper, we propose the IIR filtering in time-domain for the stable performance. It is very proper to remove the noise of speech, to enhance performance of recognition by digital filtering in time domain. While the lip-reading technique in whole lip image makes data massive, the Principal Component Analysis of pre-process allows to reduce the data quantify by detection of feature without loss of image information. For the observation performance of speech recognition using only image information, we made an experiment on recognition after choosing 22 words in available car service. We used Hidden Markov Model by speech recognition algorithm to compare this words' recognition performance. As a result, while the recognition rate of lip-reading using PCA is 64%, Time-domain filter applied to lip-reading enhances recognition rate of 72.4%.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.4
• /
• pp.526-533
• /
• 2014

In this study, we introduce design methodology to develop a guidance for issuing heavy rainfall warning by using both RBFNNs(Radial basis function neural networks) and SVR(Support vector regression) model, and then carry out the comparative studies between two pattern classifiers. Individual classifiers are designed as architecture realized with the aid of optimization and pre-processing algorithm. Because the predictive performance of the existing heavy rainfall forecast system is commonly affected from diverse processing techniques of meteorological data, under-sampling method as the pre-processing method of input data is used, and also data discretization and feature extraction method for SVR and FCM clustering and PSO method for RBFNNs are exploited respectively. The observed data, AWS(Automatic weather wtation), supplied from KMA(korea meteorological administration), is used for training and testing of the proposed classifiers. The proposed classifiers offer the related information to issue a heavy rain warning in advance before 1 to 3 hours by using the selected meteorological data and the cumulated precipitation amount accumulated for 1 to 12 hours from AWS data. For performance evaluation of each classifier, ETS(Equitable Threat Score) method is used as standard verification method for predictive ability. Through the comparative studies of two classifiers, neuro-fuzzy method is effectively used for improved performance and to show stable predictive result of guidance to issue heavy rainfall warning.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.24 no.1
• /
• pp.33-41
• /
• 2011

This study presents modeling technologies applicable to an unbonded post-tension system using a finite element software package. In this study, both direct modeling method and multiple spring method were used. The direct modeling method adopts tube-to-tube contact elements to represent the physical feature of a post-tension system. The multiple spring method uses virtual tendons attached to the real tendons using a number of rigid axial springs that freely rotate at the ends. Both modeling technologies provide accurate predictions. However, only the multiple spring method provides numerically stable and reliable responses with a consideration of concrete tension stiffening effects. Therefore, the multiple spring method turned out to be a generally applicable modeling technology for the unbonded post-tension system. Comparisons were made for the analytical and experimental results for the verification of the selected method, and parameter studies were carried out to confirm the appropriateness of the modeling assumptions and parameters adopted in the analysis.

• Journal of Digital Convergence
• /
• v.10 no.6
• /
• pp.297-302
• /
• 2012

In this paper, we present a object detection and tracking method based on image context analysis. It is robust from the image variations such as complicated background, dynamic movement of the object. Image context analysis is carried out using the hybrid network of k-means and RBF. The proposed object detection employs context-driven adaptive Bayesian framework to relive the effect due to uneven object images. The proposed method used feature vector generator using 2D Haar wavelet transform and the Bayesian discriminant method in order to enhance the speed of learning. The system took less time to learn, and learning in a wide variety of data showed consistent results. After we developed the proposed method was applied to real-world environment. As a result, in the case of the object to detect pass outside expected area or other changes in the uncertain reaction showed that stable. The experimental results show that the proposed approach can achieve superior performance using various data sets to previously methods.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.1
• /
• pp.61-74
• /
• 2004

In this paper, a contort- and speaker-dependent cepstrum extraction method and a channel normalization method for minimizing the loss of speaker characteristics in the cepstrum were proposed for a robust speaker recognition system over the channel. The proposed extraction method creates a cepstrum based on the pitch synchronous analysis using the inherent pitch of the speaker. Therefore, the cepstrum called the 〃pitch synchronous cepstrum〃 (PSC) represents the impulse response of the vocal tract more accurately in voiced speech. And the PSC can compensate for channel distortion because the pitch is more robust in a channel environment than the spectrum of speech. And the proposed channel normalization method, the 〃formant-broadened pitch synchronous CMS〃 (FBPSCMS), applies the Formant-Broadened CMS to the PSC and improves the accuracy of the intraframe processing. We compared the text-independent closed-set speaker identification on 56 females and 112 males using TIMIT and NTIMIT database, respectively. The results show that pitch synchronous km improves the error reduction rate by up to 7.7% in comparison with conventional short-time cepstrum and the error rates of the FBPSCMS are more stable and lower than those of pole-filtered CMS.

• The Journal of the Korea Contents Association
• /
• v.13 no.10
• /
• pp.584-593
• /
• 2013

The purpose of this research is to analyze students' perception of smart learning focusing on its definitions, roles and values in distance higher education. In the online survey, 1,950 students of 'A' open university were participated. The results show that the students viewed the smart learning to be more 'absorbing', 'interactive' and 'collaborative' than the existing e-learning, as it compiles their experiences into learning. However, the respondents' perceptions of smart learning varied among different age groups: more students in their 40s and 50s responded that smart learning was 'customized', 'humanlike', 'interactive', 'comfortable', 'stable', 'familiar', 'unstressful', and 'practical' than students in their 20s and 30s, and they tend to view the main feature of smart learning to be the compilation of learner experiences.

• Korean Institute of Interior Design Journal
• /
• v.22 no.4
• /
• pp.70-77
• /
• 2013

This study has analysed the composition elements in a cafe space where visual transfer-elements are filled and the perceptual characteristics of facade designs with the purpose of drawing any important elements to advertisement and their related items for uniqueness of designs. For the analysis of the perception process shown in the consecutive situations of observing and visiting cafes, the cafe facade was grouped and stereotyped for the analysis of perceptual characteristics and significant composition elements for better designing of cafes through survey with representative facades as subjects. The conclusions from this study are the followings. First, for the uniqueness specific to cafes to be integrated into facade, memory was chosen first as the most significant advertisement factor followed by interest as with male and attention as with female. The memory has much to do with furniture and finishing material of Clause (4), Chapter 4.1 and the types having effects on perception of Clause (1) and the atmosphere having effect on that of Clause (2) were found to be major factors to attention and interest. Second, it was found out that women preferred horizontally stable partition and men clearly divided facades. The factor of shape was observed first among the constituents of facade followed by color. There was no difference with 'shape' between men and women and color was found to be a space constituent having a lot of effects on women. Third, the memory of experience from visiting a cafe was very likely to offer the motivation of visiting it again, on which furniture had the most effect followed by finishing material and color. Such elevation elements as facade and logo were found not to have effect on the memory or the re-visit. Any intention of visiting again seemed to be influenced by such comprehensive images as atmosphere rather than by any concrete facade, furniture, or appliance. From the above viewpoint, facade design should have any uniqueness or impressive feature as well as the effect of making passers-by drop in and attracting them into the shop. The analysis of attributes of facade constituents revealed that the abstract images in addition to the configuration of facade had much to do with interest or behavior.

• Proceedings of the Materials Research Society of Korea Conference
• /
• 2011.05a
• /
• pp.11.2-11.2
• /
• 2011

Polymer based organic photovoltaics have attracted a great deal of attention due to the potential cost-effectiveness of light-weight and flexible solar cells. However, most BHJ polymer solar cells are not thermally stable as subsequent exposure to heat drives further development of the morphology towards a state of macrophase separation in the micrometer scale. Here we would like to show three different approaches for developing new electroactive polymers to improve the thermal stability of the BHJ solar cells, which is a critical problem for the commercialization of these solar cells. For one of the examples, we report a new series of functionalized polythiophene (PT-x) copolymers for use in solution processed organic photovoltaics (OPVs). PT-x copolymers were synthesized from two different monomers, where the ratio of the monomers was carefully controlled to achieve a UV photo-crosslinkable layer while leaving the ${\pi}-{\pi}$ stacking feature of conjugated polymers unchanged. The crosslinking stabilizes PT-x/PCBM blend morphology preventing the macro phase separation between two components, which lead to OPVs with remarkably enhanced thermal stability. The drastic improvement in thermal stabilities is further characterized by microscopy as well as grazing incidence X-ray scattering (GIXS). In the second part of talk, we will discuss the use of block copolymers as active materials for WOLEDs in which phosphorescent emitter isolation can be achieved. We have exploited the use of triarylamine (TPA) oxadiazole (OXA) diblock copolymers (TPA-b-OXA), which have been used as host materials due to their high triplet energy and charge-transport properties enabling a balance of holes and electrons. Organization of phosphorescent domains in TPA-b-OXA block copolymers is demonstrated to yield dual emission for white electroluminescence. Our approach minimizes energy transfer between two colored species by site isolation through morphology control, allowing higher loading concentration of red emitters with improved device performance. Furthermore, by varying the molecular weight of TPA-b-OXA and the ratio of blue to red emitters, we have investigated the effect of domain spacing on the electroluminescence spectrum and device performance.

• Korean Journal of Materials Research
• /
• v.11 no.8
• /
• pp.664-664
• /
• 2001

The mechanical alloying (MA) effect in $\sigma$-VFe intermetallic compound was studied by neutron and X-ray diffraction. The structure of MA $\sigma$-VFe powders were characterized by the X- ray diffraction with Cu- $K\alpha$ radiation and neutron diffraction with monochromatic neutrons of $1.835\AA$ using a high resolution powder diffractometer (HRPD). Mechanical alloying of $\sigma$-VFe compound gives rise to a dramatic structural change. After 60 hours of MA, the Fe-Fe distribution of the $\sigma$- phase VFe tetragonal structure with 30 atoms in a unit cell is found to change into that of the $\sigma$-(V,Fe) solid solution with bcc structure, which is a stable phase at elevated temperature above $1200^{\circ}C$. A comparison of X-ray diffraction data for the $\alpha$-phase has been also made with the corresponding neutron diffraction data. The (101) and (111) diffraction peaks of the $\sigma$-phase was clearly observed only in neutron diffraction pattern, which is believed to be a characteristic feature due to the chemical atomic ordering of $\sigma$- VFe phase.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.9
• /
• pp.53-62
• /
• 1998

In this paper, a genetic algorithm-based optimization technique for stereo matching is proposed. Stereo matching is an essential process to recover three-dimensional structure of objects. The proposed two-dimensional chromosomes consist fo disparity values. The cost function of each chromosome is composed of the intensity-difference between two images and smoothness of disparity. The crossover and mutation operators in the two-dimensional chromosomes are described. The operations are affected by the disparities of neighbor pixels. The knowledge-augmented operators are shown to result in rapid convergence and stable result. The genetic algorithm for stereo matching is tested on synthetic and natural images. Experimental results of various images show that the proposed algorithm has good performance even if the images have too dense or sparse feature points. severe noise, and repeating pattern.