• Journal of Electrical Engineering and Technology
• /
• v.11 no.2
• /
• pp.529-536
• /
• 2016

In this paper we proposed an unsupervised algorithm to estimate the reverberation time (RT) directly from the reverberant speech signal. For estimation process we use maximum likelihood estimation (MLE) which is a very well-known and state of the art method for estimation in the field of signal processing. All existing RT estimation methods are based on the decay rate distribution. The decay rate can be obtained either from the energy envelop decay curve analysis of noise source when it is switch off or from decay curve of impulse response of an enclosure. The analysis of a pre-existing method of reverberation time estimation is the foundation of the proposed method. In one of the state of the art method, the reverberation decay is modeled as a Laplacian distribution. In this paper, the proposed method models the reverberation decay as a Gamma distribution along with the unification of an effective technique for spotting free decay in reverberant speech. Maximum likelihood estimation technique is then used to estimate the RT from the free decays. The method was motivated by our observation that the RT of a reverberant signal when falls in specific range, then the decay rate of the signal follows Gamma distribution. Experiments are carried out on different reverberant speech signal to measure the accuracy of the suggested method. The experimental results reveal that the proposed method performs better and the accuracy is high in comparison to the state of the art method.

• KIPS Transactions on Software and Data Engineering
• /
• v.1 no.2
• /
• pp.127-136
• /
• 2012

Many research of hand gesture recognition based on vision system have been conducted which enable user operate various electronic devices more easily. 3D position calculation and meaningful gesture classification from similar gestures should be executed to recognize hand gesture accurately. A simple and cost effective method of 3D position calculation and gesture spotting (a task to recognize meaningful gesture from other similar meaningless gestures) is described in this paper. 3D position is achieved by calculation of two cameras relative position through pan/tilt module and a marker regardless with the placed position. Fuzzy garbage model is proposed to provide a variable reference value to decide whether the user gesture is the command gesture or not. The reference is achieved from fuzzy command gesture model and fuzzy garbage model which returns the score that shows the degree of belonging to command gesture and garbage gesture respectively. Two-stage user adaptation is proposed that off-line (batch) adaptation for inter-personal difference and on-line (incremental) adaptation for intra-difference to enhance the performance. Experiment is conducted for 5 different users. The recognition rate of command (discriminate command gesture) is more than 95% when only one command like meaningless gesture exists and more than 85% when the command is mixed with many other similar gestures.

• Journal of Microbiology and Biotechnology
• /
• v.19 no.7
• /
• pp.658-665
• /
• 2009

Quality control QC for spot-uniformity is a critical point in fabricating an oligonucleotide array, and quantification of targets is very important in array analysis. We developed two new types of QC probes as a means of confirming the quality of the uniformity of attached probes and the quantification of targets. We compared the signal intensities and fluorescent images of the QC and target-specific probes of arrays containing only target-specific probes and those containing both QC and target-specific probes. In a comparison of quality control methods, it was found that the arrays containing QC probes could check spot-uniformity or spot defects during all processes of array fabrication, including after spotting, after washing, and after hybridization. In a comparison of quantification results, the array fabricated by the method using QC probes showed linear and regular results because it was possible to normalize variations in spot size and morphology and amount of attached probe. This method could avoid errors originating in probe concentration and spot morphology because it could be normalized by QC probes. There were significant differences in the signal intensities of all mixtures (P<0.05). This result indicates that the method using QC probes is more useful than the ordinary method for quantification of mixed target. In the quantification of mixed targets, this method could determine a range for mixed targets of various amounts. Our results suggest that methods using QC probes for array fabrication are very useful to the quality control of spots in the fabrication processes of quantitative oligonucleotide arrays.

• BMB Reports
• /
• v.37 no.5
• /
• pp.546-551
• /
• 2004

The increasing pace of development in molecular biology during the last decade has had a direct effect on mass testing and diagnostic applications, including blood screening. We report the model Microarray that has been developed for Hepatitis B virus (HBV) and Hepatitis D virus (HDV) detection. The specific primer pairs of PCR were designed using the Primer Premier 5.00 program according to the conserved regions of HBV and HDV. PCR fragments were purified and cloned into pMD18-T vectors. The recombinant plasmids were extracted from positive clones and the target gene fragments were sequenced. The DNA microarray was prepared by robotically spotting PCR products onto the surface of glass slides. Sequences were aligned, and the results obtained showed that the products of PCR amplification were the required specific gene fragments of HBV, and HDV. Samples were labeled by Restriction Display PCR (RD-PCR). Gene chip hybridizing signals showed that the specificity and sensitivity required for HBV and HDV detection were satisfied. Using PCR amplified products to construct gene chips for the simultaneous clinical diagnosis of HBV and HDV resulted in a quick, simple, and effective method. We conclude that the DNA microarray assay system might be useful as a diagnostic technique in the clinical laboratory. Further applications of RD-PCR for the sample labeling could speed up microarray multi-virus detection.

• Journal of KIISE:Software and Applications
• /
• v.31 no.9
• /
• pp.1121-1130
• /
• 2004

This paper proposes a method for line and word segmentation for machine-printed text blocks. To separate a text region into the unit of lines, it analyses the horizontal projection profile and performs a recursive projection profile cut method. In the word segmentation, between-word gaps are identified by a hierarchical clustering method after finding gaps in the text line by using a connected component analysis. In addition, a special symbol detection technique is applied to find two types of special symbols tying between words using their morphologic features. An experiment with 84 text regions from English and Korean documents shows that the proposed method achieves 99.92% accuracy of word segmentation, while a commercial OCR software named Armi 6.0 Pro$^{TM}$ has 97.58% accuracy.y.

• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.591-600
• /
• 2006

This paper describes the development and implementation of a algorithm to decompose word images from image regions mixed text/graphics in document images using statistical analyses. To decompose word images from image regions, the character components need to be separated from graphic components. For this process, we propose a method to separate them with an analysis of box-plot using a statistics of structural components. An accuracy of this method is not sensitive to the changes of images because the criterion of separation is defined by the statistics of components. And then the character regions are determined by analyzing a local crowdedness of the separated character components. finally, we devide the character regions into text lines and word images using projection profile analysis, gap clustering, special symbol detection, etc. The proposed system could reduce the influence resulted from the changes of images because it uses the criterion based on the statistics of image regions. Also, we made an experiment with the proposed method in document image processing system for keyword spotting and showed the necessity of studying for the proposed method.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.41 no.4
• /
• pp.248-255
• /
• 2018

Ensuring the quality of molds is one of the major issues in mass production. In general, securing the quality of the molds is achieved by repeating grinding and die spotting after machining the molds based on engineer's decision. However, this heuristic method is affected by the engineer's skill and working environment. Therefore, a lot of time and resources are needed in order to ensure quality. In this study, ensuring the quality of molds using grinding map which is generated using automatic measurement is proposed. An automatic measuring system based on CMM (Coordinate Measuring Machine) is developed for measuring the molds. This system generates the measurement path automatically using the 3D CAD model of products. CAD (ComputerAided-Design), CAM (Computer-Aided-Manufacturing), and CAQ (Computer-Aided-Quality) technology is integrated using DMIS (Dimensional Measuring Interface Standard) format in the automatic measuring system. After measuring the molds, a grinding map is generated using the gap between the CAD model and measured values of mold. The grinding map displays the machining tendency and the required amount of grinding with values on a 3D map. Therefore, the quality of molds can be ensured with exactness and quickness based on the grinding map. This study shows that integrating the planning, measuring, and analyzing based on computer technology can solve the problem of quality assurance of mold using the proposed method, therefore the productivity can be increased.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.20 no.4
• /
• pp.655-666
• /
• 1996

The effect of protease (subtilisin Carlsberg) on the removal of hemoglobin as protein soil was studied. The relation between the renloval and the hydrolysis of hemoglobin by subtilisin Carlsberg was discussed. The soiled babric was prepared by spotting of hemoglobin solution evenly on the cotton fabric and was denatured by steaming. The soiled fabric was washed by using Terg-0-Tometer at various conditions. The removal efficiency was evaluated by analysis of protein on the fabrics before and after washing by means of copper-Folin method. 1. The removal of hemoglobin was increased in proportion to increasing of the enzyme concentration up to a certain point, but it began to decrease above the point. 2. The hemoglobin was removed effectively by adding of subtilisin Carlsberg, and more effectively removed by adding of AOS in the enzyme solution. 3. The removal of hemoglobin deviated from the first order reaction in detergency. 4. The renloval of hemoglobin was highest at $50^{\circ}C$ in detergency, Even at low temperature the removal efficiency of enzyme was relatively higher compared with the hydrolysis of hemoglobin by the enzyme. However the removal of hemoglobin was apparently decreased with the increase of temperature over $60^{\circ}C$. 5. The removal of hemoglobin was relatively high at pH 7.0~8.0 and increased continuously with the increase of pH in detergency 6. In detergency, the removal mechanism of hemoglobin by subtilisin Carlsberg could be explained as follows: Fisrt of all, the enzyme hydrolyzed hemoglobin substrates partially by forming E-S complex at the surface of hemoglobin on the cotton fiber, and decomposed cooperative binding of hemoglobin. Subsequently, the fragments of hemoglobin were easily removed by washing. According as the enzyme penetrated to inner part of hemoglobin gradually, the hemoglobin on the cotton fiber was effectively removed by the repetition of these process. The removal of hemoglobin was more effectively increased by adding both the enzyme and AOS in the washing solution. Therefore, it was regarded that AOS molecules were adsorbed at the hydrophobic surface of denatured hemoglobin, subsequently, decomposed more effectively cooperative binding of hemoglobin, and the fragments of hemoglobin were removed more efficiently by means of the interfacial reaction of AOS.

• The KIPS Transactions:PartB
• /
• v.12B no.4 s.100
• /
• pp.369-378
• /
• 2005

Document image is segmented and classified into text, picture, or table by a document layout analysis, and the words in table regions are significant for keyword spotting because they are more meaningful than the words in other regions. This paper proposes a method to extract words from table regions in document images. As word extraction from table regions is practically regarded extracting words from cell regions composing the table, it is necessary to extract the cell correctly. In the cell extraction module, table frame is extracted first by analyzing connected components, and then the intersection points are extracted from the table frame. We modify the false intersections using the correlation between the neighboring intersections, and extract the cells using the information of intersections. Text regions in the individual cells are located by using the connected components information that was obtained during the cell extraction module, and they are segmented into text lines by using projection profiles. Finally we divide the segmented lines into words using gap clustering and special symbol detection. The experiment performed on In table images that are extracted from Korean documents, and shows $99.16\%$ accuracy of word extraction.

• Korean Journal of Cognitive Science
• /
• v.21 no.1
• /
• pp.157-175
• /
• 2010

Understanding dialogue participant's emotion is important as well as decoding the explicit message in human communication. It is well known that non-verbal elements are more suitable for conveying speaker's emotions than verbal elements. Written texts, however, contain a variety of linguistic units that express emotions. This study aims at analyzing components for constructing an emotion ontology, that provides us with numerous applications in Human Language Technology. A majority of the previous work in text-based emotion processing focused on the classification of emotions, the construction of a dictionary describing emotion, and the retrieval of those lexica in texts through keyword spotting and/or syntactic parsing techniques. The retrieved or computed emotions based on that process did not show good results in terms of accuracy. Thus, more sophisticate components analysis is proposed and the linguistic factors are introduced in this study. (1) 5 linguistic types of emotion expressions are differentiated in terms of target (verbal/non-verbal) and the method (expressive/descriptive/iconic). The correlations among them as well as their correlation with the non-verbal expressive type are also determined. This characteristic is expected to guarantees more adaptability to our ontology in multi-modal environments. (2) As emotion-related components, this study proposes 24 emotion types, the 5-scale intensity (-2~+2), and the 3-scale polarity (positive/negative/neutral) which can describe a variety of emotions in more detail and in standardized way. (3) We introduce verbal expression-related components, such as 'experiencer', 'description target', 'description method' and 'linguistic features', which can classify and tag appropriately verbal expressions of emotions. (4) Adopting the linguistic tag sets proposed by ISO and TEI and providing the mapping table between our classification of emotions and Plutchik's, our ontology can be easily employed for multilingual processing.