• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1045-1055
• /
• 2007

Latent topic models are statistical models which automatically captures salient patterns or correlation among features underlying a data collection in a probabilistic way. They are gaining an increased popularity as an effective tool in the application of automatic semantic feature extraction from text corpus, multimedia data analysis including image data, and bioinformatics. Among the important issues for the effectiveness in the application of latent topic models to the massive data set is the efficient learning of the model. The paper proposes an accelerated learning technique for PLSA model, one of the popular latent topic models, by an incremental EM algorithm instead of conventional EM algorithm. The incremental EM algorithm can be characterized by the employment of a series of partial E-steps that are performed on the corresponding subsets of the entire data collection, unlike in the conventional EM algorithm where one batch E-step is done for the whole data set. By the replacement of a single batch E-M step with a series of partial E-steps and M-steps, the inference result for the previous data subset can be directly reflected to the next inference process, which can enhance the learning speed for the entire data set. The algorithm is advantageous also in that it is guaranteed to converge to a local maximum solution and can be easily implemented just with slight modification of the existing algorithm based on the conventional EM. We present the basic application of the incremental EM algorithm to the learning of PLSA and empirically evaluate the acceleration performance with several possible data partitioning methods for the practical application. The experimental results on a real-world news data set show that the proposed approach can accomplish a meaningful enhancement of the convergence rate in the learning of latent topic model. Additionally, we present an interesting result which supports a possible synergistic effect of the combination of incremental EM algorithm with parallel computing.

• Journal of Digital Contents Society
• /
• v.10 no.4
• /
• pp.639-648
• /
• 2009

Earth's environment issues are introduced recently and every year the social loss have been occurred by the impact of various disaster. This kind of disaster and weather problems are the increasing reason of electricity transmission network equipment's failures because of exposing by the natural environment. The emergency and abnormal status of electricity equipment make the power outage of manufacturing plant and discomfort of people's lives. So, to protect the electricity equipment from the natural disasters and to supply the power to customer as stable, the supporting systems are required. In this paper, the research results are described the development process and the outcomes of the real-time natural disaster failure analysis information system including the describing about the impact of disaster and weather change, making the natural weather information, and linking the realtime monitoring system. As of development process, according to application development methodology, techniques are enumerated including the real time interface with related systems, the analysing the geographic information on the digital map using GIS application technology to extract the malfunction equipment potentially and to manage the equipments efficiently. Through this system makes remarkable performance it minimize the failures of the equipments, the increasing the efficiency of the equipment operation, the support of scientific information related on the mid-term enhancement plan, the savings on equipment investment, the quality upgrading of electricity supply, and the various supports in the field.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.8
• /
• pp.3333-3338
• /
• 2015

Background: This study was conducted to analyze positron emission tomography (PET) / computed tomography (CT) and magnetic resonance imaging (MRI) performance with oropharyngeal non-Hodgkin's lymphoma (ONHL).Materials and Methods: The complete image data of 30 ONHL cases were analyzed, all patients were performed PET / CT and MRI examination before the treatment, with the time interval of these two inspections not exceeding 14 days. The distribution, morphology, MRI signal characteristics, enhancement feature, standardized uptake value (SUV) max value and lymph node metastasis way of the lesions were analyzed. Results: Among the 30 cases, 23 cases were derived from the B-cell (76.7%), 5 cases were derived from the peripheral T cells (16.7%) and 2 cases were derived from the NK/T cells (6.7%). 19 cases exhibited the palatine tonsil involvement (63.3%). As for the lesion appearance, 10 cases appeared as mass, 8 cases were the diffused type and 12 cases were the mixed type. 25 cases exhibited the SUVmax value of PET / CT primary lesions as 11 or more (83.3%). MRI showed that all patients exhibited various degrees of parapharyngeal side-compressed narrowing, but MRI still exhibited the high-signal fat, and the oropharyngeal mucosa was intact. 25 cases were associated with the neck lymph node metastasis, among who 22 cases had no necrosis in the metastatic lymph nodes, while the rest 3 cases exhibited the central necrosis in the metastatic lymph nodes. Conclusions: PET / CT and MRI have important value in diagnosing and determining the lesion extent of ONHL.

• Journal of Korean Neurosurgical Society
• /
• v.29 no.12
• /
• pp.1606-1611
• /
• 2000

Objective : To obtain more reliable sample in stereotactic biopsy, authors adopted proton chemical shift imaging ($^1H$-CSI)-directed biopsy. Until now, proton single voxel spectroscopy($^1H$-SVS) technique has been reported as a technique using metabolic information in stereotactic biopsy. The authors performed $^1H$-CSI with a stereotactic headframe in place and evaluated the pathologic results obtained from local metabolic information through $^1H$-CSI. Methods : $^1H$ CSI-directed stereotactic biopsy was performed in four patients. $^1H$-CSI and conventional Gd-enhancement stereotactic MRI was done simultaneously after application of the stereotatic frame. After reconstruction of metabolic maps of NAA/Cr, Cho/Cr, and Lactate/Cr ratios, the focal areas of increased Cho/Cr ratios and decreased NAA/Cr ratios were selected for target sites in the MR images Results : There was no difficulty in performing $^1H$-CSI with the stereotactic headframe in place. In pathologic examinations, the samples taken in area of increased Cho/Cr ratios and decreased NAA/Cr ratios showed the features of increased cellularity, mitoses and cellular atypism, thus facilitated the diagnosis. The pathologic samples taken from the area of increased Lactate/Cr ratios showed prominent feature of necrosis. Conclusion : $^1H$-CSI was feasible with stereotactic head frame in place. The final pathologic results obtained in our samples were concordant with the local metabolic informations from $^1H$-CSI. Authors believe that $^1H$ CSI-directed stereotactic biopsy may provide us advantages in obtaining more reliable tissue specimen in stereotactic biopsy.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.673-680
• /
• 2003

In this paper, we study the enhancement of VQ (Vector Quantization) design for text independent speaker recognition. In a concrete way, we present a non-iterative method which makes a vector quantization codebook and this method performs non-iterative learning so that the computational complexity is epochally reduced The proposed Classified Space VQ (CSVQ) design method for text Independent speaker recognition is generalized from Semi-noniterative VQ design method for text dependent speaker recognition. CSVQ contrasts with the existing desiEn method which uses the iterative learninE algorithm for every traininE speaker. The characteristics of a CSVQ design is as follows. First, the proposed method performs the non-iterative learning by using a Classified Space Codebook. Second, a quantization region of each speaker is equivalent for the quantization region of a Classified Space Codebook. And the quantization point of each speaker is the optimal point for the statistical distribution of each speaker in a quantization region of a Classified Space Codebook. Third, Classified Space Codebook (CSC) is constructed through Sample Vector Formation Method (CSVQ1, 2) and Hyper-Lattice Formation Method (CSVQ 3). In the numerical experiment, we use the 12th met-cepstrum feature vectors of 10 speakers and compare it with the existing method, changing the codebook size from 16 to 128 for each Classified Space Codebook. The recognition rate of the proposed method is 100% for CSVQ1, 2. It is equal to the recognition rate of the existing method. Therefore the proposed CSVQ design method is, reducing computational complexity and maintaining the recognition rate, new alternative proposal and CSVQ with CSC can be applied to a general purpose recognition.

• Agricultural and Biosystems Engineering
• /
• v.4 no.1
• /
• pp.8-15
• /
• 2003

In Korea, quality evaluation of dried oak mushrooms are done first by classifying them into more than 10 different categories based on the state of opening of the cap, surface pattern, and colors. And mushrooms of each category are further classified into 3 or 4 groups based on its shape and size, resulting into total 30 to 40 different grades. Quality evaluation and sorting based on the external visual features are usually done manually. Since visual features of mushroom affecting quality grades are distributed over the entire surface of the mushroom, both front (cap) and back (stem and gill) surfaces should be inspected thoroughly. In fact, it is almost impossible for human to inspect every mushroom, especially when they are fed continuously via conveyor. In this paper, considering real time on-line system implementation, image processing algorithms utilizing artificial neural network have been developed for the quality grading of a mushroom. The neural network based image processing utilized the raw gray value image of fed mushrooms captured by the camera without any complex image processing such as feature enhancement and extraction to identify the feeding state and to grade the quality of a mushroom. Developed algorithms were implemented to the prototype on-line grading and sorting system. The prototype was developed to simplify the system requirement and the overall mechanism. The system was composed of automatic devices for mushroom feeding and handling, a set of computer vision system with lighting chamber, one chip microprocessor based controller, and pneumatic actuators. The proposed grading scheme was tested using the prototype. Network training for the feeding state recognition and grading was done using static images. 200 samples (20 grade levels and 10 per each grade) were used for training. 300 samples (20 grade levels and 15 per each grade) were used to validate the trained network. By changing orientation of each sample, 600 data sets were made for the test and the trained network showed around 91 % of the grading accuracy. Though image processing itself required approximately less than 0.3 second depending on a mushroom, because of the actuating device and control response, average 0.6 to 0.7 second was required for grading and sorting of a mushroom resulting into the processing capability of 5,000/hr to 6,000/hr.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2018.06a
• /
• pp.62-62
• /
• 2018

Pt is still considered as one of the most active electrocatalysts for ORR in alkaline fuel cells. However, the high cost and scarcity of Pt hamper the widespread commercialization of fuel cells. As a strong candidate for the replacement of Pt catalyst, silver (Ag) has been extensively studied due to its high activity, abundance, and low cost. Ag is more stable than Pt in the pH range of 8~14 as the equilibrium potential of Ag/Ag+ being ${\approx}200mV$ higher than that of Pt/PtO. However, Ag is the overall catalytic activity of Ag for oxygen reduction reaction(ORR) is still not comparable to Pt catalyst since the surface Ag atoms are approximately 10 times less active than Pt atoms. Therefore, further enhancement in the ORR activity of Ag catalysts is necessary to be competitive with current cutting-edge Pt-based catalysts. We demonstrate the architectural design of Ag catalysts, synthesized using plasma discharge in liquid phase, for enhanced ORR kinetics in alkaline media. An attractive feature of this work is that the plasma status controlled via electric-field could form the Ag nanowires or dendrites without any chemical agents. The plasma reactor was made of a Teflon vessel with an inner diameter of 80 mm and a height of 80 mm, where a pair of tungsten(W) electrodes with a diameter of 2 mm was placed horizontally. The stock solutions were made by dissolving the 5-mM AgNO3 in DI water. For the synthesis of Agnanowires, the electricfield of 3.6kVcm-1 in a 200-ml AgNO3 aqueous solution was applied across the electrodes using a bipolar pulsed power supply(Kurita, Seisakusyo Co. Ltd). The repetition rate and pulse width were fixed at 30kHz and 2.0 us, respectively. The plasma discharge was carried out for a fixed reaction time of 60 min. In case of Ag nanodendrites, the electric field of 32kVcm-1 in a 200-ml AgNO3 aqueous solution was applied and other conditions were identical to the plasma discharge in water in terms of electrode configuration, repetition rate and discharge time. Using SEM and STEM, morphology of Ag nanowires and dendrites were investigated. With 3.6 kV/cm, Ag nanowire was obtained, while Ag dendrite was constructed with 32 kV/cm. The average diameter and legth of Ag nanowireses were 50 nm and 3.5 um, and thoes values of Ag dendrites were 40 nm and 3.0 um. As a results of XPS analysis, the surface defects in the Ag nanowires facilitated O2 incorporation into the surface region via the interaction between the oxygen and the electron cloud of the adjacent Ag atoms. The catalytic activity of Ag for oxygen reduction reaction(ORR) showed that the catalytic ORR activity of Ag nanowires are much better than Ag nanodendrites, and electron transfer number of Ag nanowires is similar to that of Pt (${\approx}4$).

• 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%.

• Journal of the Korean Vacuum Society
• /
• v.19 no.2
• /
• pp.128-133
• /
• 2010

ZnO:Al films were deposited by DC-pulsed magnetron sputtering using a two-step process involving the control of the oxygen pressure. The seed layers were prepared with various Ar to oxygen flow ratios and the bulk layers were deposited under pure Ar. As the oxygen pressure during the deposition of the seed layer increased, the crystallinity and degree of (002) texturing increased. The resistivity gradually decreased with increasing crystallinity from $4.7\times10^4\Omega{\cdot}cm$ (no seed) to $3.7\times10^4\Omega{\cdot}cm$ (Ar/$O_2$ = 9/1). The etched surface showed a crater-like structure and an abrupt morphology change appeared as the crystallinity was increased. The sample deposited at an Ar/$O_2$ flow ratio of 9/1 showed a very high haze value of 88% at 500 nm, which was explained by the large feature size of the craters, as shown in the AFM image.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.13 no.3
• /
• pp.197-205
• /
• 2020

Korean language has the characteristics that the pronunciation of phoneme units such as vowels and consonants are fixed and the pronunciation associated with a notation does not change, so that foreign learners can approach rather easily Korean language. However, when one pronounces words, phrases, or sentences, the pronunciation changes in a manner of a wide variation and complexity at the boundaries of syllables, and the association of notation and pronunciation does not hold any more. Consequently, it is very difficult for foreign learners to study Korean standard pronunciations. Despite these difficulties, it is believed that systematic analysis of pronunciation errors for Korean words is possible according to the advantageous observations that the relationship between Korean notations and pronunciations can be described as a set of firm rules without exceptions unlike other languages including English. In this paper, we propose a visualization framework which shows the differences between standard pronunciations and erratic ones as quantitative measures on the computer screen. Previous researches only show color representation and 3D graphics of speech properties, or an animated view of changing shapes of lips and mouth cavity. Moreover, the features used in the analysis are only point data such as the average of a speech range. In this study, we propose a method which can directly use the time-series data instead of using summary or distorted data. This was realized by using the deep learning-based technique which combines Self-organizing map, variational autoencoder model, and Markov model, and we achieved a superior performance enhancement compared to the method using the point-based data.