• Phonetics and Speech Sciences
• /
• v.6 no.3
• /
• pp.155-164
• /
• 2014

This paper proposes a new method to determine the recognition units for large vocabulary continuous speech recognition (LVCSR) in Korean by applying unsupervised segmentation and merging. In the proposed method, a text sentence is segmented into morphemes and position information is added to morphemes. Then submorpheme units are obtained by splitting the morpheme units through the maximization of posterior probability terms. The posterior probability terms are computed from the morpheme frequency distribution, the morpheme length distribution, and the morpheme frequency-of-frequency distribution. Finally, the recognition units are obtained by sequentially merging the submorpheme pair with the highest frequency. Computer experiments are conducted using a Korean LVCSR with a 100k word vocabulary and a trigram language model obtained by a 300 million eojeol (word phrase) corpus. The proposed method is shown to reduce the out-of-vocabulary rate to 1.8% and reduce the syllable error rate relatively by 14.0%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.32 no.10C
• /
• pp.990-999
• /
• 2007

In this paper, we propose the region-based image retrieval method using JSEG which is a method for unsupervised segmentation of color-texture regions. JSEG is an algorithm that discretizes an image by color classification, makes the J-image by applying a region to window mask, and then segments the image by using a region growing and merging. The segmented image from JSEG is given to a user as the query image, and a user can select a few segmented regions as the query region. After finding the MBR of regions selected by user query and generating the multiple window masks based on the center point of MBR, we extract the feature vectors from selected regions. We use the accumulated histogram as the global descriptor for performance comparison of extracted feature vectors in each method. Our approach fast and accurately supplies the relevant images for the given query, as the feature vectors extracted from specific regions and global regions are simultaneously applied to image retrieval. Experimental evidence suggests that our algorithm outperforms the recent image-based methods for image indexing and retrieval.

• Journal of the Korea Organic Resources Recycling Association
• /
• v.30 no.4
• /
• pp.27-40
• /
• 2022

In this study, the anaerobic digestion potential and thermo-chemical pre-treatment were evaluated for efficient anaerobic co-digestion of dewatered sludge(DS) and food waste(FW). As a result, the degradable organic matter concentration and methane yield of FW were evaluated to 2.2 and 1.3 times higher than that of DS, respectively. In order to increase the amount of biogas production, it was determined that it is desirable to increase the mixing ratio of FW. The efficiency of thermo-chemical pre-treatment was evaluated for the reaction temperature, NaOH concentration, reaction time and mixture ratio. As a result of evaluation through pre-treatment efficiency and dehydration capacity, the optimum pre-treatment conditions were evaluated as follows: reaction temperature 140℃, NaOH concentration 60 meq/L, reaction time 60 min, mixture ratio 1:5(DS:FW). The gas production rate and methane yield increased 1.6 and 1.5 times, respectively, compared to before and after applying the optimum pre-treatment. Therefore, it is necessary to increase the mixing ratio of food waste for efficient anaerobic co-digestion of DS and FW. and it is necessary to increase the solubilization efficiency of waste by application of pre-treatment.

• Journal of the Korean Society of Food Science and Nutrition
• /
• v.46 no.6
• /
• pp.659-670
• /
• 2017

Oxidative stress and inflammation are key factors responsible for progression of liver injury. A variety of functions of oyster hydrolysate (OH) are affected by their antioxidant and anti-inflammatory activities. However, little is known regarding the effects of OH on a liver injury model. This study was performed to evaluate the effects of OH on acute liver injury induced by lipopolysaccharide/D-galactosamine (LPS/D-GalN) in mice. Experimental groups were divided into six groups as follows (each group, n=10): control (saline), LPS/D-GalN, LPS/D-GalN+OH (100 mg/kg), LPS/D-GalN+OH (200 mg/kg), LPS/D-GalN+OH (400 mg/kg), and LPS/D-GalN+silymarin (25 mg/kg, positive control). The experimental acute liver injury model was induced with LPS ($1{\mu}g/kg$) and D-GalN (400 mg/kg). We first analyzed antioxidant and anti-inflammatory activities in OH. OH showed high DPPH and ABTS radical scavenging activities and reduced ROS generation in Chang cells in a dose-dependent manner. In addition, OH showed anti-inflammatory activities, such as inhibition of cyclooxygenase-2 and 5-lipooxygenase. Treatment with OH down-regulated tumor necrosis factor $(TNF)-{\alpha}$, interleukin (IL)-6, and $IL-1{\alpha}$ expression levels in LPS-stimulated RAW264.7 cells. OH significantly reduced LPS/D-GalN-induced increases in the concentrations of alanine transaminase and aspartate aminotransferase in serum. In the LPS/D-GalN group, liver tissues exhibited apoptosis of hepatocytes with hemorrhages. These pathological alterations were ameliorated by OH treatment. Consistently, hepatic catalase activity was low in the LPS/D-GalN group compared to the control group, and catalase activity was significantly restored by OH treatment (P<0.05). Furthermore, OH markedly reduced the LPS/D-GalN-induced increase in $TNF-{\alpha}$, $IL-1{\beta}$, and IL-6 levels in liver tissue. Taken together, these results show that OH has hepatoprotective effects on LPS/D-GalN-induced acute liver injury via inhibition of oxidative stress and inflammation, suggesting that OH could be used as a health functional food and potential therapeutic agent for acute liver injury.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.1
• /
• pp.81-92
• /
• 1999

In this paper, we propose a new image segmentation algorithm which can be use din object-based image coding applications such as MPGA-4. Since the conventional objet segmentation methods based on mathematical morphology tend to yield oversegmented results, they normally need a postprocess which merges small regions to obtain a larger one. To solve this oversegmentation problem, in this paper, we prosed a block-based segmentation algorithm that can identify large texture regions in the image. Also, by applying the watershed algorithm to the image blocks between the homogeneous regions, we can obtain the exact pixel-based contour. Experimental results show that the proposed algorithm yields larger segments, particularly in the textural area, and reduces the computational complexities.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.142-147
• /
• 1989

필기체 문자는 인쇄체 문자와는 달리, 복잡한 변형이 따르므로, 인식 하는데 많은 문제점이 따른다. 그렇기 때문에 일반적인 필기체 인식에 있어서는 필기 자체에 대한 제한을 두어 변형을 적게한 문자를 인식 대상으로 삼고 있다. 이러한 문자는, 설정된 조건만 확실하게 만족한다면, 비교적 간단하게 인식 할 수 있다. 반면에, 자유 필기체 문자는, 제한 필기체 문자와는 달리 변형이 크기 때문에, 그 인식에는 많은 연구가 필요하다. 본 연구에서는, 자유 필기체 한글의 자모를 추출하는데 있어 두개의 parameter space method를 이용했다. 화상내에서의 혼합은, 기본적으로 5 개의 element ($\mid,\;\setminus,\;/,\;-,\;o$)로 구성되어 있고, 이 element를 정의하는데는 최소한 4 개의 parameter, 즉 element의 위치 [x, y], 크기 [1] 및 type [T] 등이 필요하다. 입력 화상에서 추출된 직선 및 원의 성분은 [x, y, l] 과 [x, y, T]의 2 개의 3-D parameter space 에 누적되고, parameter space 상에서의 병합 분할 과정을 거쳐, element 가 형성된다. 추출된 element 들은, parameter space 상에서의 방향성 및 상호 위치 관계에 의한 조합 형태로서, 미리 기술되어진 자모 모델과 비교되어 인식된다. 본 방법의 특정은, 문자의 크기에 무관하고, 해석방법에 의해서는, 끊어진 element나 불필요한 element 등의 왜곡된 element 들의 처리가 가능한 점, 4 차원 parameter space를 두개의 3 차원 parameter space로 분리, 처리시간과 기억용량의 절약을 기한점 등을 들 수 있다.

• Clinical and Experimental Pediatrics
• /
• v.50 no.6
• /
• pp.565-569
• /
• 2007

Purpose : With a duration of action of approximately 24 hours and peakless levels, Lantus is a more physiologic basal insulin analogue compared with NPH. The aim of this study was to compare the glycemic control of Lantus plus Humalog with that of premixed insulin in children and adolescents with type 1 diabetes mellitus. Methods : The subjects consisted of 25 patients with type 1 diabetes mellitus, aged 12-19 years, who changed their insulin regimen from premixed insulin to Lantus plus Humalog. Daily insulin doses, frequency of hypoglycemia, fasting blood glucose, C-peptide concentration and HbA1c before and 6 months after Lantus treatment were compared. 24 hour blood glucose of 11 patients among Lantus treatment group (n=25) and premixed insulin treatment group (n=10) were self-monitored and compared. Results : 6 months after Lantus treatment, the episodes of hypoglycemia were reduced by 50%(15.1 vs. 7.6 events/month), especially nocturnal hypoglycemia by 67%(6.7 vs. 2.5 events/month). HbA1c was reduced from 9.3% to 8.7% after Lantus treatment. Self-monitored blood glucose of Lantus treatment group at postbreakfast 30, 60, 90 and 120 minutes were 171.1, 169.5, 171.0 and 154.1 mg/dL respectively and lower than those of premixed insulin treatment group (259.7, 282.7, 280.0 and 250.9 mg/dL respectively). Conclusion : Compared with premixed insulin, Lantus plus Humalog is more effective in glycemic control and reduction in nocturnal hypoglycemia in children and adolescents with type 1 diabetes mellitus.

• Journal of Korean Society for Geospatial Information Science
• /
• v.21 no.3
• /
• pp.11-17
• /
• 2013

With high social demands for the diverse utilizations of forest lands, the illegal forest land use changes have increased. We studied change detection technique to detect changes in forest land use using an object-oriented segmentation of RED bands differencing in multi-temporal aerial photographs. The new object-oriented segmentation method consists of the 5 steps, "Image Composite - Segmentation - Reshaping - Noise Remover - Change Detection". The method enabled extraction of deforested objects by selecting a suitable threshold to determine whether the objects was divided or merged, based on the relations between the objects, spectral characteristics and contextual information from multi-temporal aerial photographs. The results found that the object-oriented segmentation method detected 12% of changes in forest land use, with 96% of the average detection accuracy compared by visual interpretation. Therefore this research showed that the spatial data by the object-oriented segmentation method can be complementary to the one by a visual interpretation method, and proved the possibility of automatically detecting and extracting changes in forest land use from multi-temporal aerial photographs.

• The Journal of the Korea Contents Association
• /
• v.9 no.12
• /
• pp.19-30
• /
• 2009

The service that has recently come into the spotlight utilizes the map to first approach the map and then provide various mash-up formed results through the interface. This service can provide precise information to the users but the map is barely reusable. The sketch-map system of this paper, unlike the existing large map system, uses the method of presenting the specific spot and route in XML document and then clustering among sketch-maps. The map service system is designed to show the optimum route to the destination in a simple outline map. It is done by renovating the spot presented by the map into optimum contents. This service system, through the process of analyzing, splitting and clustering of the sketch-map's XML document input, creates a valid form of a sketch-map. It uses the LCS(Longest Common Subsequence) algorithm for splitting and merging sketch-map in the process of query. In addition, the simulation of this system's expected effects is provided. It shows how the maps that share information and knowledge assemble to form a large map and thus presents the system's ability and role as a new research portal.

• Journal of Korea Multimedia Society
• /
• v.5 no.6
• /
• pp.616-624
• /
• 2002

An extraction method of central objects in the color images is proposed, in this paper. A central object is defined as a comparatively consist of the central object in the image. First of all. an input image and its decreased resolution images are segmented. Segmented regions are classified as the outer or the inner region. The outer region is adjacent regions are included by a same region in the decreased resolution image. Then core object regions and core background regions are selected from the inner region and the outer region respectively. Core object regions are the representative regions for the object and are selected by using the information about the information about the region size and location. Each inner regions is classified into foreground or background regions by comparing values of a color histogram intersection of the inner region against the core object region and the core background regions. The core object region and foreground regions consist of the central object in the image.