• 음성과학
• /
• 제10권1호
• /
• pp.27-39
• /
• 2003

This study attempts to verify the reliability of automatically generated segment labels as compared to those obtained by conventional labelling by hand. First of all, an autolabeller is constructed using the standard HMM speech recognition technique. For evaluation, we compare the automatically generated labels with manually annotated labels for the same speech data. The comparison is performed by calculating the temporal difference between an autolabel boundary and its corresponding hand label boundary. When the mismatched duration between two labels falls within 10 msec, we consider the autolabel as correct. The results suggest that overall 78% of autolabels are correctly obtained. It is found that the boundary of obstruents is better aligned than that of sonorants and vowels. In case of stop sound classes, strong stops in manner-of-articulation wise and velar stops in place-of-articulation wise show better performance in boundary alignment. The result suggests that more phone-specific consideration is necessary to improve autosegmentation performance.

• Journal of Korean Neurosurgical Society
• /
• 제29권4호
• /
• pp.485-490
• /
• 2000

Objective : To study the expression of apoptosis and bcl-2 in the astrocytic tumors. Patients and Methods : A total of thirty-eight astrocytomas(9 cases in low grade astrocytoma, 12 cases in anaplastic astrocytoma and 17 cases in glioblastoma) are included in this study. Immunohistochemical stain for bcl-2 using monoclonal antibody, in situ end labelling technique for apoptosis were used. Results : The malignant group(anaplastic astrocytoma and glioblastoma) showed significantly higher apoptosis positive index(PI) compared to the benign group(low grade astrocytoma)(1.35 vs 0.14). However apoptosis PI and bcl-2 PI were not significantly different among three groups. Correlation between apoptosis PI and bcl-2 PI was not statistically significant(p=0.58). Conclusion : This result suggest that apoptosis PI and bcl-2 PI are not related the degree of malignancy in astrocytic neoplasm, but apoptosis PI in malignant group was higher possibly due to greater DNA damage.

• Biomolecules & Therapeutics
• /
• 제1권1호
• /
• pp.58-64
• /
• 1993

DNA addicts induced by putative chemical related to carcinogenesis were detected and determined by $^{32}$P-Postlabelling assay after exposure of 4 compounds comprising two auto dyes (amaranth, new coccine) and two flavonoid compounds (rutin, quercetin) to ICR mouse. DNA was isolated from mouse liver and digested enzymatically to deoxyribonucleoside 3'-monophosphate. The postincubation of DNA digests with nuclease Pl before $^{32}$P-labelling enhanced the technique's sensitivity. Nuclease Pl cleaves deoxyribonucleoside 3'-mono-phosphates of normal nucleotides to deoxyrihonucleosides which do not serve as substrates for polynucleotide kinase, while most of addicts were found to be totally or partially resistant to the 3'-dephosphorylating action of nuclease Pl. The adducted deoxyribonucleoside 3'-monophosphate was converted to 5'-$^{32}$P-labelled deoxynucleoside 3',5'-bisphosphate by T4 polynucleotide kinase. The nucleotides were separated by anion-exchange thin layer chromatography(TLC) on polyethyleneimine cellulose by 4-dimensional or 2-dimensional TLC then detected by autoradiography. The results show that DNA addicts were detected in liver DNA of ICR mouse after administration of amaranth and quercetin by 2-dimensional and/or 4-dimensional TLC.

• 대한핵의학회지
• /
• 제11권1호
• /
• pp.9-15
• /
• 1977

난포 자극 홀몬(hFSH)을 클로라민 티를 사용하여 방사성 요오드로 표지하였으며 평균표지수율은 대략 65%이었다. 표지홀몬을 방사면역측정용으로 사용하기 위하여 전분젤 전기영동과 젤 여과법으로 분리정제하고 그 분리정제효과를 분석한 결과 젤 여과법이 분리시간, 간편성, 항체와의 결합력등으로 보아 우수함을 알 수 있었다. 한편 유리 표지홀몬과 항체와 결합한 표지홀몬의 비율을 결정하기 위하여 이중 항체법을 크로마토 전기영동법과 비교하여 본 결과 이중항체법에 의해서만 효과적 비율결정이 가능하였다.

• International Journal of Computer Science & Network Security
• /
• 제22권3호
• /
• pp.29-36
• /
• 2022

In deep learning classification tasks, most models frequently assume that all labels are available for the training datasets. As such strategies to learn new concepts from unlabeled datasets are scarce. In fingerprint classification tasks, most of the fingerprint datasets are labelled using the subject/individual and fingerprint datasets labelled with finger type classes are scarce. In this paper, authors have developed approaches of classifying fingerprint images using the majorly known fingerprint classes. Our study provides a flexible method to learn new classes of fingerprints. Our classifier model combines both the clustering technique and use of deep learning to cluster and hence label the fingerprint images into appropriate classes. The K means clustering strategy explores the label uncertainty and high-density regions from unlabeled data to be clustered. Using similarity index, five clusters are created. Deep learning is then used to train a model using a publicly known fingerprint dataset with known finger class types. A prediction technique is then employed to predict the classes of the clusters from the trained model. Our proposed model is better and has less computational costs in learning new classes and hence significantly saving on labelling costs of fingerprint images.

• 한국컴퓨터정보학회논문지
• /
• 제18권4호
• /
• pp.13-18
• /
• 2013

디지털 카메라의 보급으로 카메라만 있으면 누구나 손쉽게 파노라마 사진을 찍을 수 있다. 파노라마 사진이란 카메라를 삼각대에 고정시킨 후, 일부분을 중첩시키면서 회전하여 얻어진 이미지를 수평으로 이동하여 이미지를 결합시키는 사진이다. 이때 수동으로 사진을 찍을 경우에는 각도가 틀어져 겹쳐지는 부분을 자연스럽게 정합하기 어렵다. 기존의 방법에서는 라벨링을 이용하여 객체를 비교한 후에 결합시키는 방법을 적용하였으나 시간이 많이 소요되고 각각의 이미지를 라벨링하는 과정에서 개체 간의 불일치가 발생하여 정확히 영상을 결합할 수 없는 경우가 발생한다. 따라서 본 논문에서는 처리 속도 개선을 위하여 전체 이미지의 1/3만 라벨링한 후에 객체 간을 비교하여 결함시킨다. 그리고 각도가 틀린 경우에는 특징점을 찾아내는 SURF 알고리즘을 적용하여 각각의 이미지에서 라벨링한 사각형의 4개의 포인터에 대해 1개의 중심점을 구하여 호모그래피를 이용하여 2개의 영상을 자연스럽게 정합한다. 본 논문에서 제안한 파노라마 영상 재구성 방법의 성능을 평가하기 위하여 다양한 이미지를 대상으로 실험한 결과, 기존의 방법보다 영상을 재구성하는데 효과적인 것을 확인하였다.

• 한국응용곤충학회지
• /
• 제20권4호
• /
• pp.207-211
• /
• 1981

수도 주요해충 벼멸구의 내충성품종선별방법을 개발하기 위하여 방사성동위원소 P-32를 이용한 섭식량과 식이선호성과의 관계를 조사중 다음과 같은 결과를 얻었다. 1. 식이선호에 의한 벼멸구의 선호도와 P-32 섭식량간에는 밀접한 관계가 있었다. 2. $ 2\~3$엽기 수도유묘를 표식할 때는 P-32의 비방사능이 $0.1{\mu}Ci/cc$가 되게 하고 처리방법은 근부를 24시간 이상 침적시킨 후 공시충은 48시간 흡즙시키는 것이 품종간차이를 비교하기 용역하였다. 3. 내충성 검정시 공시충은 성충을 이용하고 웅충보다 자충을 이용하는 것이 흡즙량의 차이가 커서 비교하기가 편리하였다.

• 패션비즈니스
• /
• 제16권4호
• /
• pp.29-45
• /
• 2012

The purpose of this study is for providing not only the latest design technique trend for zero waste fashion, but information about creative fashion design education through eco-fashion industry trend in globally and domestic which is focusing on eco-fashion labelling. The research were processed with literature related eco, sustainable, green fashion books, former articles, newspapers, and web sites. The results as follows; The certification about eco-fashion product is moving to 'Life Cycle Assessment' from focused on primary process like material, finishing, dyeing. Especially simplicity of process means reducing the wastes. And fabric wastage for adult outwear was estimated 15% percent of total fabric used in general design studios. Three cases for Zero waste fashion were as follows; First, Jigsaw puzzle by Timo Rissane and Mark Liu were different zero waste methods, but the result was same. Rissene's method was based on traditional cutting like 'cut and sew' but traditional cutting can lead to design that have an abundance of fabric and drape. Jigsaw of Rissene was approached with description a pattern-cutting technique in which all piece interlock with each other generating no waste from design production. Another Jigsaw by Liu was related with innovative textile design. DTP makes the possibilities for zero waste garment production almost endless. The dress intricately cut from 10 pieces, wastes none of the fabric required to make it. Second, Subtraction Cutting by Julian Roberts provides unexpected fluid, organic forms and zero waste fabric. Utilizing Roberts plug(tunnel) technique enables any part of the garment that is removed for fit or aesthetics to be reincorporated into the design of garment. Third was 'Bio Couture' by Suzanne Lee. She has created garments from cellulose bacteria which grow in a bathtub using only green methods addressing in such as way ecological issues and exploring the future of fashion design in conjunction with technology.

• International Journal of Computer Science & Network Security
• /
• 제23권12호
• /
• pp.151-160
• /
• 2023

Breast cancer is the most dangerous and deadly form of cancer. Initial detection of breast cancer can significantly improve treatment effectiveness. The second most common cancer among Indian women in rural areas. Early detection of symptoms and signs is the most important technique to effectively treat breast cancer, as it enhances the odds of receiving an earlier, more specialist care. As a result, it has the possible to significantly improve survival odds by delaying or entirely eliminating cancer. Mammography is a high-resolution radiography technique that is an important factor in avoiding and diagnosing cancer at an early stage. Automatic segmentation of the breast part using Mammography pictures can help reduce the area available for cancer search while also saving time and effort compared to manual segmentation. Autoencoder-like convolutional and deconvolutional neural networks (CN-DCNN) were utilised in previous studies to automatically segment the breast area in Mammography pictures. We present Automatic SegmenAN, a unique end-to-end adversarial neural network for the job of medical image segmentation, in this paper. Because image segmentation necessitates extensive, pixel-level labelling, a standard GAN's discriminator's single scalar real/fake output may be inefficient in providing steady and appropriate gradient feedback to the networks. Instead of utilising a fully convolutional neural network as the segmentor, we suggested a new adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local attributes that collect long- and short-range spatial relations among pixels. We demonstrate that an Automatic SegmenAN perspective is more up to date and reliable for segmentation tasks than the state-of-the-art U-net segmentation technique.

• 한국농업기계학회:학술대회논문집
• /
• 한국농업기계학회 2017년도 춘계공동학술대회
• /
• pp.42-42
• /
• 2017

Prediction of rice yield during a growing season would be very helpful to magnify rice yield as it also allows better farm practices to maximize yield with greater profit and lesser costs. UAV imagery based automatic detection of rice can be a relevant solution for early prediction of yield. So, we propose an image processing technique to predict rice yield using low altitude UAV images. We proposed $L^*a^*b^*$ color space based image segmentation algorithm. All images were captured using UAV mounted RGB camera. The proposed algorithm was developed to find out rice grain area from the image background. We took RGB image and applied filter to remove noise and converted RGB image to $L^*a^*b^*$ color space. All color information contain in both $a^*$ and $b^*$ layers and by using k-mean clustering classification of these colors were executed. Variation between two colors can be measured and labelling of pixels was completed by cluster index. Image was finally segmented using color. The proposed method showed that rice grain could be segmented and we can recognize rice grains from the UAV images. We can analyze grain areas and by estimating area and volume we could predict rice yield.