• 대한산업공학회지
• /
• 제28권2호
• /
• pp.147-161
• /
• 2002

In novelty detection, one attempts to discriminate abnormal patterns from normal ones. Novelty detection is quite difficult since, unlike usual two class classification problems, only normal patterns are available for training. Auto-Associative Multi-Layer Perceptron (AAMLP) has been shown to provide a good performance based upon the property that novel patterns usually have larger auto-associative errors. In this paper, we give a mathematical analysis of 2-layer AAMLP's output characteristics and empirical results of 2-layer and 4-layer AAMLPs. Various activation functions such as linear, saturated linear and sigmoid are compared. The 2-layer AAMLPs cannot identify non-linear boundaries while the 4-layer ones can. When the data distribution is multi-modal, then an ensemble of AAMLPs, each of which is trained with pre-clustered data is required. This paper contributes to understanding of AAMLP networks and leads to practical recommendations regarding its use.

• Interdisciplinary Bio Central
• /
• 제4권4호
• /
• pp.14.1-14.6
• /
• 2012

Splice site prediction in DNA sequence is a basic search problem for finding exon/intron and intron/exon boundaries. Removing introns and then joining the exons together forms the mRNA sequence. These sequences are the input of the translation process. It is a necessary step in the central dogma of molecular biology. The main task of splice site prediction is to find out the exact GT and AG ended sequences. Then it identifies the true and false GT and AG ended sequences among those candidate sequences. In this paper, we survey research works on splice site prediction based on support vector machine (SVM). The basic difference between these research works is nucleotide encoding technique and SVM kernel selection. Some methods encode the DNA sequence in a sparse way whereas others encode in a probabilistic manner. The encoded sequences serve as input of SVM. The task of SVM is to classify them using its learning model. The accuracy of classification largely depends on the proper kernel selection for sequence data as well as a selection of kernel parameter. We observe each encoding technique and classify them according to their similarity. Then we discuss about kernel and their parameter selection. Our survey paper provides a basic understanding of encoding approaches and proper kernel selection of SVM for splice site prediction.

• 대한의용생체공학회:의공학회지
• /
• 제30권2호
• /
• pp.153-161
• /
• 2009

Mammogram is one of the important techniques for mass detection, which is the early diagnosis stage of a breast cancer. Especially, the CAD(Computer Aided Diagnosis) using mammogram improves the working performance of radiologists as it offers an effective mass detection. There are two types of CAD systems using mammogram; automatic and semi-automatic CAD systems. However, the automatic segmentation is limited in performance due to the difficulty of obtaining an accurate segmentation since mass occurs in the dense areas of the breast tissue and has smoother boundaries. Semi-automatic CAD systems overcome these limitations, however, they also have problems including high FP (False Positive) rate and a large amount of training data required for training a classifier. The proposed system which overcomes the aforementioned problems to detect mass is composed of the suspected area selection, the level set segmentation and SVM (Support Vector Machine) classification. To assess the efficacy of the system, 60 test images from the FFDM (Full-Field Digital Mammography) are analyzed and compared with the previous semi-automatic system, which uses the ANN classifier. The experimental results of the proposed system indicate higher accuracy of detecting mass in comparison to the previous systems.

• 한국컴퓨터그래픽스학회논문지
• /
• 제8권2호
• /
• pp.23-29
• /
• 2002

컴퓨터 그래픽스 분야에 있어서 하드웨어의 활용은 렌더링 속도를 높이고 높은 수준의 결과를 얻기 위한 중요한 요소이다. 최근의 급속한 하드웨어의 발달은 기존에 불가능했던 다양한 여러 가지 효과들을 가능하게 해 주었으며, 쉐이더 기능을 이용하여 고급의 렌더링 기법들을 실시간에 구현할 수 있게 되었다. 본 논문에서는 이러한 하드웨어를 이용하여 최대 4가지의 물질에 대한 직접 볼륨 렌더링(direct volume rendering)을 수행할 수 있는 기법을 제안한다. 이 기법에서는 다양한 물질에 대한 렌더링 기능 이외에 그라디언트 값에 의한 물질 표면의 강조 효과, 광원의 거리에 의한 빛의 감소효과(Light Attenuation)와 Depth cueing, 복수의 광원에 의한 조명 효과 등의 다양한 고급 렌더링 기법들을 볼륨 렌더링에 적용할 수 있다.

• Geomechanics and Engineering
• /
• 제8권5호
• /
• pp.675-685
• /
• 2015

Weathering is the breaking/cutting down process of rocks due to physical and chemical processes in natural as well as artificial environment including $CO_2$ injection for storage in the sediment, or natural resource recovery process. This study suggests an alternative method to estimate the degree of weathering for granites. A series of laboratory and field experiments are performed to measure electrical resistivities on various rock samples experienced different degrees of weathering and their residual soils under different saturation conditions. It is found that the normalized electrical resistivity increases with a decrease in water absorption and the saturation. Simple boundaries are suggested to identify the weathering degree of granites, based on limited data. Field test results for three sites confirm that the suggested method could be estimated well the degree of weathering of granites compared with the other methods suggested previously. Although further research is required, this study suggests that an electrical resistivity could be an effective approach to estimate the degree of weathering of granites compared with the other methods suggested previously.

• Journal of the Optical Society of Korea
• /
• 제14권4호
• /
• pp.376-382
• /
• 2010

We propose a novel method to precisely detect car license plates by locating main characters, which are printed with large font size. The regions of the main characters are directly detected without detecting the plate region boundaries, so that license regions can be detected more precisely than by other existing methods. To generate a binary image, multiple thresholds are applied, and segmented regions are selected from multiple binarized images by a criterion of size and compactness. We do not employ any character matching methods, so that many candidates for main character groups are detected; thus, we use a neural network to reject non-main character groups from the candidates. The relation of the character regions and the intensity statistics are used as the input to the neural network for classification. The detection performance has been investigated on real images captured under various illumination conditions for 1000 vehicles. 980 plates were correctly detected, and almost all non-detected plates were so stained that their characters could not be isolated for character recognition. In addition, the processing time is fast enough for a commercial automatic license plate recognition system. Therefore, the proposed method can be used for recognition systems with high performance and fast processing.

• Archives of Plastic Surgery
• /
• 제33권2호
• /
• pp.155-160
• /
• 2006

Although several reports have been introduced about dual plane augmentation mammaplasty, the description of periareolar approach dual plane augmentation mammaplasty was few. This article describes specific characteristics, and different classification and techniques for the periareolar dual plane breast augmentation while postoperative scars resulted from inframammary crease approach caused complaints. A total of 124 patients(248 breasts) had periareolar dual plane augmentation surgery from 1998 to 2004. Anatomic implants were used in 43 cases. Most of the patients were satisfied with the outcomes of periareolar dual plane augmentation. Periareolar dual plane augmentation mammaplasty adjusts implant and tissue relationships to ensure adequate soft-tissue coverage while optimizing implant-breast parenchymal dynamics to offer increased benefits and fewer faults compared to a single pocket location in a wide range of breast types with minimal scars. Two types of dual plane classifications are discussed in this study for the periareolar approach exclusively. The boundaries of retroglandular dissection remain constant, as the costal origin of pectoralis major are divided. Type A dual plane implies that the inferior edge of pectoralis muscle lies below the inferior areolar border, and type B dual plane implies that the inferior edge lies above the superior areolar border.

• 한국지역지리학회지
• /
• 제9권3호
• /
• pp.385-394
• /
• 2003

현장 접근이 제한되어 있는 동부해안 접경지역의 지형조사 과정에서 IKONOS 위성영상과 수치지도 등의 원격탐사자료와 현장조사 자료를 이용하여 지형분류를 시도하였다. 조사결과는 위성영상자료를 활용하여 조사지역 전체를 면사상의 단위지형으로 분류하였다. 조사지역에서 나타나는 특징적인 지형은 해안사주, 해안사구, 석호, 육계사주와 육계도 등으로 구성된 해안지형과 하천습지와 석호, 하구습지 등으로 구성된 습지지형이다. 이 일대의 지형은 규모에 비해 지형요소의 유기적인 안정성이 높아 그 가치가 높게 평가된다.

• 환경생물
• /
• 제23권3호
• /
• pp.215-220
• /
• 2005

Through multiple stage analysis, the biochores in Korea were classified and organized as a hierarchy system. In the 1st step, the isopleth lines of warmth index $100^{\circ}C,\;85^{\circ}C,\;55^{\circ}C\;\cdot$ month and the coldness index $-8^{\circ}C,\;or-10^{\circ}C\;\cdot$ month, which indicate the boundaries of plant formation zones (Yim and Kira 1975; Yim 1977), were applied in the determination of major biochores. In the 2nd step, these biochores were subdivided into the five classes based on Thornthwaite's moisture index (Im) and Yim and Kira (1976), as follows: $100{\le}Im,100 In the 3 rd step, the analysis of topographic features yielded three categories of flatlands, gentle slope, and steep slope areas. These were obtained by adopting the $100{\times}100-meter$ gridded DEM and by considering the physical features of the Korean Peninsula. The features of relief in mountainous areas, waters, islands, etc. were converted into climatic indices. This grouping of biochores serves as a useful tool for the interpretation of the distributional patterns of vegetation of vascular plants and similar phenomena.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2004년도 추계학술대회논문집
• /
• pp.625-632
• /
• 2004

This study presents the NDE (non-destructive evaluation) technique for detecting the loosened bolts on joint steel structures on the basis of TOF (time of flight) and amplitudes of Lamb waves. Probabilistic neural network (PNN) technique which is an effective tool for pattern classification problem was applied to the damage estimation using PZT induced Lamb waves. Two kinds of damages were introduced by dominant damages (DD) which mean loosened bolts within the Lamb waves beam width and minor damages (MD) which mean loosened bolts out of the Lamb waves beam width. They were investigated for the establishment of the optimal decision boundaries which divide each damage class's region including the intact class. In this study, the applicability of the probabilistic neural networks was identified through the test results for the damage cases within and out of wave beam path. It has been found that the present methods are very efficient and reasonable in predicting the loosened bolts on the joint steel structures probabilistically.