http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
필러 모델과 음소 모델 네트워크를 이용한 비인식 대상 문장 거부
이병혁,하진영 강원대학교 정보통신연구소 2005 정보통신논문지 Vol.9 No.-
Non-recognition utterance rejection is very important to improve the confidence of speech recognition system. Research efforts have been made for out-of-vocabulary word rejection. However, little attention has been paid to non-recognition sentence rejection. According to the appearance of pronunciation correction systems using speech recognition technology, it is needed to reject non-recognition sentences to provide users with more accurate and robust results. In this paper, we introduce three recognition network structures - phone-level, word-level, and sentence-level filler model network - using phone models and filler models to implement non-recognition sentence rejection system. We present three types of filler models: VC(Voiced Consonant), C(unvoiced Consonant), and V(Vowel) in the recognition network. Several experiments were performed to select the best network structure. We found that the word-level filler model network outperforms both phone-level model network and sentence-level filler model network. In addition, another experiment has been performed to find an optimal garbage ratio threshold according to the number of words in each target sentence. Experimental results show that we can achieve better performance using a length dependent threshold than using a constant threshold in terms of the average of FAR and FRR.
Byeong Hyeok Yu,Kwang Hoon Chi 大韓遠隔探査學會 2008 大韓遠隔探査學會誌 Vol.24 No.5
Many studies have generally used a large number of pure pixels as an approach to training set design. The training set are used, however, varies between classifiers. In the recent research, it was reported that small mixed pixels between classes are actually more useful than larger pure pixels of each class in Support Vector Machine (SVM) classification. We evaluated a usability of small mixed pixels as a training set for the classification of high-resolution satellite imagery. We presented an advanced approach to obtain a mixed pixel readily, and evaluated the appropriateness with the land cover classification from IKONOS satellite imagery. The results showed that the accuracy of the classification based on small mixed pixels is nearly identical to the accuracy of the classification based on large pure pixels. However, it also showed a limitation that small mixed pixels used may provide insufficient information to separate the classes. Small mixed pixels of the class border region provide cost-effective training sets, but its use with other pixels must be considered in use of high-resolution satellite imagery or relatively complex land cover situations.
( Byeong Hyeok Yu ),( Kwang Hoon Chi ) 대한원격탐사학회 2009 大韓遠隔探査學會誌 Vol.25 No.3
Multi-temporal satellite imagery can be changed into a transform image that emphasizes the changed area only through the application of various change detection techniques. From the transform image, an automated change detection model calculates the optimal threshold value for classifying the changed and unchanged areas. However, the model can cause undesirable results when the histogram of the transform image is unbalanced. This is because the model uses a single threshold value in which the sign is either positive or negative and its value is constant (e.g. -1, 1), regardless of the imbalance between changed pixels. This paper proposes an advanced method that can improve accuracy by applying separate threshold values according to the increased or decreased range of the changed pixels. It applies multiple threshold values based on the cumulative producer`s and user`s accuracies in the automated binary change detection model, and the analyst can automatically extract more accurate optimal threshold values. Multi-temporal IKONOS satellite imagery for the Daejeon area was used to test the proposed method. A total of 16 transformation results were applied to the two study sites, and optimal threshold values were determined using accuracy assessment curves. The experiment showed that the accuracy of most transform images is improved by applying multiple threshold values. The proposed method is expected to be used in various study fields, such as detection of illegal urban building, detection of the damaged area in a disaster, etc.
Byeong Hyeok Ye,Eun Jung Kim,Seung Eun Baek,Young Whan Choi,So Youn Park,Chi Dae Kim 대한생리학회-대한약리학회 2018 The Korean Journal of Physiology & Pharmacology Vol.22 No.4
α-Iso-cubebene (ICB) is a dibenzocyclooctadiene lignin contained in Schisandra chinensis (SC), a well-known medicinal herb that ameliorates cardiovascular symptoms, but the mechanism responsible for this activity has not been determined. To determine the role played by ICB on the regulation of vascular tone, we investigated the inhibitory effects of ICB on vascular contractile responses by adrenergic α-receptor agonists. In addition, we investigated the role on myosin light chain (MLC) phosphorylation and cytosolic calcium concentration in vascular smooth muscle cells (VSMC). In aortic rings isolated from C57BL/6J mice, ICB significantly attenuated the contraction induced by phenylephrine (PE) and norepinephrine (NE), whereas ICB had no effects on KCl (60 mM)-induced contraction. In vasculatures precontracted with PE, ICB caused marked relaxation of aortic rings with or without endothelium, suggesting a direct effect on VSMC. In cultured rat VSMC, PE or NE increased MLC phosphorylation and increased cytosolic calcium levels. Both of these effects were significantly suppressed by ICB. In conclusion, our results showed that ICB regulated vascular tone by inhibiting MLC phosphorylation and calcium flux into VSMC, and suggest that ICB has anti-hypertensive properties and therapeutic potential for cardiovascular disorders related to vascular hypertension.
Yu, Byeong-Hyeok,Chi, Kwang-Hoon The Korean Society of Remote Sensing 2008 大韓遠隔探査學會誌 Vol.24 No.5
Many studies have generally used a large number of pure pixels as an approach to training set design. The training set are used, however, varies between classifiers. In the recent research, it was reported that small mixed pixels between classes are actually more useful than larger pure pixels of each class in Support Vector Machine (SVM) classification. We evaluated a usability of small mixed pixels as a training set for the classification of high-resolution satellite imagery. We presented an advanced approach to obtain a mixed pixel readily, and evaluated the appropriateness with the land cover classification from IKONOS satellite imagery. The results showed that the accuracy of the classification based on small mixed pixels is nearly identical to the accuracy of the classification based on large pure pixels. However, it also showed a limitation that small mixed pixels used may provide insufficient information to separate the classes. Small mixed pixels of the class border region provide cost-effective training sets, but its use with other pixels must be considered in use of high-resolution satellite imagery or relatively complex land cover situations.
Yu, Byeong-Hyeok,Chi, Kwang-Hoon The Korean Society of Remote Sensing 2009 大韓遠隔探査學會誌 Vol.25 No.3
Multi-temporal satellite imagery can be changed into a transform image that emphasizes the changed area only through the application of various change detection techniques. From the transform image, an automated change detection model calculates the optimal threshold value for classifying the changed and unchanged areas. However, the model can cause undesirable results when the histogram of the transform image is unbalanced. This is because the model uses a single threshold value in which the sign is either positive or negative and its value is constant (e.g. -1, 1), regardless of the imbalance between changed pixels. This paper proposes an advanced method that can improve accuracy by applying separate threshold values according to the increased or decreased range of the changed pixels. It applies multiple threshold values based on the cumulative producer's and user's accuracies in the automated binary change detection model, and the analyst can automatically extract more accurate optimal threshold values. Multi-temporal IKONOS satellite imagery for the Daejeon area was used to test the proposed method. A total of 16 transformation results were applied to the two study sites, and optimal threshold values were determined using accuracy assessment curves. The experiment showed that the accuracy of most transform images is improved by applying multiple threshold values. The proposed method is expected to be used in various study fields, such as detection of illegal urban building, detection of the damaged area in a disaster, etc.