http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
최수영 ( Soo Young Choi ),이인용 ( In Yong Lee ),손정호 ( Jung Ho Shon ),이용원 ( Yong Won Lee ),신수희 ( Soo Hee Shin ),이득희 ( Deuk Hee Lee ),김평환 ( Pyoung Hwan Kim ),용태순 ( Tai Soon Yong ),홍천수 ( Chein Soo Hong ),박중원 대한천식알레르기학회 2006 천식 및 알레르기 Vol.26 No.4
Background and Objective: Mechanical laundry has a key role for environmental control of allergens. However, the optimal conditions for removing allergens such as house dust mite (HDM), dog dander, and pollens are not yet clear. Method: Four cleaning modes such as 30℃, 40℃, 60℃, and steam (adapt steam and water cleaning) were evaluated. Viability of HDM was assayed with heat escape method and levels of group 1 major allergens of D. farinae (Der f 1) and dog dander (Can f 1) were assayed with 2-site ELISA. Levels of pollen protein were assayed with Bradford method. Result: At 60℃ and steam cleaning modes, all HDM were dead but at 30∼40℃ modes, only 6.4∼9.3% of HDM were dead. The levels of Der f 1 in extraction buffers immediately after 30℃, 40℃, 60℃, and steam cleaning were 26.8%, 2.4%, 1.3%, and 0.6%, respectively. The levels of Can f 1 were 41.5%, 42.7%, 12.6%, 9.8% and the pollen protein levels were 31.8%, 4.9%, 3.9%, and 2.8%, respectively. Conclusion: Steam and 60℃ cleaning is better than 30∼40℃ cleaning for removing indoor and pollen allergens. (Korean J Asthma Allergy Clin Immunol 2006;26:289-296)
박정원,김평환,김창근,허강인 동아대학교 정보기술연구소 2003 情報技術硏究所論文誌 Vol.11 No.1
In this paper, we propose effective speaker verification method using SVM(support vector machines) and ICAhdependent component analysis). In general, SVM is classification method which classify two class set by finding voluntary nonlinear boundary in vector space and possesses high classification performance under few training data number. In this paper, we compare existing algorithms with SVM, and we compare verification performance of feature parameters using ICA, PCA(principa1 component analysis), MFCC(mel frequency cepstrum coefficient) for SVM speaker verification system. In result, ICA feature parameter showed the highest verification performance because of superior linear classification.