http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
김준철,정용한,박은수,최학남,김학일 제어로봇시스템학회 2008 제어로봇시스템학회 국내학술대회 논문집 Vol.2008 No.10
In this Paper, we present a faster more efficient object recognition method for moving robots. Recognizing places or objects in real time can be a difficult task due to many different features. To attain this task, we implemented a Parallel feature extract detector using OpenMP. In the first step, Algorithms and coeds are optimized in order to execute parallel processing. The processed algorithms in parallel are debugged for robust Performance. As a result, the intelligent conversion of the source codes to exploit OpenMP technology increase processing speed by two and half times over previous detectors while still maintaining robust performance measured using a standard evaluation set.
김준철,이준환 대한전자공학회 1994 전자공학회논문지-B Vol.b31 No.3
For the analysis of textured image, it requires large storage space and computation time to calculate the matrix features such as SGLDM(Spatial Gray Level Dependence Matrix). NGLDM(Neighboring Gray Level Dependence Matrix). NSGLDM(Neighboring Spatial Gray Level Dependence Matrix) and GLRLM(Gray Level Run Length Matrix). In spite of a large amount of information that each matrix contains, a set of several correlated scalar features calculated from the matrix is not sufficient to approximate it. In this paper, we propose a new classifier for textured images based on these matrices in which the projected vectors of each matrix on the meaningful directions are used as features. In the proposed method, an unknown image is classified to the class of a known image that gives the maximum similarity between the projected model vector from the known image and the vector from the unknown image. In the experiment to classify images of agricultural products, the proposed method shows good performance as much as 85-95% of correct classification ratio.
Alteration of Autonomic Function in Female Urinary Incontinence
김준철,주관중,김진태,최종보,조대성,Yong-Yeun Won 대한배뇨장애요실금학회 2010 International Neurourology Journal Vol.14 No.4
Purpose: Stress urinary incontinence (SUI) and urge urinary incontinence (UUI) have different mechanisms of action. We believe that alteration of autonomic nervous system (ANS) activity may contribute to UUI because the lower urinary tract is regulated through the sympathetic and parasympathetic nervous systems. Heart rate variability (HRV) allows measurement of autonomic nervous function, therefore we measured and compared HRV parameters in women with urinary incontinence. Methods: From March 2008 to March 2010, we evaluated all patients who visited 2 university hospitals for treatment of urinary incontinence. Theywere performed 3-day voiding diary, urodynamic study, physical examination and routine laboratory examination. We excluded subjects who had diabetes, cardiovascular problems, or other condition that affect ANS. Patients with mixed urinary incontinence (MUI) were also excluded. Finally 47 women with SUI (group 1) and 29 women with UUI (group 2) were enrolled according to their symptoms and voiding diary. We compared their HRV parameters. And excluding 11 patients who had detrusor underactivity, we divided them again into group A, 53 women without detrusor overactivity (DO) and group B, 12 women with DO. We compared HRV parameters between DO and non-DO group. Results: Older women had a higher incidence of UUI and DO. In HRV parameters, only the ratio of low frequency (LF) and high frequency (HF) was significantly higher in group 2 than group 1 (3.5±3.6 vs. 1.6±1.1, P<0.05). Also group A had higher mean LF/HF ratio than group B (4.3±3.8 vs. 1.9±1.9, P<0.05). Conclusions: Increased LF/HF values indicate relative sympathetic hyperactivity over parasympathetic activity. Changes in ANS activity could indicate the presence of UUI and potentially DO.