中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共3条，第1-3条

帮助

条数/页：排序方式：
	Is the aspect ratio of cells important in deep learning? A robust comparison of deep learning methods for multi-scale cytopathology cell image classification: From convolutional neural networks to visual transformers 期刊论文 OAI收割 Computers in Biology and Medicine, 2022, 卷号: 141, 页码: 1-13 作者: Liu, Wanli; Li C(李晨); Rahaman, Md Mamunur; Jiang, Tao; Sun, Hongzan \| 收藏 \| 浏览/下载：47/0 \| 提交时间：2021/12/20 Cervical cancer Deep learning Pap smear Aspect ratio of cells Visual transformer Robustness comparison
	A fuzzy control method based on information integration for double inverted pendulum (EI CONFERENCE) 会议论文 OAI收割 2011 2nd International Conference on Digital Manufacturing and Automation, ICDMA 2011, August 5, 2011 - August 7, 2011, Zhangjiajie, Hunan, China 作者: Fan Y. 收藏 \| 浏览/下载：66/0 \| 提交时间：2013/03/25 This article proposes a new fuzzy controller based on information integration. The mathematical model of Linear double inverted pendulum has been studied and estabLished with dynamics analytical method and LQR theory is used to design the optimal Linear inverted pendulum controller then the integration technology is used to design the variable parameters self-tuning fuzzy controller. Thereby the fuzzy controller input variable dimension and the number of fuzzy control rules have been extremely reduced. Two controllers are designed for inverted pendulum system control and the comparison simulation experiments have been done. The results show that the controllers can both reaLize good control and the fuzzy controller has higher precision faster response better stabiLity and robustness. 2011 IEEE.
	A new accurate and fast algorithm of sub-pixel image registration (EI CONFERENCE) 会议论文 OAI收割 2010 IEEE 10th International Conference on Signal Processing, ICSP2010, October 24, 2010 - October 28, 2010, Beijing, China 作者: He B. 收藏 \| 浏览/下载：31/0 \| 提交时间：2013/03/25 In terms of large field view and multi-channel TDICCD remote sensing images previous interpolation methods and curve fitting methods are not able to achieve the high accuracy and fast registration and their noise immunity and robustness is not high. For that this paper presents a more accurate and faster method iterative pixel interpolation and surface fitting method. Firstly the method uses the some overlapping pixels between multi-channel images. Secondly the proposed technique which is based on the maximization of the correlation coefficient function combines an efficient pixel-moving interpolation scheme with surface fitting which makes use of accurate interpolation calculation and fast surface fitting in the iterative process. Finally the accuracy and speed of the algorithm is evaluated by sub-pixel registration of multi-channel images and comparison with other sorts of efficient methods. The experiment results show that the accuracy of the method reaches 0.01 pixels and it is 3 times faster than the interpolation method. In the registration of large field view and multi-channel TDICCD images the method is accurate and fast with greatly high stability noise immunity and robustness. 2010 IEEE.