다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Co-Planar Stereotaxic Atlas of the Human Brain—3-Dimensional Proportional System: An Approach to Cerebral Imaging, J. Talairach, P. Tournoux. Georg Thieme Verlag, New York (1988), 122 pp., 130 figs. DM 268

BIOE 402. Medical Technology Assessment. 2 or 3 hours. Bioentrepreneur course. Assessment of medical technology in the context of commercialization. Objectives, competition, market share, funding, pricing, manufacturing, growth, and intellectual property; many issues unique to biomedical products. Course Information: 2 undergraduate hours. 3 graduate hours. Prerequisite(s): Junior standing or above and consent of the instructor.

“Bioinformatics” 특집을 내면서

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

A region-growing algorithm requires knowledge of the position of seed points in advance and must prespecify a threshold for the homogeneity test. Thus, the process of image segmentation by this algorithm cannot be implemented automatically, which often restricts its application in engineering practice. We propose an adaptive region-growing algorithm for automatically extracting small targets from an IR image. Using support vector regression (SVR), seed points can be detected automatically by regarding the intensity of an image as a surface. Furthermore, an adaptive threshold function is given as the criterion of the homogeneity test instead of a fixed threshold, as used in conventional region-growing algorithms. Our technique can extract small targets without human intervention. We carefully design many experiments to demonstrate its validity in extracting IR small targets.

Automatic extraction of infrared small target based on support vector regression and adaptive region growing algorithm

Recently, object tracking has been widely studied as a binary classification problem. Semi-supervised learning is particularly suitable for improving classification accuracy when large quantities of unlabeled samples are generated (just like tracking procedure). The purpose of this paper is to fulfill robust and stable tracking by using collaborative learning, which belongs to the scope of semi-supervised learning, among three classifiers. Different from [1], random fern classifier is incorporated to deal with 2bitBP feature newly added and certain constraints are specially implemented in our framework. Besides, the way for selecting positive samples is also altered by us in order to achieve more stable tracking. Algorithm proposed in this paper is validated by tracking pedestrian and cup under occlusion. Experiments and comparison show that our algorithm can avoid drifting problem to some degree and make tracking result more robust and adaptive.

The Extended Co-learning Framework for Robust Object Tracking

http://or.nsfc.gov.cn/bitstream/00001903-5/523308/1/1000013920920.pdf

A robust CPD approach based on shape context

The classic mean-shift tracker has no integrated scale adaptation, which limits its performance in tracking variable scale object as wel l as the object with severe motions. Based on the variation analysis of Bhattacharyya coefficient within mean-shift framework, the sufficient conditions for accurate tracking of object with scale changes are presented. We propose that the changes of object scale and position within the region of previous tracking window will not impact the localization accuracy of mean-shift tracker. Based on our findings, a novel backward tracking method is introduced to solve scaling problem, and the solution of dealing with the severe object motions is also discussed by integrating mean-shift tracker into the low-resolution matching scheme.

Study on Bhattacharyya Coefficients within Mean-Shift Framework and its Application

Recently, fully convolutional network (FCN) and dilated convolution have shown significantly improvment in semantic segmentation task. Deep residual network (ResNet) has shown strong ability in object recognition. However, FCN-based methods utilize intermediate layers and spatial context information ineffectively. Repeated 2-step striding in ResNet is harmful for segmentation tasks. In this paper, we propose a new semantic segmentation method based on FCN and ResNet. Here, we combine the dilated convolution designed for semantic segmentation with residual unit to enlarge receptive field of ResNet. Meanwhile, “pre-activation” method is used in dilated residual unit. We propose a new segmentation architecture which intergrate multiple intermediate layers and global context information. We extract low-level features of intermediate layers with multi-path refinement which consists of relu-conv unit and chained residual pooling. Global context is gathered by a pyramid pooling method which is connected to the final output of ResNet. Outputs of these 2 modules are then fused to reach high-resolution prediction. In this way, global and local information from pyramid pooling can be enhanced by multi-path refinement. Fully-connected conditional random field is added as a “post-processing” after fusion to receive accurate boundary performance. Our proposed approach achieves 74.7% IoU on Cityscapes benchmark.

Jie Yang

Papers

Automatic extraction of infrared small target based on support vector regression and adaptive region growing algorithm

The Extended Co-learning Framework for Robust Object Tracking

A robust CPD approach based on shape context

Study on Bhattacharyya Coefficients within Mean-Shift Framework and its Application

Semantic segmentation with multi-path refinement and pyramid pooling dilated-resnet