Search

Your search keyword '"Zhang, Jianfei"' showing total 34 results
Start Over Author "Zhang, Jianfei" Publisher ieee
34 results on '"Zhang, Jianfei"'

17. Survival Classification with Two-Tied Labeling of Censored Data

Author

Wang Shengrui, Bach Aurelien, and Zhang Jianfei

Subjects
020205 medical informatics, Artificial neural network, Computer science, business.industry, 02 engineering and technology, Logistic regression, Machine learning, computer.software_genre, Censoring (statistics), Support vector machine, 03 medical and health sciences, ComputingMethodologies_PATTERNRECOGNITION, 0302 clinical medicine, Risk groups, Survival probability, 0202 electrical engineering, electronic engineering, information engineering, 030212 general & internal medicine, Artificial intelligence, business, computer, Survival analysis
Abstract

Survival classification on time-to-event clinical data is useful in clinical research. Survival analysis techniques are widely used to predict the survival probability over time that a particular event occurs. It is crucial to identify the risk of experiencing the event for patients, which can be achieved by classifying risk groups of patients. However, the existing classification methods, such as logistic regression, support vector machines and artificial neural network, cannot be applied to clinical data directly, due to the context of censoring. To address this problem, we propose a new two-tied labeling approach for reformulating the clinical data and make classifiers available to process such data. We perform such labeling on real-life clinical data and the good performances achieved by the classification methods reveal the great promise of our approach for risk group classification.

Published
2018

22. A Pulsed Approach for Electrical Impedance Spectroscopy Measurement

Author

Guo Wei, Dong Ensheng, Jiang Yilin, and Zhang Jianfei

Subjects
Engineering, business.industry, Acoustics, System of measurement, Chip, Dielectric spectroscopy, Sampling (signal processing), Hardware_GENERAL, Electrode, Electronic engineering, business, Spectroscopy, Electrical impedance, Electronic circuit
Abstract

A pulsed method for impedance spectroscopy measurement, different from the traditional swept frequency methods, is presented. A string of square-wave pulses is digitally generated as the excitation signal to the sensing electrodes. A pulsed measurement system is described. A sample-collecting method for sampling the instantaneous response signals is implemented based on a field programmable gate arrays chip. The sampled data is further processed to obtain the impedance spectrum. Experiments are carried out for the measurement of electrical impedance spectroscopy of the demo electric circuits in order to inspect the feasibility of the pulsed measurement system. The preliminary experimental results indicate that the pulsed measurement system can effectively extract the electrical impedance spectroscopy information of the object detected. The proposed approach is feasible for evaluating the electrical impedance spectroscopy of the object detected.

Published
2010

24. Research on Edge Detection for Image Based on Wavelet Transform

Author

Zhou Wenjun, Zhang Jianfei, Xie Zidian, Sun Changli, and Hua Chunmei

Subjects
Discrete wavelet transform, business.industry, Computer science, Stationary wavelet transform, Second-generation wavelet transform, ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION, Wavelet transform, ComputerApplications_COMPUTERSINOTHERSYSTEMS, Pattern recognition, Deriche edge detector, Edge detection, Wavelet packet decomposition, Canny edge detector, Computer vision, Artificial intelligence, business
Abstract

The edge detection for images based on traditional wavelet analysis has the disadvantage of not being sensitive to direction properties, so aimed at the problem the article makes some improvement and puts forward a new kind of wavelet transform used for image edge detection. Compared with the detection based on Canny operator, it can be concluded that the new kind of edge detection based on wavelet transform can obtain complete image edge as well as accurate positioning and can reserve better detail information.

Published
2009

33. Switch-Centric Data Center Network Structures Based on Hypergraphs and Combinatorial Block Designs.

Author

Qu, Guannan, Fang, Zhiyi, Zhang, Jianfei, and Zheng, Si-Qing

Subjects
ROUTING (Computer network management), SWITCHING circuits, SCALABILITY, COMPUTER networks, HYPERGRAPHS, BIPARTITE graphs, COMBINATORIAL optimization, DATA libraries
Abstract

Fat trees are considered suitable structures for data center interconnection networking. Such structures are rigid, and hard to scale up and scale out. A good data center network structure should have high scalability, efficient switch utilization, and high reliability. In this paper we present a class of data center network structures based on hypergraph theory and combinatorial block design theory. We show that our data center network structures are more flexible and scalable than fat trees. Using switches of the same size, our data center network structures can connect more nodes than fat trees, and it is possible to construct different structures with tradeoffs among inter-cluster communication capacity, reliability, the number of switches used, and the number of connected nodes. [ABSTRACT FROM AUTHOR]

Published
2015
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results