A multidimensional signal processing approach for classification of microwave measurements with application to stroke type diagnosis

Author

Mesri, Hamed Yousefi ; Najafabadi, Masoud Khazaeli ; McKelvey, Tomas

Author_Institution

Dept. of Signals & Syst., Chalmers Univ. of Technol., Gothenburg, Sweden

fYear

2011

fDate

Aug. 30 2011-Sept. 3 2011

Firstpage

6465

Lastpage

6469

Abstract

A multidimensional signal processing method is described for detection of bleeding stroke based on microwave measurements from an antenna array placed around the head of the patient. The method is data driven and the algorithm uses samples from a healthy control group to calculate the feature used for classification. The feature is derived using a tensor approach and the higher order singular value decomposition is a key component. A leave-one-out validation method is used to evaluate the properties of the method using clinical data.

Keywords

biomedical equipment; medical disorders; medical signal processing; microwave antenna arrays; microwave measurement; patient diagnosis; signal classification; tensors; antenna array; bleeding stroke detection; classification feature; data driven method; leave one out validation method; microwave measurement classification; multidimensional signal processing approach; stroke type diagnosis; tensor approach; Antenna measurements; Microwave FET integrated circuits; Microwave imaging; Microwave integrated circuits; Microwave measurements; Microwave theory and techniques; Tensile stress; HOSVD; classification; microwave scattering data; multichannel signal processing; multilinear algebra; Algorithms; Artificial Intelligence; Cerebral Hemorrhage; Decision Support Systems, Clinical; Decision Support Techniques; Electromagnetic Radiation; Equipment Design; Humans; Microwaves; Models, Statistical; Models, Theoretical; Scattering, Radiation; Signal Processing, Computer-Assisted; Stroke;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, EMBC, 2011 Annual International Conference of the IEEE

Conference_Location

Boston, MA

ISSN

1557-170X

Print_ISBN

978-1-4244-4121-1

Electronic_ISBN

1557-170X

Type

conf

DOI

10.1109/IEMBS.2011.6091596

Filename

6091596