TY - GEN
T1 - Brain tumour diagnosis with wavelets and Support Vector Machines
AU - Farias, G.
AU - Santos, M.
AU - López, V.
PY - 2008
Y1 - 2008
N2 - In this paper, a synergy of signal processing techniques and intelligent strategies is applied in order to identify different types of human brain tumours, so that to help to confirm the histological diagnosis. The Wavelet-SVM (Support Vector Machine) classifier merges wavelet transform to reduce the size of the biomedical spectra and to extract the main features, with SVM to classify them. The influence of some of the configuration parameters of each of those techniques on the clustering is analysed. The classification results are promising specially taking into account that medical knowledge has not been considered.
AB - In this paper, a synergy of signal processing techniques and intelligent strategies is applied in order to identify different types of human brain tumours, so that to help to confirm the histological diagnosis. The Wavelet-SVM (Support Vector Machine) classifier merges wavelet transform to reduce the size of the biomedical spectra and to extract the main features, with SVM to classify them. The influence of some of the configuration parameters of each of those techniques on the clustering is analysed. The classification results are promising specially taking into account that medical knowledge has not been considered.
UR - http://www.scopus.com/inward/record.url?scp=60349105954&partnerID=8YFLogxK
U2 - 10.1109/ISKE.2008.4731161
DO - 10.1109/ISKE.2008.4731161
M3 - Conference contribution
AN - SCOPUS:60349105954
SN - 9781424421978
T3 - Proceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008
SP - 1453
EP - 1459
BT - Proceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008
T2 - Proceedings of 2008 3rd International Conference on Intelligent System and Knowledge Engineering, ISKE 2008
Y2 - 17 November 2008 through 19 November 2008
ER -