论文信息 - Linear and non-linear speech features for detection of Parkinson's disease

Linear and non-linear speech features for detection of Parkinson's disease

Parkinson's disease (PD) was described by James Parkinson first time and it is now recognized as the second common neurological disorder after Alzheimer. Since most of the people with PD suffer form speech disorder, it is believed that speech analysis can be considered as the easiest way for PD detection. In this research, we try to use extracted features by genetic algorithm and ANFC for classifying between healthy and people with PD. Support vector machines (SVM) is applied as the classifier. Results show higher network accuracy of ANFC features compared to genetic algorithm features.

M. Shahbakhti | D. Taherifar | Atefeh Sorouri

[1] Joseph Picone,et al. Support vector machines for speech recognition , 1998, ICSLP.

[2] E. Růžička,et al. Investigation of non-linear properties of multichannel EEG in the early stages of Parkinson's disease , 2001, Clinical Neurophysiology.

[3] Christian Viard-Gaudin,et al. Comparison Of Support Vector Machine And Neural Network In Character Level Discriminant Training For Online Word Recognition , 2004 .

[4] Marius Ene,et al. Neural network-based approach to discriminate healthy people from those with Parkinson's disease , 2008 .

[5] Max A. Little,et al. Suitability of Dysphonia Measurements for Telemonitoring of Parkinson's Disease , 2008, IEEE Transactions on Biomedical Engineering.

[6] Magnus Johnsson,et al. Diagnosing Parkinson by using artificial neural networks and support vector machines , 2009 .

[7] Mehmet Fatih Çağlar,et al. Automatic Recognition of Parkinson's Disease from Sustained Phonation Tests Using ANN and Adaptive Neuro-Fuzzy Classifier , 2010 .

[8] R. Arefi Shirvan,et al. Voice analysis for detecting Parkinson's disease using genetic algorithm and KNN classification method , 2011, 2011 18th Iranian Conference of Biomedical Engineering (ICBME).