Deep Double-Side Learning Ensemble Model for Few-Shot Parkinson Speech Recognition

Diagnosis and therapeutic effect assessment of Parkinson disease based on voice data are very important,but its few-shot learning problem is challenging.Although deep learning is good at automatic feature extraction, it suffers from few-shot learning problem. Therefore, the general effective method is first conduct feature extraction based on prior knowledge, and then carry out feature reduction for subsequent classification. However, there are two major problems: 1) Structural information among speech features has not been mined and new features of higher quality have not been reconstructed. 2) Structural information between data samples has not been mined and new samples with higher quality have not been reconstructed. To solve these two problems, based on the existing Parkinson speech feature data set, a deep double-side learning ensemble model is designed in this paper that can reconstruct speech features and samples deeply and simultaneously. As to feature reconstruction, an embedded deep stacked group sparse auto-encoder is designed in this paper to conduct nonlinear feature transformation, so as to acquire new high-level deep features, and then the deep features are fused with original speech features by L1 regularization feature selection method. As to speech sample reconstruction, a deep sample learning algorithm is designed in this paper based on iterative mean clustering to conduct samples transformation, so as to obtain new high-level deep samples. Finally, the bagging ensemble learning mode is adopted to fuse the deep feature learning algorithm and the deep samples learning algorithm together, thereby constructing a deep double-side learning ensemble model. At the end of this paper, two representative speech datasets of Parkinson's disease were used for verification. The experimental results show that the proposed algorithm are effective.

[1]  Akash Tayal,et al.  Determination of Parkinson’s disease utilizing Machine Learning Methods , 2018, 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN).

[2]  J. Paralič,et al.  Parkinson's disease patients classification based on the speech signals , 2017, 2017 IEEE 15th International Symposium on Applied Machine Intelligence and Informatics (SAMI).

[3]  Bart Baesens,et al.  A multi-objective approach for profit-driven feature selection in credit scoring , 2019, Decis. Support Syst..

[4]  M. Dougherty,et al.  Classification of speech intelligibility in Parkinson's disease , 2014 .

[5]  Ashkan Sami,et al.  A Multiple-Classifier Framework for Parkinson's Disease Detection Based on Various Vocal Tests , 2016, International journal of telemedicine and applications.

[6]  Gang Wang,et al.  An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach , 2013, Expert Syst. Appl..

[7]  Yongming Li,et al.  Classification of Parkinson’s disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples , 2016, BioMedical Engineering OnLine.

[8]  Martine Labbé,et al.  Mixed Integer Linear Programming for Feature Selection in Support Vector Machine , 2018, Discret. Appl. Math..

[9]  M. Hariharan,et al.  A new hybrid intelligent system for accurate detection of Parkinson's disease , 2014, Comput. Methods Programs Biomed..

[10]  Hananel Hazan,et al.  Computational Diagnosis of Parkinson's Disease Directly from Natural Speech Using Machine Learning Techniques , 2014, 2014 IEEE International Conference on Software Science, Technology and Engineering.

[11]  Max A. Little,et al.  Novel Speech Signal Processing Algorithms for High-Accuracy Classification of Parkinson's Disease , 2012, IEEE Transactions on Biomedical Engineering.

[12]  Omer Eskidere,et al.  Detection of Parkinson's disease from vocal features using random subspace classifier ensemble , 2015, 2015 Twelve International Conference on Electronics Computer and Computation (ICECCO).

[13]  Keh-Shih Chuang,et al.  Dynamic feature selection for detecting Parkinson's disease through voice signal , 2015, 2015 IEEE MTT-S 2015 International Microwave Workshop Series on RF and Wireless Technologies for Biomedical and Healthcare Applications (IMWS-BIO).

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

[15]  A. Benba,et al.  Hybridization of best acoustic cues for detecting persons with Parkinson's disease , 2014, 2014 Second World Conference on Complex Systems (WCCS).

[16]  Y. Zhang Can a Smartphone Diagnose Parkinson Disease? A Deep Neural Network Method and Telediagnosis System Implementation , 2017, Parkinson's disease.

[17]  Ce Zhu,et al.  Automated Detection of Parkinson’s Disease Based on Multiple Types of Sustained Phonations Using Linear Discriminant Analysis and Genetically Optimized Neural Network , 2019, IEEE Journal of Translational Engineering in Health and Medicine.

[18]  Anil K. Jain,et al.  Artificial neural networks for feature extraction and multivariate data projection , 1995, IEEE Trans. Neural Networks.

[19]  Max A. Little,et al.  Accurate Telemonitoring of Parkinson's Disease Progression by Noninvasive Speech Tests , 2009, IEEE Transactions on Biomedical Engineering.

[20]  Zhizhong Mao,et al.  Bagging ensemble of SVM based on negative correlation learning , 2009, 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems.

[21]  Alexandre Mendes,et al.  Evolutionary Wavelet Neural Network ensembles for breast cancer and Parkinson’s disease prediction , 2018, PloS one.

[22]  Max A. Little,et al.  Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection , 2007, Biomedical engineering online.

[23]  Rabab Kreidieh Ward,et al.  Using deep stacking network to improve structured compressed sensing with Multiple Measurement Vectors , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[24]  Fikret S. Gürgen,et al.  Collection and Analysis of a Parkinson Speech Dataset With Multiple Types of Sound Recordings , 2013, IEEE Journal of Biomedical and Health Informatics.

[25]  Pawalai Kraipeerapun,et al.  Using stacked generalization and complementary neural networks to predict Parkinson's disease , 2015, 2015 11th International Conference on Natural Computation (ICNC).

[26]  Max A. Little,et al.  Accurate telemonitoring of Parkinson’s disease progression by non-invasive speech tests , 2009 .

[27]  Musa Peker,et al.  Computer-Aided Diagnosis of Parkinson's Disease Using Complex-Valued Neural Networks and mRMR Feature Selection Algorithm. , 2015, Journal of healthcare engineering.

[28]  Max A. Little,et al.  Objective Automatic Assessment of Rehabilitative Speech Treatment in Parkinson's Disease , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[29]  Ping Wang,et al.  Simultaneous learning of speech feature and segment for classification of Parkinson disease , 2017, 2017 IEEE 19th International Conference on e-Health Networking, Applications and Services (Healthcom).

[30]  Ahmed Hammouch,et al.  Using Human Factor Cepstral Coefficient on Multiple Types of Voice Recordings for Detecting Patients with Parkinson's Disease , 2017 .

[31]  WangGang,et al.  An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach , 2013 .

[32]  Ahmed Hammouch,et al.  Analysis of multiple types of voice recordings in cepstral domain using MFCC for discriminating between patients with Parkinson’s disease and healthy people , 2016, International Journal of Speech Technology.

[33]  Olcay Kursun,et al.  Telediagnosis of Parkinson’s Disease Using Measurements of Dysphonia , 2010, Journal of Medical Systems.

[34]  F. Cavallo,et al.  Comparative Motor Pre-clinical Assessment in Parkinson’s Disease Using Supervised Machine Learning Approaches , 2018, Annals of Biomedical Engineering.

[35]  Jian Yang,et al.  Visual Representation and Classification by Learning Group Sparse Deep Stacking Network , 2018, IEEE Transactions on Image Processing.

[36]  Mohd Dilshad Ansari,et al.  On K-means data clustering algorithm with genetic algorithm , 2016, 2016 Fourth International Conference on Parallel, Distributed and Grid Computing (PDGC).

[37]  Stuart I. Herbert,et al.  Computer Methods and Programs in Biomedicine 48 (1995) 21-26 , 1995 .

[38]  Fethullah Karabiber,et al.  A Machine Learning System for the Diagnosis of Parkinson’s Disease from Speech Signals and Its Application to Multiple Speech Signal Types , 2016, Arabian Journal for Science and Engineering.

[39]  Aarushi Agarwal,et al.  Prediction of Parkinson's disease using speech signal with Extreme Learning Machine , 2016, 2016 International Conference on Electrical, Electronics, and Optimization Techniques (ICEEOT).