Abstract
Machine learning-based Parkinson’s disease (PD) speech diagnosis is a current research hotspot. However, existing methods use each corpus sample as the base unit for modeling. Since different corpus samples within the same subject have different sensitive speech features, it is difficult to obtain unified and stable sensitive speech features (diagnostic markers) that reflect the pathology of the whole subject. Therefore, this study aims at compressing the corpus samples within the subject to facilitate the search for diagnostic markers with high diagnostic accuracy. A two-step sample compression module (TSCM) can solve the problem above. It includes two major parts: sample pruning module (SPM) and sample fuzzy clustering mechanism (SFCMD). Based on stacking multiple TSCMs, a multilayer sample compression module (MSCM) is formed to obtain multilayer compression samples. After that, simultaneous sample/feature selection mechanism (SS/FSM) is designed for feature selection. Based on the multilayer compression samples processed by MSCM and SS/FSM, a novel ensemble learning algorithm (EMSFE) is designed with sparse fusion ensemble learning mechanism (SFELM). The proposed EMSFE is validated by visualization of extracted features and performance comparison with related algorithms. The experimental results show that the proposed algorithm can effectively extract the stable diagnostic markers by compressing the corpus samples within the subject. Furthermore, based on LOSO cross validation, the proposed algorithm with extreme learning machine (ELM) classifier can achieve the accuracy of 92.5%, 93.75% and 91.67% on three datasets, respectively. The proposed EMSFE can extract unified and stable sensitive features that accurately reflect the overall pathology of the subject, which can better meet the requirements of clinical applications.
The code and datasets can be found in: https://github.com/wywwwww/EMSFE-supplementary-material.git
Graphical Abstract
Main flowchart of the proposed algorithm
Similar content being viewed by others
Data availability
All the experimental results are shown in the supplementary material. The supplementary material, source code, and the datasets utilized in this study can be found in GitHub (https://github.com/wywwwww/EMSFE-supplementary-material.git).
References
Arkinson C, Walden H (2018) Parkin function in Parkinson’s disease. Science 360(6386):267–268
Narendra NP, Schuller B, Alku P (2021) The detection of Parkinson’s disease from speech using voice source information. IEEE/ACM Trans Audio Speech Lang Process 29:1925–1936
Quan CQ, Ren K, Luo ZW (2021) A deep learning based method for Parkinson’s disease detection using dynamic features of speech. IEEE Access 9:10239–10252
Kodrasi I, Bourlard H (2020) Spectro-temporal sparsity characterization for dysarthric speech diagnosis. IEEE/ACM Trans Audio Speech Lang Process 28:1210–1222
Liu YC, Li YM, Tan XH, Wang P, Zhang YL (2021) Local discriminant preservation projection embedded ensemble learning based dimensionality reduction of speech data of Parkinson’s disease. Biomed Signal Proces 63:102165.1-102165.13
Peker M, En B, Delen D (2015) Computer-aided diagnosis of Parkinson’s disease using complex-valued neural networks and mRMR feature selection algorithm. J Healthcare Eng 6(3):281–302
Viswanathan R, Arjunan SP, Kempster P, Raghav S, Kumar D (2020) Estimation of Parkinson’s disease severity from voice features of vowels and consonant. In: Proc. IEEE EMBC. Montreal, vol. 27, pp 3666–3669
Kursun O, Gumus E, Sertbas A, Favorov OV (2012) Selection of vocal features for Parkinson’s disease diagnosis. Int J Data Min Bioinform 6(2):144–161
Cai ZN, Gu JH, Chen HL (2017) A new hybrid intelligent framework for predicting Parkinson’s disease. IEEE Access 5:17188–17200
Ali L, Zhu C, Zhang ZH, Liu YP (2019) Automated detection of Parkinson’s disease based on multiple types of sustained phonations using linear discriminant analysis and genetically optimized neural network. IEEE J Transl Eng He 7(99):1–10
Al-Fatlawi AH, Jabardi MH, Ling SH (2016) Efficient diagnosis system for Parkinson’s disease using deep belief network. In: Proc. IEEE CEC. Vancouver, pp 1324–1330
Gürüler H (2017) A novel diagnosis system for Parkinson’s disease using complex-valued artificial neural network with k-means clustering feature weighting method. Neural Comput Applic 28(7):1657–1666
Kadam VJ, Jadhav SM (2019) Feature ensemble learning based on sparse autoencoders for diagnosis of Parkinson’s disease. In: Conf. Proc. Comput. Commu. Signal Process., Singapore, vol. 810, pp 567–581
Grover S, Bhartia S, Akshama, Yadav A, Seeja KR (2018) Predicting severity of Parkinson’s disease using deep learning. Int Conf Comput Intell Data Sci 132:1788–1794
Oguz FE, Alkan A, Schoeler T (2023) Emotion detection from ECG signals with different learning algorithms and automated feature engineering. Signal Image Video P. [Online]. Available: https://link.springer.com/article/10.1007/s11760-023-02606-y
Sunnetci KM, Ulukaya S, Alkan A (2022) Periodontal bone loss detection based on hybrid deep learning and machine learning models with a user-friendly application. Biomed Signal Proces 77:103844.1-103844.11
Luo JH, Wong CM, Vong CM (2021) Multinomial Bayesian extreme learning machine for sparse and accurate classification model. Neurocomputing 423:24–33
Xue ZF, Zhang T, Lin LQ (2022) Progress prediction of Parkinson’s disease based on graph wavelet transform and attention weighted random forest. Expert Syst Appl 203:117483.1-117483.18
Sakar BE et al (2013) Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings. IEEE J Biomed Health Inf 17(4):828–834
Li YM et al (2017) Simultaneous learning of speech feature and segment for classification of Parkinson disease. In: Proc. IEEE Healthcom,pp 12–15
Li YM, Liu CY, Wang P, Zhang HH, Wei AH, Zhang YL (2022) Envelope multi-type transformation ensemble algorithm of Parkinson speech samples. ApplIntell. [Online]. Available: https://link.springer.com/article/10.1007/s10489-022-04345-y
Sunnetci KM, Alkan A (2023) Biphasic majority voting-based comparative COVID-19 diagnosis using chest X-ray images. Expert Syst Appl 216:119430.1-119430.14
Tsanas A, Little MA, Mcsharry PE, Spielman J, Ramig LO (2012) Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s Disease. IEEE T Biomed Eng 59(5):1264–1271
Li F, Zhang XH, Wang P, Li YM (2022) Deep instance envelope network-based imbalance learning algorithm with multilayer fuzzy C-means clustering and minimum interlayer discrepancy. Appl Soft Comput 123:108846.1-108846.18
Sunnetci KM, Kaba E, Celiker FB, Alkan A (2023) Deep network-based comprehensive parotid gland tumor detection. Acad Radiol. [Online]. https://doi.org/10.1016/j.acra.2023.04.028
Canturk I, Karabiber F (2016) A machine learning system for the diagnosis of Parkinson’s disease from speech signals and its application to multiple speech signal types. Arab J Sci Eng 41(12):5049–5059
Zhang HH et al (2016) Classification of Parkinson’s disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples. Biomed Eng Online 15(1):122–143
Benba A, Jilbab A, Hammouch A (2017) Using human factor cepstral coefficient on multiple types of voice recordings for detecting patients with Parkinson’s disease. IRBM 38(6):346–351
Benba A, Jilbab A, Hammouch A (2016) Analysis of multiple types of voice recordings in cepstral domain using MFCC for discriminating between patients with Parkinsons disease and healthy people. Int J Speech Technol 19(3):449–456
Behroozi M, Sami A (2016) A multiple-classifier framework for Parkinson’s disease detection based on various vocal tests. Int J Telemed Appl 2016:6837498
Zhang YN (2017) A deep neural network method and telediagnosis system implementation. Parkinsons Dis 2017:1–11
Khan MM, Mendes A, Chalup SK (2018) Evolutionary wavelet neural network ensembles for breast cancer and Parkinson’s disease prediction. Plos One 13(2):e0192192.1-e0192192.15
Soumaya Z, Taoufiq BD, Benayad N, Yunus K, Abdelkrim A (2021) The detection of Parkinson disease using the genetic algorithm and SVM classifier. Appl Acoust 171:107528.1-107528.10
Luukka P (2011) Feature selection using fuzzy entropy measures with similarity classifier. Expert Syst Appl 38(4):4600–4607
Spadoto AA et al (2011) Improving Parkinson's disease identification through evolutionary-based feature selection. In: Conf. Proc. IEEE Eng. Med. Biol. Soc., Boston, pp 7857–7860
Das R (2010) A comparison of multiple classification methods for diagnosis of Parkinson disease. Expert Syst Appl 37(2):1568–1572
Daliri MR (2013) Chi-square distance kernel of the gaits for the diagnosis of Parkinson’s disease. Biomed Signal Process Control 8(1):66–70
Kadam VJ, Jadhav SM (2019) Feature ensemble learning based on sparse autoencoders for diagnosis of Parkinson’s disease. In: Proc. ICCASP, Singapore, vol. 810, pp 567–581
Senturk ZK (2020) Early diagnosis of Parkinson’s disease using machine learning algorithms. Med. Hypotheses 138:109603.1-109603.5
Sharma P, Sundaram S, Sharma M, Sharma A, Gupta D (2019) Diagnosis of Parkinson’s disease using modified grey wolf optimization. Cogn Syst Res 54:100–115
Despotovic V, Skovranek T, Schommer C (2020) Speech based estimation of Parkinson’s disease using gaussian processes and automatic relevance determination. Neurocomputing 401:173–181
Lamba R, Gulati T, Alharbi HF, Jain A (2021) A hybrid system for Parkinson’s disease diagnosis using machine learning techniques. Int J Speech Technol 25:583–593
Yang SS et al (2014) Effective dysphonia detection using feature dimension reduction and kernel density estimation for patients with Parkinson’s disease. Plos One 9(2):e88825.1-e88825.10
Galaz Z et al (2016) Prosodic analysis of neutral, stress-modified and rhymed speech in patients with Parkinson’s disease. Comput Meth Prog Bio 127:301–317
Cigdem O, Demirel H (2018) Performance analysis of different classification algorithms using different feature selection methods on Parkinson’s disease detection. J Neurosci Meth 309:81–90
Acknowledgements
We are grateful for the support of the National Natural Science Foundation of China NSFC (No. 61771080, U21A20448); Basic and Advanced Research Project in Chongqing (cstc2020jscx-gksbx0009, cstc2020jcyj-msxmX0523, CSTB2021TIAD-KPX0069, and cstc2020jscx-msxm0369); Central university basic scientific research operation cost special fund (2022CDJJJ-003).
Author information
Authors and Affiliations
Contributions
Y.M. Li and P. Wang: Supervision, Conceptualization, Methodology, Software, Writing—review & editing, Writing—original draft; Y.W. Wang, F. Li, and X.H. Zhang: Methodology, Software, Formal analysis, Writing—original draft; Y.L. Zhang managed the trials and assisted with writing discussions in the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Conflict of interest
The authors declare no conflicts of interest pertaining to this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
Appendix
Appendix
The objective function of SFCMD is expressed as follows:
In the SFCMD model there are two variables \({\varvec{U}}\) and \({\varvec{V}}\) that need to be optimized, so an effective alternating variable optimization strategy can be considered to optimize the solution, i.e., to solve for one variable while fixing the other variable constant. Therefore, in solving the objective function, \({\varvec{V}}\) and \({\varvec{U}}\) can be fixed in turn and solved using the gradient descent method for the other variable, and the optimization details are specified as follows.
-
1)
Fixing \({\varvec{V}}\) to solve \({\varvec{U}}\).
By fixed \({\varvec{V}}\), the problem is solved with respect to \({\varvec{U}}\). After removing the terms unrelated to \({\varvec{U}}\), the objective function is transformed into (13).
$${J}_{1}\left({\varvec{U}},{\varvec{V}}\right)=\underset{{\varvec{U}},{\varvec{V}}}{\mathrm{min}}\sum_{i=1}^{C}\sum_{k=1}^{{N}^{\mathrm{^{\prime}}}}{\left({u}_{ik}\right)}^{m}{\Vert {{\varvec{x}}}_{k}-{{\varvec{v}}}_{i}\Vert }^{2}+\lambda \left(\sum_{i=1}^{C}{u}_{ik}-1\right)$$(13)Solve for the minimalist solution of (13).
$$\frac{{\partial J}_{1}\left({\varvec{U}},{\varvec{V}}\right)}{\partial {u}_{ik}}=m{\left({u}_{ik}\right)}^{m-1}{\Vert {{\varvec{x}}}_{k}-{{\varvec{v}}}_{i}\Vert }^{2}+\lambda =0$$(14)By calculation, the partition matrix is obtained as follows.
$${u}_{ik}=\frac{{\Vert {{\varvec{x}}}_{k}-{{\varvec{v}}}_{i}\Vert }^{-\frac{2}{m-1}}}{\sum_{w=1}^{C}{\Vert {{\varvec{x}}}_{k}-{{\varvec{v}}}_{i}\Vert }^{-\frac{2}{m-1}}}$$(15) -
2)
Fixing \({\varvec{U}}\) to solve \({\varvec{V}}\).
By fixed \({\varvec{U}}\), the problem is solved with respect to \({\varvec{V}}\). After removing the terms unrelated to \({\varvec{V}}\), the objective function is transformed into (16).
$$\begin{array}{l} J_{2} ({\varvec{U}},{\varvec{V}}) = \mathop {\min }\limits_{{{\varvec{U}},{\varvec{V}}}} \sum\limits_{{i{ = }1}}^{C} {\sum\limits_{{k{ = }1}}^{{N^{\prime} }} {\left( {u_{ik} } \right)^{m} \left\| {{\varvec{x}}_{k} - {\varvec{v}}_{i} } \right\|^{2} } } \hfill \\ + \frac{1}{{{N^{\prime}}^{2} }}\sum\limits_{{k{ = }1}}^{{N^{\prime} }} {\sum\limits_{{k^{\prime} { = }1}}^{{N^{\prime} }} {\kappa \left( {{\varvec{x}}_{k} ,{\varvec{x}}_{{k^{\prime} }} } \right)} } - \frac{2}{{N^{\prime} C}}\sum\limits_{{k{ = }1}}^{{N^{\prime} }} {\sum\limits_{{i{ = }1}}^{C} {\kappa \left( {{\varvec{x}}_{k} ,{\varvec{v}}_{i} } \right)} } + \frac{1}{{C^{2} }}\sum\limits_{{i{ = }1}}^{C} {\sum\limits_{{i^{\prime} { = }1}}^{C} {\kappa \left( {{\varvec{v}}_{i} ,{\varvec{v}}_{{i^{\prime} }} } \right)} } \hfill \\ \end{array}$$(16)Based on the kernel function \(\kappa \left({{\varvec{x}}}_{k},{{\varvec{v}}}_{i}\right)={{{\varvec{x}}}_{k}}^{T}{{\varvec{v}}}_{i}\) to solve the minimum solution of (16).
$$\frac{{\partial J_{2} \left( {{\varvec{U}},{\varvec{V}}} \right)}}{{\partial {\varvec{v}}_{i} }} = - 2\sum\limits_{{k{ = }1}}^{{N^{\prime} }} {\left( {u_{ik} } \right)^{m} } \left( {{\varvec{x}}_{k} - {\varvec{v}}_{i} } \right) - \frac{2}{{N^{\prime} C}}\sum\limits_{{k{ = }1}}^{{N^{\prime} }} {{\varvec{x}}_{k} } + \frac{2}{{C^{2} }}\sum\limits_{{i{ = }1}}^{C} {{\varvec{v}}_{i} } = 0$$(17)The envelope compressed by SFCMD is obtained from (18).
$${\varvec{V}} = {\varvec{A}}^{ - 1} \left[ {\begin{array}{*{20}c} {b_{1} } \\ {b_{2} } \\ \vdots \\ {b_{C} } \\ \end{array} } \right]$$(18)Among them:
$${\varvec{A}} = diag\left( {a_{1} ,a_{2} ,...,a_{C} } \right) + \frac{1}{{C^{2} }} * {\varvec{I}}$$$$a_{i} = \sum\limits_{k = 1}^{{N^{\prime} }} {\left( {u_{ik} } \right)^{m} ,b_{i} = \sum\limits_{k = 1}^{{N^{\prime} }} {\left[ {\left( {u_{ik} } \right)^{m} + \frac{1}{{N^{\prime} C}}} \right]} } * {\varvec{x}}_{k} ,i = 1,2,...,C$$
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Wang, Y., Li, F., Zhang, X. et al. Intra-subject enveloped multilayer fuzzy sample compression for speech diagnosis of Parkinson's disease. Med Biol Eng Comput 62, 371–388 (2024). https://doi.org/10.1007/s11517-023-02944-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11517-023-02944-6