Deep dual-side learning ensemble model for Parkinson speech recognition

•A deep sample learning algorithm (DSL) is constructed for PD speech feature data.•An embedded deep stack group sparse autoencoder (EGSAE) is designed for PD speech data.•Deep dual-side learning ensemble model is constructed by combining EGSAE and DSL.•Both the diagnosis and automatic assessment of...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Biomedical signal processing and control Ročník 69; s. 102849
Hlavní autoři: Ma, Jie, Zhang, Yuanfan, Li, Yongming, Zhou, Lang, Qin, Lingyun, Zeng, Yuwei, Wang, Pin, Lei, Yan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.08.2021
Témata:
ISSN:1746-8094, 1746-8108
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract •A deep sample learning algorithm (DSL) is constructed for PD speech feature data.•An embedded deep stack group sparse autoencoder (EGSAE) is designed for PD speech data.•Deep dual-side learning ensemble model is constructed by combining EGSAE and DSL.•Both the diagnosis and automatic assessment of treatment of PD speech data are considered. Early diagnosis of Parkinson's disease (PD) is very important Kansara et al. (2013) and Stern (1993). In recent years, machine learning-based speech data analysis has been shown to be effective for diagnosing Parkinson's disease (PD) and automatically assessing rehabilitative speech treatment in PD Sakar et al. (2013), Tsanas et al. (2012) and Little et al. (2009). Machine learning includes feature learning and sample learning. Deep learning (deep feature learning) can generate high-level and high-quality features through deep feature transformation, improving classification accuracy. For reasons such as data collection, some samples have low quality for classification. Therefore, sample learning is necessary. Sample selection removes useless samples; therefore, deep sample learning is better, since it can generate high-level and high-quality samples through deep sample transformation. However, there are no public studies about deep sample learning. To solve the problem above, a deep dual-side learning ensemble model is designed in this paper. In this model, a deep sample learning algorithm is designed and combined with a deep network (deep feature learning), thereby realizing the deep dual-side learning of PD speech data. First, an embedded stack group sparse autoencoder is designed in this paper to conduct deep feature learning to acquire new high-level deep feature data. Second, the deep features are fused with original speech features by L1 regularization feature selection methods, thereby constructing hybrid feature data. Third, an iterative mean clustering algorithm (IMC) was designed, thereby constructing a deep sample learning algorithm and conducting deep sample transformation. After that step, hierarchical sample spaces are constructed based on a deep sample learning algorithm, and the classification models are constructed on the sample spaces. Finally, the weighted fusion mechanism is designed to merge the classification models into a classification ensemble model, thereby fusing the deep feature learning algorithm and the deep sample learning algorithm together. The ensemble model is called the deep dual-side learning ensemble model. At the end of this paper, two representative speech datasets of PD were used for validation. The experimental results show that the main innovation part of the algorithm is effective. For the two datasets, the mean accuracy of the proposed algorithm reaches 98.4% and 99.6%, which are better than the state-of-art relevant algorithms. The study shows that deep dual-side learning is better for existing deep feature learning for PD speech recognition.
AbstractList •A deep sample learning algorithm (DSL) is constructed for PD speech feature data.•An embedded deep stack group sparse autoencoder (EGSAE) is designed for PD speech data.•Deep dual-side learning ensemble model is constructed by combining EGSAE and DSL.•Both the diagnosis and automatic assessment of treatment of PD speech data are considered. Early diagnosis of Parkinson's disease (PD) is very important Kansara et al. (2013) and Stern (1993). In recent years, machine learning-based speech data analysis has been shown to be effective for diagnosing Parkinson's disease (PD) and automatically assessing rehabilitative speech treatment in PD Sakar et al. (2013), Tsanas et al. (2012) and Little et al. (2009). Machine learning includes feature learning and sample learning. Deep learning (deep feature learning) can generate high-level and high-quality features through deep feature transformation, improving classification accuracy. For reasons such as data collection, some samples have low quality for classification. Therefore, sample learning is necessary. Sample selection removes useless samples; therefore, deep sample learning is better, since it can generate high-level and high-quality samples through deep sample transformation. However, there are no public studies about deep sample learning. To solve the problem above, a deep dual-side learning ensemble model is designed in this paper. In this model, a deep sample learning algorithm is designed and combined with a deep network (deep feature learning), thereby realizing the deep dual-side learning of PD speech data. First, an embedded stack group sparse autoencoder is designed in this paper to conduct deep feature learning to acquire new high-level deep feature data. Second, the deep features are fused with original speech features by L1 regularization feature selection methods, thereby constructing hybrid feature data. Third, an iterative mean clustering algorithm (IMC) was designed, thereby constructing a deep sample learning algorithm and conducting deep sample transformation. After that step, hierarchical sample spaces are constructed based on a deep sample learning algorithm, and the classification models are constructed on the sample spaces. Finally, the weighted fusion mechanism is designed to merge the classification models into a classification ensemble model, thereby fusing the deep feature learning algorithm and the deep sample learning algorithm together. The ensemble model is called the deep dual-side learning ensemble model. At the end of this paper, two representative speech datasets of PD were used for validation. The experimental results show that the main innovation part of the algorithm is effective. For the two datasets, the mean accuracy of the proposed algorithm reaches 98.4% and 99.6%, which are better than the state-of-art relevant algorithms. The study shows that deep dual-side learning is better for existing deep feature learning for PD speech recognition.
ArticleNumber 102849
Author Zhou, Lang
Li, Yongming
Zhang, Yuanfan
Lei, Yan
Zeng, Yuwei
Qin, Lingyun
Wang, Pin
Ma, Jie
Author_xml – sequence: 1
  givenname: Jie
  surname: Ma
  fullname: Ma, Jie
  organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
– sequence: 2
  givenname: Yuanfan
  surname: Zhang
  fullname: Zhang, Yuanfan
  organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
– sequence: 3
  givenname: Yongming
  surname: Li
  fullname: Li, Yongming
  email: yongmingli@cqu.edu.cn
  organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
– sequence: 4
  givenname: Lang
  surname: Zhou
  fullname: Zhou, Lang
  organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
– sequence: 5
  givenname: Lingyun
  surname: Qin
  fullname: Qin, Lingyun
  organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
– sequence: 6
  givenname: Yuwei
  surname: Zeng
  fullname: Zeng, Yuwei
  organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
– sequence: 7
  givenname: Pin
  surname: Wang
  fullname: Wang, Pin
  organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
– sequence: 8
  givenname: Yan
  surname: Lei
  fullname: Lei, Yan
  organization: School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China
BookMark eNp9kMFKAzEQhoNUsFZfwFNeYGuym02y4EWqVqGgBz2HbDKpqdtkSVbBt3eX6sVDTzMMfMP_f-doFmIAhK4oWVJC-fVu2ebeLEtS0vFQStacoDkVjBeSEjn720nDztB5zjtCmBSUzdH6DqDH9lN3RfYWcAc6BR-2GEKGfdsB3kcLHXYx4RedPnzIMeDcA5h3nMDEbfCDj-ECnTrdZbj8nQv09nD_unosNs_rp9XtpjAVIUMhGw2SM0caJ2tHjBhjuFpzy2tCLG-oAC2akhtneEW5kZUQbcttPcYHYG21QPLw16SYcwKnjB_0lGBI2neKEjUJUTs1CVGTEHUQMqLlP7RPfq_T93Ho5gDBWOrLQ1LZeAgGrB_bD8pGfwz_AcrxfCs
CitedBy_id crossref_primary_10_1016_j_knosys_2022_109701
crossref_primary_10_1080_10255842_2025_2542942
crossref_primary_10_1155_2024_8890592
crossref_primary_10_1016_j_artmed_2025_103109
crossref_primary_10_3390_app122211601
crossref_primary_10_3390_s24144625
crossref_primary_10_1016_j_inffus_2025_103175
crossref_primary_10_3390_app15169053
crossref_primary_10_1007_s43538_024_00365_z
crossref_primary_10_1109_ACCESS_2025_3575023
crossref_primary_10_1016_j_cmpb_2022_107133
crossref_primary_10_1016_j_eswa_2023_119651
crossref_primary_10_1038_s41531_025_01025_9
crossref_primary_10_1111_exsy_13790
crossref_primary_10_1007_s00521_024_09596_z
crossref_primary_10_1016_j_neucom_2023_126436
crossref_primary_10_3389_fnagi_2025_1602426
crossref_primary_10_1016_j_imu_2022_100941
crossref_primary_10_3390_healthcare11111601
crossref_primary_10_1007_s10489_022_04345_y
crossref_primary_10_3390_s22186966
crossref_primary_10_1016_j_chaos_2021_111700
crossref_primary_10_3390_app14177873
crossref_primary_10_3390_bioengineering10080984
Cites_doi 10.1109/IMWS-BIO.2015.7303822
10.1016/j.bbe.2013.10.003
10.1109/ICoCS.2014.7060885
10.1109/ICASSP.2013.6638276
10.1109/ICNC.2015.7378178
10.1007/s10772-016-9338-4
10.1007/s10439-018-2104-9
10.1109/ICICISYS.2009.5357847
10.1371/journal.pone.0192192
10.1002/mds.21360
10.1109/JBHI.2013.2245674
10.1109/ICACCCN.2018.8748662
10.1186/s12938-016-0242-6
10.1016/j.dam.2018.10.025
10.1016/j.irbm.2017.10.002
10.1109/TBME.2009.2036000
10.1109/TIP.2017.2765833
10.1109/ICECCO.2015.7416886
10.1109/JTEHM.2019.2940900
10.1007/s00702-012-0840-9
10.1109/SAMI.2017.7880326
10.1007/s10916-009-9272-y
10.1016/j.cmpb.2014.01.004
10.1109/TNSRE.2013.2293575
10.1007/s13369-016-2206-3
10.1109/ICEEOT.2016.7755419
10.1016/j.dss.2019.03.011
10.1109/TBME.2008.2005954
10.1016/j.eswa.2012.07.014
10.1109/TBME.2012.2183367
10.1260/2040-2295.6.3.281
ContentType Journal Article
Copyright 2021 Elsevier Ltd
Copyright_xml – notice: 2021 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.bspc.2021.102849
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISSN 1746-8108
ExternalDocumentID 10_1016_j_bspc_2021_102849
S1746809421004468
GroupedDBID ---
--K
--M
.~1
0R~
1B1
1~.
1~5
23N
4.4
457
4G.
5GY
5VS
6J9
7-5
71M
8P~
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
AAYFN
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABXDB
ABYKQ
ACDAQ
ACGFO
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADMUD
ADTZH
AEBSH
AECPX
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
F5P
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
HZ~
IHE
J1W
JJJVA
KOM
M41
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
Q38
RIG
ROL
RPZ
SDF
SDG
SES
SPC
SPCBC
SST
SSV
SSZ
T5K
UNMZH
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c300t-89ae864f09f85f0c7487f5a6d6500d6917ea7926cfc6316c8377bb6d5746ee4b3
ISICitedReferencesCount 27
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000685910600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 1746-8094
IngestDate Sat Nov 29 07:00:49 EST 2025
Tue Nov 18 21:19:42 EST 2025
Fri Feb 23 02:43:36 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Deep learning
Speech recognition of Parkinson's disease
Feature fusion
Deep sample learning
Automatic assessment of rehabilitative speech treatment
Deep dual-side learning
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c300t-89ae864f09f85f0c7487f5a6d6500d6917ea7926cfc6316c8377bb6d5746ee4b3
ParticipantIDs crossref_citationtrail_10_1016_j_bspc_2021_102849
crossref_primary_10_1016_j_bspc_2021_102849
elsevier_sciencedirect_doi_10_1016_j_bspc_2021_102849
PublicationCentury 2000
PublicationDate August 2021
2021-08-00
PublicationDateYYYYMMDD 2021-08-01
PublicationDate_xml – month: 08
  year: 2021
  text: August 2021
PublicationDecade 2020
PublicationTitle Biomedical signal processing and control
PublicationYear 2021
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Kansara, Trivedi, Chen, Jankovic, Le (b0005) 2013; 120
Chakraborty, Brauer, Diwan (b0035) 2020; 75
Chen, Huang, Yu, Xu, Sun, Wang, Wang (b0080) 2013; 40
Agarwal A, Chandrayan S, Sahu S S. Prediction of Parkinson's disease using speech signal with Extreme Learning Machine[C]. 2016 International Conference on Electrical, Electronics and Optimization Techniques (ICEEOT), Chennai, India, 2016:3776-3779.
Kraipeerapun P and Amornsamankul S. Using stacked generalization and complementary neural networks to predict Parkinson's disease[C]. International Conference on Natural Computation, Zhangjiajie, China, 2016:1290-1294.
Su M, Chuang K. Dynamic feature selection for detecting Parkinson's disease through voice signal[C].2015 IEEE MTT-S 2015 International Microwave Workshop Series on RF and Wireless Technologies for Biomedical and Healthcare Applications (IMWS-BIO). Taipei, Taiwan, 2015:148-149.
Li, Chang, Yang, Luo, Fu (b0130) 2018; 27
Stern (b0010) 1993; 36
Little, Mcsharry, Stephen (b0040) 2007; 25
Rovini, Maremmani, Moschetti, Esposito, Cavallo (b0060) 2018; 46
Benba A, Jilbab A and Hammouch A. Hybridization of best acoustic cues for detecting persons with Parkinson's disease[C]. 2014 Second World Conference on Complex Systems (WCCS), Agadir, 2014: 622-625.
Peker, Şen, Delen (b0070) 2015; 6
Hariharan, Polat, Sindhu (b0085) 2014; 113
Little, McSharry, Hunter, Spielman, Ramig (b0025) 2009; 56
Cantürk, Karabiber (b0155) 2016; 41
Sakar, Isenkul, Sakar, Sertbas, Gurgen, Delil, Apaydin, Kursun (b0015) 2013; 17
Benba, Jilbab, Hammouch (b0195) 2016; 19
Kapil, Chawla, Ansari (b0140) 2016
Sakar, Kursun (b0065) 2010; 34
Tsanas, Little, McSharry, Ramig (b0045) 2010; 57
Zhang (b0190) 2017; 2017
Frid, Safra, Hazan (b0105) 2014
Eskıdere Ö, Karatutlu A, and Ünal C. Detection of Parkinson's disease from vocal features using random subspace classifier ensemble[C]. 2015 Twelve Int. Conf. Electron. Comput. Comput. (ICECCO), Almaty, Kazakhstan, 2015:1-4.
Benba, Jilbab, Hammouch (b0175) 2017; 38
McCrone, Allcock, Burn (b0030) 2007; 22
Labbé, Martínez-Merino, Rodríguez-Chía (b0050) 2019; 261
Khan, Westin, Dougherty (b0110) 2014; 34
Palangi H, Ward R, Deng L. Using deep stacking network to improve structured compressed sensing with Multiple Measurement Vectors[C]. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, 2013:3337-3341.
Tsanas, Little, Fox, Ramig (b0150) 2014; 22
Tsanas, Little, McSharry, Spielman, Ramig (b0020) 2012; 59
Kaninika, Tayal A. Determination of Parkinson’s disease utilizing Machine Learning Methods[C]. 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), Greater Noida (UP), India, 2018:170-173.
Vadovský M and Paralič J. Parkinson's disease patients classification based on the speech signals[C]. 2017 IEEE 15th Int. Symp. Appl. Mach. Intell. Inform. (SAMI), Herl'any, Slovakia, 2017:321–326.
Behroozi, Sami (b0165) 2016; 2016
Khan M M, Mendes A, Chalup S K. Evolutionary wavelet neural network ensembles for breast cancer and Parkinson's disease prediction [J]. Plos One, 2018, 13(2): e0192192.
Mao, Jain (b0075) 2002; 6
Zhang, Yang, Liu, Wang, Yin, Li, Qiu, Zhu, Yan (b0170) 2016; 15
Li, Zhang, Jia (b0180) 2017
Ali, Zhu, Zhang, Liu (b0210) 2019; 7
Kozodoi, Lessmann, Papakonstantinou, Gatsoulis, Baesens (b0055) 2019; 120
Peng, Guan, Shang (b0125) 2019; 10
Hu G, Mao Z. Bagging ensemble of SVM based on negative correlation learning[C]. 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, Shanghai, China, 2009:279–283.
Ng A. Sparse autoencoder. CS294A Lecture Notes, 2011: 1-19.
Stern (10.1016/j.bspc.2021.102849_b0010) 1993; 36
Labbé (10.1016/j.bspc.2021.102849_b0050) 2019; 261
Cantürk (10.1016/j.bspc.2021.102849_b0155) 2016; 41
10.1016/j.bspc.2021.102849_b0090
Chakraborty (10.1016/j.bspc.2021.102849_b0035) 2020; 75
Kozodoi (10.1016/j.bspc.2021.102849_b0055) 2019; 120
Chen (10.1016/j.bspc.2021.102849_b0080) 2013; 40
Zhang (10.1016/j.bspc.2021.102849_b0190) 2017; 2017
Ali (10.1016/j.bspc.2021.102849_b0210) 2019; 7
Little (10.1016/j.bspc.2021.102849_b0040) 2007; 25
Peng (10.1016/j.bspc.2021.102849_b0125) 2019; 10
McCrone (10.1016/j.bspc.2021.102849_b0030) 2007; 22
10.1016/j.bspc.2021.102849_b0115
Li (10.1016/j.bspc.2021.102849_b0130) 2018; 27
10.1016/j.bspc.2021.102849_b0095
Rovini (10.1016/j.bspc.2021.102849_b0060) 2018; 46
Khan (10.1016/j.bspc.2021.102849_b0110) 2014; 34
Kapil (10.1016/j.bspc.2021.102849_b0140) 2016
Kansara (10.1016/j.bspc.2021.102849_b0005) 2013; 120
10.1016/j.bspc.2021.102849_b0135
Tsanas (10.1016/j.bspc.2021.102849_b0020) 2012; 59
Hariharan (10.1016/j.bspc.2021.102849_b0085) 2014; 113
Behroozi (10.1016/j.bspc.2021.102849_b0165) 2016; 2016
Tsanas (10.1016/j.bspc.2021.102849_b0045) 2010; 57
Li (10.1016/j.bspc.2021.102849_b0180) 2017
10.1016/j.bspc.2021.102849_b0160
Zhang (10.1016/j.bspc.2021.102849_b0170) 2016; 15
Sakar (10.1016/j.bspc.2021.102849_b0065) 2010; 34
Benba (10.1016/j.bspc.2021.102849_b0175) 2017; 38
Sakar (10.1016/j.bspc.2021.102849_b0015) 2013; 17
Mao (10.1016/j.bspc.2021.102849_b0075) 2002; 6
10.1016/j.bspc.2021.102849_b0205
Little (10.1016/j.bspc.2021.102849_b0025) 2009; 56
Peker (10.1016/j.bspc.2021.102849_b0070) 2015; 6
Tsanas (10.1016/j.bspc.2021.102849_b0150) 2014; 22
10.1016/j.bspc.2021.102849_b0185
10.1016/j.bspc.2021.102849_b0120
Benba (10.1016/j.bspc.2021.102849_b0195) 2016; 19
10.1016/j.bspc.2021.102849_b0100
Frid (10.1016/j.bspc.2021.102849_b0105) 2014
10.1016/j.bspc.2021.102849_b0145
10.1016/j.bspc.2021.102849_b0200
References_xml – volume: 27
  start-page: 464
  year: 2018
  end-page: 476
  ident: b0130
  article-title: Visual representation and classification by learning group sparse deep stacking network
  publication-title: IEEE Trans. Image Process.
– volume: 120
  start-page: 106
  year: 2019
  end-page: 117
  ident: b0055
  article-title: A multi-objective approach for profit-driven feature selection in credit scoring
  publication-title: Decis. Support Syst.
– volume: 38
  start-page: 346
  year: 2017
  end-page: 351
  ident: b0175
  article-title: Using human factor cepstral coefficient on multiple types of voice recordings for detecting patients with Parkinson's disease
  publication-title: IRBM
– volume: 6
  start-page: 281
  year: 2015
  end-page: 302
  ident: b0070
  article-title: Computer-aided diagnosis of parkinson's disease using complex-valued neural networks and mRMR feature selection algorithm
  publication-title: J. Healthc. Eng.
– volume: 10
  start-page: 2019
  year: 2019
  ident: b0125
  article-title: Predicting Parkinson's disease genes based on node2vec and autoencoder
  publication-title: Front. Genet.
– volume: 15
  year: 2016
  ident: b0170
  article-title: Classification of Parkinson's disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples
  publication-title: Biomed. Eng. Online
– volume: 261
  start-page: 276
  year: 2019
  end-page: 304
  ident: b0050
  article-title: Mixed integer linear programming for feature selection in support vector machine
  publication-title: Discrete Appl. Math.
– volume: 6
  start-page: 296
  year: 2002
  end-page: 317
  ident: b0075
  article-title: Artificial neural networks for feature extraction and multivariate data projection
  publication-title: IEEE Trans. Neural Netw.
– reference: Benba A, Jilbab A and Hammouch A. Hybridization of best acoustic cues for detecting persons with Parkinson's disease[C]. 2014 Second World Conference on Complex Systems (WCCS), Agadir, 2014: 622-625.
– reference: Eskıdere Ö, Karatutlu A, and Ünal C. Detection of Parkinson's disease from vocal features using random subspace classifier ensemble[C]. 2015 Twelve Int. Conf. Electron. Comput. Comput. (ICECCO), Almaty, Kazakhstan, 2015:1-4.
– volume: 75
  start-page: 1
  year: 2020
  end-page: 4
  ident: b0035
  article-title: Possible therapies of Parkinson's disease: a review
  publication-title: J. Clin. Neurosci.
– start-page: 202
  year: 2016
  end-page: 206
  ident: b0140
  publication-title: On K-means data clustering algorithm with genetic algorithm[C]
– reference: Khan M M, Mendes A, Chalup S K. Evolutionary wavelet neural network ensembles for breast cancer and Parkinson's disease prediction [J]. Plos One, 2018, 13(2): e0192192.
– reference: Kraipeerapun P and Amornsamankul S. Using stacked generalization and complementary neural networks to predict Parkinson's disease[C]. International Conference on Natural Computation, Zhangjiajie, China, 2016:1290-1294.
– volume: 2016
  start-page: 1
  year: 2016
  end-page: 9
  ident: b0165
  article-title: A multiple-classifier framework for Parkinson's disease detection based on various vocal tests
  publication-title: Int. J. Telemed. Appl.
– volume: 34
  start-page: 591
  year: 2010
  end-page: 599
  ident: b0065
  article-title: Telediagnosis of Parkinson's disease using measurements of dysphonia
  publication-title: J. Med. Syst.
– volume: 40
  start-page: 263
  year: 2013
  end-page: 271
  ident: b0080
  article-title: An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach
  publication-title: Expert Syst. Appl.
– volume: 46
  start-page: 2057
  year: 2018
  end-page: 2068
  ident: b0060
  article-title: Comparative motor pre-clinical assessment in Parkinson’s disease using supervised machine learning approaches
  publication-title: Ann. Biomed. Eng.
– volume: 36
  start-page: 439
  year: 1993
  end-page: 446
  ident: b0010
  article-title: Parkinson's disease: early diagnosis and management
  publication-title: J. Fam. Pract.
– volume: 34
  start-page: 35
  year: 2014
  end-page: 45
  ident: b0110
  article-title: Classification of speech intelligibility in Parkinson's disease
  publication-title: Biocybernet. Biomed. Eng.
– volume: 59
  start-page: 1264
  year: 2012
  end-page: 1271
  ident: b0020
  article-title: Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s disease
  publication-title: IEEE Trans. Biomed. Eng.
– volume: 25
  start-page: 1186
  year: 2007
  end-page: 1214
  ident: b0040
  article-title: Exploiting nonlinear recurrence and fractal scaling properties for voice disorder detection
  publication-title: Biomed. Eng. Online
– reference: Ng A. Sparse autoencoder. CS294A Lecture Notes, 2011: 1-19.
– volume: 22
  start-page: 181
  year: 2014
  end-page: 190
  ident: b0150
  article-title: Objective automatic assessment of rehabilitative speech treatment in Parkinson's disease
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
– volume: 113
  start-page: 904
  year: 2014
  end-page: 913
  ident: b0085
  article-title: A new hybrid intelligent system for accurate detection of Parkinson's disease
  publication-title: Comput. Methods Programs Biomed.
– reference: Vadovský M and Paralič J. Parkinson's disease patients classification based on the speech signals[C]. 2017 IEEE 15th Int. Symp. Appl. Mach. Intell. Inform. (SAMI), Herl'any, Slovakia, 2017:321–326.
– volume: 19
  start-page: 449
  year: 2016
  end-page: 456
  ident: b0195
  article-title: Analysis of multiple types of voice recordings in cepstral domain using MFCC for discriminating between patients with Parkinson's disease and healthy people
  publication-title: Int. J. Speech Technol.
– volume: 17
  start-page: 828
  year: 2013
  end-page: 834
  ident: b0015
  article-title: Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings
  publication-title: IEEE J. Biomed. Health. Inf.
– reference: Agarwal A, Chandrayan S, Sahu S S. Prediction of Parkinson's disease using speech signal with Extreme Learning Machine[C]. 2016 International Conference on Electrical, Electronics and Optimization Techniques (ICEEOT), Chennai, India, 2016:3776-3779.
– volume: 57
  start-page: 884
  year: 2010
  end-page: 893
  ident: b0045
  article-title: Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests
  publication-title: IEEE Trans. Biomed. Eng.
– start-page: 1
  year: 2017
  end-page: 6
  ident: b0180
  publication-title: Simultaneous learning of speech feature and segment for classification of Parkinson disease[C].2017
– volume: 120
  start-page: 197
  year: 2013
  end-page: 210
  ident: b0005
  article-title: Early diagnosis and therapy of Parkinson's disease: can disease progression be curbed?
  publication-title: J. Neural Trans.
– volume: 41
  start-page: 5049
  year: 2016
  end-page: 5059
  ident: b0155
  article-title: A machine learning system for the diagnosis of Parkinson’s disease from speech signals and its application to multiple speech signal types
  publication-title: Arab. J. Sci. Eng.
– volume: 56
  start-page: 1015
  year: 2009
  end-page: 1022
  ident: b0025
  article-title: Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease
  publication-title: IEEE Trans. Biomed. Eng.
– reference: Kaninika, Tayal A. Determination of Parkinson’s disease utilizing Machine Learning Methods[C]. 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), Greater Noida (UP), India, 2018:170-173.
– volume: 7
  start-page: 1
  year: 2019
  end-page: 10
  ident: b0210
  article-title: Automated detection of Parkinson’s disease based on multiple types of sustained phonations using linear discriminant analysis and genetically optimized neural network
  publication-title: IEEE J. Trans. Eng. Health Med.
– start-page: 50
  year: 2014
  end-page: 53
  ident: b0105
  publication-title: Computational Diagnosis of Parkinson's Disease Directly from Natural Speech Using Machine Learning Techniques[C].2014
– volume: 2017
  start-page: 1
  year: 2017
  end-page: 11
  ident: b0190
  article-title: A deep neural network method and telediagnosis system implementation
  publication-title: Parkinsons Dis.
– volume: 22
  start-page: 804
  year: 2007
  end-page: 812
  ident: b0030
  article-title: Predicting the cost of Parkinson's disease
  publication-title: Mov. Disord.
– reference: Palangi H, Ward R, Deng L. Using deep stacking network to improve structured compressed sensing with Multiple Measurement Vectors[C]. 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, BC, 2013:3337-3341.
– reference: Hu G, Mao Z. Bagging ensemble of SVM based on negative correlation learning[C]. 2009 IEEE International Conference on Intelligent Computing and Intelligent Systems, Shanghai, China, 2009:279–283.
– reference: Su M, Chuang K. Dynamic feature selection for detecting Parkinson's disease through voice signal[C].2015 IEEE MTT-S 2015 International Microwave Workshop Series on RF and Wireless Technologies for Biomedical and Healthcare Applications (IMWS-BIO). Taipei, Taiwan, 2015:148-149.
– ident: 10.1016/j.bspc.2021.102849_b0115
  doi: 10.1109/IMWS-BIO.2015.7303822
– volume: 34
  start-page: 35
  issue: 1
  year: 2014
  ident: 10.1016/j.bspc.2021.102849_b0110
  article-title: Classification of speech intelligibility in Parkinson's disease
  publication-title: Biocybernet. Biomed. Eng.
  doi: 10.1016/j.bbe.2013.10.003
– ident: 10.1016/j.bspc.2021.102849_b0100
  doi: 10.1109/ICoCS.2014.7060885
– ident: 10.1016/j.bspc.2021.102849_b0135
  doi: 10.1109/ICASSP.2013.6638276
– ident: 10.1016/j.bspc.2021.102849_b0200
  doi: 10.1109/ICNC.2015.7378178
– volume: 19
  start-page: 449
  issue: 3
  year: 2016
  ident: 10.1016/j.bspc.2021.102849_b0195
  article-title: Analysis of multiple types of voice recordings in cepstral domain using MFCC for discriminating between patients with Parkinson's disease and healthy people
  publication-title: Int. J. Speech Technol.
  doi: 10.1007/s10772-016-9338-4
– volume: 46
  start-page: 2057
  issue: 12
  year: 2018
  ident: 10.1016/j.bspc.2021.102849_b0060
  article-title: Comparative motor pre-clinical assessment in Parkinson’s disease using supervised machine learning approaches
  publication-title: Ann. Biomed. Eng.
  doi: 10.1007/s10439-018-2104-9
– volume: 75
  start-page: 1
  issue: 5
  year: 2020
  ident: 10.1016/j.bspc.2021.102849_b0035
  article-title: Possible therapies of Parkinson's disease: a review
  publication-title: J. Clin. Neurosci.
– ident: 10.1016/j.bspc.2021.102849_b0145
  doi: 10.1109/ICICISYS.2009.5357847
– ident: 10.1016/j.bspc.2021.102849_b0205
  doi: 10.1371/journal.pone.0192192
– volume: 22
  start-page: 804
  issue: 6
  year: 2007
  ident: 10.1016/j.bspc.2021.102849_b0030
  article-title: Predicting the cost of Parkinson's disease
  publication-title: Mov. Disord.
  doi: 10.1002/mds.21360
– volume: 17
  start-page: 828
  issue: 4
  year: 2013
  ident: 10.1016/j.bspc.2021.102849_b0015
  article-title: Collection and analysis of a Parkinson speech dataset with multiple types of sound recordings
  publication-title: IEEE J. Biomed. Health. Inf.
  doi: 10.1109/JBHI.2013.2245674
– ident: 10.1016/j.bspc.2021.102849_b0095
  doi: 10.1109/ICACCCN.2018.8748662
– start-page: 1
  year: 2017
  ident: 10.1016/j.bspc.2021.102849_b0180
– volume: 15
  issue: 1
  year: 2016
  ident: 10.1016/j.bspc.2021.102849_b0170
  article-title: Classification of Parkinson's disease utilizing multi-edit nearest-neighbor and ensemble learning algorithms with speech samples
  publication-title: Biomed. Eng. Online
  doi: 10.1186/s12938-016-0242-6
– volume: 261
  start-page: 276
  year: 2019
  ident: 10.1016/j.bspc.2021.102849_b0050
  article-title: Mixed integer linear programming for feature selection in support vector machine
  publication-title: Discrete Appl. Math.
  doi: 10.1016/j.dam.2018.10.025
– ident: 10.1016/j.bspc.2021.102849_b0120
– volume: 38
  start-page: 346
  issue: 6
  year: 2017
  ident: 10.1016/j.bspc.2021.102849_b0175
  article-title: Using human factor cepstral coefficient on multiple types of voice recordings for detecting patients with Parkinson's disease
  publication-title: IRBM
  doi: 10.1016/j.irbm.2017.10.002
– volume: 57
  start-page: 884
  issue: 4
  year: 2010
  ident: 10.1016/j.bspc.2021.102849_b0045
  article-title: Accurate telemonitoring of Parkinson’s disease progression by noninvasive speech tests
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2009.2036000
– start-page: 50
  year: 2014
  ident: 10.1016/j.bspc.2021.102849_b0105
– volume: 27
  start-page: 464
  issue: 1
  year: 2018
  ident: 10.1016/j.bspc.2021.102849_b0130
  article-title: Visual representation and classification by learning group sparse deep stacking network
  publication-title: IEEE Trans. Image Process.
  doi: 10.1109/TIP.2017.2765833
– volume: 36
  start-page: 439
  issue: 4
  year: 1993
  ident: 10.1016/j.bspc.2021.102849_b0010
  article-title: Parkinson's disease: early diagnosis and management
  publication-title: J. Fam. Pract.
– ident: 10.1016/j.bspc.2021.102849_b0160
  doi: 10.1109/ICECCO.2015.7416886
– volume: 7
  start-page: 1
  year: 2019
  ident: 10.1016/j.bspc.2021.102849_b0210
  article-title: Automated detection of Parkinson’s disease based on multiple types of sustained phonations using linear discriminant analysis and genetically optimized neural network
  publication-title: IEEE J. Trans. Eng. Health Med.
  doi: 10.1109/JTEHM.2019.2940900
– volume: 120
  start-page: 197
  issue: 1
  year: 2013
  ident: 10.1016/j.bspc.2021.102849_b0005
  article-title: Early diagnosis and therapy of Parkinson's disease: can disease progression be curbed?
  publication-title: J. Neural Trans.
  doi: 10.1007/s00702-012-0840-9
– ident: 10.1016/j.bspc.2021.102849_b0185
  doi: 10.1109/SAMI.2017.7880326
– start-page: 202
  year: 2016
  ident: 10.1016/j.bspc.2021.102849_b0140
– volume: 34
  start-page: 591
  issue: 4
  year: 2010
  ident: 10.1016/j.bspc.2021.102849_b0065
  article-title: Telediagnosis of Parkinson's disease using measurements of dysphonia
  publication-title: J. Med. Syst.
  doi: 10.1007/s10916-009-9272-y
– volume: 113
  start-page: 904
  issue: 3
  year: 2014
  ident: 10.1016/j.bspc.2021.102849_b0085
  article-title: A new hybrid intelligent system for accurate detection of Parkinson's disease
  publication-title: Comput. Methods Programs Biomed.
  doi: 10.1016/j.cmpb.2014.01.004
– volume: 22
  start-page: 181
  issue: 1
  year: 2014
  ident: 10.1016/j.bspc.2021.102849_b0150
  article-title: Objective automatic assessment of rehabilitative speech treatment in Parkinson's disease
  publication-title: IEEE Trans. Neural Syst. Rehabil. Eng.
  doi: 10.1109/TNSRE.2013.2293575
– volume: 41
  start-page: 5049
  issue: 12
  year: 2016
  ident: 10.1016/j.bspc.2021.102849_b0155
  article-title: A machine learning system for the diagnosis of Parkinson’s disease from speech signals and its application to multiple speech signal types
  publication-title: Arab. J. Sci. Eng.
  doi: 10.1007/s13369-016-2206-3
– ident: 10.1016/j.bspc.2021.102849_b0090
  doi: 10.1109/ICEEOT.2016.7755419
– volume: 120
  start-page: 106
  year: 2019
  ident: 10.1016/j.bspc.2021.102849_b0055
  article-title: A multi-objective approach for profit-driven feature selection in credit scoring
  publication-title: Decis. Support Syst.
  doi: 10.1016/j.dss.2019.03.011
– volume: 10
  start-page: 2019
  issue: 226
  year: 2019
  ident: 10.1016/j.bspc.2021.102849_b0125
  article-title: Predicting Parkinson's disease genes based on node2vec and autoencoder
  publication-title: Front. Genet.
– volume: 56
  start-page: 1015
  issue: 4
  year: 2009
  ident: 10.1016/j.bspc.2021.102849_b0025
  article-title: Suitability of dysphonia measurements for telemonitoring of Parkinson’s disease
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2008.2005954
– volume: 2017
  start-page: 1
  year: 2017
  ident: 10.1016/j.bspc.2021.102849_b0190
  article-title: A deep neural network method and telediagnosis system implementation
  publication-title: Parkinsons Dis.
– volume: 25
  start-page: 1186
  issue: 6
  year: 2007
  ident: 10.1016/j.bspc.2021.102849_b0040
  article-title: Exploiting nonlinear recurrence and fractal scaling properties for voice disorder detection
  publication-title: Biomed. Eng. Online
– volume: 40
  start-page: 263
  issue: 1
  year: 2013
  ident: 10.1016/j.bspc.2021.102849_b0080
  article-title: An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2012.07.014
– volume: 6
  start-page: 296
  issue: 2
  year: 2002
  ident: 10.1016/j.bspc.2021.102849_b0075
  article-title: Artificial neural networks for feature extraction and multivariate data projection
  publication-title: IEEE Trans. Neural Netw.
– volume: 59
  start-page: 1264
  issue: 5
  year: 2012
  ident: 10.1016/j.bspc.2021.102849_b0020
  article-title: Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s disease
  publication-title: IEEE Trans. Biomed. Eng.
  doi: 10.1109/TBME.2012.2183367
– volume: 6
  start-page: 281
  issue: 3
  year: 2015
  ident: 10.1016/j.bspc.2021.102849_b0070
  article-title: Computer-aided diagnosis of parkinson's disease using complex-valued neural networks and mRMR feature selection algorithm
  publication-title: J. Healthc. Eng.
  doi: 10.1260/2040-2295.6.3.281
– volume: 2016
  start-page: 1
  year: 2016
  ident: 10.1016/j.bspc.2021.102849_b0165
  article-title: A multiple-classifier framework for Parkinson's disease detection based on various vocal tests
  publication-title: Int. J. Telemed. Appl.
SSID ssj0048714
Score 2.383251
Snippet •A deep sample learning algorithm (DSL) is constructed for PD speech feature data.•An embedded deep stack group sparse autoencoder (EGSAE) is designed for PD...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 102849
SubjectTerms Automatic assessment of rehabilitative speech treatment
Deep dual-side learning
Deep learning
Deep sample learning
Feature fusion
Speech recognition of Parkinson's disease
Title Deep dual-side learning ensemble model for Parkinson speech recognition
URI https://dx.doi.org/10.1016/j.bspc.2021.102849
Volume 69
WOSCitedRecordID wos000685910600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1746-8108
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0048714
  issn: 1746-8094
  databaseCode: AIEXJ
  dateStart: 20060101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1LT9wwELZa4NAeKihUpS3Ih96ioDyc2D6ilhZQxYlWyylKnMl2EWQjdrfi53f83IW2CA69RCvLmc16vh3POPPNEPKRQQIttGj9MBiIGW_xP4deRCxaqCVuQKwz7Xx-fONnZ2I0kv6N7sy0E-B9L25v5fBfVY1jqGxNnX2CuoNQHMDPqHS8otrx-ijFfwYYIs2winUnTt8WYhxhvArXmidlmt-Y9EJNeTbsr2g2AKifUUgncsryb3sNR98SKCdj7b8Oll_gGY4u4X15vG3AMQmgCcfSF4u671bSgEwuwcW0H1_7LdTMni4sZ9uNuVOJLA05cd6QcqYLHdsGxt7S2qYszlRqz8ZWK_3DitsDhcuDZjboKpNZerCcfLdk9r2tLCQY-ty1y0rLqLSMysp4TtYzXkg0gOuHJ0ejU79tY-BmCsGHB3cMK5sMeP9J_u7FrHgm55vklQsp6KGFwhZ5Bv1r8nKl0OQ2-apBQQMoqAcF9aCgBhQUQUEDKKgFBV0BxQ75_uXo_NNx7FpoxCpPknksZA2iZF0iO1F0ieL4M7uiLlt0zJO2xFgdai6zUnWqzNNSiZzzpinbAlcBgDX5G7LWT3t4S2gj81wwldVKKZbzRDaQp6zIEoFSmhR2SeqXpFKuvrxuc3JV_VsZuyQK9wy2usqDswu_0pXzD63fVyFwHrjv3ZO-5T15sQT0B7I2v1nAHtlQv-aT2c2-Q81vyxKFkg
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Deep+dual-side+learning+ensemble+model+for+Parkinson+speech+recognition&rft.jtitle=Biomedical+signal+processing+and+control&rft.au=Ma%2C+Jie&rft.au=Zhang%2C+Yuanfan&rft.au=Li%2C+Yongming&rft.au=Zhou%2C+Lang&rft.date=2021-08-01&rft.issn=1746-8094&rft.volume=69&rft.spage=102849&rft_id=info:doi/10.1016%2Fj.bspc.2021.102849&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_bspc_2021_102849
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1746-8094&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1746-8094&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1746-8094&client=summon