Diagnosis of Parkinson's disease from electroencephalography signals using linear and self-similarity features

被引:28
作者
Bhurane, Ankit A. [1 ]
Dhok, Shivani [1 ]
Sharma, Manish [2 ]
Yuvaraj, Rajamanickam [3 ]
Murugappan, Murugappan [4 ]
Acharya, U. Rajendra [5 ,6 ,7 ]
机构
[1] Indian Inst Informat Technol, Dept Elect & Commun, Nagpur IIITN, Nagpur, Maharashtra, India
[2] IITRAM, Dept Elect Engn, Ahmadabad, Gujarat, India
[3] Nanyang Technol Univ, Sch Elect & Elect Engn, Singapore, Singapore
[4] Kuwait Coll Sci & Technol, Elect & Commun Engn, Doha, Kuwait
[5] Ngee Ann Polytech, Dept Elect & Comp Engn, Singapore, Singapore
[6] SUSS, Dept Biomed Engn, Sch Sci & Technol, Singapore, Singapore
[7] Taylors Univ, Fac Hlth & Med Sci, Sch Med, Subang Jaya, Malaysia
关键词
correlation coefficients; electroencephalogram (EEG); linear predictive coefficients; Parkinson's disease; SVM; WAVELET TRANSFORM; FILTER BANKS; EEG; CLASSIFICATION; GAIT; PATTERNS; SYSTEM; STATE;
D O I
10.1111/exsy.12472
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
An early stage detection of Parkinson's disease (PD) is crucial for its appropriate treatment. The quality of life degrades with the advancement of the disease. In this paper, we propose a natural (time) domain technique for the diagnosis of PD. The proposed technique eliminates the need for transformation of the signal to other domains by extracting the feature of electroencephalography signals in the time domain. We hypothesize that two inter-channel similarity features, correlation coefficients and linear predictive coefficients, are able to detect the PD signals automatically using support vector machines classifier with third degree polynomial kernel. A progressive feature addition analysis is employed using selected features obtained based on the feature ranking and principal component analysis techniques. The proposed approach is able to achieve a maximum accuracy of 99.1 +/- 0.1%. The presented computer-aided diagnosis system can act as an assistive tool to confirm the finding of PD by the clinicians.
引用
收藏
页数:12
相关论文
共 60 条
[1]  
[Anonymous], 1908, BIOMETRIKA, V6, P1
[2]  
[Anonymous], 2019, NEURAL COMPUTING APP
[3]  
[Anonymous], 2018, NEURAL COMPUTING APP
[4]  
[Anonymous], 2003, A tutorial on principal component analysis
[5]  
[Anonymous], 2006, Neurological disorders: public health challenges Internet
[6]   Parkinson's disease: Cause factors, measurable indicators, and early diagnosis [J].
Bhat, Shreya ;
Acharya, U. Rajendra ;
Hagiwara, Yuki ;
Dadmehr, Nahid ;
Adeli, Hojjat .
COMPUTERS IN BIOLOGY AND MEDICINE, 2018, 102 :234-241
[7]   An efficient detection of congestive heart failure using frequency localized filter banks for the diagnosis with ECG signals [J].
Bhurane, Ankit A. ;
Sharma, Manish ;
San-Tan, Ru ;
Acharya, U. Rajendra .
COGNITIVE SYSTEMS RESEARCH, 2019, 55 :82-94
[8]   Epidemiology of Emerging Fungal Infections in ICU [J].
Chakrabarti, Arunaloke ;
Sharma, Megha .
CURRENT FUNGAL INFECTION REPORTS, 2019, 13 (01) :1-10
[9]   An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach [J].
Chen, Hui-Ling ;
Huang, Chang-Cheng ;
Yu, Xin-Gang ;
Xu, Xin ;
Sun, Xin ;
Wang, Gang ;
Wang, Su-Jing .
EXPERT SYSTEMS WITH APPLICATIONS, 2013, 40 (01) :263-271
[10]   SUPPORT-VECTOR NETWORKS [J].
CORTES, C ;
VAPNIK, V .
MACHINE LEARNING, 1995, 20 (03) :273-297