EEG-Based Classification Between Individuals with Mild Cognitive Impairment and Healthy Controls Using Conformal Kernel-Based Fuzzy Support Vector Machine

Hsiao, Yu-Tsung; Wu, C. T.; Tsai, Chia-Ming; Liu, Yi-Hung; Trinh, Thanh-Tung; Lee, Chun-Ying

doi:10.1007/s40815-021-01186-8

Cited by 7 publications

(6 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, evaluation metrics like accuracy, sensitivity, specificity, and precision F‐score are analyzed. The efficiency is compared with four existing models, such as multiclass recognition of AD neurological diseases using PAA support vector machine (MCC‐EEG‐PAA‐SVM), 26 multiclass recognition of AD neurological diseases using Pearson correlation coefficient‐based feature selection (PCCFS) strategy and then fed into a linear discriminant analysis (LDA) classifier (MCC‐EEG‐PCC‐LDA), 28 multiclass recognition of AD neurological diseases using convolutional neural network (MCC‐EEG‐CNN), 29 multiclass recognition of AD neurological diseases using conformal kernel‐based fuzzy support vector machine (MCC‐EEG‐CKF‐SVM) 30 …”

Section: Results With Discussionmentioning

confidence: 99%

“…Hsiao et al, 30 have presented a classification based on EEG amid the individuals with MCI and HC utilizing conformal kernel‐base fuzzy support vector machine (CKF‐SVM). The presented method deals the problem of classifying individuals with MCI versus HC depending on resting‐state EEG.…”

Section: Literature Surveymentioning

confidence: 99%

“…Generally, TSVM method not reveals any adoption of optimization methods to compute the optimal parameters for assuring correct detection of AD disease. Moreover, GDO algorithm is utilized to optimize TSVM which detects AD diseases accurately 35 Finally, the proposed model classifies the AD disease accurately with low execution time. The proposed MCC‐EEG‐TSVM‐GDO method is done in MATLAB, its efficiency is estimated using various performances metrics, includes accuracy, precision, recall, F‐score, specificity, sensitivity, error rate. The performance of the MCC‐EEG‐TSVM‐GDO method is compared with four existing methods, such as multiclass recognition of AD neurological diseases using piecewise aggregate approximation support vector machine (MCC‐EEG‐ PAA‐SVM), 26 multiclass recognition of AD neurological diseases using Pearson correlation coefficient‐based feature selection strategy with linear discriminant analysis classifier (MCC‐EEG‐ PCC‐LDA), 28 multiclass recognition of AD neurological diseases using convolutional neural network (MCC‐EEG‐ CNN), 29 multiclass recognition of AD neurological diseases using conformal kernel‐based fuzzy support vector machine (MCC‐EEG‐CKF‐SVM) 30 The remaining segment of this manuscript is organized as follows: Section 2 delineates the literature survey, Section 3 describes the proposed method of AD disease classification using TSVM‐GDO, Section 4 proves the result and discussion, Section 5 presents the conclusion of this manuscript.…”

Section: Introductionmentioning

confidence: 99%

“…[21][22][23][24][25] Several feature extraction and classification methods are discussed in literature survey but that method provide high over fitting problem, which leads to low detection accuracy. [26][27][28][29][30][31] These are motivated to do this work.…”

mentioning

confidence: 99%

“…• The performance of the MCC-EEG-TSVM-GDO method is compared with four existing methods, such as multiclass recognition of AD neurological diseases using piecewise aggregate approximation support vector machine (MCC-EEG-PAA-SVM), 26 multiclass recognition of AD neurological diseases using Pearson correlation coefficient-based feature selection strategy with linear discriminant analysis classifier (MCC-EEG-PCC-LDA), 28 multiclass recognition of AD neurological diseases using convolutional neural network (MCC-EEG-CNN), 29 multiclass recognition of AD neurological diseases using conformal kernel-based fuzzy support vector machine (MCC-EEG-CKF-SVM). 30 The remaining segment of this manuscript is organized as follows: Section 2 delineates the literature survey, Section 3 describes the proposed method of AD disease classification using TSVM-GDO, Section 4 proves the result and discussion, Section 5 presents the conclusion of this manuscript.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Multiclass recognition of AD neurological diseases using a bag of deep reduced features coupled with gradient descent optimized twin support vector machine classifier for early diagnosis

Velliangiri

Pandiaraj

et al. 2022

Concurrency and Computation

View full text Add to dashboard Cite

Alzheimer's disease (AD) is an advanced neurodegenerative disease of the brain that affects the nerve system of brain. Previously, several feature extraction and classification methods were discussed, but that methods provide high over fitting problem, which leads to minimization of detection accuracy. To overcome these issues, the multi class classification of AD diseases using bag of deep feature reduction technique and twin support vector machine classifier (TSVM) optimized with gradient decent optimizer is proposed in this manuscript for classifying the AD disease as severe AD, mild cognitive impairment, healthy control. At first, the input EEG signals are pre-processed. To decrease the execution time and processing time with feature size, a bag of deep features reduction technique is used. The reduced feature signals are classified by optimized TSVM. The simulation process is implemented in MAT-LAB environment. The proposed model achieves higher accuracy 33.84%, 28.93%, 33.03%, 27.93%, higher precision 22.87%, 16.97%, 16.97%, and 36.97%, compared with the existing methods, such as piecewise aggregate approximation support vector machine (MCC-EEG-PAA-SVM), convolutional neural network (MCC-EEG-CNN), conformal kernel-based fuzzy support vector machine (MCC-EEG-CKF-SVM), Pearson correlation coefficient-based feature selection strategy with linear discriminant analysis classifier (MCC-EEG-PCC-LDA). K E Y W O R D S bag of deep features (BoDrF) reduction, gradient decent optimizer, multi class classification, twin support vector machine classifier INTRODUCTIONAlzheimer's disease is a permanent neurodegenerative disease and the most predominant form of dementia. [1][2][3][4] The initial symptoms of the AD disease contain disremembering the current actions. When the disease grows, a person who affected by Alzheimer's disease also grows severe memory impairment and drops the capability to carry everyday jobs. [5][6][7] AD caused difficult to absorb as well as thinking. The indications of this AD diseases are severe in the last stage. If the AD diseases grow to its last stage, it destroys brain nerves systems. [8][9][10][11][12][13] When the brain functions are totally affected, it may leads to death. Presently, more than 46.8 million peoples affected dementia in the world, it is predictable to spread 74.7 million in 2030. [14][15][16]

show abstract