An adaptive kernel-based weighted extreme learning machine approach for effective detection of Parkinson’s disease

Wang, Yang; Ai, Qing; Sun, Hao

doi:10.1016/j.bspc.2017.06.015

Cited by 28 publications

(11 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accordingly, the weight factor was calculated using the obtained values of k, d, land bto substitute in Eq. (12) as follows: w impact = k/d + l/b = (300/300) + (50/100) = 1.5 (15) Thus, in the present work, the weight factor is found to be w impact = 1.5.…”

Section: E Step 4: Second Level Selection (Fv 2 ) and Weight Factor supporting

confidence: 48%

A Novel Framework of Two Successive Feature Selection Levels Using Weight-Based Procedure for Voice-Loss Detection in Parkinson’s Disease

et al. 2020

View full text Add to dashboard Cite

Parkinson's disease (PD) is one of the public neuro-degenerative disorders. Speech/voice disorder is considered one of the symptoms at an early stage. Acoustic and speech signal processing methods can potentially evaluate and measure PD-related vocal impairment. The present work proposed a novel feature selection framework using two levels of the feature selection procedure for voice-loss detection in PD patients. At the first level selection, the principal component analysis (PCA) and the eigenvector centrality feature selection (ECFS) methods are initially calculated independently, and the selected features from each method are considered as a separated sublist, namely ECFS selected features sublist, and PCA selected features sublist, in the first set. Accordingly, the first set, which is the first level selection set, is generated from the union of these two sublists using the top-selected features from both methods. In the training phase, a second level selection, which forms the second set (which is a subset from the first set), is generated to calculate the proposed weight of each selection method. Since in the present work, the ECFS provided superior performance to the PCA in the first level selection, the ECFS is applied to the first set in order to find weight values based on the contribution/ impact of the top-selected PCA-and ECFS-features in the second level. This weight is determined by finding a proposed ratio, which is multiplied directly by the selected ECFS features in the first level. The selected weighted ECFS features are then combined with the same PCA features to avoid ignoring any of the top-ranked features from the first level. This combination includes the final weighted-hybrid selected features that fed to a support vector machine (SVM) classifier to evaluate the proposed weighted hybrid selected features. Hence, in the test phase, the generated weight is used directly without any further need for the second level selection. Several comparative studies were conducted to evaluate the proposed feature selection performance for PD voice-loss detection. The experimental results established the superiority of the proposed procedure using cubic kernel-SVM with 94% accuracy for voiceloss detection in PD, while, with the same classifier, 88% accuracy was achieved without using the proposed selection method.

show abstract

Section: E Step 4: Second Level Selection (Fv 2 ) and Weight Factor supporting

confidence: 48%

A Novel Framework of Two Successive Feature Selection Levels Using Weight-Based Procedure for Voice-Loss Detection in Parkinson’s Disease

et al. 2020

View full text Add to dashboard Cite

show abstract

“…ELM is a kind of single-hidden layer feed-forward neural networks (SLFNs) [26]- [28]. Given x is an 1 n  feature vector, and j t is an 1 m target vector.…”

Section: A Kernel Extreme Learning Machine (Kelm)mentioning

confidence: 99%

“…The input weights and hidden layer biases can be generated randomly and need not be adjusted at all. So the output weights can be calculated by finding the Least Square solution β HT   of Hβ T  , where H  is the Moore-Penrose generalized inverse of matrix H [28]. In short, the description of ELM algorithm is as follows.…”

Section: A Kernel Extreme Learning Machine (Kelm)mentioning

confidence: 99%

Enhanced Kernel-Based Multilayer Fuzzy Weighted Extreme Learning Machines

Wang

Sun

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

The high-dimensional and imbalanced data classification appears in many actual applications, but there are many problems encountered in practical operation. To overcome the disadvantages of kernelbased multilayer extreme learning machines (ML-KELM), enhanced kernel-based multilayer fuzzy weighted extreme learning machines (EML-KFWELM) has been proposed in this study. First, ML-KELM ignores imbalance learning, so we embed weighted strategy into ML-KELM to enhance the classification performance of the minority class. Meanwhile, we propose fuzzy membership to eliminate classification error caused by outlier and noise samples. Furthermore, we develop an enhanced grey wolf optimization (EGWO) method to perform the parameters optimization and improve the generalization performance of ML-KELM. In addition, the advantage of EML-KFWELM is that representation learning and classification can be integrated into a single learning process. Finally, computational comparisons with other state-of-theart methods are performed on various real-world and gene expression data. Experimental results demonstrate that the proposed EML-KFWELM has good stability and can efficiently deal with the highdimensional and imbalanced data. INDEX TERMS Imbalanced data, kernel-based multilayer extreme learning machines, fuzzy membership, grey wolf optimization.

show abstract

“…The square distance (D 2 is ) between an unknown pattern (U) and training sample is then computed and passed to the kernel function. The units of summation layer-X performs minimization of exp [−D 2 is /(2σ 2 )] * Y i associated with U i and Y performs the minimization of exp [−D 2 is /(2σ 2 )] which provides the output of the predicted result. Although, ANN has been popular due to its unique benefits but suffers from certain drawbacks such as hardware dependency, hard interpretation, etc.…”

Section: A Supervised Learningmentioning

confidence: 99%

“…Over past years, the unique characteristics of the human body known as biometric (e.g. handwriting [1], speech [2], gait, etc.) have been enormously analyzed to make excellent progress in clinical diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Computer-Vision Based Diagnosis of Parkinson’s Disease via Gait: A Survey

2019

View full text Add to dashboard Cite

Parkinson's Disease (PD) being the second most hazardous neurological disorder has developed its roots in damaging people's quality of life (QOL). The ineffectiveness of clinical rating scales makes the PD diagnosis a very complicated task. Thus, more efficient systems are required to perform an automated evaluation of PD for its earlier detection and to enhance life expectancy rate. Gait based clinical diagnosis can provide useful indications regarding the presence of PD. From recent years, computer vision-based (VB) analysis is in great demand and seems to be highly effective in PD inspection. The objective of this article is to systematically analyze the applications of computer vision in PD evaluation through gait. This paper surveys the VB PD gait acquisition modalities as well as provides a concise overview of preprocessing techniques. The study presents a description of PD related gait features, extraction and selection methods used for PD analysis. A number of machine learning techniques for classification of PD and healthy gait are also discussed. This article extensively surveys PD gait datasets considering data from 1997 to 2018. Also, several research gaps in existing studies have identified that need to be addressed in the future. At last, an outline of the proposed idea is given that can cope up with the related issues and can lead to quality VB PD gait investigation.

show abstract

An adaptive kernel-based weighted extreme learning machine approach for effective detection of Parkinson’s disease

Cited by 28 publications

References 33 publications

A Novel Framework of Two Successive Feature Selection Levels Using Weight-Based Procedure for Voice-Loss Detection in Parkinson’s Disease

A Novel Framework of Two Successive Feature Selection Levels Using Weight-Based Procedure for Voice-Loss Detection in Parkinson’s Disease

Enhanced Kernel-Based Multilayer Fuzzy Weighted Extreme Learning Machines

Computer-Vision Based Diagnosis of Parkinson’s Disease via Gait: A Survey

Contact Info

Product

Resources

About