Optimal Stacked Autoencoder-Based Automated Parkinson’s Disease Detection by Implementing Feature Selection Process
Optimal Stacked Autoencoder-Based Automated Parkinson’s Disease Detection by Implementing Feature Selection Process |
||
 |
 |
|
| © 2023 by IJETT Journal | ||
| Volume-71 Issue-9 |
||
| Year of Publication : 2023 | ||
| Author : N. Navaneetha, T. Suresh, V. Sathiyasuntharam |
||
| DOI : 10.14445/22315381/IJETT-V71I9P229 | ||
How to Cite?
N. Navaneetha, T. Suresh, V. Sathiyasuntharam, "Optimal Stacked Autoencoder-Based Automated Parkinson’s Disease Detection by Implementing Feature Selection Process," International Journal of Engineering Trends and Technology, vol. 71, no. 9, pp. 331-340, 2023. Crossref, https://doi.org/10.14445/22315381/IJETT-V71I9P229
Abstract
Parkinson's Disease (PD) recognition generally depends on the valuation of clinical signs and medical observations, which includes the characterization of various motor symptoms. However, classical diagnostic techniques may undergo bias since they depend on activity assessment that can be irregularly delicate to human vision and thus tough to categorize, causing probable misclassification. Simultaneously, initial non-motor PD indications will be insignificant, and others will occur in many other circumstances. Hence, such indications were often unnoticed, making PD diagnosis at an initial stage challenging. For solving such complexities and for refining the assessment procedures and diagnosis of PD, Deep Learning (DL) approaches were applied for classifying PD and vigorous controls or patients who have clinical performances (for example, other Parkinsonian syndromes or movement disorders). This study develops an Automated PD Detection using Feature Selection with Optimal Stacked Autoencoder (APDD-FSOSAE) technique. The presented APDD-FSOSAE technique focuses on assessing PD using Feature Selection (FS) and DL approaches. To attain this, the presented APDD-FSOSAE model comprises the design of a chicken swarm optimization-based FS approach for the selection of optimum features. Next, the APDD-FSOSAE technique utilizes SAE for detecting and classifying PD. Finally, the hyperparameters of the SAE model can be optimally selected by the Bayesian Optimization (BO) model. The investigational output evaluation of the APDD-FSOSAE approach is examined on a benchmark PD dataset. The experimental outputs suggested that the APDD-FSOSAE approach results in improved PD detection results over other models.
Keywords
Data mining, Healthcare, Parkinson’s disease, Deep learning, Feature selection.
References
[1] G. Pahuja, and T.N. Nagabhushan, “A Comparative Study of Existing Machine Learning Approaches for Parkinson's Disease Detection,” IETE Journal of Research, vol. 67, no. 1, pp. 4-14, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[2] C. Okan Sakar et al., “A Comparative Analysis of Speech Signal Processing Algorithms for Parkinson’s Disease Classification and the Use of the Tunable Q-Factor Wavelet Transform,” Applied Soft Computing, vol. 74, pp. 255-263, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Liaqat Ali et al., “Early Diagnosis of Parkinson’s Disease from Multiple Voice Recordings by Simultaneous Sample and Feature Selection,” Expert Systems with Applications, vol. 137, pp. 22-28, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Rohit Lamba et al., “A Hybrid System for Parkinson’s Disease Diagnosis using Machine Learning Techniques,” International Journal of Speech Technology, vol. 25, pp. 583-593, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Amira S. Ashour et al., “A Novel Framework of Two Successive Feature Selection Levels using Weight-Based Procedure for Voice-Loss Detection in Parkinson’s Disease,” IEEE Access, vol. 8, pp. 76193-76203, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Gabriel Solana-Lavalle, and Roberto Rosas-Romero, “Classification of PPMI MRI Scans with Voxel-Based Morphometry and Machine Learning to Assist in the Diagnosis of Parkinson’s Disease,” Computer Methods and Programs in Biomedicine, vol. 198, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Amin Ul Haq et al., “Feature Selection Based on L1-Norm Support Vector Machine and Effective Recognition System for Parkinson’s Disease using Voice Recordings,” IEEE Access, vol. 7, pp. 37718-37734, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Ozkan Cigdem, and Hasan Demirel, “Performance Analysis of Different Classification Algorithms using Different Feature Selection Methods on Parkinson's Disease Detection,” Journal of Neuroscience Methods, vol. 309, pp. 81-90, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Rohit Lamba, Tarun Gulati, and Anurag Jain, “Comparative Analysis of Parkinson’s Disease Diagnosis System,” Advances in Mathematics: Scientific Journal, vol. 9, no. 6, pp. 3399-3406, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Iqra Nissar et al., “Voice-Based Detection of Parkinson’s Disease through Ensemble Machine Learning Approach: A Performance Study,” EAI Endorsed Transactions on Pervasive Health and Technology, vol. 5, no. 19, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Adel A. Bahaddad et al., “Metaheuristics with Deep Learning-Enabled Parkinson’s Disease Diagnosis and Classification Model,” Journal of Healthcare Engineering, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[12] M. Amirthalingam, and R. Ponnusamy, "Intelligent Wireless Endoscopic Image Classification using Gannet Optimization with Deep Learning Model," SSRG International Journal of Electrical and Electronics Engineering, vol. 10, no. 3, pp. 104-113, 2023.
[CrossRef] [Publisher Link]
[13] Yanhao Xiong, and Yaohua Lu, “Deep Feature Extraction from the Vocal Vectors using Sparse Autoencoders for Parkinson’s Classification,” IEEE Access, vol. 8, pp. 27821-27830, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Son V.T. Dao et al., “An Analysis of Vocal Features for Parkinson’s Disease Classification Using Evolutionary Algorithms,” Diagnostics, vol. 12, no. 8, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] R. Sakthi Prabha, and M. Vadivel, "Brain Tumor Stages Prediction using FMS-DLNN Classifier and Automatic RPO-RG Segmentation," SSRG International Journal of Electrical and Electronics Engineering, vol. 10, no. 2, pp. 110-121, 2023.
[CrossRef] [Publisher Link]
[16] Hakan Gunduz, “An Efficient Dimensionality Reduction Method using Filter-Based Feature Selection and Variational Autoencoders on Parkinson's Disease Classification,” Biomedical Signal Processing and Control, vol. 66, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] D. Barathi, "RSF: Roughset Theory Based Fuzzy Classification in Randomized Dimensionality Feature Selection," SSRG International Journal of Computer Science and Engineering, vol. 6, no. 4, pp. 25-28, 2019.
[CrossRef] [Publisher Link]
[18] Muntasir Hoq, Mohammed Nazim Uddin, and Seung-Bo Park, “Vocal Feature Extraction-Based Artificial Intelligent Model for Parkinson’s Disease Detection,” Diagnostics, vol. 11, no. 6, p. 1076, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[19] G. Rajasekaran, and C. Sunitha Ram, "Effective Breast Cancer Prediction based on Feature Extraction, Fusion and Selection using Hybrid Methodologies," SSRG International Journal of Electrical and Electronics Engineering, vol. 10, no. 5, pp. 131-142, 2023.
[CrossRef] [Publisher Link]
[20] Zhi-Feng Liu et al., “Prediction Short-Term Photovoltaic Power using Improved Chicken Swarm Optimizer-Extreme Learning Machine Model,” Journal of Cleaner Production, vol. 248, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Qi Li et al., “Deep Sparse Autoencoder and Recursive Neural Network for EEG Emotion Recognition,” Entropy, vol. 24, no. 9, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Louise Bloch, and Christoph M. Friedrich, “Using Bayesian Optimization to Effectively Tune Random Forest and Xgboost Hyperparameters for Early Alzheimer’s Disease Diagnosis,” International Conference on Wireless Mobile Communication and Healthcare, Springer, pp. 285-299, 2020.
[CrossRef] [Google Scholar] [Publisher Link]