Optimized Hybrid Model for Enhanced Parkinson’s Disease Classification Using Feature Fused Voice Signal

International Journal of Electronics and Communication Engineering

© 2023 by SSRG - IJECE Journal

Volume 10 Issue 11

Year of Publication : 2023

Authors : S. Sharanyaa, M. Sambath

10.14445/23488549/IJECE-V10I11P102

How to Cite?

S. Sharanyaa, M. Sambath, "Optimized Hybrid Model for Enhanced Parkinson’s Disease Classification Using Feature Fused Voice Signal," SSRG International Journal of Electronics and Communication Engineering, vol. 10,  no. 11, pp. 11-26, 2023. Crossref, https://doi.org/10.14445/23488549/IJECE-V10I11P102

Abstract:

Parkinson’s Disease (PD) is a common neuro disorder that leads to reduced nerve function in the brain as a result of decreased dopamine generation. The disease is progressive, and patients may have difficulty speaking, resulting in speech variations. Hence, it is essential to detect the disease at an early stage, and through proper diagnosis, the effect of Parkinson’s disease can be controlled. This work aims to detect and classify PD based on a vocal feature set using a hybrid CNN-ALSTM model. The model is trained with Spectral, Acoustic, and Mel-Spectrogram features obtained from de-noised voice signals. This proposed work involves four phases. In the first phase, voice signals are extracted from the voice input data, and de-noising is done using Improved Optimized Variational Mode Decomposition (IO-VMD). In the second phase, the Mel-Spectrograms are generated from the pre-processed data, where deep features are extracted and trained using Custom CNN, EfficientNetB0, and Inceptionv3 models. In the third phase, a metaheuristic Squirrel Search Water Cycle Algorithm (SSWA) is applied to the feature vectors, where SSWA is used for feature selection and hyper parameter tuning. Finally, the spectral and acoustic features extracted from voice signals are concatenated with the mel spectrogram feature vectors, trained, and classified using the Attention based Long Short Term Memory (ALSTM) model. A comparative analysis of models like CNN-ALSTM, Inceptionv3- ALSTM, and EfficientNetB0-ALSTM is carried out to classify PD. From the result analysis, the SSWA algorithm with a proposed hybrid EfficientNetB0-ALSTM model achieves an accuracy of 96.8% and performs better than the other models.

Keywords:

Neural network, Optimization algorithm, Spectrogram, Transfer learning, Voice signal.

References:

[1] Liaqat Ali et al., “A Novel Sample and Feature Dependent Ensemble Approach for Parkinson’s Disease Detection,” Neural Computing and Applications, vol. 35, pp. 15997-16010, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Carlo Ricciardi et al., “Using Gait Analysis’ Parameters to Classify Parkinsonism: A Data Mining Approach,” Computer Methods and Programs in Biomedicine, vol. 180, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Lucijano Berus et al., “Classifying Parkinson’s Disease Based on Acoustic Measures Using Artificial Neural Networks,” Sensor, vol. 19, no. 1, pp. 1-15, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Marjolein A.E. van Stiphout et al., “Oral Health of Parkinson’s Disease Patients: A Case-Control Study,” Parkinson’s Disease, vol. 2018, pp. 1-8, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[5] M. Abdar, and M. Zomorodi-Moghadam, “Impact of Patients’ Gender on Parkinson’s Disease Using Classification Algorithms,” Journal of AI and Data Mining, vol. 6, no. 2, pp. 277-285, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Rania Khaskhoussy, and Yassine Ben Ayed, “Improving Parkinson’s Disease Recognition through Voice Analysis Using Deep Learning,” Pattern Recognition Letters, vol. 168, pp. 64-70, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Zhi-Jing Xu et al., “Parkinson’s Disease Detection Based on Spectrogram-Deep Convolutional Generative Adversarial Network Sample Augmentation,” IEEE Access, vol. 8, pp. 206888-206900, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Luiz C.F. Ribeiro, Luis C.S. Afonso, and João P. Papa, “Bag of Samplings for Computer-Assisted Parkinson’s Disease Diagnosis Based on Recurrent Neural Networks,” Computers in Biology and Medicine, vol. 115, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Afzal Hussain Shahid, and Maheshwari Prasad Singh, “A Deep Learning Approach for Prediction of Parkinson’s Disease Progression,” Biomedical Engineering Letters, vol. 10, pp. 227-239, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Atiqur Rahman et al., “Parkinson’s Disease Diagnosis in Cepstral Domain Using MFCC and Dimensionality Reduction with SVM Classifier,” Mobile Information Systems, vol. 2021, pp. 1-10, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Wondimu Lambamo, Ramasamy Srinivasagan, and Worku Jifara, “Analyzing Noise Robustness of Cochleogram and Mel Spectrogram Features in Deep Learning Based Speaker Recognition,” Applied Sciences, vol. 13, no. 1, pp. 1-12, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Jan Hlavnička et al., “Automated Analysis of Connected Speech Reveals Early Biomarkers of Parkinson’s Disease in Patients with Rapid Eye Movement Sleep Behaviour Disorder,” Scientific Reports, vol. 7, no. 1, pp. 1-13, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Zayrit Soumaya et al., “The Detection of Parkinson Disease Using the Genetic Algorithm and SVM Classifier,” Applied Acoustics, vol. 171, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Pedro Gómez-Vilda et al., “The Role of Data Analytics in the Assessment of Pathological Speech-A Critical Appraisal,” Applied Sciences, vol. 12, no. 21, pp. 1-24, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Fatih Demir et al., “A Simple and Effective Approach Based on a Multi-Level Feature Selection for Automated Parkinson’s Disease Detection,” Journal of Personalized Medicine, vol. 12, no. 1, pp. 1-14, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[16] N.P. Narendra, Björn Schuller, and Paavo Alku, “The Detection of Parkinson’s Disease from Speech Using Voice Source Information,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 29, pp. 1925-1936, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Biswajit Karan, Sitanshu Sekhar Sahu, and Kartik Mahto, “Parkinson Disease Prediction Using Intrinsic Mode Function Based Features from Speech Signal,” Biocybernetics and Biomedical Engineering, vol. 40, no. 1, pp. 249-264, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Andrius Lauraitis et al., “Detection of Speech Impairments Using Cepstrum, Auditory Spectrogram and Wavelet Time Scattering Domain Features,” IEEE Access, vol. 8, pp. 96162-96172, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Javier Carrón et al., “A Mobile-Assisted Voice Condition Analysis System for Parkinson’s Disease: Assessment of Usability Conditions,” Biomedical Engineering Online, vol. 20, pp. 1-24, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Aditi Govindu, and Sushila Palwe, “Early Detection of Parkinson’s Disease Using Machine Learning,” Procedia Computer Science, vol. 218, pp. 249-261, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Nada R. Yousif et al., “A Generic Optimization and Learning Framework for Parkinson Disease via Speech and Handwritten Record,” Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 8, pp. 10673-10693, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[22] K. Kamalakannan, G. Anandharaj, and M.A. Gunavathie, “Performance Analysis of Attributes Selection and Discretization of Parkinson’s Disease Dataset Using Machine Learning Techniques: A Comprehensive Approach,” International Journal of System Assurance Engineering and Management, vol. 14, pp. 1523-1529, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Máté Hireš et al., “Voice-Specific Augmentations for Parkinson’s Disease Detection Using Deep Convolutional Neural Network,” 2022 IEEE 20th Jubilee World Symposium on Applied Machine Intelligence and Informatics (SAMI), Poprad, Slovakia, pp. 213-218, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Dharani M.K., and R. Thamilselvan, “Hybrid Optimization Enabled Deep Learning Model for Parkinson’s Disease Classification,” The Imaging Science Journal, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Giovanni Costantini et al., “Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison,” Sensors, vol. 23, no. 4, pp. 1-22, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Sanjana Singh, and Wenyao Xu, “Robust Detection of Parkinson’s Disease Using Harvested Smartphone Voice Data: A Telemedicine Approach,” Telemedicine and E-Health, vol. 26, no. 3, pp. 327-334, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Changqin Quan et al., “End-to-End Deep Learning Approach for Parkinson’s Disease Detection from Speech Signals,” Biocybernetics and Biomedical Engineering, vol. 42, no. 2, pp. 556-574, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Valerio Cesarini et al., “Voice Disorder Multi-Class Classification for the Distinction of Parkinson’s Disease and Adductor Spasmodic Dysphonia,” Applied Sciences, vol. 13, no. 15, pp. 1-16, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Sabrina Scimeca et al., “Robust and Language-Independent Acoustic Features in Parkinson’s Disease,” Frontiers in Neurology, vol. 14, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Guidong Bao et al., “Classification of Dysphonic Voices in Parkinson’s Disease with Semi-Supervised Competitive Learning Algorithm,” Biosensors, vol. 12, no. 7, pp. 1-17, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Brett Koonce, EfficientNet Convolutional Neural Networks with Swift for Tensorflow, Image Recognition and Dataset Categorization, 1st ed., Apress Berkeley, CA, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[32] P. Ravi Prakash et al., “A Novel Convolutional Neural Network with Gated Recurrent Unit for Automated Speech Emotion Recognition and Classification,” Journal of Control and Decision, vol. 10, no. 1, pp. 54-63, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[33] N. Dong et al., “Inception v3 Based Cervical Cell Classification Combined with Artificially Extracted Features,” Applied Soft Computing, vol. 93, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[34] mPower Public Researcher Portal, mPower: Mobile Parkinson Disease Study, 2015. [Online]. Available: https://www.synapse.org/#!Synapse:syn4993293/wiki/247859 [35] Hua Li et al., “An Optimized VMD Method and Its Applications in Bearing Fault Diagnosis,” Measurement, vol. 166, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[36] Mohit Jain, Vijander Singh, and Asha Rani, “A Novel Nature-Inspired Algorithm for Optimization: Squirrel Search Algorithm,” Swarm and Evolutionary Computation, vol. 44, pp. 148-175, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[37] Hadi Eskandar et al., “Water Cycle Algorithm–A Novel Metaheuristic Optimization Method for Solving Constrained Engineering Optimization Problems,” Computers & Structures, vol. 110-111, pp. 151-166, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[38] K. Sangeetha, and D. Prabha, “Sentiment Analysis of Student Feedback Using Multi-Head Attention Fusion Model of Word and Context Embedding for LSTM,” Journal of Ambient Intelligence and Humanized Computing, vol. 12, pp. 4117-4126, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[39] Hanbin Zhang et al., “DeepVoice: A Voiceprint-Based Mobile Health Framework for Parkinson's Disease Identification,” 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI), Las Vegas, NV, USA, pp. 214-217, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[40] Timothy J. Wroge et al., “Parkinson’s Disease Diagnosis Using Machine Learning and Voice,” 2018 IEEE Signal Processing in Medicine and Biology Symposium (SPMB), Philadelphia, PA, USA, pp. 1-7, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[41] Onur Karaman et al., “Robust Automated Parkinson Disease Detection Based on Voice Signals with Transfer Learning,” Expert Systems with Applications, vol. 178, 2021.
[CrossRef] [Google Scholar] [Publisher Link]