Investigation of the MobileNetV2 Optimal Feature Extraction Layer for EEG-Based Dementia Severity Classification: A Comparative Study
Abstract
1. Introduction
2. Materials and Methods
2.1. Participants and EEG Signal Acquisition
2.2. Preprocessing Steps
- Conventional Filtering and Wavelet DenoisingIn the first step, each channel of EEG-based working memory datasets was tackled with conventional filters, including a notch-filter at 50 Hz and a 0.1–70 Hz band-pass-filter to remove high-frequency noise, such as muscle-related EMG signals typically exceeding 20–50 Hz [26,27]. Additionally, the discrete wavelet transform (DWT) was an additional preprocessing procedure that was used to enhance data quality and to reduce EMG contamination in EEG signals [27].
- Spectrogram ImagesThe signals from each of the denoised EEG electrodes were split into 6 segments of 10 s each. Each epoch has samples because Hz. Therefore, each problem that needed to be examined was saved on a computer and dealt with separately. The power spectral densities () were figured out from these segments. A periodogram, which determined the frequency distribution of the EEG data, is a good way to find [28]. The Fourier transform of the autocorrelation function is a nonparametric evaluation of . For example, Equation (1) shows the periodogram of a signal with a length of L [28], as follows:The spectrogram function was used to figure out the of the EEG time series for this study. This is because the modified periodogram reduces the spectral leakage of the standard periodogram and softens the edges of the signal. It has a high resolution and can be used to analyse biomedical signs [29].The PSD EEG images were turned into three-dimensional images and were resized into pixels to fit the CNN MobileNetV2 input design that is used to automatically extract and sort features.
2.3. Deep Feature Extraction with MobileNetV2 Layers
2.4. Classification
2.4.1. Deep MobileNetV2 Classifier
2.4.2. Machine Learning Classifiers
3. Results and Discussion
3.1. Results of the Preprocessing
3.2. Results of Deep MobileNetV2 Feature Extraction
3.3. Results of Classification
4. Conclusions
Author Contributions
Funding
Data Availability Statement
Conflicts of Interest
References
- Korczyn, A.D.; Vakhapova, V.; Grinberg, L.T. Vascular dementia. J. Neurol. Sci. 2012, 322, 2–10. [Google Scholar] [CrossRef]
- Rizzi, L.; Rosset, I.; Roriz-Cruz, M. Global epidemiology of dementia: Alzheimer’s and vascular types. BioMed Res. Int. 2014, 2014, 908915. [Google Scholar] [CrossRef]
- Acharya, M.; Deo, R.C.; Tao, X.; Barua, P.D.; Devi, A.; Atmakuru, A.; Tan, R.S. Deep learning techniques for automated Alzheimer’s and mild cognitive impairment disease using EEG signals: A comprehensive review of the last decade (2013–2024). Comput. Methods Programs Biomed. 2025, 259, 108506. [Google Scholar] [CrossRef] [PubMed]
- Al-Qazzaz, N.K.; Ali, S.H.B.; Ahmad, S.A.; Chellappan, K.; Islam, M.; Escudero, J. Role of EEG as biomarker in the early detection and classification of dementia. Sci. World J. 2014, 2014, 906038. [Google Scholar] [CrossRef]
- Mellon, L.; Brewer, L.; Hall, P.; Horgan, F.; Williams, D.; Hickey, A. Cognitive impairment six months after ischaemic stroke: A profile from the ASPIRE-S study. BMC Neurol. 2015, 15, 31–39. [Google Scholar] [CrossRef] [PubMed]
- Kalaria, R.N.; Akinyemi, R.; Ihara, M. Stroke injury, cognitive impairment and vascular dementia. Biochim. Biophys. Acta—Mol. Basis Dis. 2016, 1862, 915–925. [Google Scholar] [CrossRef] [PubMed]
- Song, J.; Lee, W.T.; Park, K.A.; Lee, J.E. Association between risk factors for vascular dementia and Adiponectin. BioMed Res. Int. 2014, 2014, 261672. [Google Scholar] [CrossRef]
- Gorelick, P.B.; Scuteri, A.; Black, S.E.; DeCarli, C.; Greenberg, S.M.; Iadecola, C.; Launer, L.J.; Laurent, S.; Lopez, O.L.; Seshadri, S.; et al. Vascular contributions to cognitive impairment and dementia: A statement for healthcare professionals from the American Heart Association/American Stroke Association. Stroke 2011, 42, 2672–2713. [Google Scholar] [CrossRef]
- Meghdadi, A.H.; Stevanovic Karic, M.; McConnell, M.; Rupp, G.; Richard, C.; Hamilton, J.; Salat, D.; Berka, C. Resting state EEG biomarkers of cognitive decline associated with Alzheimer’s disease and mild cognitive impairment. Front. Aging Neurosci. 2021, 16, e0244180. [Google Scholar] [CrossRef]
- Bonanni, L.; Franciotti, R.; Nobili, F.; Kramberger, M.G.; Taylor, J.P.; Garcia-Ptacek, S.; Falasca, N.W.; Famá, F.; Cromarty, R.; E-DLB Study Group; et al. EEG markers of dementia with Lewy bodies: A multicenter cohort study. J. Alzheimer’s Dis. 2016, 54, 1649–1657. [Google Scholar] [CrossRef]
- Escudero, J.; Hornero, R.; Abásolo, D.; Fernández, A. Quantitative evaluation of artifact removal in real magnetoencephalogram signals with blind source separation. Ann. Biomed. Eng. 2011, 39, 2274–2286. [Google Scholar] [CrossRef]
- Siuly, S.; Alçin, Ö.F.; Wang, H.; Li, Y.; Wen, P. Exploring rhythms and channels-based EEG biomarkers for early detection of alzheimer’s disease. IEEE Trans. Emerg. Top. Comput. Intell. 2024, 8, 1609–1623. [Google Scholar] [CrossRef]
- Al-Qazzaz, N.K.; Ali, S.H.B.M.; Ahmad, S.A.; Islam, M.S.; Escudero, J. Discrimination of stroke-related mild cognitive impairment and vascular dementia using EEG signal analysis. Med. Biol. Eng. Comput. 2018, 56, 137–157. [Google Scholar] [CrossRef] [PubMed]
- Cataldo, A.; Criscuolo, S.; De Benedetto, E.; Masciullo, A.; Pesola, M.; Picone, J.; Schiavoni, R. EEG complexity-based algorithm using Multiscale Fuzzy Entropy: Towards a detection of Alzheimer’s disease. Measurement 2024, 225, 114040. [Google Scholar] [CrossRef]
- Subramanian, N.; Elharrouss, O.; Al-Maadeed, S.; Chowdhury, M. A review of deep learning-based detection methods for COVID-19. Comput. Biol. Med. 2022, 143, 105233. [Google Scholar] [CrossRef]
- Soomro, T.A.; Zheng, L.; Afifi, A.J.; Ali, A.; Soomro, S.; Yin, M.; Gao, J. Image segmentation for MR brain tumor detection using machine learning: A Review. IEEE Rev. Biomed. Eng. 2022, 16, 70–90. [Google Scholar] [CrossRef]
- Marin, I.; Marasović, T.; Gotovac, S. Siamese Network for Content-Based Image Retrieval: Detection of Alzheimer’s Disease from neuroimaging data. In Proceedings of the 2022 IEEE International Conference on Software, Telecommunications and Computer Networks (SoftCOM), Split, Croatia, 22–24 September 2022; pp. 1–6. [Google Scholar]
- Klimesch, W. EEG alpha and theta oscillations reflect cognitive and memory performance: A review and analysis. Brain Res. Rev. 1999, 29, 169–195. [Google Scholar] [CrossRef]
- Boutros, N.N.; Arfken, C.; Galderisi, S.; Warrick, J.; Pratt, G.; Iacono, W. The status of spectral EEG abnormality as a diagnostic test for schizophrenia. Schizophr. Res. 2008, 99, 225–237. [Google Scholar] [CrossRef]
- James, L.M.; Halliday, D.M.; Stephens, J.A.; Farmer, S.F. On the development of human corticospinal oscillations: Age-related changes in EEG–EMG coherence and cumulant. Eur. J. Neurosci. 2008, 27, 3369–3379. [Google Scholar] [CrossRef]
- Amin, S.U.; Alsulaiman, M.; Muhammad, G.; Mekhtiche, M.A.; Hossain, M.S. Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion. Future Gener. Comput. Syst. 2019, 101, 542–554. [Google Scholar] [CrossRef]
- Grosse, P.; Cassidy, M.J.; Brown, P. EEG–EMG, MEG–EMG and EMG–EMG frequency analysis: Physiological principles and clinical applications. Clin. Neurophysiol. 2002, 113, 1523–1531. [Google Scholar] [CrossRef]
- Liu, J.; Sheng, Y.; Liu, H. Corticomuscular coherence and its applications: A review. Front. Hum. Neurosci. 2019, 13, 100. [Google Scholar] [CrossRef]
- Tuncel, D.; Dizibuyuk, A.; Kiymik, M.K. Time frequency based coherence analysis between EEG and EMG activities in fatigue duration. J. Med. Syst. 2010, 34, 131–138. [Google Scholar] [CrossRef]
- Al-Qazzaz, N.K.; Ali, S.; Ahmad, S.A.; Islam, M.S.; Ariff, M.I. Selection of mother wavelets thresholding methods in denoising multi-channel EEG signals during working memory task. In Proceedings of the 2014 IEEE Conference on Biomedical Engineering and Sciences (IECBES), Kuala Lumpur, Malaysia, 8–10 December 2014; pp. 214–219. [Google Scholar]
- Al-Qazzaz, N.K.; Sabir, M.K.; Ali, S.H.B.M.; Ahmad, S.A.; Grammer, K. Multichannel optimization with hybrid spectral-entropy markers for gender identification enhancement of emotional-based EEGs. IEEE Access 2021, 9, 107059–107078. [Google Scholar] [CrossRef]
- Makaram, N.; Gupta, S.; Pesce, M.; Bolton, J.; Stone, S.; Haehn, D.; Pomplun, M.; Papadelis, C.; Pearl, P.; Rotenberg, A.; et al. Deep learning-based visual complexity analysis of electroencephalography time-frequency images: Can it localize the epileptogenic zone in the brain? Algorithms 2023, 16, 567. [Google Scholar] [CrossRef] [PubMed]
- Al-Qazzaz, N.K.; Hamid Bin Mohd Ali, S.; Ahmad, S.A.; Islam, M.S.; Escudero, J. Automatic artifact removal in EEG of normal and demented individuals using ICA–WT during working memory tasks. Sensors 2017, 17, 1326. [Google Scholar] [CrossRef] [PubMed]
- Ieracitano, C.; Mammone, N.; Bramanti, A.; Hussain, A.; Morabito, F.C. A convolutional neural network approach for classification of dementia stages based on 2D-spectral representation of EEG recordings. Neurocomputing 2019, 323, 96–107. [Google Scholar] [CrossRef]
- Rahman, T.; Khandakar, A.; Qiblawey, Y.; Tahir, A.; Kiranyaz, S.; Kashem, S.B.A.; Islam, M.T.; Al Maadeed, S.; Zughaier, S.M.; Khan, M.S.; et al. Exploring the effect of image enhancement techniques on COVID-19 detection using chest X-ray images. Comput. Biol. Med. 2021, 132, 104319. [Google Scholar] [CrossRef]
- Chandra, S.K.; Bajpai, M.K. Fractional mesh-free linear diffusion method for image enhancement and segmentation for automatic tumor classification. Biomed. Signal Process. Control 2020, 58, 101841. [Google Scholar] [CrossRef]
- Sandler, M.; Howard, A.; Zhu, M.; Zhmoginov, A.; Chen, L.C. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–22 June 2018; pp. 4510–4520. [Google Scholar]
- Rabcan, J.; Levashenko, V.; Zaitseva, E.; Kvassay, M. EEG signal classification based on fuzzy classifiers. IEEE Trans. Ind. Inform. 2021, 18, 757–766. [Google Scholar] [CrossRef]
- Ganaie, M.; Kumari, A.; Malik, A.K.; Tanveer, M. EEG signal classification using improved intuitionistic fuzzy twin support vector machines. Neural Comput. Appl. 2024, 36, 163–179. [Google Scholar] [CrossRef]
- Cherian, R.; Kanaga, E.G. Theoretical and methodological analysis of EEG based seizure detection and prediction: An exhaustive review. J. Neurosci. Methods 2022, 369, 109483. [Google Scholar] [CrossRef]
- Lin, F.; Han, J.; Xue, T.; Lin, J.; Chen, S.; Zhu, C.; Lin, H.; Chen, X.; Lin, W.; Huang, H. Predicting cognitive impairment in outpatients with epilepsy using machine learning techniques. Sci. Rep. 2021, 11, 20002. [Google Scholar] [CrossRef] [PubMed]
- Hashmi, A.; Barukab, O. Dementia classification using deep reinforcement learning for early diagnosis. Appl. Sci. 2023, 13, 1464. [Google Scholar] [CrossRef]
- Ayman, U.; Zia, M.S.; Okon, O.D.; Rehman, N.U.; Meraj, T.; Ragab, A.E.; Rauf, H.T. Epileptic patient activity recognition system using extreme learning machine method. Biomedicines 2023, 11, 816. [Google Scholar] [CrossRef] [PubMed]
- Rokach, L.; Maimon, O. Data Mining with Decision Trees, 2nd ed.; World Scientific: Singapore, 2014. [Google Scholar]
- de Miras, J.R.; Ibáñez-Molina, A.J.; Soriano, M.F.; Iglesias-Parro, S. Schizophrenia classification using machine learning on resting state EEG signal. Biomed. Signal Process. Control 2023, 79, 104233. [Google Scholar] [CrossRef]
MobileNetV2 | Evaluation Metrics | Control | MCI | VaD |
---|---|---|---|---|
precision | 71.2 | 76.9 | 76.1 | |
sensitivity | 64.9 | 70.2 | 89.5 | |
specificity | 86.8 | 89.5 | 86 | |
accuracy | 74.9 | 74.9 | 74.9 | |
F-measure | 67.9 | 73.4 | 82.3 |
KNN | Evaluation Metrics | Control | MCI | VaD |
---|---|---|---|---|
‘Conv-1’ | precision | 89.8 | 96.2 | 93.2 |
sensitivity | 93 | 89.5 | 96.5 | |
specificity | 94.7 | 98.2 | 96.5 | |
accuracy | 93 | 93 | 93 | |
F-measure | 91.4 | 92.7 | 94.8 | |
‘Conv-1-bn’ | precision | 89.8 | 96.2 | 93.2 |
sensitivity | 93 | 89.5 | 96.5 | |
specificity | 94.7 | 98.2 | 96.5 | |
accuracy | 93 | 93 | 93 | |
F-measure | 91.4 | 92.7 | 94.8 | |
‘out-relu’ | precision | 59.6 | 94.7 | 98.2 |
sensitivity | 100 | 80.6 | 80 | |
specificity | 100 | 83.2 | 97.1 | |
accuracy | 84.2 | 84.2 | 84.2 | |
F-measure | 74.7 | 87 | 88.2 | |
‘global-average-pooling2d-1’ | precision | 91.7 | 98.1 | 94.8 |
sensitivity | 96.5 | 91.2 | 96.5 | |
specificity | 95.6 | 99.1 | 97.4 | |
accuracy | 94.7 | 94.7 | 94.7 | |
F-measure | 94 | 94.5 | 95.7 | |
‘fc’ | precision | 94.5 | 93.1 | 96.6 |
sensitivity | 91.2 | 94.7 | 98.2 | |
specificity | 97.4 | 96.5 | 98.2 | |
accuracy | 94.2 | 94.2 | 94.2 | |
F-measure | 92.9 | 93.9 | 97.4 |
DT | Evaluation Metrics | Control | MCI | VaD |
---|---|---|---|---|
‘Conv-1’ | precision | 93.1 | 96.4 | 94.7 |
sensitivity | 94.7 | 94.7 | 94.7 | |
specificity | 96.5 | 98.2 | 97.4 | |
accuracy | 94.7 | 94.7 | 94.7 | |
F-measure | 93.9 | 95.6 | 94.7 | |
‘Conv-1-bn’ | precision | 93.1 | 96.4 | 94.7 |
sensitivity | 94.7 | 94.7 | 94.7 | |
specificity | 96.5 | 98.2 | 97.4 | |
accuracy | 94.7 | 94.7 | 94.7 | |
F-measure | 93.9 | 95.6 | 94.7 | |
‘out-relu’ | precision | 96.4 | 88.7 | 98.1 |
sensitivity | 93 | 96.5 | 93 | |
specificity | 98.2 | 93.9 | 99.1 | |
accuracy | 94.2 | 94.2 | 94.2 | |
F-measure | 94.6 | 92.4 | 95.5 | |
‘global-average-pooling2d-1’ | precision | 94.8 | 96.4 | 96.5 |
sensitivity | 96.5 | 94.7 | 96.5 | |
specificity | 97.4 | 98.2 | 98.2 | |
accuracy | 95.9 | 95.9 | 95.9 | |
F-measure | 95.7 | 95.6 | 96.5 | |
‘fc’ | precision | 96.4 | 94.8 | 96.6 |
sensitivity | 93 | 96.5 | 98.2 | |
specificity | 98.2 | 97.4 | 98.2 | |
accuracy | 95.3 | 95.3 | 95.3 | |
F-measure | 94.6 | 95.7 | 97.4 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Al-Qazzaz, N.K.; Ali, S.H.B.M.; Ahmad, S.A. Investigation of the MobileNetV2 Optimal Feature Extraction Layer for EEG-Based Dementia Severity Classification: A Comparative Study. Algorithms 2025, 18, 620. https://doi.org/10.3390/a18100620
Al-Qazzaz NK, Ali SHBM, Ahmad SA. Investigation of the MobileNetV2 Optimal Feature Extraction Layer for EEG-Based Dementia Severity Classification: A Comparative Study. Algorithms. 2025; 18(10):620. https://doi.org/10.3390/a18100620
Chicago/Turabian StyleAl-Qazzaz, Noor Kamal, Sawal Hamid Bin Mohd Ali, and Siti Anom Ahmad. 2025. "Investigation of the MobileNetV2 Optimal Feature Extraction Layer for EEG-Based Dementia Severity Classification: A Comparative Study" Algorithms 18, no. 10: 620. https://doi.org/10.3390/a18100620
APA StyleAl-Qazzaz, N. K., Ali, S. H. B. M., & Ahmad, S. A. (2025). Investigation of the MobileNetV2 Optimal Feature Extraction Layer for EEG-Based Dementia Severity Classification: A Comparative Study. Algorithms, 18(10), 620. https://doi.org/10.3390/a18100620