OpenLB
Open Library of Bioscience
Advanced Search
Physical and engineering sciences in medicine
Dec, 2023;46 (4): 1519-1534.

Development of hybrid feature learner model integrating FDOSM for golden subject identification in motor imagery.

Z T Al-Qaysi, A S Albahri, M A Ahmed, Saleh Mahdi Mohammed
Author Information
  1. Z T Al-Qaysi: Department of Computer Science, Computer Science and Mathematics College, Tikrit University, Tikrit, Iraq.
  2. A S Albahri: Iraqi Commission for Computers and Informatics (ICCI), Baghdad, Iraq. ahmed.bahri1978@gmail.com. ORCID
  3. M A Ahmed: Department of Computer Science, Computer Science and Mathematics College, Tikrit University, Tikrit, Iraq.
  4. Saleh Mahdi Mohammed: Department of Computer Technology Engineering, College of Information Technology, Imam Ja'afar Al-Sadiq University, Baghdad, Iraq.
PMID: 37603133 DOI: 10.1007/s13246-023-01316-6

Abstract

Brain-computer interfaces (BCIs) based on motor imagery (MI) face challenges due to the complex nature of brain activity, nonstationary and high-dimensional properties, and individual variations in motor behaviour. The identification of a consistent "golden subject" in MI-based BCIs remains an open challenge, complicated by multiple evaluation metrics and conflicting trade-offs, presenting complex Multi-Criteria Decision Making (MCDM) problems. This study proposes a hybrid brain signal decoding model called Hybrid Adaboost Feature Learner (HAFL), which combines feature extraction and classification using VGG-19, STFT, and Adaboost classifier. The model is validated using a pre-recorded MI-EEG dataset from the BCI competition at Graz University. The fuzzy decision-making framework is integrated with HAFL to allocate a golden subject for MI-BCI applications through the Golden Subject Decision Matrix (GSDM) and the Fuzzy Decision by Opinion Score Method (FDOSM). The effectiveness of the HAFL model in addressing inter-subject variability in EEG-based MI-BCI is evaluated using an MI-EEG dataset involving nine subjects. Comparing subject performance fairly is challenging due to complexity variations, but the FDOSM method provides valuable insights. Through FDOSM-based External Group Aggregation (EGA), subject S5 achieves the highest score of 2.900, identified as the most promising golden subject for subject-to-subject transfer learning. The proposed methodology is compared against other benchmark studies from various key perspectives and exhibits significant novelty in several aspects. The findings contribute to the development of more robust and effective BCI systems, paving the way for advancements in subject-to-subject transfer learning for BCI-MI applications.

Keywords

Brain-computer interface FDOSM Golden subject Motor imagery Short-time fourier transform Transfer learning VGG-19

References

  1. Al-Saegh A et al (2021) Deep learning for motor imagery EEG-based classification: a review. Biomed Signal Process Control 63:102172 [DOI: 10.1016/j.bspc.2020.102172]
  2. Albahri A et al (2023) A systematic review of using deep learning technology in the steady-state visually evoked potential-based brain-computer interface applications: current trends and future trust methodology. Int J Telemed Appl. https://doi.org/10.1155/2023/7741735 [DOI: 10.1155/2023/7741735]
  3. Zhang R et al (2019) “A new convolutional neural network for motor imagery classification,” in 2019. Chinese Control Conference (CCC) 2019:8428–8432 [DOI: 10.23919/ChiCC.2019.8865152]
  4. Al-Qaysi Z et al (2018) A review of disability EEG based wheelchair control system: coherent taxonomy, open challenges and recommendations. Comput Methods Programs Biomed 164:221–237 [DOI: 10.1016/j.cmpb.2018.06.012]
  5. Liu R et al (2017) Identification of anisomerous motor imagery EEG signals based on complex algorithms. Comput Intell Neurosci. https://doi.org/10.1155/2017/2727856 [DOI: 10.1155/2017/2727856]
  6. Ferdous MJ, Ali MS (2017) Time-frequency analysis of EEG signal processing for artifact detection. Int J Sci Res 53:2319–7064
  7. Chaudhary S et al (2019) Convolutional neural network based approach towards motor imagery tasks EEG signals classification. IEEE Sens J 19:4494–4500 [DOI: 10.1109/JSEN.2019.2899645]
  8. Y. Du, et al., "Classification of seizure EEGs based on short-time fourier transform and hidden markov model," in 2020 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), 2020, pp. 875-880
  9. N. Sharma, et al., "Epileptic seizure detection using STFT based peak mean feature and support vector machine," in 2021 8th International Conference on Signal Processing and Integrated Networks (SPIN), 2021, pp. 1131–1136.
  10. Qiao W, Bi X (2020) Ternary-task convolutional bidirectional neural turing machine for assessment of EEG-based cognitive workload. Biomed Signal Process Control 57:101745 [DOI: 10.1016/j.bspc.2019.101745]
  11. Freer D, Yang G-Z (2020) Data augmentation for self-paced motor imagery classification with C-LSTM. J Neural Eng 17:016041 [DOI: 10.1088/1741-2552/ab57c0]
  12. Amin SU et al (2019) Deep Learning for EEG motor imagery classification based on multi-layer CNNs feature fusion. Futur Gener Comput Syst 101:542–554 [DOI: 10.1016/j.future.2019.06.027]
  13. K. S. Omar, et al., "A machine learning approach to predict autism spectrum disorder," in 2019 International conference on electrical, computer and communication engineering (ECCE), 2019, pp. 1–6.
  14. Al-Saegh A et al (2021) CutCat: an augmentation method for EEG classification. Neural Netw 141:433–443 [DOI: 10.1016/j.neunet.2021.05.032]
  15. Al-Qaysi Z et al (2021) Systematic review of training environments with motor imagery brain–computer interface: coherent taxonomy, open issues and recommendation pathway solution. Heal Technol 11:783–801 [DOI: 10.1007/s12553-021-00560-8]
  16. X. Wang, et al., "A Hybrid Transfer Learning Approach for Motor Imagery Classification in Brain-Computer Interface," In: 2021 IEEE 3rd Global Conference on Life Sciences and Technologies (LifeTech), 2021, pp. 496–500.
  17. W. Wei, et al., "A transfer learning framework for RSVP-based brain computer interface," in 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 2020, pp. 2963–2968.
  18. X. Wei, et al., "Inter-subject deep transfer learning for motor imagery eeg decoding," in 2021 10th International IEEE/EMBS Conference on Neural Engineering (NER), 2021, pp. 21–24.
  19. D.-K. Kim, et al., “Sequential Transfer Learning via Segment After Cue Enhances the Motor Imagery-based Brain-Computer Interface,” in 2021 9th International Winter Conference on Brain-Computer Interface (BCI), 2021, pp. 1–5.
  20. K.-T. Kim, et al., "Subject-Transfer Approach based on Convolutional Neural Network for the SSSEP-BCIs," In: 2021 9th International Winter Conference on Brain-Computer Interface (BCI), 2021, pp. 1–3.
  21. Al-Qaysi Z et al (2022) Wavelet-based Hybrid learning framework for motor imagery classification. Iraqi J Electr Electron Eng. https://doi.org/10.37917/ijeee.19.1.6 [DOI: 10.37917/ijeee.19.1.6]
  22. T. Kaur and T. K. Gandhi, "Automated brain image classification based on VGG-16 and transfer learning," in 2019 International Conference on Information Technology (ICIT), 2019, pp. 94-98
  23. Sharma M (2019) Improved autistic spectrum disorder estimation using Cfs subset with greedy stepwise feature selection technique. Int J Inf Technol. https://doi.org/10.1007/s41870-019-00335-5 [DOI: 10.1007/s41870-019-00335-5]
  24. Alahmari F (2020) A comparison of resampling techniques for medical data using machine learning. J Inf Knowl Manag 19:2040016 [DOI: 10.1142/S021964922040016X]
  25. Y. Mangalmurti and N. Wattanapongsakorn, "COVID-19 and Other Lung Disease Detection Using VGG19 Pretrained Features and Support Vector Machine," In: 2021 25th International Computer Science and Engineering Conference (ICSEC), 2021, pp. 51–56.
  26. M. Ahmed, et al., "Automatic COVID-19 pneumonia diagnosis from x-ray lung image: A Deep Feature and Machine Learning Solution," In: Journal of Physics: Conference Series, 2021, p. 012099.
  27. A. Saidi, et al., "A novel epileptic seizure detection system using scalp EEG signals based on hybrid CNN-SVM classifier," in 2021 IEEE Symposium on Industrial Electronics & Applications (ISIEA), 2021, pp. 1-6
  28. Sun B et al (2022) Golden subject is everyone: a subject transfer neural network for motor imagery-based brain computer interfaces. Neural Netw 151:111–120 [DOI: 10.1016/j.neunet.2022.03.025]
  29. Roy AM (2022) Adaptive transfer learning-based multiscale feature fused deep convolutional neural network for EEG MI multiclassification in brain–computer interface. Eng Appl Artif Intell 116:105347 [DOI: 10.1016/j.engappai.2022.105347]
  30. Ahmed M et al (2023) Intelligent decision-making framework for evaluating and benchmarking hybridized multi-deep transfer learning models: managing COVID-19 and beyond. Int J Inf Technol Decis Mak. https://doi.org/10.1142/S0219622023500463 [DOI: 10.1142/S0219622023500463]
  31. Alamoodi A et al (2023) Hospital selection framework for remote MCD patients based on fuzzy q-rung orthopair environment. Neural Comput Appl 35:6185–6196 [DOI: 10.1007/s00521-022-07998-5]
  32. Albahri OS et al (2019) Fault-tolerant mHealth framework in the context of IoT-based real-time wearable health data sensors. IEEE access 7:50052–50080 [DOI: 10.1109/ACCESS.2019.2910411]
  33. Ferdous MJ, Ali MS (2017) Time-frequency analysis of EEG signal processing for artifact detection. Int J Sci Res 53:2319–7064
  34. Alsalem M et al (2021) Based on T-spherical fuzzy environment: a combination of FWZIC and FDOSM for prioritising COVID-19 vaccine dose recipients. J Infect Public Health 14:1513–1559 [DOI: 10.1016/j.jiph.2021.08.026]
  35. Salih MM et al (2023) Benchmarking framework for COVID-19 classification machine learning method based on fuzzy decision by opinion score method. Iraqi J Sci. https://doi.org/10.24996/ijs.2023.64.2.36 [DOI: 10.24996/ijs.2023.64.2.36]
  36. Salih MM et al (2022) A new extension of fuzzy decision by opinion score method based on fermatean fuzzy: a benchmarking COVID-19 machine learning methods. J Intell Fuzzy Syst. https://doi.org/10.3233/JIFS-220707 [DOI: 10.3233/JIFS-220707]
  37. Mahmoud U et al (2022) DAS benchmarking methodology based on FWZIC II and FDOSM II to support industrial community characteristics in the design and implementation of advanced driver assistance systems in vehicles. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-022-04201-4 [DOI: 10.1007/s12652-022-04201-4]
  38. Alamoodi A et al (2022) Based on neutrosophic fuzzy environment: a new development of FWZIC and FDOSM for benchmarking smart e-tourism applications. Complex Intell Syst 8:3479–3503 [DOI: 10.1007/s40747-022-00689-7]
  39. Al-Qaysi Z et al (2023) A systematic rank of smart training environment applications with motor imagery brain-computer interface. Multimed Tools Appl 82:17905–17927 [DOI: 10.1007/s11042-022-14118-x]
  40. Tangermann M et al (2012) Review of the BCI competition IV. Front Neurosci. https://doi.org/10.3389/fnins.2012.00055 [DOI: 10.3389/fnins.2012.00055]
  41. Jasim MH et al (2019) Emotion detection among muslims and Non-muslims while listening to quran recitation using EEG. Int J Acad Res Bus Soc Sci 9:10–16
  42. Huang C et al (2020) Predicting human intention-behavior through EEG signal analysis using multi-scale CNN. IEEE/ACM Trans Comput Biol Bioinf 18:1722–1729 [DOI: 10.1109/TCBB.2020.3039834]
  43. T. H. Shovon, et al., "Classification of motor imagery EEG signals with multi-input convolutional neural network by augmenting STFT," in 2019 5th International Conference on Advances in Electrical Engineering (ICAEE), 2019, pp. 398–403.
  44. Xu G et al (2019) A deep transfer convolutional neural network framework for EEG signal classification. IEEE Access 7:112767–112776 [DOI: 10.1109/ACCESS.2019.2930958]
  45. Begum N, Hazarika MK (2022) Maturity detection of tomatoes using transfer learning. Measurement: Food 7:100038
  46. Y. Xia, et al., "A Switch State Recognition Method based on Improved VGG19 network," in 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), 2019, pp. 1658-1662
  47. S. Kavitha, et al., "Neural Style Transfer Using VGG19 and Alexnet," in 2021 International Conference on Advancements in Electrical, Electronics, Communication, Computing and Automation (ICAECA), 2021, pp. 1–6.
  48. N. Abuared, et al., "Skin Cancer Classification Model Based on VGG 19 and Transfer Learning," in 2020 3rd International Conference on Signal Processing and Information Security (ICSPIS), 2020, pp. 1–4.
  49. S. Mascarenhas and M. Agarwal, "A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for Image Classification," in 2021 International Conference on Disruptive Technologies for Multi-Disciplinary Research and Applications (CENTCON), 2021, pp. 96-99
  50. Mumtaz W et al (2017) Electroencephalogram (EEG)-based computer-aided technique to diagnose major depressive disorder (MDD). Biomed Signal Process Control 31:108–115 [DOI: 10.1016/j.bspc.2016.07.006]
  51. Nanthini BS, Santhi B (2017) Electroencephalogram signal classification for automated epileptic seizure detection using genetic algorithm. J Nat Sci, Biol, Med 8:159 [DOI: 10.4103/jnsbm.JNSBM_285_16]
  52. Al-Samarraay MS et al (2022) Extension of interval-valued Pythagorean FDOSM for evaluating and benchmarking real-time SLRSs based on multidimensional criteria of hand gesture recognition and sensor glove perspectives. Appl Soft Comput 116:108284 [DOI: 10.1016/j.asoc.2021.108284]
  53. R. Masoomi and A. Khadem, "Enhancing LDA-based discrimination of left and right hand motor imagery: Outperforming the winner of BCI Competition II," in 2015 2nd International Conference on Knowledge-Based Engineering and Innovation (KBEI), 2015, pp. 392–398.
  54. Jang T-U et al (2016) Motor-imagery EEG signal classification using position matching and vector quantisation. Int J Telemed Clin Prac 1:306–313 [DOI: 10.1504/IJTMCP.2016.078426]
  55. Bashar SK, Bhuiyan MIH (2016) Classification of motor imagery movements using multivariate empirical mode decomposition and short time Fourier transform based hybrid method. Eng Sci Technol, Int J 19:1457–1464
  56. R. Chatterjee, et al., "Dimensionality reduction of EEG signal using fuzzy discernibility matrix," in 2017 10th International Conference on Human System Interactions (HSI), 2017, pp. 131–136.
  57. S. V. Eslahi, et al., "A GA-based feature selection of the EEG signals by classification evaluation: Application in BCI systems," arXiv preprint arXiv:1903.02081 , 2019.
  58. Lee HK, Choi Y-S (2019) Application of continuous wavelet transform and convolutional neural network in decoding motor imagery brain-computer interface. Entropy 21:1199 [DOI: 10.3390/e21121199]
  59. Kant P et al (2020) CWT Based transfer learning for motor imagery classification for brain computer interfaces. J Neurosci Methods 345:108886 [DOI: 10.1016/j.jneumeth.2020.108886]
  60. M. Wei, et al., "Motor Imagery EEG Signal Classification based on Deep Transfer Learning," in 2021 IEEE 34th International Symposium on Computer-Based Medical Systems (CBMS), 2021, pp. 85–90.
  61. Noori Worood Esam et al (2023) Towards trustworthy myopia detection: integration methodology of deep learning approach, xai visualization, and user interface system. Appl Data Sci Anal. https://doi.org/10.58496/ADSA/2023/001 [DOI: 10.58496/ADSA/2023/001]
  62. Hammed Samar Hazim et al (2023) Unlocking the potential of autism detection: integrating traditional feature selection and machine learning techniques. Appl Data Sci Anal. https://doi.org/10.58496/ADSA/2023/003 [DOI: 10.58496/ADSA/2023/003]
  63. Talib Hiba Mohammed et al (2023) Fuzzy decision-making framework for sensitively prioritizing autism patients with moderate emergency level. Appl Data Sci Anal. https://doi.org/10.58496/ADSA/2023/002 [DOI: 10.58496/ADSA/2023/002]

MeSH Term

Humans
Electroencephalography
Imagination
Imagery, Psychotherapy
Brain-Computer Interfaces
Learning
Journal Article

Word Cloud

Created with Highcharts 10.0.0subjectmodelFDOSMmotorimageryDecisionHAFLusinggoldenlearningBrain-computerBCIsduecomplexbrainvariationsidentificationhybridAdaboostfeatureVGG-19MI-EEGdatasetBCIMI-BCIapplicationsGoldensubject-to-subjecttransferinterfacesbasedMIfacechallengesnatureactivitynonstationaryhigh-dimensionalpropertiesindividualbehaviourconsistent"goldensubject"MI-basedremainsopenchallengecomplicatedmultipleevaluationmetricsconflictingtrade-offspresentingMulti-CriteriaMakingMCDMproblemsstudyproposessignaldecodingcalledHybridFeatureLearnercombinesextractionclassificationSTFTclassifiervalidatedpre-recordedcompetitionGrazUniversityfuzzydecision-makingframeworkintegratedallocateSubjectMatrixGSDMFuzzyOpinionScoreMethodeffectivenessaddressinginter-subjectvariabilityEEG-basedevaluatedinvolvingninesubjectsComparingperformancefairlychallengingcomplexitymethodprovidesvaluableinsightsFDOSM-basedExternalGroupAggregationEGAS5achieveshighestscore2900identifiedpromisingproposedmethodologycomparedbenchmarkstudiesvariouskeyperspectivesexhibitssignificantnoveltyseveralaspectsfindingscontributedevelopmentrobusteffectivesystemspavingwayadvancementsBCI-MIDevelopmentlearnerintegratinginterfaceMotorShort-timefouriertransformTransfer

Similar Articles

Cited By