Understanding Learning from EEG Data: Combining Machine Learning and Feature Engineering Based on Hidden Markov Models and Mixed Models.
Deep learning
EEG data
Hidden Markov models
Machine learning
Time series
Journal
Neuroinformatics
ISSN: 1559-0089
Titre abrégé: Neuroinformatics
Pays: United States
ID NLM: 101142069
Informations de publication
Date de publication:
10 Sep 2024
10 Sep 2024
Historique:
accepted:
29
08
2024
medline:
10
9
2024
pubmed:
10
9
2024
entrez:
10
9
2024
Statut:
aheadofprint
Résumé
Theta oscillations, ranging from 4-8 Hz, play a significant role in spatial learning and memory functions during navigation tasks. Frontal theta oscillations are thought to play an important role in spatial navigation and memory. Electroencephalography (EEG) datasets are very complex, making any changes in the neural signal related to behaviour difficult to interpret. However, multiple analytical methods are available to examine complex data structures, especially machine learning-based techniques. These methods have shown high classification performance, and their combination with feature engineering enhances their capability. This paper proposes using hidden Markov and linear mixed effects models to extract features from EEG data. Based on the engineered features obtained from frontal theta EEG data during a spatial navigation task in two key trials (first, last) and between two conditions (learner and non-learner), we analysed the performance of six machine learning methods on classifying learner and non-learner participants. We also analysed how different standardisation methods used to pre-process the EEG data contribute to classification performance. We compared the classification performance of each trial with data gathered from the same subjects, including solely coordinate-based features, such as idle time and average speed. We found that more machine learning methods perform better classification using coordinate-based data. However, only deep neural networks achieved an area under the ROC curve higher than 80% using the theta EEG data alone. Our findings suggest that standardising the theta EEG data and using deep neural networks enhances the classification of learner and non-learner subjects in a spatial learning task.
Identifiants
pubmed: 39254794
doi: 10.1007/s12021-024-09690-6
pii: 10.1007/s12021-024-09690-6
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : Science Foundation Ireland
ID : 18/CRT/6049
Pays : Ireland
Informations de copyright
© 2024. The Author(s).
Références
R Core Team. (2022). R: A Language and Environment for Statistical Computing. Vienna, Austria: R Foundation for Statistical Computing.
Buzsáki, G. (2005). Theta rhythm of navigation: link between path integration and landmark navigation, episodic and semantic memory. Hippocampus, 15(7), 827–840.
doi: 10.1002/hipo.20113
pubmed: 16149082
Buzsáki, G., & Moser, E. I. (2013). Memory, navigation and theta rhythm in the hippocampal-entorhinal system. Nature Neuroscience, 16(2), 130–138.
doi: 10.1038/nn.3304
pubmed: 23354386
pmcid: 4079500
Chrastil, E. R., Rice, C., Goncalves, M., Moore, K. N., Wynn, S. C., Stern, C. E., & Nyhus, E. (2022a). Theta oscillations support active exploration in human spatial navigation. NeuroImage, 262, 119581.
Chrastil, E. R., Rice, C., Goncalves, M., Moore, K. N., Wynn, S. C., Stern, C. E., & Nyhus, E. (2022b). Theta oscillations support active exploration in human spatial navigation. NeuroImage, 262, 119581.
Commins, S., Duffin, J., Chaves, K., Leahy, D., Corcoran, K., Caffrey, M., Keenan, L., Finan, D., & Thornberry, C. (2020). Navwell: A simplified virtual-reality platform for spatial navigation and memory experiments. Behavior Research Methods, 52, 1189–1207.
doi: 10.3758/s13428-019-01310-5
pubmed: 31637666
Coughlan, G., Laczó, J., Hort, J., Minihane, A.-M., & Hornberger, M. (2018). Spatial navigation deficits—overlooked cognitive marker for preclinical alzheimer disease? Nature Reviews Neurology, 14(8), 496–506.
doi: 10.1038/s41582-018-0031-x
pubmed: 29980763
Coughlan, G., Puthusseryppady, V., Lowry, E., Gillings, R., Spiers, H., Minihane, A.-M., & Hornberger, M. (2020). Test-retest reliability of spatial navigation in adults at-risk of alzheimer’s disease. PLoS One, 15(9), e0239077.
doi: 10.1371/journal.pone.0239077
pubmed: 32960930
pmcid: 7508365
Crespo-García, M., Zeiller, M., Leupold, C., Kreiselmeyer, G., Rampp, S., Hamer, H. M., & Dalal, S. S. (2016). Slow-theta power decreases during item-place encoding predict spatial accuracy of subsequent context recall. Neuroimage, 142, 533–543.
doi: 10.1016/j.neuroimage.2016.08.021
pubmed: 27521743
Du, Y. K., Liang, M., McAvan, A. S., Wilson, R. C., & Ekstrom, A. D. (2023). Frontal-midline theta and posterior alpha oscillations index early processing of spatial representations during active navigation. Cortex, 169, 65–80.
doi: 10.1016/j.cortex.2023.09.005
pubmed: 37862831
Greenberg, J. A., Burke, J. F., Haque, R., Kahana, M. J., & Zaghloul, K. A. (2015). Decreases in theta and increases in high frequency activity underlie associative memory encoding. Neuroimage, 114, 257–263.
doi: 10.1016/j.neuroimage.2015.03.077
pubmed: 25862266
Herweg, N. A., Solomon, E. A., & Kahana, M. J. (2020). Theta oscillations in human memory. Trends in Cognitive Sciences, 24(3), 208–227.
doi: 10.1016/j.tics.2019.12.006
pubmed: 32029359
pmcid: 8310425
Hsiao, Y.-T., Wu, C.-T., Tsai, C.-F., Liu, Y.-H., Trinh, T.-T., & Lee, C.-Y. (2021). Eeg-based classification between individuals with mild cognitive impairment and healthy controls using conformal kernel-based fuzzy support vector machine. International Journal of Fuzzy Systems, 23, 2432–2448.
doi: 10.1007/s40815-021-01186-8
Johannesen, J. K., Bi, J., Jiang, R., Kenney, J. G., & Chen, C.-M.A. (2016). Machine learning identification of eeg features predicting working memory performance in schizophrenia and healthy adults. Neuropsychiatric Electrophysiology, 2, 1–21.
doi: 10.1186/s40810-016-0017-0
Kang, T., Chen, Y., Fazli, S., & Wallraven, C. (2020). Eeg-based prediction of successful memory formation during vocabulary learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 28(11), 2377–2389.
doi: 10.1109/TNSRE.2020.3023116
pubmed: 32915743
Kaplan, R., Bush, D., Bonnefond, M., Bandettini, P. A., Barnes, G. R., Doeller, C. F., & Burgess, N. (2014). Medial prefrontal theta phase coupling during spatial memory retrieval. Hippocampus, 24(6), 656–665.
doi: 10.1002/hipo.22255
pubmed: 24497013
pmcid: 4028411
Kaplan, R., Doeller, C. F., Barnes, G. R., Litvak, V., Düzel, E., Bandettini, P. A., & Burgess, N. (2012). Movement-related theta rhythm in humans: coordinating self-directed hippocampal learning. PLoS Biology, 10(2), e1001267.
doi: 10.1371/journal.pbio.1001267
pubmed: 22389627
pmcid: 3289589
Kerrén, C., Linde-Domingo, J., Hanslmayr, S., & Wimber, M. (2018). An optimal oscillatory phase for pattern reactivation during memory retrieval. Current Biology, 28(21), 3383–3392.
doi: 10.1016/j.cub.2018.08.065
pubmed: 30344116
Kiiski, H., Jollans, L., Donnchadha, S. Ó., Nolan, H., Lonergan, R., Kelly, S., O’Brien, M. C., Kinsella, K., Bramham, J., Burke, T., et al. (2018). Machine learning eeg to predict cognitive functioning and processing speed over a 2-year period in multiple sclerosis patients and controls. Brain Topography, 31, 346–363.
doi: 10.1007/s10548-018-0620-4
pubmed: 29380079
Klimesch, W., Doppelmayr, M., Schimke, H., & Ripper, B. (1997). Theta synchronization and alpha desynchronization in a memory task. Psychophysiology, 34(2), 169–176.
Kunz, L., Schröder, T. N., Lee, H., Montag, C., Lachmann, B., Sariyska, R., Reuter, M., Stirnberg, R., Stöcker, T., Messing-Floeter, P. C., et al. (2015). Reduced grid-cell-like representations in adults at genetic risk for alzheimer’s disease. Science, 350(6259), 430–433.
doi: 10.1126/science.aac8128
pubmed: 26494756
Liang, M., Zheng, J., Isham, E., & Ekstrom, A. (2021). Common and distinct roles of frontal midline theta and occipital alpha oscillations in coding temporal intervals and spatial distances. Journal of Cognitive Neuroscience, 33(11), 2311–2327.
doi: 10.1162/jocn_a_01765
pubmed: 34347871
Liang, M., Zheng, J., Isham, E., & Ekstrom, A. (2021). Common and distinct roles of frontal midline theta and occipital alpha oscillations in coding temporal intervals and spatial distances. Journal of Cognitive Neuroscience, 33(11), 2311–2327.
doi: 10.1162/jocn_a_01765
pubmed: 34347871
Lin, J.-J., Rugg, M. D., Das, S., Stein, J., Rizzuto, D. S., Kahana, M. J., & Lega, B. C. (2017). Theta band power increases in the posterior hippocampus predict successful episodic memory encoding in humans. Hippocampus, 27(10), 1040–1053.
doi: 10.1002/hipo.22751
pubmed: 28608960
pmcid: 6517838
Longo, L. (2023). Explainable Artificial Intelligence: First World Conference, xAI 2023, Lisbon, Portugal, July 26–28, 2023, Proceedings. Springer Nature: Part II.
doi: 10.1007/978-3-031-44070-0
Mitchell, D. J., McNaughton, N., Flanagan, D., & Kirk, I. J. (2008). Frontal-midline theta from the perspective of hippocampal “theta”. Progress in Neurobiology,86(3), 156–185.
Musaeus, C. S., Engedal, K., Høgh, P., Jelic, V., Mørup, M., Naik, M., Oeksengaard, A.-R., Snaedal, J., Wahlund, L.-O., Waldemar, G., et al. (2018). Eeg theta power is an early marker of cognitive decline in dementia due to alzheimer’s disease. Journal of Alzheimer’s Disease, 64(4), 1359–1371.
doi: 10.3233/JAD-180300
pubmed: 29991135
Nirabi, A., Abd Rahman, F., Habaebi, M. H., Sidek, K. A., & Yusoff, S. (2021). Machine learning-based stress level detection from eeg signals. In 2021 IEEE 7th International Conference on Smart Instrumentation, Measurement and Applications (ICSIMA) (pp. 53–58). IEEE.
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). " why should i trust you?" explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135–1144).
Rigby, R. A., & Stasinopoulos, D. M. (2005). Generalized additive models for location, scale and shape,(with discussion). Applied Statistics, 54, 507–554.
Roberts, B. M., Hsieh, L.-T., & Ranganath, C. (2013). Oscillatory activity during maintenance of spatial and temporal information in working memory. Neuropsychologia, 51(2), 349–357.
doi: 10.1016/j.neuropsychologia.2012.10.009
pubmed: 23084981
Stasinopoulos, M. D., Rigby, R. A., Heller, G. Z., Voudouris, V., & Bastiani, F. D. (2017). Flexible regression and smoothing : using GAMLSS in R. R. Chapman and Hall/CRC.
Tadel, F., Baillet, S., Mosher, J. C., Pantazis, D., & Leahy, R. M. (2011). Brainstorm: a user-friendly application for meg/eeg analysis. Computational Intelligence and Neuroscience, 2011, 1–13.
doi: 10.1155/2011/879716
Tang, C., Li, Y., & Chen, B. (2022). Comparison of cross-subject eeg emotion recognition algorithms in the bci controlled robot contest in world robot contest 2021. Brain Science Advances, 8(2), 142–152.
doi: 10.26599/BSA.2022.9050013
Thornberry, C., Caffrey, M., & Commins, S. (2023). Theta oscillatory power decreases in humans are associated with spatial learning in a virtual water maze task. European Journal of Neuroscience, 58(11), 4341–4356.
Vahid, A., Mückschel, M., Neuhaus, A., Stock, A.-K., & Beste, C. (2018). Machine learning provides novel neurophysiological features that predict performance to inhibit automated responses. Scientific Reports, 8(1), 16235.
doi: 10.1038/s41598-018-34727-7
pubmed: 30390016
pmcid: 6215005
Visser, I., & Speekenbrink, M. (2010). depmixS4: An R package for hidden markov models. Journal of Statistical Software, 36(7), 1–21.
Zucchini, W., & MacDonald, I. L. (2016). Hidden Markov models for time series: an introduction using R. Chapman and Hall/CRC, second edition.
Żygierewicz, J., Janik, R. A., Podolak, I. T., Drozd, A., Malinowska, U., Poziomska, M., Wojciechowski, J., Ogniewski, P., Niedbalski, P., Terczynska, I., et al. (2022). Decoding working memory-related information from repeated psychophysiological eeg experiments using convolutional and contrastive neural networks. Journal of Neural Engineering, 19(4), 046053.