*Result*: MSFHNet: a hybrid deep learning network for multi-scale spatiotemporal feature extraction of spatial cognitive EEG signals in BCI-VR systems.
Title:
MSFHNet: a hybrid deep learning network for multi-scale spatiotemporal feature extraction of spatial cognitive EEG signals in BCI-VR systems.
Authors:
Liu X; School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, 066004, China.; Hebei Key Laboratory of Marine Perception Network and Data Processing, Northeastern University, Qinhuangdao, 066004, China., Jia Z; School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, 066004, China.; Hebei Key Laboratory of Marine Perception Network and Data Processing, Northeastern University, Qinhuangdao, 066004, China., Xun M; School of Computer and Communication Engineering, Northeastern University, Qinhuangdao, 066004, China.; Hebei Key Laboratory of Marine Perception Network and Data Processing, Northeastern University, Qinhuangdao, 066004, China., Wan X; School of Intelligence Science and Technology, University of Science and Technology Beijing , Beijing, 100083, China., Lu H; School of Information Science and Engineering, Yanshan University, Qinhuangdao, 066004, China., Zhou Y; School of Information Science and Engineering, Yanshan University, Qinhuangdao, 066004, China. yhzhou168@163.com.
Source:
Medical & biological engineering & computing [Med Biol Eng Comput] 2025 Nov; Vol. 63 (11), pp. 3203-3220. Date of Electronic Publication: 2025 Jun 05.
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Springer Country of Publication: United States NLM ID: 7704869 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1741-0444 (Electronic) Linking ISSN: 01400118 NLM ISO Abbreviation: Med Biol Eng Comput Subsets: MEDLINE
Imprint Name(s):
Publication: New York, NY : Springer
Original Publication: Stevenage, Eng., Peregrinus.
Original Publication: Stevenage, Eng., Peregrinus.
MeSH Terms:
References:
Zhou Y, Liu X, Wen D et al (2025) Spatial cognitive electroencephalogram network topological features extraction based on cross fuzzy entropy network graph. Symmetry 17:243. https://doi.org/10.3390/sym17020243. (PMID: 10.3390/sym17020243)
Allison SL, Fagan AM, Morris JC, Head D (2016) Spatial navigation in preclinical Alzheimer’s disease. J Alzheimers Dis 52:77–90. https://doi.org/10.3233/JAD-150855. (PMID: 10.3233/JAD-150855269672095091813)
Laczó J, Parizkova M, Moffat SD et al (2016) P1‐355: The effect of early‐stage Alzheimer’s disease on spatial navigation strategies: a pilot study. Alzheimers Dement 12. https://doi.org/10.1016/j.jalz.2016.06.1106.
Hongyu L, Chongde L (2005) A sturctural research on the spatial-cognitive ability of high school students. Psychol Sci 28:269–271.
Wolbers T, Hegarty M (2010) What determines our navigational abilities? Trends Cogn Sci 14:138–146. https://doi.org/10.1016/j.tics.2010.01.001. (PMID: 10.1016/j.tics.2010.01.00120138795)
Mavros P, Austwick MZ, Smith AH (2016) Geo-EEG: towards the use of EEG in the study of urban behaviour. Appl Spat Anal Policy 9:191–212. https://doi.org/10.1007/s12061-015-9181-z. (PMID: 10.1007/s12061-015-9181-z)
Klencklen G, Després O, Dufour A (2012) What do we know about aging and spatial cognition? Reviews and perspectives. Ageing Res Rev 11:123–135. https://doi.org/10.1016/j.arr.2011.10.001. (PMID: 10.1016/j.arr.2011.10.00122085884)
Kelly ME, Loughrey D, Lawlor BA et al (2014) The impact of cognitive training and mental stimulation on cognitive and everyday functioning of healthy older adults: a systematic review and meta-analysis. Ageing Res Rev 15:28–43. https://doi.org/10.1016/j.arr.2014.02.004. (PMID: 10.1016/j.arr.2014.02.00424607830)
Wen D, Yuan J, Zhou Y et al (2020) The EEG signal analysis for spatial cognitive ability evaluation based on multivariate permutation conditional mutual information-multi-spectral image. IEEE Trans Neural Syst Rehabil Eng 28:2113–2122. https://doi.org/10.1109/TNSRE.2020.3018959. (PMID: 10.1109/TNSRE.2020.301895932833638)
Wen D, Liang B, Li J et al (2023) Feature extraction method of EEG signals evaluating spatial cognition of community elderly with permutation conditional mutual information common space model. IEEE Trans Neural Syst Rehabil Eng 31:2370–2380. https://doi.org/10.1109/TNSRE.2023.3273119. (PMID: 10.1109/TNSRE.2023.327311937141070)
Lawhern VJ, Solon AJ, Waytowich NR et al (2018) EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. J Neural Eng 15:056013. https://doi.org/10.1088/1741-2552/aace8c. (PMID: 10.1088/1741-2552/aace8c29932424)
Zhang C, Kim Y-K, Eskandarian A (2021) EEG-inception: an accurate and robust end-to-end neural network for EEG-based motor imagery classification. J Neural Eng 18:046014. https://doi.org/10.1088/1741-2552/abed81. (PMID: 10.1088/1741-2552/abed81)
Ji Y, Li F, Fu B et al (2024) A novel hybrid decoding neural network for EEG signal representation. Pattern Recognit 155:110726. https://doi.org/10.1016/j.patcog.2024.110726. (PMID: 10.1016/j.patcog.2024.110726)
Liu S, Zhao Y, An Y et al (2023) GLFANet: a global to local feature aggregation network for EEG emotion recognition. Biomed Signal Process Control 85:104799. https://doi.org/10.1016/j.bspc.2023.104799. (PMID: 10.1016/j.bspc.2023.104799)
Woo S, Park J, Lee J-Y, Kweon IS (2018) CBAM: Convolutional Block Attention Module. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer Vision – ECCV 2018. Springer International Publishing, Cham, pp 3–19. https://doi.org/10.1007/978-3-030-01234-2_1.
Wang Y, Wang G, Chen C, Pan Z (2019) Multi-scale dilated convolution of convolutional neural network for image denoising. Multimed Tools Appl 78:19945–19960. https://doi.org/10.1007/s11042-019-7377-y. (PMID: 10.1007/s11042-019-7377-y)
Kim H, Park CH, Suh C et al (2023) MPARN: multi-scale path attention residual network for fault diagnosis of rotating machines. J Comput Des Eng 10:860–872. https://doi.org/10.1093/jcde/qwad031. (PMID: 10.1093/jcde/qwad031)
Alotaiby T, El-Samie FEA, Alshebeili SA, Ahmad I (2015) A review of channel selection algorithms for EEG signal processing. EURASIP J Adv Signal Process 2015:66. https://doi.org/10.1186/s13634-015-0251-9. (PMID: 10.1186/s13634-015-0251-9)
Hu J, Shen L, Albanie S et al (2020) Squeeze-and-Excitation networks. IEEE Trans Pattern Anal Mach Intell 42:2011–2023. https://doi.org/10.1109/TPAMI.2019.2913372. (PMID: 10.1109/TPAMI.2019.291337231034408)
Lei D, Dong C, Guo H et al (2024) A fused multi-subfrequency bands and CBAM SSVEP-BCI classification method based on convolutional neural network. Sci Rep 14:8616. https://doi.org/10.1038/s41598-024-59348-1. (PMID: 10.1038/s41598-024-59348-13861620411016546)
Delorme A, Makeig S (2004) EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods 134:9–21. https://doi.org/10.1016/j.jneumeth.2003.10.009. (PMID: 10.1016/j.jneumeth.2003.10.00915102499)
Müller-Gerking J, Pfurtscheller G, Flyvbjerg H (1999) Designing optimal spatial filters for single-trial EEG classification in a movement task. Clin Neurophysiol 110:787–798. https://doi.org/10.1016/S1388-2457(98)00038-8. (PMID: 10.1016/S1388-2457(98)00038-810400191)
Lotte F, Bougrain L, Cichocki A et al (2018) A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. J Neural Eng 15:031005. https://doi.org/10.1088/1741-2552/aab2f2. (PMID: 10.1088/1741-2552/aab2f229488902)
Ismail LE, Karwowski W (2020) A graph theory-based modeling of functional brain connectivity based on EEG: a systematic review in the context of neuroergonomics. IEEE Access 8:155103–155135. https://doi.org/10.1109/ACCESS.2020.3018995. (PMID: 10.1109/ACCESS.2020.3018995)
Azami H, Li P, Arnold SE et al (2019) Fuzzy entropy metrics for the analysis of biomedical signals: assessment and comparison. IEEE Access 7:104833–104847. https://doi.org/10.1109/ACCESS.2019.2930625. (PMID: 10.1109/ACCESS.2019.2930625)
Xie H-B, Zheng Y-P, Guo J-Y, Chen X (2010) Cross-fuzzy entropy: a new method to test pattern synchrony of bivariate time series. Inf Sci 180:1715–1724. https://doi.org/10.1016/j.ins.2010.01.004. (PMID: 10.1016/j.ins.2010.01.004)
Stefano Filho CA, Attux R, Castellano G (2018) Can graph metrics be used for EEG-BCIs based on hand motor imagery? Biomed Signal Process Control 40:359–365. https://doi.org/10.1016/j.bspc.2017.09.026. (PMID: 10.1016/j.bspc.2017.09.026)
Ma J, Yang B, Qiu W et al (2022) A large EEG dataset for studying cross-session variability in motor imagery brain-computer interface. Sci Data 9:531. https://doi.org/10.1038/s41597-022-01647-1. (PMID: 10.1038/s41597-022-01647-1360503949436944)
Santamaría-Vázquez E, Martínez-Cagigal V, Vaquerizo-Villar F, Hornero R (2020) EEG-Inception: a novel deep convolutional neural network for assistive ERP-based brain-computer interfaces. IEEE Trans Neural Syst Rehabil Eng 28:2773–2782. https://doi.org/10.1109/TNSRE.2020.3048106. (PMID: 10.1109/TNSRE.2020.304810633378260)
Vashishtha G, Chauhan S, Sehri M et al (2025) Advancing machine fault diagnosis: a detailed examination of convolutional neural networks. Meas Sci Technol 36:022001. https://doi.org/10.1088/1361-6501/ada178. (PMID: 10.1088/1361-6501/ada178)
Corsi M-C, Troisi Lopez E, Sorrentino P et al (2024) Neuronal avalanches in temporal lobe epilepsy as a noninvasive diagnostic tool investigating large scale brain dynamics. Sci Rep 14:14039. https://doi.org/10.1038/s41598-024-64870-3. (PMID: 10.1038/s41598-024-64870-33889036311189588)
Li D, Huang Y, Luo R, et al (2025) Enhancing detection of SSVEPs using discriminant compacted network. J Neural Eng 22. https://doi.org/10.1088/1741-2552/adb0f2.
Mei J, Luo R, Xu L et al (2024) MetaBCI: an open-source platform for brain-computer interfaces. Comput Biol Med 168:107806. https://doi.org/10.1016/j.compbiomed.2023.107806. (PMID: 10.1016/j.compbiomed.2023.10780638081116)
Allison SL, Fagan AM, Morris JC, Head D (2016) Spatial navigation in preclinical Alzheimer’s disease. J Alzheimers Dis 52:77–90. https://doi.org/10.3233/JAD-150855. (PMID: 10.3233/JAD-150855269672095091813)
Laczó J, Parizkova M, Moffat SD et al (2016) P1‐355: The effect of early‐stage Alzheimer’s disease on spatial navigation strategies: a pilot study. Alzheimers Dement 12. https://doi.org/10.1016/j.jalz.2016.06.1106.
Hongyu L, Chongde L (2005) A sturctural research on the spatial-cognitive ability of high school students. Psychol Sci 28:269–271.
Wolbers T, Hegarty M (2010) What determines our navigational abilities? Trends Cogn Sci 14:138–146. https://doi.org/10.1016/j.tics.2010.01.001. (PMID: 10.1016/j.tics.2010.01.00120138795)
Mavros P, Austwick MZ, Smith AH (2016) Geo-EEG: towards the use of EEG in the study of urban behaviour. Appl Spat Anal Policy 9:191–212. https://doi.org/10.1007/s12061-015-9181-z. (PMID: 10.1007/s12061-015-9181-z)
Klencklen G, Després O, Dufour A (2012) What do we know about aging and spatial cognition? Reviews and perspectives. Ageing Res Rev 11:123–135. https://doi.org/10.1016/j.arr.2011.10.001. (PMID: 10.1016/j.arr.2011.10.00122085884)
Kelly ME, Loughrey D, Lawlor BA et al (2014) The impact of cognitive training and mental stimulation on cognitive and everyday functioning of healthy older adults: a systematic review and meta-analysis. Ageing Res Rev 15:28–43. https://doi.org/10.1016/j.arr.2014.02.004. (PMID: 10.1016/j.arr.2014.02.00424607830)
Wen D, Yuan J, Zhou Y et al (2020) The EEG signal analysis for spatial cognitive ability evaluation based on multivariate permutation conditional mutual information-multi-spectral image. IEEE Trans Neural Syst Rehabil Eng 28:2113–2122. https://doi.org/10.1109/TNSRE.2020.3018959. (PMID: 10.1109/TNSRE.2020.301895932833638)
Wen D, Liang B, Li J et al (2023) Feature extraction method of EEG signals evaluating spatial cognition of community elderly with permutation conditional mutual information common space model. IEEE Trans Neural Syst Rehabil Eng 31:2370–2380. https://doi.org/10.1109/TNSRE.2023.3273119. (PMID: 10.1109/TNSRE.2023.327311937141070)
Lawhern VJ, Solon AJ, Waytowich NR et al (2018) EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces. J Neural Eng 15:056013. https://doi.org/10.1088/1741-2552/aace8c. (PMID: 10.1088/1741-2552/aace8c29932424)
Zhang C, Kim Y-K, Eskandarian A (2021) EEG-inception: an accurate and robust end-to-end neural network for EEG-based motor imagery classification. J Neural Eng 18:046014. https://doi.org/10.1088/1741-2552/abed81. (PMID: 10.1088/1741-2552/abed81)
Ji Y, Li F, Fu B et al (2024) A novel hybrid decoding neural network for EEG signal representation. Pattern Recognit 155:110726. https://doi.org/10.1016/j.patcog.2024.110726. (PMID: 10.1016/j.patcog.2024.110726)
Liu S, Zhao Y, An Y et al (2023) GLFANet: a global to local feature aggregation network for EEG emotion recognition. Biomed Signal Process Control 85:104799. https://doi.org/10.1016/j.bspc.2023.104799. (PMID: 10.1016/j.bspc.2023.104799)
Woo S, Park J, Lee J-Y, Kweon IS (2018) CBAM: Convolutional Block Attention Module. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer Vision – ECCV 2018. Springer International Publishing, Cham, pp 3–19. https://doi.org/10.1007/978-3-030-01234-2_1.
Wang Y, Wang G, Chen C, Pan Z (2019) Multi-scale dilated convolution of convolutional neural network for image denoising. Multimed Tools Appl 78:19945–19960. https://doi.org/10.1007/s11042-019-7377-y. (PMID: 10.1007/s11042-019-7377-y)
Kim H, Park CH, Suh C et al (2023) MPARN: multi-scale path attention residual network for fault diagnosis of rotating machines. J Comput Des Eng 10:860–872. https://doi.org/10.1093/jcde/qwad031. (PMID: 10.1093/jcde/qwad031)
Alotaiby T, El-Samie FEA, Alshebeili SA, Ahmad I (2015) A review of channel selection algorithms for EEG signal processing. EURASIP J Adv Signal Process 2015:66. https://doi.org/10.1186/s13634-015-0251-9. (PMID: 10.1186/s13634-015-0251-9)
Hu J, Shen L, Albanie S et al (2020) Squeeze-and-Excitation networks. IEEE Trans Pattern Anal Mach Intell 42:2011–2023. https://doi.org/10.1109/TPAMI.2019.2913372. (PMID: 10.1109/TPAMI.2019.291337231034408)
Lei D, Dong C, Guo H et al (2024) A fused multi-subfrequency bands and CBAM SSVEP-BCI classification method based on convolutional neural network. Sci Rep 14:8616. https://doi.org/10.1038/s41598-024-59348-1. (PMID: 10.1038/s41598-024-59348-13861620411016546)
Delorme A, Makeig S (2004) EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J Neurosci Methods 134:9–21. https://doi.org/10.1016/j.jneumeth.2003.10.009. (PMID: 10.1016/j.jneumeth.2003.10.00915102499)
Müller-Gerking J, Pfurtscheller G, Flyvbjerg H (1999) Designing optimal spatial filters for single-trial EEG classification in a movement task. Clin Neurophysiol 110:787–798. https://doi.org/10.1016/S1388-2457(98)00038-8. (PMID: 10.1016/S1388-2457(98)00038-810400191)
Lotte F, Bougrain L, Cichocki A et al (2018) A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update. J Neural Eng 15:031005. https://doi.org/10.1088/1741-2552/aab2f2. (PMID: 10.1088/1741-2552/aab2f229488902)
Ismail LE, Karwowski W (2020) A graph theory-based modeling of functional brain connectivity based on EEG: a systematic review in the context of neuroergonomics. IEEE Access 8:155103–155135. https://doi.org/10.1109/ACCESS.2020.3018995. (PMID: 10.1109/ACCESS.2020.3018995)
Azami H, Li P, Arnold SE et al (2019) Fuzzy entropy metrics for the analysis of biomedical signals: assessment and comparison. IEEE Access 7:104833–104847. https://doi.org/10.1109/ACCESS.2019.2930625. (PMID: 10.1109/ACCESS.2019.2930625)
Xie H-B, Zheng Y-P, Guo J-Y, Chen X (2010) Cross-fuzzy entropy: a new method to test pattern synchrony of bivariate time series. Inf Sci 180:1715–1724. https://doi.org/10.1016/j.ins.2010.01.004. (PMID: 10.1016/j.ins.2010.01.004)
Stefano Filho CA, Attux R, Castellano G (2018) Can graph metrics be used for EEG-BCIs based on hand motor imagery? Biomed Signal Process Control 40:359–365. https://doi.org/10.1016/j.bspc.2017.09.026. (PMID: 10.1016/j.bspc.2017.09.026)
Ma J, Yang B, Qiu W et al (2022) A large EEG dataset for studying cross-session variability in motor imagery brain-computer interface. Sci Data 9:531. https://doi.org/10.1038/s41597-022-01647-1. (PMID: 10.1038/s41597-022-01647-1360503949436944)
Santamaría-Vázquez E, Martínez-Cagigal V, Vaquerizo-Villar F, Hornero R (2020) EEG-Inception: a novel deep convolutional neural network for assistive ERP-based brain-computer interfaces. IEEE Trans Neural Syst Rehabil Eng 28:2773–2782. https://doi.org/10.1109/TNSRE.2020.3048106. (PMID: 10.1109/TNSRE.2020.304810633378260)
Vashishtha G, Chauhan S, Sehri M et al (2025) Advancing machine fault diagnosis: a detailed examination of convolutional neural networks. Meas Sci Technol 36:022001. https://doi.org/10.1088/1361-6501/ada178. (PMID: 10.1088/1361-6501/ada178)
Corsi M-C, Troisi Lopez E, Sorrentino P et al (2024) Neuronal avalanches in temporal lobe epilepsy as a noninvasive diagnostic tool investigating large scale brain dynamics. Sci Rep 14:14039. https://doi.org/10.1038/s41598-024-64870-3. (PMID: 10.1038/s41598-024-64870-33889036311189588)
Li D, Huang Y, Luo R, et al (2025) Enhancing detection of SSVEPs using discriminant compacted network. J Neural Eng 22. https://doi.org/10.1088/1741-2552/adb0f2.
Mei J, Luo R, Xu L et al (2024) MetaBCI: an open-source platform for brain-computer interfaces. Comput Biol Med 168:107806. https://doi.org/10.1016/j.compbiomed.2023.107806. (PMID: 10.1016/j.compbiomed.2023.10780638081116)
Grant Information:
62276022 National Natural Science Foundation of China; 62206014 National Natural Science Foundation of China
Contributed Indexing:
Keywords: Electroencephalogram; Feature extraction; Hybrid neural network; Spatial cognition
Entry Date(s):
Date Created: 20250605 Date Completed: 20260205 Latest Revision: 20260205
Update Code:
20260205
DOI:
10.1007/s11517-025-03386-y
PMID:
40471491
Database:
MEDLINE
*Further Information*
*The integration of brain-computer interface (BCI) and virtual reality (VR) systems offers transformative potential for spatial cognition training and assessment. By leveraging artificial intelligence (AI) to analyze electroencephalogram (EEG) data, brain activity patterns during spatial tasks can be decoded with high precision. In this context, a hybrid neural network named MSFHNet is proposed, optimized for extracting spatiotemporal features from spatial cognitive EEG signals. The model employs a hierarchical architecture where its temporal module uses multi-scale dilated convolutions to capture dynamic EEG variations, while its spatial module integrates channel-spatial attention mechanisms to model inter-channel dependencies and spatial distributions. Cross-stacked modules further refine discriminative features through deep-level fusion. Evaluations demonstrate the superiority of MSFHNet in the beta2 frequency band, achieving 98.58% classification accuracy and outperforming existing models. This innovation enhances EEG signal representation, advancing AI-powered BCI-VR systems for robust spatial cognitive training.
(© 2025. International Federation for Medical and Biological Engineering.)*
*Declarations. Ethical approval and consent to participate: The study was conducted according to the guidelines of the Declaration of Helsinki and approved by the Ethics Committee of University of Science and Technology Beijing (No. 2022–1-104). Informed consent was obtained from all subjects involved in the study. Competing interests: The authors declare no competing interests.*