KaydedilenlerDerginizi ekleyin

Dergiler / Uludağ Üniversitesi Mühendislik Fakültesi Dergisi / 2025 / Cilt: 30 Sayı: 3

MOTOR İMGELEME EEG SİNYALLERİNDE SINIFLANDIRMA PERFORMANSINI ARTTIRMAYA YÖNELİK ADAPTİF SEGMENTASYON YAKLAŞIMI

Adaptive Segmentation Approach for an Improved Classification of MI-EEG Signals

Tuğçe Ballı(KADİR HAS ÜNİVERSİTESİ)0000-0002-6509-3725
Sayfa
711–730
Yayın Tarihi
2025-12-19
🏛️Bu makalenin bibliyografik verileri ve tam metin bağlantısı DergiPark üzerinden sağlanmıştır.
DergiPark Kaydı ↗
✨

Yapay Zeka Hızlı Bakış & Çıkarımlar

AI Insight
⚡ TL;DR(1 Cümlede Hızlı Çıkarım)

Dört sınıflı sınıflandırma görevinde ise ortalama %7,5 oranında bir başarı artışı sağlanmış olup, katılımcı bazlı performans artışları %3,93 ile %11,11 aralığında değişmiştir.

📌 3 Maddede Bu Makale

🎯
Amaç & Hipotez:Elektroansefalogram (EEG) tabanlı beyin-bilgisayar arayüzlerinin (BBA) performansı, sistem tasarımında kullanılan sinyal işleme yöntemlerine doğrudan bağlıdır.
📊
Temel Bulgular & Veri:Önerilen yöntemin, sabit segmentasyona kıyasla etkinliği, BCI Competition IV 2a veri seti kullanılarak değerlendirilmiştir.
💡
Sonuç & Katkı:Dört sınıflı sınıflandırma görevinde ise ortalama %7,5 oranında bir başarı artışı sağlanmış olup, katılımcı bazlı performans artışları %3,93 ile %11,11 aralığında değişmiştir.
🔬Tür:Uygulamalı Anket & Alan Araştırması
📍Kapsam:9 katılımcı
⚙️Değişkenler:EEG · Motor İmgeleme · Değişim Noktası Tespiti

Özet

Elektroansefalogram (EEG) tabanlı beyin-bilgisayar arayüzlerinin (BBA) performansı, sistem tasarımında kullanılan sinyal işleme yöntemlerine doğrudan bağlıdır. EEG sinyal işleme süreci; önişleme, öznitelik çıkarma, seçme ve sınıflandırma adımlarını içerir. EEG verilerinden öznitelik çıkarımı genellikle sabit uzunlukta pencerelere ayrıldıktan sonra yapılmaktadır. Bu çalışmada özniteliklerin veri temsiliyetini artırmak için değişim noktası tespitine (change point detection, CPD) dayalı adaptif bir segmentasyon yaklaşımı önerilmiştir. Bu amaçla budanmış kesin doğrusal zaman (pruned exact linear time, PELT) algoritması kullanılmıştır. Bu yöntem, değişim noktalarını uygun bir maliyet fonksiyonu ile duyarlılık parametresinin belirlenmesi yoluyla tespit etmektedir. Önerilen yöntemin, sabit segmentasyona kıyasla etkinliği, BCI Competition IV 2a veri seti kullanılarak değerlendirilmiştir. Bu veri seti, 9 katılımcının sol el, sağ el, ayak ve dil imgeleme görevlerini gerçekleştirirken kaydedilmiş EEG verilerini içermektedir. Sonuçlar, CPD tabanlı yöntemin hem ikili hem de dört sınıflı sınıflandırmada test verisi üzerindeki sınıflandırma başarımını artırdığını göstermiştir. İkili sınıflandırma senaryosunda, önerilen yöntemin performans artışı %5,81 ile %8,72 arasında değişmiştir. En yüksek sınıflandırma performansı, sol el ve dil görevleri arasında gözlemlenmiş; katılımcı bazında performans artışları %4,16 ve %12,73 aralığında değişmiştir. Dört sınıflı sınıflandırma görevinde ise ortalama %7,5 oranında bir başarı artışı sağlanmış olup, katılımcı bazlı performans artışları %3,93 ile %11,11 aralığında değişmiştir.

Abstract

Electroencephalogram (EEG)-based brain-computer interfaces (BCI) rely on effective design of signal processing pipelines to achieve high classification performance. The fundamental EEG signal processing steps include preprocessing, feature extraction, selection, and classification. In the feature extraction step, EEG signals are typically segmented using a fixed window length. This study proposes an adaptive segmentation scheme using change point detection (CPD) to achieve optimal segmentation for enhanced feature representation. Pruned exact linear time (PELT) algorithm was used to detect change points by minimizing a cost function with a sensitivity parameter for avoiding over segmentation. The proposed and fixed-point segmentation approaches were evaluated using BCI Competition IV dataset 2a, which contains EEG recordings from 9 subjects performing motor imagery tasks involving left-hand, righthand, foot and tongue movements. Results demonstrated that the CPD-based method improved classification performance on test data for both binary and four-class classification tasks. In binary classification, performance improvement ranged from 5.81% to 8.72%, depending on class pair. The highest classification performance was observed in left hand and tongue movements, with participantspecific improvements ranging from 4.16% to 12.73%. In four-class task, an average improvement of 7.5% was observed, with participant-specific improvements ranging from 3.93% to 11.11%.

🔖

Bu Makaleye Atıf Yap

Ballı, T. (2025). MOTOR İMGELEME EEG SİNYALLERİNDE SINIFLANDIRMA PERFORMANSINI ARTTIRMAYA YÖNELİK ADAPTİF SEGMENTASYON YAKLAŞIMI. Uludağ Üniversitesi Mühendislik Fakültesi Dergisi, Cilt: 30 Sayı: 3, 711–730. https://doi.org/10.17482/uumfd.1698204

📄 Tam Metin PDF Okuyucu

📄

PDF görüntüleyici hazırlanıyor...

Kaynakça (56)

  1. Abbas, W., & Khan, N. A. (2018, July). FBCSP-based multi-class motor imagery classification using BP and TDP features. In 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 215-218). IEEE. Doi: 10.1109/EMBC.2018.8512238
  2. Al-Saegh, A., Dawwd, S. A., & Abdul-Jabbar, J. M. (2021). Deep learning for motor imagery EEG-based classification: A review. Biomedical Signal Processing and Control, 63, 102172. Doi: 10.1016/j.bspc.2020.102172
  3. Allison, B. Z., & Neuper, C. (2010). Could anyone use a BCI?. In Brain-computer interfaces: Applying our minds to human-computer interaction (pp. 35-54). London: Springer London. Doi: 10.1007/978-1-84996-272-8_3
  4. Altaheri, H., Muhammad, G., Alsulaiman, M., Amin, S. U., Altuwaijri, G. A., Abdul, W., Bencherif, M.A. & Faisal, M. (2023). Deep learning techniques for classification of electroencephalogram (EEG) motor imagery (MI) signals: A review. Neural Computing and Applications, 35(20), 14681-14722. Doi: 10.1007/s00521-021-06352-5
  5. Amer, N. S., & Belhaouari, S. B. (2023). Eeg signal processing for medical diagnosis, healthcare, and monitoring: A comprehensive review. IEEE Access, 11, 143116-143142. Doi: 10.1109/ACCESS.2023.3341419
  6. Ang, K. K., Chin, Z. Y., Wang, C., Guan, C., & Zhang, H. (2012). Filter bank common spatial pattern algorithm on BCI competition IV datasets 2a and 2b. Frontiers in neuroscience, 6, 39. Doi: 10.3389/fnins.2012.00039
  7. Azami, H., Anisheh, S. M., & Hassanpour, H. (2013, December). An Adaptive Automatic EEG Signal Segmentation Method Based on Generalized Likelihood Ratio. In International Symposium on Artificial Intelligence and Signal Processing (pp. 172-180). Cham: Springer International Publishing. Doi: 10.1007/978-3-319-10849-0_18
  8. Bentlemsan, M., Zemouri, E. T., Bouchaffra, D., Yahya-Zoubir, B., & Ferroudji, K. (2014, January). Random forest and filter bank common spatial patterns for EEG-based motor imagery classification. In 2014 5th International conference on intelligent systems, modelling and simulation (pp. 235-238). IEEE. Doi: 10.1109/ISMS.2014.46
  9. Blanco-Diaz, C. F., da Silva Serafini, E. R., Bastos-Filho, T., de Azevedo Dantas, A. F. O., do Espirito Santo, C. C., & Delisle-Rodriguez, D. (2024). A gait imagery-based brain-computer interface with visual feedback for spinal cord injury rehabilitation on lokomat. IEEE Transactions on Biomedical Engineering. Doi: 10.1109/TBME.2024.3440036
  10. Brunner, C., Leeb, R., Müller-Putz, G., Schlögl, A., & Pfurtscheller, G. (2008). BCI Competition 2008–Graz data set A. Institute for knowledge discovery (laboratory of brain-computer interfaces), Graz University of Technology, 16(1-6), 1. Doi: 10.21227/katb-zv89
  11. Candra, H., Yuwono, M., Chai, R., Handojoseno, A., Elamvazuthi, I., Nguyen, H. T., & Su, S. (2015, August). Investigation of window size in classification of EEG-emotion signal with wavelet entropy and support vector machine. In 2015 37th Annual international conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 7250-7253). IEEE. Doi: 10.1109/EMBC.2015.7320065
  12. Cantillo-Negrete, J., Carino-Escobar, R. I., Carrillo-Mora, P., Elias-Vinas, D., & Gutierrez-Martinez, J. (2018). Motor Imagery‐Based Brain‐Computer Interface Coupled to a Robotic Hand Orthosis Aimed for Neurorehabilitation of Stroke Patients. Journal of healthcare engineering, 2018(1), 1624637. Doi: 10.1155/2018/1624637
  13. Chaer, M. S. I., Nugroho, A. P., Putra, G. M. D., Ngadisih, N., Sutiarso, L., & Okayasu, T. (2022, March). Early warning system using change point analysis to detect microclimate anomalies. In 2nd International Conference on Smart and Innovative Agriculture (ICoSIA 2021) (pp. 144-149). Atlantis Press. Doi: 10.2991/absr.k.220305.021
  14. Chin, Z. Y., Ang, K. K., Guan, C., Wang, C., & Zhang, H. (2011, July). Filter Bank Feature Combination (FBFC) approach for brain-computer interface. In The 2011 International Joint Conference on Neural Networks (pp. 1352-1357). IEEE. 15. Chou, T. P., Wang, W. R., & Chang, T. S. (2015, July). Low complexity real time BCI for stroke rehabilitation. In 2015 IEEE International Conference on Digital Signal Processing (DSP) (pp. 809-812). IEEE. Doi: 10.1109/IJCNN.2011.6033381
  15. Chou, T. P., Wang, W. R., & Chang, T. S. (2015, July). Low complexity real time BCI for stroke rehabilitation. In 2015 IEEE International Conference on Digital Signal Processing (DSP) (pp. 809-812). IEEE. Doi: 10.1109/ICDSP.2015.7251988
  16. Chu, Y., Zhao, X., Zou, Y., Xu, W., Song, G., Han, J., & Zhao, Y. (2020). Decoding multiclass motor imagery EEG from the same upper limb by combining Riemannian geometry features and partial least squares regression. Journal of neural engineering, 17(4), 046029. Doi: 10.1088/1741-2552/aba7cd
  17. Craik, A., He, Y., & Contreras-Vidal, J. L. (2019). Deep learning for electroencephalogram (EEG) classification tasks: a review. Journal of neural engineering, 16(3), 031001. Doi: 10.1088/1741-2552/ab0ab5
  18. D'Croz-Baron, D., Ramirez, J. M., Baker, M., Alarcon-Aquino, V., & Carrera, O. (2012, February). A BCI motor imagery experiment based on parametric feature extraction and fisher criterion. In CONIELECOMP 2012, 22nd International Conference on Electrical Communications and Computers (pp. 257-261). IEEE. Doi: 10.1109/CONIELECOMP.2012.6189920
  19. Dagdevir, E., & Tokmakci, M. (2023). Determination of effective signal processing stages for brain computer interface on BCI competition IV data set 2b: a review study. IETE Journal of Research, 69(6), 3144-3155. Doi: 10.1080/03772063.2021.1914204
  20. Dreyer, P., Roc, A., Pillette, L., Rimbert, S., & Lotte, F. (2023). A large EEG database with users’ profile information for motor imagery brain-computer interface research. Scientific Data, 10(1), 580. Doi: 10.1038/s41597-023-02445-z
  21. Esri. (t.y.). How change point detection works. ArcGIS Pro documentation. https://pro.arcgis.com/en/pro-app/latest/tool-reference/space-time-pattern-mining/how-change-point-detection-works.htm
  22. Fang, H., Jin, J., Daly, I., & Wang, X. (2022). Feature extraction method based on filter banks and Riemannian tangent space in motor-imagery BCI. IEEE journal of biomedical and health informatics, 26(6), 2504-2514. Doi: 10.1109/JBHI.2022.3146274
  23. Ferdi, A. Y., & Ghazli, A. (2025). Mind-Controlled Web Browser Navigation Based on Brain Computer Interfaces. Algerian Journal of Signals and Systems, 10(1), 24-28. Doi: 10.51485/ajss.v10i1.260
  24. Firoz, K. F., Seong, Y., & Yi, S. (2024). A preliminary study of neural signals of motor imagery task of arm movements through electroencephalography data classification with machine learning. In Proceedings of the 2024 IEEE 4th International Conference on Human-Machine Systems (ICHMS) (pp. 1–6). IEEE. Doi: 10.1109/ICHMS59971.2024.10555801
  25. Gao Z, Lu G, Yan P, Lyu C, Li X, Shang W, Xie Z, Zhang W. (2018). Automatic change detection for real-time monitoring of EEG signals. Frontiers in physiology, 9, 325. Doi: 10.3389/fphys.2018.00325
  26. Góngora, L., Paglialonga, A., Mastropietro, A., Rizzo, G., & Barbieri, R. (2022). A novel approach for segment-length selection based on stationarity to perform effective connectivity analysis applied to resting-state eeg signals. Sensors, 22(13), 4747. Doi: 10.3390/s22134747
  27. González-Cely, A. X., Soekadar, S. R., Delisle-Rodriguez, D., & Bastos-Filho, T. (2025, May). Lower-Limb Motor Imagery-Based Brain-Computer Interface to Control Treadmill Velocities. In 2025 International Conference On Rehabilitation Robotics (ICORR) (pp. 76-81). IEEE. Doi: 10.1109/ICORR66766.2025.11063181
  28. Hamavar, R., & Asl, B. M. (2025). Feature selection based on game theory optimization to achieve desired performance metrics in seizure onset detection. Biomedical Signal Processing and Control, 100, 107008. Doi: 10.1016/j.bspc.2024.107008
  29. Hamner, B., Leeb, R., Tavella, M., & Millán, J. D. R. (2011, August). Phase-based features for motor imagery brain-computer interfaces. In 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society (pp. 2578-2581). IEEE. Doi: 10.1109/IEMBS.2011.6090712
  30. Hou, Y., Chen, T., Lun, X., & Wang, F. (2022). A novel method for classification of multi-class motor imagery tasks based on feature fusion. Neuroscience Research, 176, 40-48. Doi: 10.1016/j.neures.2021.09.002
  31. Isa, N. M., Amir, A., Ilyas, M. Z., & Razalli, M. S. (2019). Motor imagery classification in Brain computer interface (BCI) based on EEG signal by using machine learning technique. Bulletin of Electrical Engineering and Informatics, 8(1), 269-275. Doi: 10.11591/eei.v8i1.1402
  32. Jin, L., Song, Y., Zhao, H., Cao, J., Cheung, V. C., & Liao, W. H. (2025). Frequency-Aware Spatial-Temporal Attention Explainable Network for EEG Decoding. IEEE Journal of Biomedical and Health Informatics. Doi: 10.1109/JBHI.2025.3576088
  33. Jo, S., Jung, J. H., Yang, M. J., Lee, Y., Jang, S. J., Feng, J., Heo, S., Kim, J., Shin, J., Jeon, J. & Park, H. S. (2022, July). EEG-EMG hybrid real-time classification of hand grasp and release movements intention in chronic stroke patients. In 2022 International Conference on Rehabilitation Robotics (ICORR) (pp. 1-6). IEEE. Doi: 10.1109/ICORR55369.2022.9896592
  34. Joy, M. M. H., Hasan, M., Miah, A. S. M., Ahmed, A., Tohfa, S. A., Bhuaiyan, M. F. I., Zannat, A. & Rashid, M. M. (2020, March). Multiclass mi-task classification using logistic regression and filter bank common spatial patterns. In International Conference on Computing Science, Communication and Security (pp. 160-170). Singapore: Springer Singapore. Doi: 10.1007/978-981-15-6648-6_13
  35. Kaplan, A., Röschke, J., Darkhovsky, B., & Fell, J. (2001). Macrostructural EEG characterization based on nonparametric change point segmentation: application to sleep analysis. Journal of neuroscience methods, 106(1), 81-90. Doi: 10.1016/S0165-0270(01)00331-4
  36. Keković, G., & Sekulić, S. (2019). Detection of change points in time series with moving average filters and wavelet transform: Application to EEG signals. Neurophysiology, 51, 2-8. Doi: 10.1007/s11062-019-09783-y
  37. Killick, R., Fearnhead, P., & Eckley, I. A. (2012). Optimal detection of changepoints with a linear computational cost. Journal of the American Statistical Association, 107(500), 1590-1598. Doi: 10.1080/01621459.2012.737745
  38. Kim, K., Park, J. H., Lee, M., & Song, J. W. (2022). Unsupervised change point detection and trend prediction for financial time-series using a new cusum-based approach. IEEE Access, 10, 34690-34705. Doi: 10.1109/ACCESS.2022.3162399
  39. Kirch, C., Muhsal, B., & Ombao, H. (2015). Detection of changes in multivariate time series with application to EEG data. Journal of the American Statistical Association, 110(511), 1197-1216. Doi: 10.1080/01621459.2014.957545
  40. Koles, Z. J., Lazar, M. S., & Zhou, S. Z. (1990). Spatial patterns underlying population differences in the background EEG. Brain topography, 2(4), 275-284. Doi: 10.1007/BF01129656
  41. Maarouf, K., Alzahab, N. A., & Saad, G. (2024, October). The Effect of EEG Segment's Length on Mental Workload Detection. In 2024 IEEE International Conference on Metrology for eXtended Reality, Artificial Intelligence and Neural Engineering (MetroXRAINE) (pp. 271-276). IEEE. Doi: 10.1109/MetroXRAINE62247.2024.10795942
  42. Malladi, R., Kalamangalam, G. P., & Aazhang, B. (2013, November). Online Bayesian change point detection algorithms for segmentation of epileptic activity. In 2013 Asilomar conference on signals, systems and computers (pp. 1833-1837). IEEE. Doi: 10.1109/ACSSC.2013.6810619
  43. Manca, G., & Fay, A. (2022, March). Off-line detection of abrupt and transitional change points in industrial process signals. In 2022 4th International Conference on Applied Automation and Industrial Diagnostics (ICAAID) (Vol. 1, pp. 1-6). IEEE. Doi: 10.1109/ICAAID51067.2022.9799507
  44. Rosiani, U. D., Saputra, P. Y., & Hendrawan, M. A. (2021, October). The Impact of Segment Length on EEG Based Biometric System. In 2021 IEEE 7th Information Technology International Seminar (ITIS) (pp. 1-5). IEEE. Doi: 10.1109/ITIS53497.2021.9791686
  45. Sarma, P., & Barma, S. (2021). Emotion recognition by distinguishing appropriate EEG segments based on random matrix theory. Biomedical Signal Processing and Control, 70, 102991. Doi: 10.1016/j.bspc.2021.102991
  46. Schröder, A. L., & Ombao, H. (2019). FreSpeD: Frequency-specific change-point detection in epileptic seizure multi-channel EEG data. Journal of the American Statistical Association, 114(525), 115-128. Doi: 10.1080/01621459.2018.1476238
  47. Shahlaei, F., Bagh, N., Shaligram, A. D., Reddy, M. R., & Zambare, M. S. (2018, June). Classification of motor imagery tasks using inter trial variance in the brain computer interface. In 2018 IEEE International Symposium on Medical Measurements and Applications (MeMeA) (pp. 1-6). IEEE. Doi: 10.1109/MeMeA.2018.8438648
  48. Steyrl, D., Scherer, R., Faller, J., & Müller-Putz, G. R. (2016). Random forests in non-invasive sensorimotor rhythm brain-computer interfaces: a practical and convenient non-linear classifier. Biomedical Engineering/Biomedizinische Technik, 61(1),77-86. Doi: 10.1515/bmt-2014-0117
  49. Subasi, A., & Mian Qaisar, S. (2021). The Ensemble Machine Learning‐Based Classification of Motor Imagery Tasks in Brain‐Computer Interface. Journal of Healthcare Engineering, 2021(1), 1970769. Doi: 10.1155/2021/1970769
  50. Truong, C., Oudre, L., & Vayatis, N. (2020). Selective review of offline change point detection methods. Signal Processing, 167, 107299. Doi: 10.1016/j.sigpro.2019.107299
  51. Vidaurre, C., Sannelli, C., Müller, K. R., & Blankertz, B. (2010, June). Machine-learning based co-adaptive calibration: a perspective to fight BCI illiteracy. In International Conference on Hybrid Artificial Intelligence Systems (pp. 413-420). Berlin, Heidelberg: Springer Berlin Heidelberg. Doi: 10.1007/978-3-642-13769-3_50
  52. Vuckovic, A., Wallace, L., & Allan, D. B. (2015). Hybrid brain-computer interface and functional electrical stimulation for sensorimotor training in participants with tetraplegia: a proof-of-concept study. Journal of neurologic physical therapy, 39(1), 3-14. Doi: 10.1097/NPT.0000000000000063
  53. Xu, F., Uszkoreit, H., Du, Y., Fan, W., Zhao, D., & Zhu, J. (2019, September). Explainable AI: A brief survey on history, research areas, approaches and challenges. In CCF international conference on natural language processing and Chinese computing (pp. 563-574). Cham: Springer International Publishing. Doi: 10.1007/978-3-030-32236-6_51
  54. Yang, J., Ma, Z., & Shen, T. (2021). Multi-time and multi-band CSP motor imagery EEG feature classification algorithm. Applied Sciences, 11(21), 10294. Doi: 10.3390/app112110294
  55. Zhang, C., & Eskandarian, A. (2020, July). A computationally efficient multiclass time-frequency common spatial pattern analysis on EEG motor imagery. In 2020 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) (pp. 514-518). IEEE. Doi: 10.1109/EMBC44109.2020.9176705
  56. Zhang, R., Xiao, X., Liu, Z., Jiang, W., Li, J., Cao, Y., Ren, J., Jiang, D. & Cui, L. (2018). A new motor imagery EEG classification method FB-TRCSP+ RF based on CSP and random forest. IEEE Access, 6, 44944-44950. Doi: 10.1109/ACCESS.2018.2860633