Real-Time Cognitive Risk Classification Using TGAM EEG Sensor with IoT and Fuzzy Logic Integration

Öz

This study presents an IoT-based approach to classifying the cognitive risk levels of individuals working in critical fields such as education, healthcare, transportation, and security in real time. Attention and meditation data obtained from the TGAM single-channel EEG sensor are transferred to the ThingSpeak platform via ESP32 and analyzed using a rule-based fuzzy logic system developed in MATLAB. The system classifies the individual's cognitive state into three risk levels: low, medium, and high. The results demonstrate that the proposed portable and low-cost system can effectively and reliably monitor cognitive state in work environments requiring high levels of attention.

Anahtar Kelimeler

• EEG monitoring
• Real-time
• IoT
• Fuzzy Logic
• ThingSpeak

Proje Numarası

FHD-2024-1332

IoT ve Bulanık Mantık Entegrasyonuyla TGAM EEG Sensörü Kullanılarak Gerçek Zamanlı Bilişsel Risk Sınıflandırması

Öz

Bu çalışma, eğitim, sağlık, ulaşım ve güvenlik gibi kritik alanlarda çalışan bireylerin bilişsel risk düzeylerini gerçek zamanlı olarak sınıflandırmaya yönelik IoT tabanlı bir yaklaşım sunmaktadır. TGAM tek kanallı EEG sensöründen elde edilen dikkat ve meditasyon verileri, ESP32 üzerinden ThingSpeak platformuna aktarılmakta ve MATLAB ortamında geliştirilen kural tabanlı bulanık mantık sistemi ile analiz edilmektedir. Sistem, bireyin bilişsel durumunu düşük, orta ve yüksek olmak üzere üç risk seviyesinde sınıflandırmaktadır. Elde edilen sonuçlar, önerilen taşınabilir ve düşük maliyetli sistemin, yüksek dikkat gerektiren çalışma ortamlarında bilişsel durumun etkin ve güvenilir biçimde izlenebileceğini göstermektedir.

Anahtar Kelimeler

• EEG izlenmesi
• Gerçek zamanlı
• IoT
• Bulanık Mantık
• ThingSpeak

Proje Numarası

FHD-2024-1332

Kaynakça

1. G. M. Rojas, C. Alvarez, C. E. Montoya, M. De La Iglesia-Vayá, J. E. Cisternas, ve M. Gálvez, “Study of Resting-State Functional Connectivity Networks Using EEG Electrodes Position As Seed”, Front. Neurosci., c. 12, s. 235, Nis. 2018, doi: 10.3389/fnins.2018.00235.
2. J. Zhang, Z. Yin, P. Chen, ve S. Nichele, “Emotion recognition using multi-modal data and machine learning techniques: A tutorial and review”, Information Fusion, c. 59, ss. 103-126, Tem. 2020, doi: 10.1016/j.inffus.2020.01.011.
3. M.-P. Hosseini, A. Hosseini, ve K. Ahi, “A Review on Machine Learning for EEG Signal Processing in Bioengineering”, IEEE Rev. Biomed. Eng., c. 14, ss. 204-218, 2021, doi: 10.1109/RBME.2020.2969915.
4. M. Abo-Zahhad, S. M. Ahmed, ve S. N. Abbas, “A New EEG Acquisition Protocol for Biometric Identification Using Eye Blinking Signals”, IJISA, c. 7, sy. 6, ss. 48-54, May. 2015, doi: 10.5815/ijisa.2015.06.05.
5. S. Zhang, Z. Yan, S. Sapkota, S. Zhao, ve W. T. Ooi, “Moment-to-Moment Continuous Attention Fluctuation Monitoring through Consumer-Grade EEG Device”, Sensors, c. 21, sy. 10, s. 3419, May. 2021, doi: 10.3390/s21103419.
6. X. Wan vd., “A Review on Electroencephalogram Based Brain Computer Interface for Elderly Disabled”, IEEE Access, c. 7, ss. 36380-36387, 2019, doi: 10.1109/ACCESS.2019.2903235.
7. S. Siuly, Y. Li, ve Y. Zhang, “Significance of EEG Signals in Medical and Health Research”, içinde EEG Signal Analysis and Classification, içinde Health Information Science. , Cham: Springer International Publishing, 2016, ss. 23-41. doi: 10.1007/978-3-319-47653-7_2.
8. J. R. Wolpaw, “Brain-computer interfaces (BCIs) for communication and control”, içinde Proceedings of the 9th international ACM SIGACCESS conference on Computers and accessibility, Tempe Arizona USA: ACM, Eki. 2007, ss. 1-2. doi: 10.1145/1296843.1296845.

9. Y. Zhang vd., “Identification of psychiatric disorder subtypes from functional connectivity patterns in resting-state electroencephalography”, Nat Biomed Eng, c. 5, sy. 4, ss. 309-323, Eki. 2020, doi: 10.1038/s41551-020-00614-8.
10. W. Wu vd., “An electroencephalographic signature predicts antidepressant response in major depression”, Nat Biotechnol, c. 38, sy. 4, ss. 439-447, Nis. 2020, doi: 10.1038/s41587-019-0397-3.
11. B. M. Ravirahul, V. R. Balaji, K. A. Ram Balaji, S. Gowtham, ve S. Surya, “Mind Wave Controlled Assistive Robot”, içinde 2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India: IEEE, Mar. 2021, ss. 1507-1509. doi: 10.1109/ICACCS51430.2021.9441684.
12. A. Saibene, M. Caglioni, S. Corchs, ve F. Gasparini, “EEG-Based BCIs on Motor Imagery Paradigm Using Wearable Technologies: A Systematic Review”, Sensors, c. 23, sy. 5, s. 2798, Mar. 2023, doi: 10.3390/s23052798.
13. A. S. Al-Fahoum ve A. A. Al-Fraihat, “Methods of EEG Signal Features Extraction Using Linear Analysis in Frequency and Time-Frequency Domains”, ISRN Neuroscience, c. 2014, ss. 1-7, Şub. 2014, doi: 10.1155/2014/730218.
14. “NeuroSky, “Brain Wave Signal (EEG) of NeuroSky"”, developer.neurosky.com. [Çevrimiçi]. Erişim adresi: http://developer.neurosky.com/docs/lib/exe/fetch.php?media=mindwave_user_guide_en.pdf.
15. V. J. Lawhern, A. J. Solon, N. R. Waytowich, S. M. Gordon, C. P. Hung, ve B. J. Lance, “EEGNet: a compact convolutional neural network for EEG-based brain–computer interfaces”, J. Neural Eng., c. 15, sy. 5, s. 056013, Eki. 2018, doi: 10.1088/1741-2552/aace8c.
16. L. Yin, C. Zhang, ve Z. Cui, “Experimental research on real-time acquisition and monitoring of wearable EEG based on TGAM module”, Computer Communications, c. 151, ss. 76-85, Şub. 2020, doi: 10.1016/j.comcom.2019.12.055.
17. H. Zhao vd., “Wearable sensors and features for diagnosis of neurodegenerative diseases: A systematic review”, DIGITAL HEALTH, c. 9, s. 20552076231173569, Oca. 2023, doi: 10.1177/20552076231173569.
18. M. S. Sharif, M. Raj Theeng Tamang, C. H. Y. Fu, A. Baker, A. I. Alzahrani, ve N. Alalwan, “An Innovative Random-Forest-Based Model to Assess the Health Impacts of Regular Commuting Using Non-Invasive Wearable Sensors”, Sensors, c. 23, sy. 6, s. 3274, Mar. 2023, doi: 10.3390/s23063274.
19. A. Nijholt, “Competing and Collaborating Brains: Multi-brain Computer Interfacing”, içinde Brain-Computer Interfaces, c. 74, A. E. Hassanien ve A. T. Azar, Ed., içinde Intelligent Systems Reference Library, vol. 74. , Cham: Springer International Publishing, 2015, ss. 313-335. doi: 10.1007/978-3-319-10978-7_12.
20. M. Zhou vd., “Epileptic Seizure Detection Based on EEG Signals and CNN”, Front. Neuroinform., c. 12, s. 95, Ara. 2018, doi: 10.3389/fninf.2018.00095.
21. S. Vaid, P. Singh, ve C. Kaur, “EEG Signal Analysis for BCI Interface: A Review”, içinde 2015 Fifth International Conference on Advanced Computing & Communication Technologies, Haryana, India: IEEE, Şub. 2015, ss. 143-147. doi: 10.1109/ACCT.2015.72.
22. L. A. Zadeh, “Fuzzy sets”, Information and Control, c. 8, sy. 3, ss. 338-353, Haz. 1965, doi: 10.1016/S0019-9958(65)90241-X.
23. T. J. Ross, Fuzzy logic with engineering applications, 3rd ed. Chichester, U.K: John Wiley, 2010.