Open Access
Research Article
Age prediction on EEG signals via hybrid feature engineering approach
Wanus Srimaharajwanus_s@payap.ac.thDepartment of Information Technology The International College Payap UniversityChiang Mai, 50000, ThailandView full profile → , *Neeta N. ThuneCorresponding authorneeta.thune@gmail.comDepartment of Electronics and Telecommunication Engineering Marathwada Mitra Mandal’s College of Engineering Savitribai Phule Pune University (SPPU)Pune, Maharashtra, 411052, IndiaView full profile → , Supansa Chaisingsupansa.cha@mfu.ac.thSustainability and Entrepreneurship Research Center School of Management Mae Fah Luang UniversityChiang Rai, 57100, ThailandView full profile → , A. B. Kanwadearchanakanwade@mmcoe.edu.inDepartment of Electronics and Telecommunication Engineering Marathwada Mitra Mandal’s College of Engineering Savitribai Phule Pune University (SPPU)Pune, Maharashtra, 411052, IndiaView full profile → , G. S. Gawandegawandeg25@gmail.comDepartment of Electronics and Telecommunications Engineering MIT-ADT University Loni KalbhorPune, Maharashtra, 412201, IndiaView full profile →
* Corresponding author · click or hover a name for details
- Received:
- 01 Apr 2025
- Published Online:
- 01 May 2026
- Article type:
- Research Article
- Language:
- EN
- Article no.:
- JIOS-2295
- Pages:
- 2043–2052
Abstract
This study proposes a Gaussian Process Regression (GPR) model with a custom composite kernel for age prediction from normal electroencephalogram (EEG) signals. Using the TUH Abnormal EEG Corpus from the Temple University EEG dataset, the model combines Radial Basis Function (RBF) and Matérn kernels to capture both global and local variations in EEG features. The prediction framework demonstrates a mean absolute error of 5.252 years and shows higher accuracy for middle-aged individuals. The composite kernel enables flexible adaptation to EEG signal characteristics across age ranges. The approach highlights differences in prediction performance across age groups and suggests clinical applicability for EEG-based age estimation. The findings demonstrate the potential of combining feature engineering and kernel-based learning for age prediction from normal EEG signals.
Keywords
Subject Classifications
Primary 93A30Secondary 49K15
References
[1] H. Lin and N. W. Bergmann, “IoT privacy and security challenges for smart home environments,” Information, vol. 7, no. 3, p. 44 (2016).[2] “Internet of Behavior (IoB) and its effects on your life and business,” Matellio. [Online]. Available: https://www.matellio.com. Accessed: (Jan. 14, 2024).[3] “What you should know about the Internet of Behaviors (IoB),” Datafloq. [Online]. Available: https://datafloq.com. Accessed: (Jan. 14, 2024).[4] “The Internet of Bodies (IoB) and its impact on today’s healthcare,” LinkedIn. [Online]. Available: https://www.linkedin.com. Accessed: (Jan. 14, 2024).[5] “The Internet of Bodies will change everything, for better or worse,” RAND Corporation. [Online]. Available: https://www.rand.org. Accessed: (Jan. 14, 2024).[6] M. Mendula, “Interaction and behaviour evaluation for smart homes: Data collection and analytics in the ScaledHome project,” in Proc. 23rd Int. ACM Conf. Modeling, Analysis and Simulation of Wireless and Mobile Systems, pp. 225–233 (Nov. 2020).[7] H. Wang, K. Wang, H. Zhao, and Y. Yue, “Prediction of user behavior in smart home based on improved ARIMA model,” in Proc. IEEE Int. Conf. Mechatronics and Automation (ICMA), pp. 298–302 (Aug. 2018).[8] A. Kumar, K. Singh, and T. Khan, “Study from EEG signals,” Journal of Information & Optimization Sciences, vol. 43, no. 4, pp. 855–891 (2022).[9] E. S. Abbas, E. A. Kuffi, and A. A. Jawad, “New integral ‘Kuffi-Abbas-Jawad’ KAJ transform and its application on ordinary differential equations,” Journal of Interdisciplinary Mathematics, vol. 25, no. 5, pp. 1427-1433 (2022).[10] S. M. Karmuse, A. L. Kakhandki, and M. Anandhalli, “Cloud based multivariate signal based heart abnormality detection,” Journal of Information and Optimization Sciences, vol. 43, no. 8, pp. 1935–1952 (2022).[11] N. N. Thune, A. Archana, N. Ganvir, and M. Navale, “Integrated adaptive driver alert system using IoT for road safety,” Journal of Information and Optimization Sciences, vol. 46, no. 2, pp. 273–280 (2025).[12] O. Al Zoubi, “Predicting age from brain EEG signals—A machine learning approach,” Frontiers in Aging Neuroscience, vol. 10, p. 184 (2018), doi: 10.3389/fnagi.2018.00184.[13] M. Khayretdinova, “Predicting age from resting-state scalp EEG signals with deep convolutional neural networks on TD-brain dataset,” Frontiers in Aging Neuroscience, vol. 14, p. 742954 (2022), doi: 10.3389/fnagi.2022.742954.[14] D. A. Engemann, “A reusable benchmark of brain-age prediction from M/EEG resting-state signals,” NeuroImage, vol. 262, p. 119521 (2022), doi: 10.1016/j.neuroimage.2020.119521.[15] P. Kaushik, A. Gupta, P. Roy, and D. P. Dogra, “EEG-based age and gender prediction using deep BLSTM-LSTM network model,” IEEE Sensors Journal, pp. 1–1 (2018), doi: 10.1109/JSEN.2018.2885582.[16] G. Sinha, “Machine learning methods for electroencephalogram-based age prediction,” in Proc. IEEE SENSORS, pp. 1–4 (Oct. 2023), doi: 10.1109/SENSORS53035.2023.9314276.[17] K. Jusseaume and I. Valova, “Brain age prediction/classification through recurrent deep learning with electroencephalogram recordings of seizure subjects,” Sensors, vol. 22, no. 21, p. 8112 (2022), doi: 10.3390/s22218112.[18] N. Sakib, “EEG-driven age prediction: Advancements in machine learning models,” in Proc. 3rd Int. Conf. Electronic and Electrical Engineering and Intelligent System (ICE3IS), pp. 383–388 (Aug. 2023), doi: 10.1109/ICE3IS52725.2023.9676922.[19] B. M. A. Bruns, “Predicting developmental age in young children by applying deep learning approaches to EEG data,” Master’s thesis (2021).[20] Y. Joo, E. Namgung, H. Jeong, I. Kang, J. Kim, S. Oh, I. K. Lyoo, S. Yoon, and J. Hwang, “Brain age prediction using combined deep convolutional neural network and multi-layer perceptron algorithms,” Scientific Reports, vol. 13, no. 1, p. 22388 (2023), doi: 10.1038/s41598-023-11884-2.[21] V. M. Joshi, P. P. Dandavate, R. Rashmi, G. R. Shinde, and R. Mirajkar, “DeepCervix: Enhancing cervical cancer detection through transfer learning with VGG-16 architecture,” Indonesian Journal of Electrical Engineering and Computer Sciences, vol. 36, no. 3, pp. 1895–1903(2024), doi: 10.11591/ijeecs.v36.i3.
Views: 89Downloads: 8Citations: 0
