AI-Driven EKO-ALSTM Modeling of EEG-Based Emotion Recognition for Assistive Brain–Computer Interface Applications

Khalid Ayed Alharthi; R. Kishore Kanna; M. B. Shyjith; Mohamed Kchaou

doi:10.48084/etasr.16774

Authors

Khalid Ayed Alharthi Department of Computer Science, College of Computing, University of Bisha, Bisha, Saudi Arabia
R. Kishore Kanna Department of Biomedical Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology, Chennai, India
M. B. Shyjith Department of Computer Science & Engineering, Jyothi Engineering College, Thrissur, Kerala, India
Mohamed Kchaou Department of Industrial Engineering, College of Engineering, University of Bisha, Bisha, Saudi Arabia

Volume: 16 | Issue: 3 | Pages: 36279-36289 | June 2026 | https://doi.org/10.48084/etasr.16774

Received: 7 December 2025 | Revised: 10 January 2026, 27 January 2026, and 10 February 2026 | Accepted: 13 February 2026 | Online: 6 June 2026

Corresponding author: R. Kishore Kanna

Abstract

Current Electroencephalography (EEG)-based emotion recognition models designed to facilitate assistive Brain–Computer Interface (BCI) applications suffer from inconsistent accuracy, primarily due to the incomplete exploitation of deep learning optimization and insufficient modeling of temporal dependencies in neural signals. These deficiencies prevent the seamless integration of such models into process-oriented healthcare systems. In response, an optimized framework called EKO-ALSTM is proposed. This architecture integrates the Enhanced Kookaburras Optimization (EKO) algorithm, a bio-inspired optimization mechanism, and Adjustable Long Short-Term Memory (ALSTM) networks. The EKO algorithm dynamically optimizes the hyperparameters of the ALSTM using iterative exploration–exploitation strategies inspired by the foraging behavior of kookaburras, thus mitigating vanishing gradients while preserving long-term temporal dependencies essential for effective emotion recognition. The proposed framework was rigorously validated on the benchmark DEAP dataset in a 10-fold stratified cross-validation scheme under a subject-independent partitioning. Evaluation metrics included accuracy, sensitivity, specificity, and Positive Predictive Value (PPV) of the arousal, valence, and dominance dimensions. Statistical significance was assessed using a paired t-test with Bonferroni correction (α = 0.05). The EKO-ALSTM model achieved an accuracy of 98.62 ± 0.34%, sensitivity of 98.12 ± 0.28%, specificity of 98.22 ± 0.31%, and PPV of 95.97 ± 0.42%. These results indicate statistically significant improvements of 3–15% compared with contemporary models such as Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM), Support Vector Machine (SVM), and conventional LSTM (p < 0.05). Furthermore, classification error was reduced by 46% through hybrid optimization compared with non-optimized architectures.

Keywords:

EKO-ALSTM hybrid model, process-oriented healthcare applications, BCI, optimization

References

A. N. Belkacem, N. Jamil, J. A. Palmer, S. Ouhbi, and C. Chen, "Brain Computer Interfaces for Improving the Quality of Life of Older Adults and Elderly Patients," Frontiers in Neuroscience, vol. 14, June 2020, Art. no. 692.

W. H. Elashmawi et al., "A Comprehensive Review on Brain–Computer Interface (BCI)-Based Machine and Deep Learning Algorithms for Stroke Rehabilitation," Applied Sciences, vol. 14, no. 14, July 2024, Art. no. 6347.

J. R. Wolpaw, N. Birbaumer, D. J. McFarland, G. Pfurtscheller, and T. M. Vaughan, "Brain–computer interfaces for communication and control," Clinical Neurophysiology, vol. 113, no. 6, pp. 767–791, June 2002.

I. Lazarou, S. Nikolopoulos, P. C. Petrantonakis, I. Kompatsiaris, and M. Tsolaki, "EEG-Based Brain–Computer Interfaces for Communication and Rehabilitation of People with Motor Impairment: A Novel Approach of the 21st Century," Frontiers in Human Neuroscience, vol. 12, Jan. 2018, Art. no. 14.

K. D. Tzimourta et al., "Evaluation of window size in classification of epileptic short-term EEG signals using a Brain Computer Interface software," Engineering, Technology & Applied Science Research, vol. 8, no. 4, pp. 3093–3097, Aug. 2018.

B. Blankertz and C. Vidaurre, "Towards a cure for BCI illiteracy: machine learning based co-adaptive learning," BMC Neuroscience, vol. 10, no. 1, July 2009, Art. no. P85.

F. Lotte, F. Larrue, and C. Mühl, "Flaws in current human training protocols for spontaneous Brain-Computer Interfaces: lessons learned from instructional design," Frontiers in Human Neuroscience, vol. 7, Sept. 2013, Art. no. 568.

H. Chen et al., "Toward the Construction of Affective Brain-Computer Interface: A Systematic Review," ACM Computing Surveys, vol. 57, no. 6, Feb. 2025, Art. no. 156.

J. R. Wolpaw and D. J. McFarland, "Control of a two-dimensional movement signal by a noninvasive brain-computer interface in humans," Proceedings of the National Academy of Sciences, vol. 101, no. 51, pp. 17849–17854, Dec. 2004.

G. R. K. Reddy, A. D. Bhavani, and V. K. Odugu, "Optimized recurrent neural network based brain emotion recognition technique," Multimedia Tools and Applications, vol. 84, no. 8, pp. 4655–4674, Mar. 2025.

B. Yu, L. Cao, J. Jia, C. Fan, Y. Dong, and C. Zhu, "E-FNet: A EEG-fNIRS dual-stream model for Brain–Computer Interfaces," Biomedical Signal Processing and Control, vol. 100, Feb. 2025, Art. no. 106943.

A. Goshvarpour and A. Goshvarpour, "Cognitive-Inspired Spectral Spatiotemporal Analysis for Emotion Recognition Utilizing Electroencephalography Signals," Cognitive Computation, vol. 17, no. 1, Nov. 2024, , Art. no. 2.

M. M. El-Amir, W. Al-Atabany, and M. A. Eldosoky, "Emotion Recognition via Detrended Fluctuation Analysis and Fractal Dimensions," in 2019 36th National Radio Science Conference, Port Said, Egypt, 2019, pp. 200–208.

S. Zhong, J. Shi, and Y. Wang, "Knowledge-guided quantization-aware training for EEG-based emotion recognition," Journal of Visual Communication and Image Representation, vol. 108, Apr. 2025, , Art. no. 104415.

S. Koelstra et al., "DEAP: A Database for Emotion Analysis ;Using Physiological Signals," IEEE Transactions on Affective Computing, vol. 3, no. 1, pp. 18–31, Jan. 2012.

W.-L. Zheng. "SEED EEG Dataset Repository." Wei-Long Zheng. https://weilongzheng.github.io/datasets/.

S. Katsigiannis and N. Ramzan, "DREAMER: A Database for Emotion Recognition Through EEG and ECG Signals From Wireless Low-cost Off-the-Shelf Devices," IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 1, pp. 98–107, Jan. 2018.

M. Soleymani, J. Lichtenauer, T. Pun, and M. Pantic, "A Multimodal Database for Affect Recognition and Implicit Tagging," IEEE Transactions on Affective Computing, vol. 3, no. 1, pp. 42–55, Jan. 2012.

J. A. Miranda-Correa, M. K. Abadi, N. Sebe, and I. Patras, "AMIGOS: A Dataset for Affect, Personality and Mood Research on Individuals and Groups," IEEE Transactions on Affective Computing, vol. 12, no. 2, pp. 479–493, Apr. 2021.

Z. Yin, M. Zhao, Y. Wang, J. Yang, and J. Zhang, "Recognition of emotions using multimodal physiological signals and an ensemble deep learning model," Computer Methods and Programs in Biomedicine, vol. 140, pp. 93–110, Mar. 2017.

W. Liu, W.-L. Zheng, and B.-L. Lu, "Multimodal Emotion Recognition Using Multimodal Deep Learning." arXiv, Feb. 26, 2016.

"EEG Brain Signals Emotion Classification." Kaggle. [Online]. Available: https://kaggle.com/code/oliverright/eeg-brain-signals-emotion-classification.

A. Danquah-Amoah, K. K. R, D. A. Bonah, and S. Amponsah, "A Review of the Ethical Frameworks in Wearable Nano Biosensors for Real-Time Monitoring of Metabolic Disorders," NanoNEXT, vol. 4, no. 4, pp. 32–40, Dec. 2023.

A. Delorme and S. Makeig, "EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis," Journal of Neuroscience Methods, vol. 134, no. 1, pp. 9–21, Mar. 2004.

K. K. R, A. Danquah-Amoah, and S. Amponsah, "Next-Generation Neural Interfaces Enabled by Nano-Bioelectronics- Review," NanoNEXT, vol. 5, no. 4, pp. 27–37, Dec. 2024.

N. K, S. D, M. M.C, and K. R, "Comprehensive EEG Signal Feature Extraction for Neurological Disorder Diagnosis: Focus on Alzheimer’s, Parkinson’s, and Seizure Disorders," International Research Journal of Multidisciplinary Technovation, vol. 6, no. 5, pp. 80–93, Sept. 2024.

P. Jahankhani, V. Kodogiannis, and K. Revett, "EEG Signal Classification Using Wavelet Feature Extraction and Neural Networks," in IEEE John Vincent Atanasoff 2006 International Symposium on Modern Computing, Sofia, Bulgaria, 2006, pp. 120–124.

R. K. Kanna et al., "Improving EEG based brain computer interface emotion detection with EKO ALSTM model," Scientific Reports, vol. 15, no. 1, July 2025, Art. no. 20727.