EEG- and Language Generation-Based Emotional Arousal Assistance System for Alzheimer's Disease Patients
Academic Journal of Computing & Information Science · 2026 · 9 (5)
DOI: 10.25236/ajcis.2026.090505 ↗Kurz gefasst
Fachartikel in der Zeitschrift Academic Journal of Computing & Information Science, 2026.
Themen: Demenz
Abstract (Originalsprache)
Patients with Alzheimer's disease (AD) frequently present both cognitive decline and emotional dysregulation. Pharmacological treatment may reduce symptom progression, but side effects and long-term cost remain concerns, while traditional non-pharmacological interventions are often limited in personalization and objective evaluation. To address this gap, this paper proposes an emotional-arousal assistance system that combines electroencephalography (EEG) and large language models. The system performs real-time emotion recognition from EEG, generates simplified personalized poetry from autobiographical memory cues, and delivers coordinated multimodal stimulation with soothing music. Experiments on 2,132 EEG samples with six deep-learning models show that LSTM performs best (Accuracy 91.56%, Precision 92.9%, Recall 91.51%, F1-score 91.42%). Pilot testing indicates improved emotional arousal experience. The study provides a practical path toward personalized and quantifiable non-pharmacological intervention for AD.
Zitieren
APA
(2026). EEG- and Language Generation-Based Emotional Arousal Assistance System for Alzheimer's Disease Patients. Academic Journal of Computing & Information Science, 9(5). https://doi.org/10.25236/ajcis.2026.090505
Vancouver
EEG- and Language Generation-Based Emotional Arousal Assistance System for Alzheimer's Disease Patients. Academic Journal of Computing & Information Science. 2026;9(5). doi:10.25236/ajcis.2026.090505
BibTeX
@article{euvimed2026,
title = {EEG- and Language Generation-Based Emotional Arousal Assistance System for Alzheimer's Disease Patients},
journal = {Academic Journal of Computing & Information Science},
year = {2026},
volume = {9},
number = {5},
doi = {10.25236/ajcis.2026.090505}
}
EUVIMED