Multi Scale Temporal Convolution for Resting State Electroencephalography Analysis of Alzheimer’s Disease and Frontotemporal Dementia

Kanchana Boontasri; Kamonlak Chaidee; Bunyarat Umsura

doi:10.2991/978-94-6239-797-2_35

<Previous Article In Volume

Next Article In Volume>

Multi Scale Temporal Convolution for Resting State Electroencephalography Analysis of Alzheimer’s Disease and Frontotemporal Dementia

Authors

Kanchana Boontasri¹, Kamonlak Chaidee², Bunyarat Umsura²^{, *}

¹Department of Faculty of Science and Agricultural Technology, Rajamangala University of Technology Lanna, Chiang Mai, Thailand

²Department of Business Information System, Rajamangala University of Technology Lanna, Chiang Mai, Thailand

^*Corresponding author. Email: bunyarat.um@rmutl.ac.th

Corresponding Author

Bunyarat Umsura

Available Online 14 October 2026.

DOI: 10.2991/978-94-6239-797-2_35 How to use a DOI?
Keywords: Alzheimer’s Disease; Electroencephalography; Multi-Scale Convolution; OpenNeuro; Neurodegeneration; Computational Mathematics
Abstract: Alzheimer’s disease (AD) is a widespread neurodegenerative disorder. Early diagnosis improves intervention outcomes. Electroencephalography (EEG) provides a noninvasive method for detecting neuronal changes. The study proposes a Multi-Scale Temporal Convolution framework to classify AD, Frontotemporal Dementia (FTD), and Cognitively Normal subjects. The framework evaluates the OpenNeuro dataset ds004504 containing resting state EEG recordings from 88 participants. The architecture applies parallel convolution operations with varying kernel dimensions to extract features across different frequency resolutions. The model achieves 88.6% binary classification accuracy and 86.4% multiclass accuracy. The sensitivity for detecting AD reached 91.2% with 89.5% specificity. It indicates that processing time series data at multiple temporal resolutions extracts discriminative features effectively. The findings support the development of accessible diagnostic tools.
Copyright: © 2026 The Author(s)
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the 2nd International Conference on Lifespan Innovation (ICLI 2026) national Conference on Lifespan Innovation
Series: Advances in Social Science, Education and Humanities Research
Publication Date: 14 October 2026
ISBN: 978-94-6239-797-2
ISSN: 2352-5398
DOI: 10.2991/978-94-6239-797-2_35 How to use a DOI?
Open Access: Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

ris enw bib

TY  - CONF
AU  - Kanchana Boontasri
AU  - Kamonlak Chaidee
AU  - Bunyarat Umsura
PY  - 2026
DA  - 2026/10/14
TI  - Multi Scale Temporal Convolution for Resting State Electroencephalography Analysis of Alzheimer’s Disease and Frontotemporal Dementia
BT  - Proceedings of the 2nd International Conference on Lifespan Innovation (ICLI 2026) national Conference on Lifespan Innovation
PB  - Atlantis Press
SP  - 356
EP  - 364
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-94-6239-797-2_35
DO  - 10.2991/978-94-6239-797-2_35
ID  - Boontasri2026
ER  -

download .riscopy to clipboard