Q-SleepNet: A Lightweight Quantized Deep Learning Framework for EEG-Based Sleep Stage Classification on Android

Atharva Bhatkande; Amogh Kulkarni; Aarya Ningaraddiyavar; Anika Malige; Niranjan Muchandi

doi:10.2991/978-94-6463-978-0_60

<Previous Article In Volume

Q-SleepNet: A Lightweight Quantized Deep Learning Framework for EEG-Based Sleep Stage Classification on Android

Authors

Atharva Bhatkande¹^{, *}, Amogh Kulkarni¹, Aarya Ningaraddiyavar¹, Anika Malige¹, Niranjan Muchandi¹

¹KLE Technological University, Belgavi, Karnataka, 590008, India

^*Corresponding author. Email: 02fe22bci011@kletech.ac.in

Corresponding Author

Atharva Bhatkande

Available Online 31 December 2025.

DOI: 10.2991/978-94-6463-978-0_60 How to use a DOI?
Keywords: Sleep stage classification; EEG; TensorFlow Lite; Android; MobileNet; Deep Learning
Abstract: Sleep is essential for preserving general health, emotional stability, and cognitive function. However, because conventional diagnostic techniques are not widely available, the prevalence of undiagnosed sleep disorders continues to be high. Making Use of the Sleep-EDF We created a unique convolutional neural network (CNN) specifically for sleep stage classification using an expanded dataset. This study suggests a simple and effective method for automated sleep stage classification using EEG signals in order to overcome these difficulties. We used TensorFlow Lite for post-training quantisation in order to facilitate deployment on devices with limited resources. The final quantized model is integrated into an Android application to facilitate real-time, user-friendly sleep monitoring outside clinical environments. Experimental results demonstrate that the quantized model achieves an accuracy of approximately 90%, highlighting the feasibility of deep learning-driven, edge-compatible solutions for accessible and affordable sleep health monitoring.
Copyright: © 2025 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

Volume Title: Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
Series: Advances in Engineering Research
Publication Date: 31 December 2025
ISBN: 978-94-6463-978-0
ISSN: 2352-5401
DOI: 10.2991/978-94-6463-978-0_60 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  - Atharva Bhatkande
AU  - Amogh Kulkarni
AU  - Aarya Ningaraddiyavar
AU  - Anika Malige
AU  - Niranjan Muchandi
PY  - 2025
DA  - 2025/12/31
TI  - Q-SleepNet: A Lightweight Quantized Deep Learning Framework for EEG-Based Sleep Stage Classification on Android
BT  - Proceedings of the 1st Engineering Data Analytics and Management Conference (EAMCON 2025)
PB  - Atlantis Press
SP  - 716
EP  - 728
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-978-0_60
DO  - 10.2991/978-94-6463-978-0_60
ID  - Bhatkande2025
ER  -

download .riscopy to clipboard