OSCR

EEG and ECG Wearable Biosensor-Based Affective State Analysis Using Deep Learning over 6G IoT Healthcare Networks.

Overview

Authors: Hazal Su Bıçakcı Yeşilkaya1, Mete Özbaltan1, Nihan Özbaltan2, Cihat Şeker1, Bartu Yeşilkaya3, Bengisu Yalçınkaya2
ORCID iDs: Hazal Su Bıçakcı Yeşilkaya, Mete Özbaltan, Nihan Özbaltan, Cihat Şeker, Bartu Yeşilkaya, Bengisu Yalçınkaya
  1. Department of Electrical and Electronics Engineering, Faculty of Engineering and Architecture, İzmir Bakırçay University, 35665 İzmir, Türkiye; (M.Ö.); (C.Ş.)
  2. Department of Computer Engineering, Faculty of Engineering and Architecture, İzmir Bakırçay University, 35665 İzmir, Türkiye; (N.Ö.); (B.Y.)
  3. Department of Biomedical Engineering, Faculty of Engineering and Architecture, İzmir Katip Çelebi University, Balatcik Campus, 35620 İzmir, Türkiye
Institutions: Bakırçay Üniversitesi (Türkiye); Izmir Kâtip Çelebi University (Türkiye)
Journal: Biosensors, volume 16, issue 8, article 400
Dates: received 22 June 2026; accepted 21 July 2026; published online 23 July 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/bios16080400 · PMID 42645018 · PMCID PMC13511720 · OpenAlex W7170195011
Open access: gold, a free copy (OpenAlex)
Status: data only (how the code is found and verified)
Categories: EEG (modality), other (modality), human (organism)
Methods: Spectral & time-frequency, Connectivity, Smoothing, state filtering, decompositions, Machine learning, Statistics, Preprocessing, Single-unit activity, calcium imaging, Evoked potentials, Physiology & signal measures
Keywords: wearable biosensors, EEG, ECG, affective state analysis, deep learning, emotion recognition, 6G IoT networks, ray tracing
MeSH: Biosensing Techniques*, Deep Learning*, Electrocardiography*, Electroencephalography*, Wearable Electronic Devices*, Convolutional Neural Networks, Digital Health, Humans, Internet of Things, Signal Processing, Computer-Assisted (* major topic)
Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Citations: not cited yet (Europe PMC); 93 references in the paper

Abstract

Physiological signal analysis using wearable biosensors like an electroencephalogram (EEG) and an electrocardiogram (ECG) is widely investigated for affective computing; however, the integration of deep learning-based affective computing within 6G-driven IoT healthcare infrastructures remains limited, with data transmission latency posing a significant challenge. This study proposes a framework for EEG and ECG-based affective state analysis over 6G IoT networks. We utilize an attention-based deep learning model for three-class emotion recognition from EEG signals, and a ResNet50-based convolutional neural network for three-class stress/affective state classification using ECG data. The framework’s communication performance is evaluated through ray tracing simulations in a virtual hospital environment at 7 GHz and 92 GHz bands. Experimental results on SEED and WESAD datasets demonstrate that the EEG model achieved 90.93% classification accuracy, while the ECG model yielded 82.26% validation and 65.64% test accuracy. Wireless analysis showed RMS delay spread values of 6.53 ns (7 GHz) and 3.32 ns (92 GHz), with correlation bandwidths of 30.63 MHz and 60.24 MHz, respectively. These findings demonstrate the feasibility of integrating wearable biosensor-based affective state analysis with 6G-oriented IoT healthcare communication frameworks, providing a robust foundation for future personalized health and human state monitoring applications.

Reproduced under the paper's license (CC BY), from the paper cited above.

Code

The paper links to its data and to no code of its authors: see the Data section.

Tracing map

A tracing map links a paper to the code its authors published: this paper has none, so it has no map.

Data

Datasets cited

Data Availability Statement

The datasets used in this study are publicly available. The SEED EEG dataset and the WESAD ECG dataset were used for the experimental evaluations. The corresponding acquisition details and references are provided in Section 4.2.

Reproduced under the paper's license (CC BY), from the paper cited above.

Versions

The history of this record: each version stored by the harvester or made by a correction of its authors or of the maintainers of its code, and what changed in its facts. The texts of the paper (its abstract, its availability statements) are not part of it; versions that changed only those are not listed.

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 6 authors, 8 keywords, 10 MeSH terms, 90 references.

Cite

This paper

Bıçakcı Yeşilkaya, H. S., Özbaltan, M., Özbaltan, N., Şeker, C., Yeşilkaya, B., & Yalçınkaya, B. (2026). EEG and ECG Wearable Biosensor-Based Affective State Analysis Using Deep Learning over 6G IoT Healthcare Networks. Biosensors, 16(8), 400. https://doi.org/10.3390/bios16080400

BibTeX

@article{bcakcyesilkaya2026eeg,
author = {Bıçakcı Yeşilkaya, Hazal Su and Özbaltan, Mete and Özbaltan, Nihan and Şeker, Cihat and Yeşilkaya, Bartu and Yalçınkaya, Bengisu},
title = {{EEG and ECG Wearable Biosensor-Based Affective State Analysis Using Deep Learning over 6G IoT Healthcare Networks}},
journal = {Biosensors},
year = {2026},
month = jul,
volume = {16},
number = {8},
pages = {400},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2079-6374},
doi = {10.3390/bios16080400},
url = {https://doi.org/10.3390/bios16080400},
pmid = {42645018},
pmcid = {PMC13511720}
}

RIS

TY - JOUR
AU - Bıçakcı Yeşilkaya, Hazal Su
AU - Özbaltan, Mete
AU - Özbaltan, Nihan
AU - Şeker, Cihat
AU - Yeşilkaya, Bartu
AU - Yalçınkaya, Bengisu
TI - EEG and ECG Wearable Biosensor-Based Affective State Analysis Using Deep Learning over 6G IoT Healthcare Networks
T2 - Biosensors
J2 - Biosensors (Basel)
PY - 2026
DA - 2026/07/23
VL - 16
IS - 8
SP - 400
SN - 2079-6374
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/bios16080400
UR - https://doi.org/10.3390/bios16080400
LA - en
ER -

CSL-JSON

{
"id": "10.3390/bios16080400",
"type": "article-journal",
"title": "EEG and ECG Wearable Biosensor-Based Affective State Analysis Using Deep Learning over 6G IoT Healthcare Networks",
"container-title": "Biosensors",
"author": [
{
"family": "Bıçakcı Yeşilkaya",
"given": "Hazal Su"
},
{
"family": "Özbaltan",
"given": "Mete"
},
{
"family": "Özbaltan",
"given": "Nihan"
},
{
"family": "Şeker",
"given": "Cihat"
},
{
"family": "Yeşilkaya",
"given": "Bartu"
},
{
"family": "Yalçınkaya",
"given": "Bengisu"
}
],
"container-title-short": "Biosensors (Basel)",
"volume": "16",
"issue": "8",
"page": "400",
"DOI": "10.3390/bios16080400",
"PMID": "42645018",
"PMCID": "PMC13511720",
"ISSN": "2079-6374",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/bios16080400",
"language": "en",
"issued": {
"date-parts": [
[
2026,
7,
23
]
]
}
}

Similar papers

The papers with a page that share the most with this one: the tools found in their code, their categories, datasets, cited references and authors, the rarest counting most.

[1] doi:10.12688/f1000research.171170.2
A Review of Deep Learning Techniques for EEG-Based Emotion Recognition: Models, Methods, and Datasets.
Journal: F1000Research
In common: EEG, 14 references
[2] doi:10.1007/s11571-023-10004-w [code]
EEG-based emotion recognition using a temporal-difference minimizing neural network.
Journal: Cognitive neurodynamics
In common: EEG, 12 references
[3] doi:10.3390/s23052387 [code]
Online Learning for Wearable EEG-Based Emotion Classification.
Journal: Sensors (Basel, Switzerland)
In common: other, EEG, 10 references
[4] doi:10.3390/bios16080421
GLSTNet: A Global-Local Spatial Relations and Temporal Dynamics Network for EEG-Based Emotion Recognition.
Journal: Biosensors
In common: EEG, 10 references
[5] doi:10.3390/e24121830 [code]
Multidimensional Feature in Emotion Recognition Based on Multi-Channel EEG Signals.
Journal: Entropy (Basel, Switzerland)
In common: EEG, 9 references
[6] doi:10.3390/brainsci16070716
RGB-Style Input Representations for EEG: Evaluating Spatial Concatenation Versus Band-Wise Stacking in Deep Emotion Recognition.
Journal: Brain sciences
In common: EEG, 9 references
[7] doi:10.3389/fnhum.2025.1715410
Exploring physical and functional EEG connectivity with multilayer graph transformer convolutional networks for emotion recognition.
Journal: Frontiers in human neuroscience
In common: EEG, 8 references
[8] doi:
EEG emotion-recognition datasets for neuroarchitecture: an appraisal of openness, AI-readiness and ontology maturity
Journal: Frontiers in neuroinformatics
In common: EEG, 8 references
[9] doi:10.3389/fnins.2024.1320645 [code]
ERTNet: an interpretable transformer-based framework for EEG emotion recognition.
Journal: Frontiers in neuroscience
In common: EEG, 8 references
[10] doi:10.1038/s41597-026-07456-0
A multimodal dataset for emotional transition analysis in virtual reality.
Journal: Scientific data
In common: other, EEG, 7 references

Contribute

The authors of this paper can claim it, correct its record and validate its tracing map, and the maintainers of its code (its owner, or a public member of its organization) correct what it says of their repository; anyone signed in can ask for its removal. Every request goes to OSCR's own machine, which answers it; your account page follows them.

Sign in with ORCID to claim this paper as one of its authors, correct its record or validate its tracing map: when the paper's metadata lists your ORCID iD, you are recognized at once. Maintainers of its code: sign in with GitHub, then claim the repository on your account page.

Request its removal

To ask OSCR to remove this record, the copies of its authors' scripts or its tracing map, use the removal request page: signed in, you say who you are, what to remove and why, then review and confirm the request. Published rules decide every request (how).

Discussion, reproductions, activity

Discussion: code errors and mismatches between the code and the paper about this paper and its code, from readers and its authors, beside the paper and its tracing map.

Reproductions: reports from readers who ran the authors' code and did not get the paper's result, what they ran, with which environment, commit and data.

Activity: what happens around this paper: new versions of its record, its map's validation, discussions and reproductions. It opens with sign-in.