OSCR

Multiscale Cosine Convolution Neural Network for Robust and Interpretable Epileptic EEG Detection.

Overview

  1. School of Integrated Circuits, Shandong University, Jinan 250101, China; (J.C.); (W.Z.)
  2. Shenzhen Research Institute of Shandong University, Shenzhen 518000, China
Institutions: Shandong University (China)
Journal: Biosensors, volume 16, issue 4, article 203
Dates: received 6 February 2026; accepted 31 March 2026; published online 2 April 2026
Type: Research article · Language: English
License: CC BY
Identifiers: DOI 10.3390/bios16040203 · PMID 42041424 · PMCID PMC13114204 · OpenAlex W7148460935
Open access: gold, a free copy (OpenAlex)
Categories: EEG (modality), human (organism), epilepsy (population)
Methods: Connectivity, Machine learning, Preprocessing, Smoothing, state filtering, decompositions, Physiology & signal measures
Keywords: seizure detection, multiscale convolutional neural network, cosine convolution, Heterogeneous Two-Stream Network, EEG signal processing
MeSH: Electroencephalography*, Epilepsy*, Algorithms, Convolutional Neural Networks, Humans, Neural Networks, Computer, Signal Processing, Computer-Assisted (* major topic)
Topic: EEG and Brain-Computer Interfaces (Cognitive Neuroscience, Neuroscience), according to OpenAlex
Funding: National Natural Science Foundation of China (62401342, 62271291); Natural Science Foundation of Shandong Province (ZR2024QF092, ZR2024LZH007, ZR2025ZD24); Guangdong Basic and Applied Basic Research Foundation (2025A1515011826, 2026A1515010768); Shenzhen Fundamental Research Program (JCYJ20250604124702003); National Key Research and Development Program of China (2024YFC2418300, 2024YFC2418303)
Citations: cited by 2 papers (Europe PMC); 53 references in the paper
Research resources: RRID:SCR_00734510

Abstract

The accurate detection of epileptic seizures using an electroencephalogram (EEG) is essential for clinical diagnosis and reducing the burden on clinicians but remains challenging due to low detection performance and model interpretability. In this study, we propose a Multiscale Cosine Convolutional Heterogeneous Two-Stream Cosine Convolution Network (MCC-HTSCC) to overcome these limitations. First, the raw EEG signals are input into the Multiscale Cosine Convolution (MCC) module, where multiscale temporal features are extracted by cosine convolutional layers with varying kernel lengths. Subsequently, the extracted temporal features are further processed through spatial convolutional layers to obtain comprehensive spatiotemporal representations. These spatiotemporal features are fused and subsequently fed into the Heterogeneous Two-Stream Cosine Convolution (HTSCC) module, comprising both deep and shallow subnetworks to perform hierarchical feature extraction and classification. Extensive evaluations were conducted on the publicly available CHB-MIT dataset and a clinically collected SH-SDU dataset, achieving accuracies of 98.52% and 94.56%, sensitivities of 97.98% and 88.09%, and specificities of 98.50% and 95.89%, respectively. Furthermore, the cosine convolution operators reduce the learnable parameters of our model by approximately 18.12% compared to the model with traditional convolution operators, making it more suitable for embedded deployment. By employing the Gradient-Weighted Class Activation Mapping (Grad-CAM) technique, we further provide interpretability and transparency in model decision making, highlighting the substantial potential of MCC-HTSCC for effective patient-specific epilepsy monitoring and diagnostics.

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 data are available from the corresponding author upon reasonable request, subject to ethical and privacy restrictions.

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, 28 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 3 authors, 5 keywords, 7 MeSH terms, 5 funders, 44 references, 1 RRID.

Cite

This paper

Chen, J., Zhou, W., & Liu, G. (2026). Multiscale Cosine Convolution Neural Network for Robust and Interpretable Epileptic EEG Detection. Biosensors, 16(4), 203. https://doi.org/10.3390/bios16040203

BibTeX

@article{chen2026multiscale,
author = {Chen, Jiale and Zhou, Weidong and Liu, Guoyang},
title = {{Multiscale Cosine Convolution Neural Network for Robust and Interpretable Epileptic EEG Detection}},
journal = {Biosensors},
year = {2026},
month = apr,
volume = {16},
number = {4},
pages = {203},
publisher = {Multidisciplinary Digital Publishing Institute (MDPI)},
issn = {2079-6374},
doi = {10.3390/bios16040203},
url = {https://doi.org/10.3390/bios16040203},
pmid = {42041424},
pmcid = {PMC13114204}
}

RIS

TY - JOUR
AU - Chen, Jiale
AU - Zhou, Weidong
AU - Liu, Guoyang
TI - Multiscale Cosine Convolution Neural Network for Robust and Interpretable Epileptic EEG Detection
T2 - Biosensors
J2 - Biosensors (Basel)
PY - 2026
DA - 2026/04/02
VL - 16
IS - 4
SP - 203
SN - 2079-6374
PB - Multidisciplinary Digital Publishing Institute (MDPI)
DO - 10.3390/bios16040203
UR - https://doi.org/10.3390/bios16040203
LA - en
ER -

CSL-JSON

{
"id": "10.3390/bios16040203",
"type": "article-journal",
"title": "Multiscale Cosine Convolution Neural Network for Robust and Interpretable Epileptic EEG Detection",
"container-title": "Biosensors",
"author": [
{
"family": "Chen",
"given": "Jiale"
},
{
"family": "Zhou",
"given": "Weidong"
},
{
"family": "Liu",
"given": "Guoyang"
}
],
"container-title-short": "Biosensors (Basel)",
"volume": "16",
"issue": "4",
"page": "203",
"DOI": "10.3390/bios16040203",
"PMID": "42041424",
"PMCID": "PMC13114204",
"ISSN": "2079-6374",
"publisher": "Multidisciplinary Digital Publishing Institute (MDPI)",
"URL": "https://doi.org/10.3390/bios16040203",
"language": "en",
"issued": {
"date-parts": [
[
2026,
4,
2
]
]
}
}

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:10.3390/diagnostics16132012
Power and Phase Fusion Spectrogram with Three-Dimensional Convolution and Vision Transformer for Seizure Detection.
Journal: Diagnostics (Basel, Switzerland)
In common: DOI 10.13026/c2k01r, epilepsy, EEG, 6 references, 2 authors
[2] doi:10.3390/s24010077
Automatic Seizure Detection Based on Stockwell Transform and Transformer.
Journal: Sensors (Basel, Switzerland)
In common: epilepsy, EEG, 5 references, 2 authors
[3] doi:10.1098/rsos.230601 [code]
Epileptic seizure detection using CHB-MIT dataset: The overlooked perspectives.
Journal: Royal Society open science
In common: DOI 10.13026/c2k01r, epilepsy, EEG, 4 references
[4] doi:10.3389/fneur.2024.1389731
Single-channel seizure detection with clinical confirmation of seizure locations using CHB-MIT dataset.
Journal: Frontiers in neurology
In common: epilepsy, EEG, 6 references
[5] doi:10.1186/s42492-025-00208-8
Comprehensive review of machine learning and deep learning techniques for epileptic seizure detection and prediction based on neuroimaging modalities.
Journal: Visual computing for industry, biomedicine, and art
In common: epilepsy, EEG, 6 references
[6] doi:10.3390/biomimetics11060377
PG-MCTFormer: A Prior-Guided Multi-Scale Convolutional Transformer for Interpretable Motor Imagery EEG Classification.
Journal: Biomimetics (Basel, Switzerland)
In common: EEG, 2 authors
[7] doi:10.1038/s41598-025-18479-9 [code]
Epileptic seizure detection from electroencephalogram signals based on 1D CNN-LSTM deep learning model using discrete wavelet transform.
Journal: Scientific reports
In common: DOI 10.13026/c2k01r, epilepsy, EEG, 3 references
[8] doi:10.3389/fnins.2024.1468967
A review of epilepsy detection and prediction methods based on EEG signal processing and deep learning.
Journal: Frontiers in neuroscience
In common: epilepsy, EEG, 5 references
[9] doi:10.3389/fnins.2025.1693079 [code]
CPRSCA-ResNet: a novel ResNet-based model with Channel-Partitioned Resolution Spatial-Channel Attention for EEG-based seizure detection.
Journal: Frontiers in neuroscience
In common: epilepsy, EEG, 5 references
[10] doi:10.3390/e28060599
Large-Scale Synchronization Dynamics During Epileptic Seizures: A Patient-Independent EEG Network Analysis.
Journal: Entropy (Basel, Switzerland)
In common: DOI 10.13026/c2k01r, epilepsy, EEG, 2 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.