Can Less Be More? Benchmarking Lightweight Models Against State-of-the-Art Deep Learning Architectures for Deployable Seizure Detection

Isaiah Essien, Donna-lee Ginsberg, Jesse Thornburg
Conference on Parsimony and Learning, PMLR 328:720-734, 2026.

Abstract

Over the past decades, emerging research in seizure detection has highlighted the critical need for resource-constrained, deployable models that can operate in low-infrastructure environments. Seizure detection models that achieve high accuracy on benchmarks rarely run on the hardware available in low-resource contexts like developing countries, where epilepsy takes the heaviest toll. This work addresses the fundamental disconnect between model performance and real-world deployability by developing and evaluating parsimonious deep learning architectures for real-time epileptic seizure detection on consumer smartphones. This study systematically develops and compares two lightweight models: a Convolutional Neural Network with Gated Recurrent Units (CNN-GRU) and a 1D Convolutional Network with Multi-Head Attention (1D CNN-MHA). The optimal model is selected for both detection performance and deployment feasibility. The parsimonious 1D CNN-MHA model achieved superior performance with 96% accuracy, 93% sensitivity, and 0.99 AUC, outperforming the CNN-GRU model in both accuracy and sensitivity. Benchmarking against state-of-the-art models reveals a persistent deployment gap: while "lightweight" models in the literature lack deployment evidence, and high-accuracy models are bound to server-grade hardware, the 23.8 KB TensorFlow Lite model bridges this gap by delivering competitive accuracy while running in real-time on mid-range Android devices. Crucially, these results establish deployment feasibility rather than clinical validity: the system demonstrates that seizure-like motion patterns can be reliably discriminated under strict on-device constraints using commodity smartphones. The findings therefore support the principle that carefully designed parsimonious architectures can approach the performance of heavier models while remaining executable in real-world edge environments. This work can be interpreted as a feasibility study of deployability designed to enable subsequent large-scale clinical validation rather than as a population-level diagnostic model.

Cite this Paper

BibTeX
@InProceedings{pmlr-v328-essien26a, title = {Can Less Be More? Benchmarking Lightweight Models Against State-of-the-Art Deep Learning Architectures for Deployable Seizure Detection}, author = {Essien, Isaiah and Ginsberg, Donna-lee and Thornburg, Jesse}, booktitle = {Conference on Parsimony and Learning}, pages = {720--734}, year = {2026}, editor = {Burkholz, Rebekka and Liu, Shiwei and Ravishankar, Saiprasad and Redman, William and Huang, Wei and Su, Weijie and Zhu, Zhihui}, volume = {328}, series = {Proceedings of Machine Learning Research}, month = {23--26 Mar}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v328/main/assets/essien26a/essien26a.pdf}, url = {https://proceedings.mlr.press/v328/essien26a.html}, abstract = {Over the past decades, emerging research in seizure detection has highlighted the critical need for resource-constrained, deployable models that can operate in low-infrastructure environments. Seizure detection models that achieve high accuracy on benchmarks rarely run on the hardware available in low-resource contexts like developing countries, where epilepsy takes the heaviest toll. This work addresses the fundamental disconnect between model performance and real-world deployability by developing and evaluating parsimonious deep learning architectures for real-time epileptic seizure detection on consumer smartphones. This study systematically develops and compares two lightweight models: a Convolutional Neural Network with Gated Recurrent Units (CNN-GRU) and a 1D Convolutional Network with Multi-Head Attention (1D CNN-MHA). The optimal model is selected for both detection performance and deployment feasibility. The parsimonious 1D CNN-MHA model achieved superior performance with 96% accuracy, 93% sensitivity, and 0.99 AUC, outperforming the CNN-GRU model in both accuracy and sensitivity. Benchmarking against state-of-the-art models reveals a persistent deployment gap: while "lightweight" models in the literature lack deployment evidence, and high-accuracy models are bound to server-grade hardware, the 23.8 KB TensorFlow Lite model bridges this gap by delivering competitive accuracy while running in real-time on mid-range Android devices. Crucially, these results establish deployment feasibility rather than clinical validity: the system demonstrates that seizure-like motion patterns can be reliably discriminated under strict on-device constraints using commodity smartphones. The findings therefore support the principle that carefully designed parsimonious architectures can approach the performance of heavier models while remaining executable in real-world edge environments. This work can be interpreted as a feasibility study of deployability designed to enable subsequent large-scale clinical validation rather than as a population-level diagnostic model.} }
Endnote
%0 Conference Paper %T Can Less Be More? Benchmarking Lightweight Models Against State-of-the-Art Deep Learning Architectures for Deployable Seizure Detection %A Isaiah Essien %A Donna-lee Ginsberg %A Jesse Thornburg %B Conference on Parsimony and Learning %C Proceedings of Machine Learning Research %D 2026 %E Rebekka Burkholz %E Shiwei Liu %E Saiprasad Ravishankar %E William Redman %E Wei Huang %E Weijie Su %E Zhihui Zhu %F pmlr-v328-essien26a %I PMLR %P 720--734 %U https://proceedings.mlr.press/v328/essien26a.html %V 328 %X Over the past decades, emerging research in seizure detection has highlighted the critical need for resource-constrained, deployable models that can operate in low-infrastructure environments. Seizure detection models that achieve high accuracy on benchmarks rarely run on the hardware available in low-resource contexts like developing countries, where epilepsy takes the heaviest toll. This work addresses the fundamental disconnect between model performance and real-world deployability by developing and evaluating parsimonious deep learning architectures for real-time epileptic seizure detection on consumer smartphones. This study systematically develops and compares two lightweight models: a Convolutional Neural Network with Gated Recurrent Units (CNN-GRU) and a 1D Convolutional Network with Multi-Head Attention (1D CNN-MHA). The optimal model is selected for both detection performance and deployment feasibility. The parsimonious 1D CNN-MHA model achieved superior performance with 96% accuracy, 93% sensitivity, and 0.99 AUC, outperforming the CNN-GRU model in both accuracy and sensitivity. Benchmarking against state-of-the-art models reveals a persistent deployment gap: while "lightweight" models in the literature lack deployment evidence, and high-accuracy models are bound to server-grade hardware, the 23.8 KB TensorFlow Lite model bridges this gap by delivering competitive accuracy while running in real-time on mid-range Android devices. Crucially, these results establish deployment feasibility rather than clinical validity: the system demonstrates that seizure-like motion patterns can be reliably discriminated under strict on-device constraints using commodity smartphones. The findings therefore support the principle that carefully designed parsimonious architectures can approach the performance of heavier models while remaining executable in real-world edge environments. This work can be interpreted as a feasibility study of deployability designed to enable subsequent large-scale clinical validation rather than as a population-level diagnostic model.
APA
Essien, I., Ginsberg, D. & Thornburg, J.. (2026). Can Less Be More? Benchmarking Lightweight Models Against State-of-the-Art Deep Learning Architectures for Deployable Seizure Detection. Conference on Parsimony and Learning, in Proceedings of Machine Learning Research 328:720-734 Available from https://proceedings.mlr.press/v328/essien26a.html.

Related Material