Hybrid Edge-Cloud Asymmetric Analytics for Portable Multimodal BCI Biosensors.

Overview

1. Department of Biophysics and Radiation Biology, Semmelweis University, 1085 Budapest, Hungary; (S.G.)
2. Department of Integrative Biology, Vellore Institute of Technology, Vellore 632014, India
3. Department of General Medicine, PSG Institute of Medical Sciences & Research, Coimbatore 641004, India
4. Department of Artificial Intelligence and Data Science, Panimalar Engineering College, Chennai 600123, India
5. Department of Instrumentation, Vellore Institute of Technology, Vellore 632014, India
6. Cognitive Neuroimaging Centre, Experimental Medicine, Nanyang Technological University, Singapore 636921, Singapore
7. Department of Clinical Neuroscience, Karolinska Institute, 17176 Stockholm, Sweden
8. Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore 636921, Singapore
9. Division of Neuroradiology, Department of Medical Imaging, Faculty of Medicine, Semmelweis University, 1083 Budapest, Hungary

Abstract

Portable biosensor hardware can now sustain continuous multimodal physiological acquisition at the edge, yet the analytical layer that converts raw signals into deployment-consistent inference remains the main bottleneck for practical embedded systems. This study addresses that bottleneck by presenting the machine-learning layer of the Real-time Cognitive Grid, the analytical companion to the previously reported hardware architecture, which equips a fixed-wiring biosensor assembly with real-time physiological-state classification through an asymmetric edge–cloud workflow. The proposed framework assigns analytical responsibility across tiers: a locked 17-feature schema comprising 5 EMG features, 6 EEG spectral features, 2 cross-modal features, 2 HRV features, 1 EOG feature, and 1 EEG quality indicator governs window-bounded inference on the Arduino Nano RP2040 Connect with an LDA edge artefact requiring approximately 716 B RAM, whereas the cloud tier supports public-dataset pretraining, hardware-aligned refinement, multimodal fusion, deployment comparison, and feature-importance analysis under the same schema contract. To evaluate analytical consistency across physiological diversity, five public repositories covering stress physiology (WESAD), affective EEG (DEAP), inertial activity recognition (PAMAP2), sEMG gesture decoding (EMG Gestures), and motor-imagery EEG (EEGMMIDB) were evaluated under subject-disjoint GroupKFold (k = 5) protocols. To test whether the same contract survives translation to the physical rig, the hardware branch was evaluated under session-disjoint GroupKFold across five bench-acquired sessions. Unimodal performance was strongest in sEMG- and IMU-dominant tasks, whereas multimodal fusion improved macro-F1 by up to 0.141 over the strongest unimodal baseline in WESAD and by 0.109 in PAMAP2. In the hardware branch, the deployed edge LDA artefact reached 0.9435 macro-F1 with 0.9470 accuracy, while the retained cloud Random Forest reached 0.8792 macro-F1 with 0.8799 accuracy; feature-importance analysis further showed that the final 17-feature branch was dominated by EMG descriptors, with EEG spectral terms contributing secondary support and hardware-exclusive variables remaining weak under the present bench regime. These results show that a compact multimodal sensing assembly can be elevated beyond passive signal capture into an intelligent portable biosensor that performs context-aware interpretation with minimal user intervention, supported by a reproducible analytical workflow that remains coherent across heterogeneous benchmark repositories, hardware-specific refinement, and microcontroller-class deployment, thereby establishing cross-session bench feasibility as a structured basis for future multi-subject wearable validation.

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

Code

The paper links to its data, not to its authors' code: 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

• archive.ics.uci.edu/dataset/481, at archive.ics.uci.edu; found in the references
• physionet.org/content/eegmmidb, at PhysioNet; found in the references

Data Availability Statement

The data that support the findings of this study are not publicly available as the data are part of an ongoing study; the evaluation dataset comprises proprietary firmware configurations, cloud infrastructure parameters, and controlled bench evaluation session logs; and access is restricted to protect confidential and proprietary information.

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 2, 28 September 2026

• Funding: added Nanyang Technological University; Semmelweis Egyetem; Nemzeti Kutatási Fejlesztési és Innovációs Hivatal: HUN-REN RGH151414, RGH151414; Magyarország Kormánya: HUN-REN RGH151414; Lee Kong Chian School of Medicine, Nanyang Technological University; National Research, Development and Innovation Office: HUN-REN RGH151414; Data Science and Artificial Intelligence Research Centre, Nanyang Technological University

Version 1, 27 September 2026: the first record

Recorded: type, language, journal, volume, issue, pages, dates, 8 authors, 10 keywords, 8 MeSH terms, 68 references.

Cite

This paper

Ghosh, S., Sindhujaa, P., Senthil Kumar, P., Mohan, A., Mahalakshmi, P., Gulyás, B., Máthé, D., & Padmanabhan, P. (2026). Hybrid Edge-Cloud Asymmetric Analytics for Portable Multimodal BCI Biosensors. Biosensors, 16(7), 394. https://doi.org/10.3390/bios16070394

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/s26134045

Brain Signal for Secure EEG Biometric Authentication: A Comprehensive Survey.

Journal: Sensors (Basel, Switzerland)

In common: physionet.org/content/eegmmidb, methods / tools, EEG, 5 references

[2] doi:10.1038/s41598-026-56070-y [code]

SSDLabeler: realistic semi-synthetic data generation for multi-label artifact classification in EEG.

Journal: Scientific reports

In common: physionet.org/content/eegmmidb, EEG, 4 references

[3] doi:10.3390/brainsci16080873

Evaluating Validation Strategies in Motor Imagery EEG: A Full-Cohort GAF-PLV Analysis and Matched Sensitivity Study.

Journal: Brain sciences

In common: physionet.org/content/eegmmidb, methods / tools, EEG, 4 references

[4] doi:10.3389/fnins.2026.1851006

Domain-aware domain-class adaptation network for motor execution to motor imagery EEG classification.

Journal: Frontiers in neuroscience

In common: physionet.org/content/eegmmidb, EEG, 4 references

[5] doi:10.3390/s26103065 [code]

Subject-Wise Depression Screening from Eight-Channel Resting-State EEG Using Asymmetry-Aware Spectral Features and Connectivity Ablation.

Journal: Sensors (Basel, Switzerland)

In common: other, EEG, 5 references

[6] doi:10.1038/s41598-026-47041-4

An intelligent EEG-based ensemble framework for communication assistance in Locked-In Syndrome patients.

Journal: Scientific reports

In common: physionet.org/content/eegmmidb, EEG, 2 references

[7] doi:10.3390/mi17060697

Miniaturized Wearable System for Multimodal EEG/ECG/EMG Sensing and Real-Time Physiological Monitoring.

Journal: Micromachines

In common: other, EEG, 4 references

[8] doi:10.3390/s26134019 [code]

NeuroStat: An Open-Source EEG Connectivity Platform for Randomised Controlled Trials.

Journal: Sensors (Basel, Switzerland)

In common: physionet.org/content/eegmmidb, EEG, 2 references

[9] 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, 5 references

[10] doi:10.3389/fnhum.2026.1811759

MCFANet: a multi-class fusion attention network for motor imagery EEG classification.

Journal: Frontiers in human neuroscience

In common: EEG, 5 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.

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: questions and error reports about this paper and its code, from signed-in readers and its authors. It opens with sign-in.

Reproductions: reports from readers who ran the authors' code: what they reproduced, with which environment, commit and data. It opens with sign-in.

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