Submit to Special Issue Submit Abstract to Special Issue Review for Sensors Propose a Special Issue

Journal Menu

Journal Browser

► Journal Browser

Machine Learning in Biomedical Signal Processing

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Benefits of Publishing in a Special Issue
Published Papers

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Biomedical Sensors".

Deadline for manuscript submissions: 31 August 2026 | Viewed by 5098

Share This Special Issue

Special Issue Editor

Dr. Alan Jović

E-Mail Website
Guest Editor

University of Zagreb Faculty of Electrical Engineering and Computing, Zagreb, Croatia
Interests: artificial intelligence in medicine; data mining; machine learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Biomedical signals—electrocardiograms (ECGs), electroencephalograms (EEGs), electromyograms (EMGs), photoplethysmograms (PPGs), and other physiological recordings—are increasingly acquired through diverse sensing technologies, including wearable, implantable, and mobile health devices. These advances enable continuous monitoring and real-time applications but also introduce challenges related to signal quality, calibration, inter-subject variability, high dimensionality, and robustness under real-world conditions.

To address these challenges, researchers are turning to advanced machine learning methods, ranging from classical approaches to modern deep learning architectures and hybrid models. These methods enhance the value of sensor-acquired signals by enabling robust preprocessing, efficient feature extraction, improved classification and prediction, and better generalization across heterogeneous populations and acquisition contexts.

The focus of this Special Issue will be on novel machine learning methodologies and their applications in biomedical signal processing, with a particular emphasis on the interplay between algorithms and sensing technologies. Topics of interest include (but are not limited to) the following:

The integration of multimodal biomedical signals and sensor data through machine learning models;
Preprocessing and denoising strategies tailored to machine learning pipelines;
Feature engineering and representation learning from multimodal biomedical sensor data;
Deep learning and advanced neural network architectures (CNNs, RNNs, transformers, graph neural networks) for biomedical signal analysis;
Explainable and interpretable machine learning models for biomedical signal analysis;
Transfer learning, domain adaptation, and federated learning across heterogeneous sensing environments;
Machine learning applications for real-time monitoring, diagnosis, prognosis, and decision support.

Application areas may include (but are not limited to): cardiology, neurology, rehabilitation, mental health, telemedicine, ambient assisted living, and human–computer interaction. Contributions that highlight novel datasets, open-source tools, and clinically validated results are particularly encouraged.

Both original research articles and review papers are welcome.

Dr. Alan Jović
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

biomedical signal processing
biomedical time series analysis
multimodal biomedical signals and sensor data processing
machine learning
deep learning
feature extraction
feature selection
hybrid machine learning architecture

Benefits of Publishing in a Special Issue

Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
Reprint: MDPI Books provides the opportunity to republish successful Special Issues in book format, both online and in print.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (9 papers)

Download All Papers

Order results

Result details

Show export options Show export options

Select all

Export citation of selected articles as:

Research

Jump to: Review

25 pages, 2601 KB

Open AccessArticle

A Robust Deep Learning Approach for COPD Automated Detection

by Shuting Xu, Ravinesh C. Deo, Salvin S. Prasad, Prabal D. Barua, Jeffrey Soar and Rajendra Acharya

Sensors 2026, 26(9), 2713; https://doi.org/10.3390/s26092713 - 28 Apr 2026

Abstract

COPD remains a prevalent and debilitating respiratory condition, necessitating early and accurate diagnosis for optimal clinical intervention. In this study, we propose a novel deep learning-based diagnostic framework that employs the ECAPA-TDNN (Emphasized Channel Attention, Propagation and Aggregation—Time Delay Neural Network) architecture to classify respiratory sound signals from the ICBHI dataset. Originally designed for speaker verification, ECAPA-TDNN introduces channel attention and multi-scale feature aggregation, which we adapt for the first time to the domain of medical acoustic analysis. This architecture allows the model to effectively capture subtle and discriminative patterns in pathological breathing sounds, overcoming the limitations of conventional CNN-based methods. Our methodology integrates rigorous signal preprocessing, log-Mel spectrogram extraction, and data augmentation to enhance robustness and generalization. An Attentive Statistics Pooling mechanism is employed for temporal feature summarization, while Grad-CAM-based explainability is incorporated to improve the interpretability of the diagnostic predictions. The model is rigorously validated using a five-fold cross-validation scheme, achieving a mean validation accuracy of 96.8% with consistently high F1-scores and recall rates across all folds. Comparative analysis with prior methods highlights the superiority of our ECAPA-TDNN-based approach in terms of diagnostic precision, robustness, and potential clinical applicability. To the best of our knowledge, this is the first work to adapt ECAPA-TDNN for COPD detection from respiratory sounds, establishing a new benchmark in interpretable and high-performance acoustic-based respiratory disease screening. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

► Show Figures

Figure 1

25 pages, 10933 KB

Open AccessArticle

Combining Video Magnification with Machine Learning-Based Source Identification for Contactless Heart Rate Monitoring

by Tiago de Avelar, Vicente M. Garção and Hugo Plácido da Silva

Sensors 2026, 26(9), 2706; https://doi.org/10.3390/s26092706 - 27 Apr 2026

Abstract

Conventional contact-based monitoring of heart rate (HR) presents challenges such as patient discomfort, skin irritation, and poor long-term adherence, motivating the development of contactless, video-based sensing systems. This study proposes a robust hybrid framework combining advanced signal processing with machine learning to enhance HR estimation accuracy from facial video. The methodology integrates a two-stage geometric stabilization pipeline with dense facial tessellation to mitigate motion. Eulerian Video Magnification (EVM) amplifies subtle color variations, followed by chrominance-based roi filtering. Signal recovery utilizes a sliding-window Principal Component Analysis (PCA) for local coherence, followed by Second-Order Blind Identification (SOBI), with a Light Gradient Boosting Machine (LightGBM) classifier employed to automatically identify physiological sources. Validated on the challenging COHFACE dataset, the approach achieves a Mean Absolute Error (MAE) of 1.50 bpm, a Root Mean Square Error (RMSE) of 3.07 bpm, and a Pearson Correlation Coefficient (PCC) of 0.97 on the test set. The method demonstrates robustness across diverse lighting conditions, outperforming traditional algorithms and achieving parity with state-of-the-art deep learning models, while offering an interpretable solution for contactless health monitoring. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

16 pages, 1624 KB

Open AccessArticle

Surface EMG-Based Hand Gesture Recognition Using a Hybrid Multistream Deep Learning Architecture

by Yusuf Çelik and Umit Can

Sensors 2026, 26(7), 2281; https://doi.org/10.3390/s26072281 - 7 Apr 2026

Viewed by 477

Abstract

Surface electromyography (sEMG) enables non-invasive measurement of muscle activity for applications such as human–machine interaction, rehabilitation, and prosthesis control. However, high noise levels, inter-subject variability, and the complex nature of muscle activation hinder robust gesture classification. This study proposes a multistream hybrid deep-learning architecture for the FORS-EMG dataset to address these challenges. The model integrates Temporal Convolutional Networks (TCN), depthwise separable convolutions, bidirectional Long Short-Term Memory (LSTM)–Gated Recurrent Unit (GRU) layers, and a Transformer encoder to capture complementary temporal and spectral patterns, and an ArcFace-based classifier to enhance class separability. We evaluate the approach under three protocols: subject-wise, random split without augmentation, and random split with augmentation. In the augmented random-split setting, the model attains 96.4% accuracy, surpassing previously reported values. In the subject-wise setting, accuracy is 74%, revealing limited cross-user generalization. The results demonstrate the method’s high performance and highlight the impact of data-partition strategies for real-world sEMG-based gesture recognition. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

► Show Figures

Figure 1

16 pages, 2796 KB

Open AccessArticle

A Multi-Center Trained Residual Neural Network for Robust Classification of Atrial High-Rate Episodes in Remotely Monitored Pacemakers and Defibrillators

by Lars van Krimpen, Arlene John, Anand Thiyagarajah, Tanner Carbonati, Benjamin Sacristan, Karim Benali, Antoine Da Costa, Pierre Mondoly, Rémi Chauvel, Romain Eschalier, Josselin Duchateau, Remi Dubois, Sylvain Ploux, Pierre Bordachar and Marc Strik

Sensors 2026, 26(7), 2241; https://doi.org/10.3390/s26072241 - 4 Apr 2026

Viewed by 520

Abstract

Remote monitoring of pacemakers and defibrillators increases patient safety but also increases clinical workload. Review of atrial high-rate episodes is particularly demanding as episodes can contain atrial tachycardia or atrial fibrillation (AT/AF), noise, or far-field oversensing (FFO). Automatic review of atrial high-rate episodes by an Artificial Intelligence (AI) model can decrease the workload of remote monitoring, provided it maintains high sensitivity for true atrial tachycardia. A residual network is trained using a center-level fourfold cross validation. The four resulting models achieved a precision of 97.2–99.4% for AT/AF, 93.1–97.7% for noise, and 75.4–94.4% for FFO, while maintaining high sensitivity 98.9–99.3% for AT/AF. The four models were combined through averaging prediction probabilities to create an ensemble model. Thresholding ensemble predictions with probability > 95% resulted in a robust ensemble model that made only two errors (<0.1%) after reviewing 3925 episodes (91.9%) of the total 4271 episodes. This shows how AI models can reliably assist in remote monitoring. Future research should be aimed at classification models for other episode types and clinical validation of AI models to assist remote monitoring of pacemakers and defibrillators. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

► Show Figures

Figure 1

25 pages, 3627 KB

Open AccessArticle

Optimizing Session Frequency in EEG Biofeedback: A Comparative Study of Protocol Dynamics and Neuromuscular Adaptation in Elite Judo Athletes

by Alicja Markiel, Dariusz Skalski, Kinga Łosińska, Marcin Żak and Adam Maszczyk

Sensors 2026, 26(7), 2077; https://doi.org/10.3390/s26072077 - 26 Mar 2026

Viewed by 569

Abstract

Background: The optimal frequency of EEG biofeedback sessions for elite athletes remains unclear, despite growing adoption of neurofeedback in high-performance sport. Methods: This randomized, controlled study compared three EEG biofeedback protocols (daily, every-other-day, every-third-day) in 24 national-level male judo athletes stratified into three phenotypic groups. Each protocol comprised 15 standardized sessions. Pre- and post-intervention assessments included functional indices (strength, power) and neurophysiological measures (Frontal Alpha Index, EMG amplitude/RMS, corrected strength sum). Biosensor performance was validated via signal quality metrics. Results: Daily EEG biofeedback produced superior improvements in strength, FAI, and fatigue resistance. Although LRG showed the largest pre–post RMS increase (+17.44 μV vs. +16.54 μV in HRG), HRG maintained the highest post-intervention RMS values and best fatigue resistance (MF_drop = −2.15 Hz). Significant group × time interactions were observed for FAI (p = 0.027) and RMS (p = 0.019). Every-other-day protocols yielded moderate gains, while every-third-day protocols produced minimal or maladaptive EMG–load dynamics. A robust dose–response relationship was evident. Conclusions: Session frequency is critical for optimizing neurofeedback interventions in elite athletes. Daily EEG biofeedback confers superior adaptation compared to less frequent dosing. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

► Show Figures

Figure 1

15 pages, 1297 KB

Open AccessArticle

Predicting Performance in Working Memory During the Waking Period by Applying a Convolutional Neural Network to EEG Data in the N-Back Task: A Pilot Study

by Masaya Shigemoto, Soma Shimizu and Kiyohisa Natsume

Sensors 2026, 26(3), 772; https://doi.org/10.3390/s26030772 - 23 Jan 2026

Viewed by 315

Abstract

Memory performance is regulated by circadian rhythms, and electroencephalograms (EEG) measure biological signals related to memory mechanisms and circadian rhythms. Therefore, EEG could be used to detect changes in diurnal memory. In this study, we measured the EEG signals of participants conducting a memory-related task and tested the effectiveness of a convolutional neural network (CNN) in predicting memory task performance at different times. EEG signals from participants performing N-back tasks at 8–9 a.m. and 3–4 p.m. were recorded. While performance showed no significant differences between times, differences were observed in EEG relative power. A CNN was trained using the relative power and raw waveform data of the EEG signals recorded during the tasks. When predicting the time at which the working memory (WM) was enhanced, the relative power CNN exhibited a significantly higher accuracy than the raw waveform CNN. However, the performance dropped in the test where the training data did not include the EEG data of the same participant. Overall, these results suggest that while EEG signals using a relative power CNN have high predictive potential, developing a personalized classification system that reflects individual chronotypes is effective for practical applications. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

► Show Figures

Figure 1

15 pages, 2006 KB

Open AccessArticle

Automated Neuromuscular Assessment: Machine-Learning-Based Facial Palsy Classification Using Surface Electromyography

by Ibrahim Manzoor, Aryana Popescu, Sarah Ricchizzi, Aldo Spolaore, Mykola Gorbachuk, Marcos Tatagiba, Georgios Naros and Kathrin Machetanz

Sensors 2026, 26(1), 173; https://doi.org/10.3390/s26010173 - 26 Dec 2025

Viewed by 752

Abstract

Facial palsy (FP) impairs voluntary control of facial muscles, resulting in facial asymmetry and difficulties in emotional expression. Traditional assessment methods to define the severity of FP (e.g., House–Brackmann score, HB) rely on visual examinations and, therefore, are highly examiner-dependent. This study proposes an alternative approach using facial surface electromyography (EMG) for automated HB prediction. Time-domain EMG features were extracted during different facial movements (i.e., smile, close eyes, and raise forehead) and analyzed through nine different machine learning (ML) models in 58 subjects (51.98 ± 1.67 years, 20 male) with variable facial nerve function (HB 1: n = 16, HB 2–3: n = 32; HB 4–6: n = 10). Model performances were evaluated based on accuracy, precision, recall, and F1-score. Among the evaluated models, ensemble-based approaches—particularly a random forest model with 100 trees and a decision tree ensemble—proved to be the most effective with classification accuracies ranging from 81.7 to 84.8% and from 81.7 to 84.7%, depending on the evaluated facial movement. The results indicate that ensemble-based ML models can reliably distinguish between different FP grades using non-invasive EMG data. The approach offers a robust alternative to subjective clinical scoring, potentially improving diagnostic consistency and supporting longitudinal monitoring in clinical and research applications. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

► Show Figures

Figure 1

25 pages, 2290 KB

Open AccessArticle

Machine Learning-Based Risk Stratification for Sudden Cardiac Death Using Clinical and Device-Derived Data

by Hana Ivandic, Branimir Pervan, Mislav Puljevic, Vedran Velagic and Alan Jovic

Sensors 2026, 26(1), 86; https://doi.org/10.3390/s26010086 - 22 Dec 2025

Viewed by 882

Abstract

Sudden cardiac death (SCD) remains a major clinical challenge, with implantable cardioverter-defibrillators (ICDs) serving as the primary preventive intervention. Current patient selection guidelines rely on limited and imperfect risk markers. This study explores the potential of machine learning (ML) models to improve SCD risk prediction using tabular clinical data that include features derived from medical sensing devices such as electrocardiograms (ECGs) and ICDs. Several ML models, including tree-based models, Naive Bayes (NB), logistic regression (LR), and voting classifiers (VC), were trained on demographic, clinical, laboratory, and device-derived variables from patients who underwent ICD implantation at a Croatian tertiary center. The target variable was the activation of the ICD device (appropriate or inappropriate/missed), serving as a surrogate for high-risk SCD detection. Models were optimized for the F2-score to prioritize high-risk patient detection, and interpretability was achieved with post hoc SHAP value analysis, which confirmed known and revealed additional potential SCD predictors. The random forest (RF) model achieved the highest F2-score (F2-score 0.74, AUC-ROC 0.73), demonstrating a recall of 97.30% and meeting the primary objective of high true positive detection, while the VC classifier achieved the highest overall discrimination (F2-score 0.71, AUC-ROC 0.76). The predictive performance of multiple ML models, particularly the high recall they achieved, demonstrates the promising potential of ML to refine ICD patient selection. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

► Show Figures

Figure 1

Review

Jump to: Research

22 pages, 1046 KB

Open AccessReview

Use of Artificial Intelligence in the Classification of Upper-Limb Motion Using EEG and EMG Signals: A Review

by Isabel Bandes and Yasuharu Koike

Sensors 2026, 26(5), 1457; https://doi.org/10.3390/s26051457 - 26 Feb 2026

Viewed by 567

Abstract

This systematic review summarizes the application of artificial intelligence (AI) in classifying upper-limb motion using Electroencephalogram (EEG) and Electromyogram (EMG) signals, focusing on the field’s progression from Traditional Machine Learning (TML) to Deep Learning (DL) architectures. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, a search of PubMed, IEEEXplore, and Web of Science yielded 301 eligible studies published up to June 2025. The results indicate a change from classical classifiers like Linear Discriminant Analysis (LDA) and Support Vector Machines (SVMs) toward DL approaches. While Convolutional Neural Networks (CNNs) remain the most frequently implemented, emerging architectures, including Long Short-Term Memory (LSTM) networks and Transformers, have demonstrated remarkable performance. Despite the rise of DL, classical models remain highly relevant due to their robustness and efficiency. This review also identifies a heavy reliance on EEG-only modalities (60%), with only 7% of studies utilizing hybrid EEG-EMG systems, representing a potential missed opportunity for signal fusion. Full article

(This article belongs to the Special Issue Machine Learning in Biomedical Signal Processing)

► Show Figures

Journal Menu

Journal Browser

Machine Learning in Biomedical Signal Processing

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (9 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI