applsci-logo

Journal Browser

Journal Browser

Deep Networks for Biosignals

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Applied Biosciences and Bioengineering".

Deadline for manuscript submissions: closed (20 November 2024) | Viewed by 22371

Special Issue Editors


E-Mail Website
Guest Editor
IT Research Institute, Chosun University, 309 Pilmun-Daero, Dong-gu, Gwangju 61452, Republic of Korea
Interests: biosignal processing; biometrics; pattern recognition; wearable embedded system
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
IT Research Institute, Chosun University, Gwangju 61452, Republic of Korea
Interests: pattern recognition; machine learning; biometrics; signal processing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Biosignals are electrical, mechanical, thermal, or acoustic signals measured over time from the human body. Various biosignals were discovered that could be derived from the skin or from inside the human body. Initially, analysis of biosignals was performed manually; later, statistical classifiers were applied to support making decisions. However, existing approaches are ineffective for continuously collecting complex, multi-dimensional, real-world data from various sensors. Artificial intelligence helps in the automated and effective analysis of biosignals. Deep networks are one of the well-known techniques used to develop high-level systems for the clustering, detection, and recognition of changes in the human body. Biosignals are generally non-linear, non-stationary, dynamic, and complex; thus, linear and non-linear methods have failed to analyze their characteristics robustly. Furthermore, handcrafted or manually selected features are time-consuming, not optimal, and domain specific. However, deep networks, fed with raw data but not with handcrafted features, perform feature extraction and selection within the network. Deep networks attempt to automatically detect the unobservable patterns needed for analyzing raw data. Multiple layers in the network are interconnected to transform the raw data into a higher level of abstract data representation. Deep networks have gained remarkable performance in various fields, such as computer vision, image understanding, natural language processing, bioinformatics, and physiological analysis for clinical treatments. Thus, deep network models may provide tools and interfaces to complex biosignals for better understanding.

This Special Issue aims to collect advanced research achievements in biosignal processing and analysis using deep networks to address a wide range of application scenarios, which include, but are not limited to, the following:

  • Human identification
  • Analysis of human movements (gait, hand gesture, etc.)
  • Emotion detection and classification
  • Human–computer interaction
  • Healthcare monitoring (computer-aided diagnostics, remote health system, etc.)
  • Various techniques for biosignal processing (ECG, EMG, EEG, PCG, PPG, BCG, etc.)
  • Multimodal feature extraction and integration.
  • New deep network architectures targeting biosignals

Prof. Dr. Sung Bum Pan
Dr. EunSang Bak
Guest Editors

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 100 words) can be sent to the Editorial Office for announcement on this website.

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. Applied Sciences 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 2400 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

  • deep networks
  • human identification
  • emotion classification
  • movement analysis
  • human–computer interaction
  • biosignal processing
  • multimodal feature integration
  • healthcare system

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.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

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

Related Special Issue

Published Papers (7 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review, Other

14 pages, 900 KiB  
Article
BIMO: Bootstrap Inter–Intra Modality at Once Unsupervised Learning for Multivariate Time Series
by Seongsil Heo, Sungsik Kim and Jaekoo Lee
Appl. Sci. 2024, 14(9), 3825; https://doi.org/10.3390/app14093825 - 30 Apr 2024
Viewed by 876
Abstract
It is difficult to learn meaningful representations of time-series data since they are sparsely labeled and unpredictable. Hence, we propose bootstrap inter–intra modality at once (BIMO), an unsupervised representation learning method based on time series. Unlike previous works, the proposed BIMO method learns [...] Read more.
It is difficult to learn meaningful representations of time-series data since they are sparsely labeled and unpredictable. Hence, we propose bootstrap inter–intra modality at once (BIMO), an unsupervised representation learning method based on time series. Unlike previous works, the proposed BIMO method learns both inter-sample and intra-temporal modality representations simultaneously without negative pairs. BIMO comprises a main network and two auxiliary networks, namely inter-auxiliary and intra-auxiliary networks. The main network is trained to learn inter–intra modality representations sequentially by regulating the use of each auxiliary network dynamically. Thus, BIMO thoroughly learns inter–intra modality representations simultaneously. The experimental results demonstrate that the proposed BIMO method outperforms the state-of-the-art unsupervised methods and achieves comparable performance to existing supervised methods. Full article
(This article belongs to the Special Issue Deep Networks for Biosignals)
Show Figures

Figure 1

17 pages, 10307 KiB  
Article
Multi-Session Electrocardiogram–Electromyogram Database for User Recognition
by Jin Su Kim, Cheol Ho Song, Jae Myung Kim, Jimin Lee, Yeong-Hyeon Byeon, Jaehyo Jung, Hyun-Sik Choi, Keun-Chang Kwak, Youn Tae Kim, EunSang Bak and Sungbum Pan
Appl. Sci. 2024, 14(6), 2607; https://doi.org/10.3390/app14062607 - 20 Mar 2024
Viewed by 1113
Abstract
Current advancements in biosignal-based user recognition technology are paving the way for a next-generation solution that addresses the limitations of face- and fingerprint-based user recognition methods. However, existing biosignal benchmark databases (DBs) for user recognition often suffer from limitations, such as data collection [...] Read more.
Current advancements in biosignal-based user recognition technology are paving the way for a next-generation solution that addresses the limitations of face- and fingerprint-based user recognition methods. However, existing biosignal benchmark databases (DBs) for user recognition often suffer from limitations, such as data collection from a small number of subjects in a single session, hindering comprehensive analysis of biosignal variability. This study introduces CSU_MBDB1 and CSU_MBDB2, databases containing electrocardiogram (ECG) and electromyogram (EMG) signals from diverse experimental subjects recorded across multiple sessions. These in-house DBs comprise ECG and EMG data recorded in multiple sessions from 36 and 58 subjects, respectively, with a time interval of more than one day between sessions. During the experiments, subjects performed a total of six gestures while comfortably seated at a desk. CSU_MBDB1 and CSU_MBDB2 consist of three identical gestures, providing expandable data for various applications. When the two DBs are expanded, ECGs and EMGs from 94 subjects can be used, which is the largest number among the multi-biosignal benchmark DBs built by multi-sessions. To assess the usability of the constructed DBs, a user recognition experiment was conducted, resulting in an accuracy of 66.39% for ten subjects. It is important to emphasize that we focused on demonstrating the applicability of the constructed DBs using a basic neural network without signal denoising capabilities. While this approach results in a sacrifice in accuracy, it concurrently provides substantial opportunities for performance enhancement through the implementation of optimized algorithms. Adapting signal denoising processes to the constructed DBs and designing a more sophisticated neural network would undoubtedly contribute to improving the recognition accuracy. Consequently, these constructed DBs hold promise in user recognition, offering valuable research for future investigations. Additionally, DBs can be used in research to analyze the nonlinearity characteristics of ECG and EMG. Full article
(This article belongs to the Special Issue Deep Networks for Biosignals)
Show Figures

Figure 1

31 pages, 7639 KiB  
Article
Unsupervised Detection of Covariate Shift Due to Changes in EEG Headset Position: Towards an Effective Out-of-Lab Use of Passive Brain–Computer Interface
by Daniele Germano, Nicolina Sciaraffa, Vincenzo Ronca, Andrea Giorgi, Giacomo Trulli, Gianluca Borghini, Gianluca Di Flumeri, Fabio Babiloni and Pietro Aricò
Appl. Sci. 2023, 13(23), 12800; https://doi.org/10.3390/app132312800 - 29 Nov 2023
Cited by 2 | Viewed by 1147
Abstract
In the field of passive Brain–computer Interfaces (BCI), the need to develop systems that require rapid setup, suitable for use outside of laboratories is a fundamental challenge, especially now, that the market is flooded with novel EEG headsets with a good quality. However, [...] Read more.
In the field of passive Brain–computer Interfaces (BCI), the need to develop systems that require rapid setup, suitable for use outside of laboratories is a fundamental challenge, especially now, that the market is flooded with novel EEG headsets with a good quality. However, the lack of control in operational conditions can compromise the performance of the machine learning model behind the BCI system. First, this study focuses on evaluating the performance loss of the BCI system, induced by a different positioning of the EEG headset (and of course sensors), so generating a variation in the control features used to calibrate the machine learning algorithm. This phenomenon is called covariate shift. Detecting covariate shift occurrences in advance allows for preventive measures, such as informing the user to adjust the position of the headset or applying specific corrections in new coming data. We used in this study an unsupervised Machine Learning model, the Isolation Forest, to detect covariate shift occurrence in new coming data. We tested the method on two different datasets, one in a controlled setting (9 participants), and the other in a more realistic setting (10 participants). In the controlled dataset, we simulated the movement of the EEG cap using different channel and reference configurations. For each test configuration, we selected a set of electrodes near the control electrodes. Regarding the realistic dataset, we aimed to simulate the use of the cap outside the laboratory, mimicking the removal and repositioning of the cap by a non-expert user. In both datasets, we recorded multiple test sessions for each configuration while executing a set of Workload tasks. The results obtained using the Isolation Forest model allowed the identification of covariate shift in the data, even with a 15-s recording sample. Moreover, the results showed a strong and significant negative correlation between the percentage of covariate shift detected by the method, and the accuracy of the passive BCI system (p-value < 0.01). This novel approach opens new perspectives for developing more robust and flexible BCI systems, with the potential to move these technologies towards out-of-the-lab use, without the need for supervision for use by a non-expert user. Full article
(This article belongs to the Special Issue Deep Networks for Biosignals)
Show Figures

Figure 1

14 pages, 1102 KiB  
Article
Revolutionizing Soccer Injury Management: Predicting Muscle Injury Recovery Time Using ML
by Arian Skoki, Mateja Napravnik, Marin Polonijo, Ivan Štajduhar and Jonatan Lerga
Appl. Sci. 2023, 13(10), 6222; https://doi.org/10.3390/app13106222 - 19 May 2023
Cited by 4 | Viewed by 2264
Abstract
Predicting the optimal recovery time following a soccer player’s injury is a complex task with heavy implications on team performance. While most current decision-based models rely on the physician’s perspective, this study proposes a machine learning (ML)-based approach to predict recovery duration using [...] Read more.
Predicting the optimal recovery time following a soccer player’s injury is a complex task with heavy implications on team performance. While most current decision-based models rely on the physician’s perspective, this study proposes a machine learning (ML)-based approach to predict recovery duration using three modeling techniques: linear regression, decision tree, and extreme gradient boosting (XGB). Performance is compared between the models, against the expert, and together with the expert. The results demonstrate that integrating the expert’s predictions as a feature improves the performance of all models, with XGB performing best with a mean R2 score of 0.72, outperforming the expert’s predictions with an R2 score of 0.62. This approach has significant implications for sports medicine, as it could help teams make better decisions on the return-to-play of their players, leading to improved performance and reduced risk of re-injury. Full article
(This article belongs to the Special Issue Deep Networks for Biosignals)
Show Figures

Figure 1

19 pages, 13227 KiB  
Article
Electrocardiogram Analysis by Means of Empirical Mode Decomposition-Based Methods and Convolutional Neural Networks for Sudden Cardiac Death Detection
by Manuel A. Centeno-Bautista, Angel H. Rangel-Rodriguez, Andrea V. Perez-Sanchez, Juan P. Amezquita-Sanchez, David Granados-Lieberman and Martin Valtierra-Rodriguez
Appl. Sci. 2023, 13(6), 3569; https://doi.org/10.3390/app13063569 - 10 Mar 2023
Cited by 10 | Viewed by 2408
Abstract
Sudden cardiac death (SCD) is a global health problem, which represents 15–20% of global deaths. This type of death can be due to different heart conditions, where ventricular fibrillation has been reported as the main one. These cardiac alterations can be seen in [...] Read more.
Sudden cardiac death (SCD) is a global health problem, which represents 15–20% of global deaths. This type of death can be due to different heart conditions, where ventricular fibrillation has been reported as the main one. These cardiac alterations can be seen in an electrocardiogram (ECG) record, where the heart’s electrical activity is altered. The present research uses these variations to be able to predict 30 min in advance when the SCD event will occur. In this regard, a methodology based on the complete ensemble empirical mode decomposition (CEEMD) method to decompose the cardiac signal into its intrinsic mode functions (IMFs) and a convolutional neural network (CNN) for automatic diagnosis is proposed. Results for the ensemble empirical mode decomposition (EEMD) method and the empirical mode decomposition (EMD) method are also compared. Results demonstrate that the combination of the CEEMD and the CNN is a potential solution for SCD prediction since 97.5% of accuracy is achieved up to 30 min in advance of the SCD event. Full article
(This article belongs to the Special Issue Deep Networks for Biosignals)
Show Figures

Figure 1

Review

Jump to: Research, Other

24 pages, 3280 KiB  
Review
Electromyographic Activity of the Pectoralis Major Muscle during Traditional Bench Press and Other Variants of Pectoral Exercises: A Systematic Review and Meta-Analysis
by Abraham López-Vivancos, Noelia González-Gálvez, Francisco Javier Orquín-Castrillón, Rodrigo Gomes de Souza Vale and Pablo Jorge Marcos-Pardo
Appl. Sci. 2023, 13(8), 5203; https://doi.org/10.3390/app13085203 - 21 Apr 2023
Cited by 2 | Viewed by 11724
Abstract
The popularity of the bench press (BP) is justified by being one of the most effective exercises to improve strength and power in the upper body. The primary aim of this systematic review and meta-analysis was to compare the electromyography activity (EMG) of [...] Read more.
The popularity of the bench press (BP) is justified by being one of the most effective exercises to improve strength and power in the upper body. The primary aim of this systematic review and meta-analysis was to compare the electromyography activity (EMG) of pectoralis muscle between BP and other variants of pectoral exercises (OP). Methods: This study was conducted according to the PRISMA. Original research articles published by March 2023, were located using an electronic search of four databases and yielded 951 original publications. This review included studies that compared the EMG activity of pectoralis muscle between BP and OP. Data were extracted and independently coded by three researchers. Finally, 23 studies were included for systematic review and meta-analysis. Meta-analysis with fixed or random effect model was performed to infer the pooled estimated standardized mean difference, depending on the heterogeneity. The studies were grouped according to the type of the comparison: grip widths, type of grip, inclination of the bench, stability, or exercise type. Results: The original option of BP activates the sternal portion significantly more than the variant with the inclined bench (SMD = 1.80; 95%CI 0.40 to 3.19; p = 0.017). Performing the exercise in an unstable situation produced significantly more activation during the concentric phase than performing the exercise in a stable situation (SMD = −0.18; 95%CI −0.33 to 3.74; p = 0.029). When comparing by type of exercise, greater activations are also seen in the original bench press vs. the comparisons (p = 0.023 to 0.001). Conclusions: The results suggest that the traditional bench press performed with the bench in a horizontal position, with a bar and a grip width between 150% and 200% of the biacromial distance (BAD) results from a greater EMG involvement of the pectoralis major in most variations with the same relative load. However, the sternal portion of pectoralis major showed greater activation with the declined variant of bench press. Full article
(This article belongs to the Special Issue Deep Networks for Biosignals)
Show Figures

Figure 1

Other

Jump to: Research, Review

9 pages, 1405 KiB  
Brief Report
Biosignals by In-Shoe Plantar Pressure Sensors on Different Hardness Mats during Running: A Cross-Over Study
by Jaime García-Arroyo, Soraya Pacheco-da-Costa, Francisco Molina-Rueda, Davinia Vicente-Campos, César Calvo-Lobo and Isabel M. Alguacil-Diego
Appl. Sci. 2023, 13(4), 2157; https://doi.org/10.3390/app13042157 - 8 Feb 2023
Viewed by 1683
Abstract
Although the effects of running on plantar pressures have been detailed on several surfaces with different hardness, there is a lack of studies assessing the mechanical behavior analysis by in-shoe plantar pressure sensors on different hardness mats during running. The aim of the [...] Read more.
Although the effects of running on plantar pressures have been detailed on several surfaces with different hardness, there is a lack of studies assessing the mechanical behavior analysis by in-shoe plantar pressure sensors on different hardness mats during running. The aim of the present study was to determine in-shoe maximum forces and peak plantar pressures on mats with different hardness, such as hard, soft and air chamber mats, during running. A cross-over study was carried out including 36 amateur runners from a sport center. The maximum force and peak pressures of the foot plantar region were analyzed on three different mat hardnesses —soft and hard polyurethane foam mats and air chamber mats—by in-shoe instrumented insoles. Running on soft polyurethane foam mats presented reduced maximum forces in the whole plantar region and mainly peak pressures in the anterior part of the foot plantar region, such as the toes and first to fourth metatarsal heads, compared to hard polyurethane foam and air chamber mats. The peak pressure in the fifth metatarsal head was specifically reduced during running on soft compared to hard polyurethane foam mats, and running on these soft mats decreased calcaneus peak pressures compared to running on air chamber mats. Running on air chamber mats increased peak plantar pressures in the first metatarsal head compared to running on hard polyurethane foam mats. The mechanical behavior of mats of different hardness could be used to adjust the degree of impact on plantar pressures to determine the most appropriate materials and hardness for running. Full article
(This article belongs to the Special Issue Deep Networks for Biosignals)
Show Figures

Figure 1

Back to TopTop