sensors-logo

Journal Browser

Journal Browser

Special Issue "Biomedical Signal Processing"

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

Deadline for manuscript submissions: closed (30 March 2020) | Viewed by 34553

Special Issue Editors

Prof. Dr. Javier Ramírez
E-Mail Website
Guest Editor
Department of Signal Theory, Telematics and Communications, University of Granada, 18071 Granada, Spain
Interests: biomedical signal processing; medical imaging; machine learning; computer aided diagnosis; neuroimaging
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Juan Manuel Gorriz
E-Mail Website
Guest Editor
Prof. Dr. Andrés Ortiz García
E-Mail Website
Guest Editor
Departamento de Ingeniería de Comunicaciones, Universidad de Málaga, 29071 Málaga, Spain
Interests: intelligence systems; neurosciences; signal processing with biomedical applications; high performance computing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Currently, biomedical sensors provide vast amounts of electric and nonelectric biomedical signals, enabling the study of human body health and the early diagnosis of a number of diseases. In addition, recent advances and developments in the Internet of Things (IoT) have generated extensive opportunities and challenges in the health care field that require the development of effective signal processing technologies for medical IoT devices. This Special Issue aims to create a sharing opportunity between experts on biomedical sensors and signal processing practicioners that apply such technology within the biomedical field. Topics of interest include signal processing methods, machine learning methods, and applications that rely on such technologies, with emphasis on but not only including diagnostics, guiding therapy, patient monitoring, disease prevention, and risk assessment in a clinical setting. Original papers that describe new research or innovative biomedical signal processing application are welcome. We look forward to your participation in this Special Issue.

Prof. Dr. Javier Ramírez
Prof. Dr. Juan M. Górriz Sáez
Prof. Dr. Andrés Ortiz García
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. 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 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

  • biomedical signals analysis
  • Bioelectrical signal (EEG, ECG, …) processing
  • biomagnetic signal (MEG) processing
  • inertial sensor signal processing
  • statistical signal processing
  • medical imaging
  • machine learning including deep learning
  • signal processing in medical IOT devices
  • clinical applications: diagnostic, guiding therapy, patient monitoring, disease prevention, and risk assessment

Published Papers (18 papers)

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

Research

Article
Vital Sign Detection during Large-Scale and Fast Body Movements Based on an Adaptive Noise Cancellation Algorithm Using a Single Doppler Radar Sensor
Sensors 2020, 20(15), 4183; https://doi.org/10.3390/s20154183 - 28 Jul 2020
Cited by 7 | Viewed by 1413
Abstract
The non-contact detection of human vital signs (i.e., respiration rate (RR) and heartbeat rate (HR)) using a continuous-wave (CW) Doppler radar sensor has great potential for intensive care monitoring, home healthcare, etc. However, large-scale and fast random body movement (RBM) has been a [...] Read more.
The non-contact detection of human vital signs (i.e., respiration rate (RR) and heartbeat rate (HR)) using a continuous-wave (CW) Doppler radar sensor has great potential for intensive care monitoring, home healthcare, etc. However, large-scale and fast random body movement (RBM) has been a bottleneck for vital sign detection using a single CW Doppler radar. To break this dilemma, this study proposed a scheme combining adaptive noise cancellation (ANC) with polynomial fitting, which could retrieve the weak components of both respiration and heartbeat signals that were submerged under serious RBM interference. In addition, the new-type discrete cosine transform (N-DCT) was introduced to improve the detection accuracy. This scheme was first verified using a numerical simulation. Then, experiments utilizing a 10-GHz Doppler radar sensor that was built from general-purpose radio frequency (RF) and communication instruments were also carried out. No extra RF/microwave components and modules were needed, and neither was a printed circuit board nor an integrated-chip design required. The experimental results showed that both the RR and HR could still be extracted during large-scale and fast body movements using only a single Doppler radar sensor because the RBM noises could be greatly eliminated by utilizing the proposed ANC algorithm. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Evaluation of Vertical Ground Reaction Forces Pattern Visualization in Neurodegenerative Diseases Identification Using Deep Learning and Recurrence Plot Image Feature Extraction
Sensors 2020, 20(14), 3857; https://doi.org/10.3390/s20143857 - 10 Jul 2020
Cited by 10 | Viewed by 2175
Abstract
To diagnose neurodegenerative diseases (NDDs), physicians have been clinically evaluating symptoms. However, these symptoms are not very dependable—particularly in the early stages of the diseases. This study has therefore proposed a novel classification algorithm that uses a deep learning approach to classify NDDs [...] Read more.
To diagnose neurodegenerative diseases (NDDs), physicians have been clinically evaluating symptoms. However, these symptoms are not very dependable—particularly in the early stages of the diseases. This study has therefore proposed a novel classification algorithm that uses a deep learning approach to classify NDDs based on the recurrence plot of gait vertical ground reaction force (vGRF) data. The irregular gait patterns of NDDs exhibited by vGRF data can indicate different variations of force patterns compared with healthy controls (HC). The classification algorithm in this study comprises three processes: a preprocessing, feature transformation and classification. In the preprocessing process, the 5-min vGRF data divided into 10-s successive time windows. In the feature transformation process, the time-domain vGRF data are modified into an image using a recurrence plot. The total recurrence plots are 1312 plots for HC (16 subjects), 1066 plots for ALS (13 patients), 1230 plots for PD (15 patients) and 1640 plots for HD (20 subjects). The principal component analysis (PCA) is used in this stage for feature enhancement. Lastly, the convolutional neural network (CNN), as a deep learning classifier, is employed in the classification process and evaluated using the leave-one-out cross-validation (LOOCV). Gait data from HC subjects and patients with amyotrophic lateral sclerosis (ALS), Huntington’s disease (HD) and Parkinson’s disease (PD) obtained from the PhysioNet Gait Dynamics in Neurodegenerative disease were used to validate the proposed algorithm. The experimental results included two-class and multiclass classifications. In the two-class classification, the results included classification of the NDD and the HC groups and classification among the NDDs. The classification accuracy for (HC vs. ALS), (HC vs. HD), (HC vs. PD), (ALS vs. PD), (ALS vs. HD), (PD vs. HD) and (NDDs vs. HC) were 100%, 98.41%, 100%, 95.95%, 100%, 97.25% and 98.91%, respectively. In the multiclass classification, a four-class gait classification among HC, ALS, PD and HD was conducted and the classification accuracy of HC, ALS, PD and HD were 98.99%, 98.32%, 97.41% and 96.74%, respectively. The proposed method can achieve high accuracy compare to the existing results, but with shorter length of input signal (Input of existing literature using the same database is 5-min gait signal, but the proposed method only needs 10-s gait signal). Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
A Comparative Study of Vaginal Labor and Caesarean Section Postpartum Uterine Myoelectrical Activity
Sensors 2020, 20(11), 3023; https://doi.org/10.3390/s20113023 - 26 May 2020
Cited by 5 | Viewed by 1189
Abstract
Postpartum hemorrhage (PPH) is one of the major causes of maternal mortality and morbidity worldwide, with uterine atony being the most common origin. Currently there are no obstetrical techniques available for monitoring postpartum uterine dynamics, as tocodynamometry is not able to detect weak [...] Read more.
Postpartum hemorrhage (PPH) is one of the major causes of maternal mortality and morbidity worldwide, with uterine atony being the most common origin. Currently there are no obstetrical techniques available for monitoring postpartum uterine dynamics, as tocodynamometry is not able to detect weak uterine contractions. In this study, we explored the feasibility of monitoring postpartum uterine activity by non-invasive electrohysterography (EHG), which has been proven to outperform tocodynamometry in detecting uterine contractions during pregnancy. A comparison was made of the temporal, spectral, and non-linear parameters of postpartum EHG characteristics of vaginal deliveries and elective cesareans. In the vaginal delivery group, EHG obtained a significantly higher amplitude and lower kurtosis of the Hilbert envelope, and spectral content was shifted toward higher frequencies than in the cesarean group. In the non-linear parameters, higher values were found for the fractal dimension and lower values for Lempel-Ziv, sample entropy and spectral entropy in vaginal deliveries suggesting that the postpartum EHG signal is extremely non-linear but more regular and predictable than in a cesarean. The results obtained indicate that postpartum EHG recording could be a helpful tool for earlier detection of uterine atony and contribute to better management of prophylactic uterotonic treatment for PPH prevention. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Electrohysterogram for ANN-Based Prediction of Imminent Labor in Women with Threatened Preterm Labor Undergoing Tocolytic Therapy
Sensors 2020, 20(9), 2681; https://doi.org/10.3390/s20092681 - 08 May 2020
Cited by 7 | Viewed by 1144
Abstract
Threatened preterm labor (TPL) is the most common cause of hospitalization in the second half of pregnancy and entails high costs for health systems. Currently, no reliable labor proximity prediction techniques are available for clinical use. Regular checks by uterine electrohysterogram (EHG) for [...] Read more.
Threatened preterm labor (TPL) is the most common cause of hospitalization in the second half of pregnancy and entails high costs for health systems. Currently, no reliable labor proximity prediction techniques are available for clinical use. Regular checks by uterine electrohysterogram (EHG) for predicting preterm labor have been widely studied. The aim of the present study was to assess the feasibility of predicting labor with a 7- and 14-day time horizon in TPL women, who may be under tocolytic treatment, using EHG and/or obstetric data. Based on 140 EHG recordings, artificial neural networks were used to develop prediction models. Non-linear EHG parameters were found to be more reliable than linear for differentiating labor in under and over 7/14 days. Using EHG and obstetric data, the <7- and <14-day labor prediction models achieved an AUC in the test group of 87.1 ± 4.3% and 76.2 ± 5.8%, respectively. These results suggest that EHG can be reliable for predicting imminent labor in TPL women, regardless of the tocolytic therapy stage. This paves the way for the development of diagnostic tools to help obstetricians make better decisions on treatments, hospital stays and admitting TPL women, and can therefore reduce costs and improve maternal and fetal wellbeing. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Wheezing Sound Separation Based on Informed Inter-Segment Non-Negative Matrix Partial Co-Factorization
Sensors 2020, 20(9), 2679; https://doi.org/10.3390/s20092679 - 08 May 2020
Cited by 4 | Viewed by 1039
Abstract
Wheezing reveals important cues that can be useful in alerting about respiratory disorders, such as Chronic Obstructive Pulmonary Disease. Early detection of wheezing through auscultation will allow the physician to be aware of the existence of the respiratory disorder in its early stage, [...] Read more.
Wheezing reveals important cues that can be useful in alerting about respiratory disorders, such as Chronic Obstructive Pulmonary Disease. Early detection of wheezing through auscultation will allow the physician to be aware of the existence of the respiratory disorder in its early stage, thus minimizing the damage the disorder can cause to the subject, especially in low-income and middle-income countries. The proposed method presents an extended version of Non-negative Matrix Partial Co-Factorization (NMPCF) that eliminates most of the acoustic interference caused by normal respiratory sounds while preserving the wheezing content needed by the physician to make a reliable diagnosis of the subject’s airway status. This extension, called Informed Inter-Segment NMPCF (IIS-NMPCF), attempts to overcome the drawback of the conventional NMPCF that treats all segments of the spectrogram equally, adding greater importance for signal reconstruction of repetitive sound events to those segments where wheezing sounds have not been detected. Specifically, IIS-NMPCF is based on a bases sharing process in which inter-segment information, informed by a wheezing detection system, is incorporated into the factorization to reconstruct a more accurate modelling of normal respiratory sounds. Results demonstrate the significant improvement obtained in the wheezing sound quality by IIS-NMPCF compared to the conventional NMPCF for all the Signal-to-Noise Ratio (SNR) scenarios evaluated, specifically, an SDR, SIR and SAR improvement equals 5.8 dB, 4.9 dB and 7.5 dB evaluating a noisy scenario with SNR = −5 dB. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Parkinson’s Disease EMG Data Augmentation and Simulation with DCGANs and Style Transfer
Sensors 2020, 20(9), 2605; https://doi.org/10.3390/s20092605 - 03 May 2020
Cited by 16 | Viewed by 3009
Abstract
This paper proposes two new data augmentation approaches based on Deep Convolutional Generative Adversarial Networks (DCGANs) and Style Transfer for augmenting Parkinson’s Disease (PD) electromyography (EMG) signals. The experimental results indicate that the proposed models can adapt to different frequencies and amplitudes of [...] Read more.
This paper proposes two new data augmentation approaches based on Deep Convolutional Generative Adversarial Networks (DCGANs) and Style Transfer for augmenting Parkinson’s Disease (PD) electromyography (EMG) signals. The experimental results indicate that the proposed models can adapt to different frequencies and amplitudes of tremor, simulating each patient’s tremor patterns and extending them to different sets of movement protocols. Therefore, one could use these models for extending the existing patient dataset and generating tremor simulations for validating treatment approaches on different movement scenarios. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Investigating an Integrated Sensor Fusion System for Mental Fatigue Assessment for Demanding Maritime Operations
Sensors 2020, 20(9), 2588; https://doi.org/10.3390/s20092588 - 02 May 2020
Cited by 3 | Viewed by 1219
Abstract
Human-related issues are currently the most significant factor in maritime causalities, especially in demanding operations that require coordination between two or more vessels and/or other maritime structures. Some of these human-related issues include incorrect, incomplete, or nonexistent following of procedures; lack of situational [...] Read more.
Human-related issues are currently the most significant factor in maritime causalities, especially in demanding operations that require coordination between two or more vessels and/or other maritime structures. Some of these human-related issues include incorrect, incomplete, or nonexistent following of procedures; lack of situational awareness; and physical or mental fatigue. Among these, mental fatigue is especially dangerous, due to its capacity to reduce reaction time, interfere in the decision-making process, and affect situational awareness. Mental fatigue is also especially hard to identify and quantify. Self-assessment of mental fatigue may not be reliable and few studies have assessed mental fatigue in maritime operations, especially in real time. In this work we propose an integrated sensor fusion system for mental fatigue assessment using physiological sensors and convolutional neural networks. We show, by using a simulated navigation experiment, how data from different sensors can be fused into a robust mental fatigue assessment tool, capable of achieving up to 100 % detection accuracy for single-subject classification. Additionally, the use of different sensors seems to favor the representation of the transition between mental fatigue states. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Intra- and Inter-Rater Reliability of Manual Feature Extraction Methods in Movement Related Cortical Potential Analysis
Sensors 2020, 20(8), 2427; https://doi.org/10.3390/s20082427 - 24 Apr 2020
Viewed by 1434
Abstract
Event related potentials (ERPs) provide insight into the neural activity generated in response to motor, sensory and cognitive processes. Despite the increasing use of ERP data in clinical research little is known about the reliability of human manual ERP labelling methods. Intra-rater and [...] Read more.
Event related potentials (ERPs) provide insight into the neural activity generated in response to motor, sensory and cognitive processes. Despite the increasing use of ERP data in clinical research little is known about the reliability of human manual ERP labelling methods. Intra-rater and inter-rater reliability were evaluated in five electroencephalography (EEG) experts who labelled the peak negativity of averaged movement related cortical potentials (MRCPs) derived from thirty datasets. Each dataset contained 50 MRCP epochs from healthy people performing cued voluntary or imagined movement, or people with stroke performing cued voluntary movement. Reliability was assessed using the intraclass correlation coefficient and standard error of measurement. Excellent intra- and inter-rater reliability was demonstrated in the voluntary movement conditions in healthy people and people with stroke. In comparison reliability in the imagined condition was low to moderate. Post-hoc secondary epoch analysis revealed that the morphology of the signal contributed to the consistency of epoch inclusion; potentially explaining the differences in reliability seen across conditions. Findings from this study may inform future research focused on developing automated labelling methods for ERP feature extraction and call to the wider community of researchers interested in utilizing ERPs as a measure of neurophysiological change or in the delivery of EEG-driven interventions. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
End-To-End Deep Learning Architecture for Continuous Blood Pressure Estimation Using Attention Mechanism
Sensors 2020, 20(8), 2338; https://doi.org/10.3390/s20082338 - 20 Apr 2020
Cited by 35 | Viewed by 2948
Abstract
Blood pressure (BP) is a vital sign that provides fundamental health information regarding patients. Continuous BP monitoring is important for patients with hypertension. Various studies have proposed cuff-less BP monitoring methods using pulse transit time. We propose an end-to-end deep learning architecture using [...] Read more.
Blood pressure (BP) is a vital sign that provides fundamental health information regarding patients. Continuous BP monitoring is important for patients with hypertension. Various studies have proposed cuff-less BP monitoring methods using pulse transit time. We propose an end-to-end deep learning architecture using only raw signals without the process of extracting features to improve the BP estimation performance using the attention mechanism. The proposed model consisted of a convolutional neural network, a bidirectional gated recurrent unit, and an attention mechanism. The model was trained by a calibration-based method, using the data of each subject. The performance of the model was compared to the model that used each combination of the three signals, and the model with the attention mechanism showed better performance than other state-of-the-art methods, including conventional linear regression method using pulse transit time (PTT). A total of 15 subjects were recruited, and electrocardiogram, ballistocardiogram, and photoplethysmogram levels were measured. The 95% confidence interval of the reference BP was [86.34, 143.74] and [51.28, 88.74] for systolic BP (SBP) and diastolic BP (DBP), respectively. The R 2 values were 0.52 and 0.49, and the mean-absolute-error values were 4.06 ± 4.04 and 3.33 ± 3.42 for SBP and DBP, respectively. In addition, the results complied with global standards. The results show the applicability of the proposed model as an analytical metric for BP estimation. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Deep Learning Classification for Diabetic Foot Thermograms
Sensors 2020, 20(6), 1762; https://doi.org/10.3390/s20061762 - 22 Mar 2020
Cited by 27 | Viewed by 2710
Abstract
According to the World Health Organization (WHO), Diabetes Mellitus (DM) is one of the most prevalent diseases in the world. It is also associated with a high mortality index. Diabetic foot is one of its main complications, and it comprises the development of [...] Read more.
According to the World Health Organization (WHO), Diabetes Mellitus (DM) is one of the most prevalent diseases in the world. It is also associated with a high mortality index. Diabetic foot is one of its main complications, and it comprises the development of plantar ulcers that could result in an amputation. Several works report that thermography is useful to detect changes in the plantar temperature, which could give rise to a higher risk of ulceration. However, the plantar temperature distribution does not follow a particular pattern in diabetic patients, thereby making it difficult to measure the changes. Thus, there is an interest in improving the success of the analysis and classification methods that help to detect abnormal changes in the plantar temperature. All this leads to the use of computer-aided systems, such as those involved in artificial intelligence (AI), which operate with highly complex data structures. This paper compares machine learning-based techniques with Deep Learning (DL) structures. We tested common structures in the mode of transfer learning, including AlexNet and GoogleNet. Moreover, we designed a new DL-structure, which is trained from scratch and is able to reach higher values in terms of accuracy and other quality measures. The main goal of this work is to analyze the use of AI and DL for the classification of diabetic foot thermograms, highlighting their advantages and limitations. To the best of our knowledge, this is the first proposal of DL networks applied to the classification of diabetic foot thermograms. The experiments are conducted over thermograms of DM and control groups. After that, a multi-level classification is performed based on a previously reported thermal change index. The high accuracy obtained shows the usefulness of AI and DL as auxiliary tools to aid during the medical diagnosis. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Exploration of Brain Connectivity during Human Inhibitory Control Using Inter-Trial Coherence
Sensors 2020, 20(6), 1722; https://doi.org/10.3390/s20061722 - 19 Mar 2020
Cited by 7 | Viewed by 1745
Abstract
Inhibitory control is a cognitive process that inhibits a response. It is used in everyday activities, such as driving a motorcycle, driving a car and playing a game. The effect of this process can be compared to the red traffic light in the [...] Read more.
Inhibitory control is a cognitive process that inhibits a response. It is used in everyday activities, such as driving a motorcycle, driving a car and playing a game. The effect of this process can be compared to the red traffic light in the real world. In this study, we investigated brain connectivity under human inhibitory control using the phase lag index and inter-trial coherence (ITC). The human brain connectivity gives a more accurate representation of the functional neural network. Results of electroencephalography (EEG), the data sets were generated from twelve healthy subjects during left and right hand inhibitions using the auditory stop-signal task, showed that the inter-trial coherence in delta (1–4 Hz) and theta (4–7 Hz) band powers increased over the frontal and temporal lobe of the brain. These EEG delta and theta band activities neural markers have been related to human inhibition in the frontal lobe. In addition, inter-trial coherence in the delta-theta and alpha (8–12 Hz) band powers increased at the occipital lobe through visual stimulation. Moreover, the highest brain connectivity was observed under inhibitory control in the frontal lobe between F3-F4 channels compared to temporal and occipital lobes. The greater EEG coherence and phase lag index in the frontal lobe is associated with the human response inhibition. These findings revealed new insights to understand the neural network of brain connectivity and underlying mechanisms during human response inhibition. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Comparison of Motion Artefact Reduction Methods and the Implementation of Adaptive Motion Artefact Reduction in Wearable Electrocardiogram Monitoring
Sensors 2020, 20(5), 1468; https://doi.org/10.3390/s20051468 - 07 Mar 2020
Cited by 11 | Viewed by 1329
Abstract
A motion artefact is a kind of noise that exists widely in wearable electrocardiogram (ECG) monitoring. Reducing motion artefact is challenging in ECG signal preprocessing because the spectrum of motion artefact usually overlaps with the very important spectral components of the ECG signal. [...] Read more.
A motion artefact is a kind of noise that exists widely in wearable electrocardiogram (ECG) monitoring. Reducing motion artefact is challenging in ECG signal preprocessing because the spectrum of motion artefact usually overlaps with the very important spectral components of the ECG signal. In this paper, the performance of the finite impulse response (FIR) filter, infinite impulse response (IIR) filter, moving average filter, moving median filter, wavelet transform, empirical mode decomposition, and adaptive filter in motion artefact reduction is studied and compared. The results of this study demonstrate that the adaptive filter performs better than other denoising methods, especially in dealing with the abnormal ECG signal which is measured from a patient with heart disease. In the implementation of adaptive motion artefact reduction, the results show that the use of the impedance pneumography signal as the reference input signal for the adaptive filter can effectively reduce the motion artefact in the ECG signal. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
The Study of Influence of Sound on Visual ERP-Based Brain Computer Interface
Sensors 2020, 20(4), 1203; https://doi.org/10.3390/s20041203 - 21 Feb 2020
Cited by 6 | Viewed by 1299
Abstract
The performance of the event-related potential (ERP)-based brain–computer interface (BCI) declines when applying it into the real environment, which limits the generality of the BCI. The sound is a common noise in daily life, and whether it has influence on this decline is [...] Read more.
The performance of the event-related potential (ERP)-based brain–computer interface (BCI) declines when applying it into the real environment, which limits the generality of the BCI. The sound is a common noise in daily life, and whether it has influence on this decline is unknown. This study designs a visual-auditory BCI task that requires the subject to focus on the visual interface to output commands and simultaneously count number according to an auditory story. The story is played at three speeds to cause different workloads. Data collected under the same or different workloads are used to train and test classifiers. The results show that when the speed of playing the story increases, the amplitudes of P300 and N200 potentials decrease by 0.86 μV (p = 0.0239) and 0.69 μV (p = 0.0158) in occipital-parietal area, leading to a 5.95% decline (p = 0.0101) of accuracy and 9.53 bits/min decline (p = 0.0416) of information transfer rate. The classifier that is trained by the high workload data achieves higher accuracy than the one trained by the low workload if using the high workload data to test the performance. The result indicates that the sound could affect the visual ERP-BCI by increasing the workload. The large similarity of the training data and testing data is as important as the amplitudes of the ERP on obtaining high performance, which gives us an insight on how make to the ERP-BCI generalized. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
3D Hermite Transform Optical Flow Estimation in Left Ventricle CT Sequences
Sensors 2020, 20(3), 595; https://doi.org/10.3390/s20030595 - 21 Jan 2020
Cited by 4 | Viewed by 1033
Abstract
Heart diseases are the most important causes of death in the world and over the years, the study of cardiac movement has been carried out mainly in two dimensions, however, it is important to consider that the deformations due to the movement of [...] Read more.
Heart diseases are the most important causes of death in the world and over the years, the study of cardiac movement has been carried out mainly in two dimensions, however, it is important to consider that the deformations due to the movement of the heart occur in a three-dimensional space. The 3 D + t analysis allows to describe most of the motions of the heart, for example, the twisting motion that takes place on every beat cycle that allows us identifying abnormalities of the heart walls. Therefore, it is necessary to develop algorithms that help specialists understand the cardiac movement. In this work, we developed a new approach to determine the cardiac movement in three dimensions using a differential optical flow approach in which we use the steered Hermite transform (SHT) which allows us to decompose cardiac volumes taking advantage of it as a model of the human vision system (HVS). Our proposal was tested in complete cardiac computed tomography (CT) volumes ( 3 D + t ), as well as its respective left ventricular segmentation. The robustness to noise was tested with good results. The evaluation of the results was carried out through errors in forwarding reconstruction, from the volume at time t to time t + 1 using the optical flow obtained (interpolation errors). The parameters were tuned extensively. In the case of the 2D algorithm, the interpolation errors and normalized interpolation errors are very close and below the values reported in ground truth flows. In the case of the 3D algorithm, the results were compared with another similar method in 3D and the interpolation errors remained below 0.1. These results of interpolation errors for complete cardiac volumes and the left ventricle are shown graphically for clarity. Finally, a series of graphs are observed where the characteristic of contraction and dilation of the left ventricle is evident through the representation of the 3D optical flow. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Electroencephalogram Profiles for Emotion Identification over the Brain Regions Using Spectral, Entropy and Temporal Biomarkers
Sensors 2020, 20(1), 59; https://doi.org/10.3390/s20010059 - 20 Dec 2019
Cited by 9 | Viewed by 1754
Abstract
Identifying emotions has become essential for comprehending varied human behavior during our daily lives. The electroencephalogram (EEG) has been adopted for eliciting information in terms of waveform distribution over the scalp. The rationale behind this work is twofold. First, it aims to propose [...] Read more.
Identifying emotions has become essential for comprehending varied human behavior during our daily lives. The electroencephalogram (EEG) has been adopted for eliciting information in terms of waveform distribution over the scalp. The rationale behind this work is twofold. First, it aims to propose spectral, entropy and temporal biomarkers for emotion identification. Second, it aims to integrate the spectral, entropy and temporal biomarkers as a means of developing spectro-spatial ( S S ) , entropy-spatial ( E S ) and temporo-spatial ( T S ) emotional profiles over the brain regions. The EEGs of 40 healthy volunteer students from the University of Vienna were recorded while they viewed seven brief emotional video clips. Features using spectral analysis, entropy method and temporal feature were computed. Three stages of two-way analysis of variance (ANOVA) were undertaken so as to identify the emotional biomarkers and Pearson’s correlations were employed to determine the optimal explanatory profiles for emotional detection. The results evidence that the combination of applied spectral, entropy and temporal sets of features may provide and convey reliable biomarkers for identifying S S , E S and T S profiles relating to different emotional states over the brain areas. EEG biomarkers and profiles enable more comprehensive insights into various human behavior effects as an intervention on the brain. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Graphical abstract

Article
Heartbeat Sound Signal Classification Using Deep Learning
Sensors 2019, 19(21), 4819; https://doi.org/10.3390/s19214819 - 05 Nov 2019
Cited by 41 | Viewed by 4827
Abstract
Presently, most deaths are caused by heart disease. To overcome this situation, heartbeat sound analysis is a convenient way to diagnose heart disease. Heartbeat sound classification is still a challenging problem in heart sound segmentation and feature extraction. Dataset-B applied in this study [...] Read more.
Presently, most deaths are caused by heart disease. To overcome this situation, heartbeat sound analysis is a convenient way to diagnose heart disease. Heartbeat sound classification is still a challenging problem in heart sound segmentation and feature extraction. Dataset-B applied in this study that contains three categories Normal, Murmur and Extra-systole heartbeat sound. In the purposed framework, we remove the noise from the heartbeat sound signal by applying the band filter, After that we fixed the size of the sampling rate of each sound signal. Then we applied down-sampling techniques to get more discriminant features and reduce the dimension of the frame rate. However, it does not affect the results and also decreases the computational power and time. Then we applied a purposed model Recurrent Neural Network (RNN) that is based on Long Short-Term Memory (LSTM), Dropout, Dense and Softmax layer. As a result, the purposed method is more competitive compared to other methods. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
A Novel Signal Separation and De-Noising Technique for Doppler Radar Vital Signal Detection
Sensors 2019, 19(21), 4751; https://doi.org/10.3390/s19214751 - 01 Nov 2019
Cited by 3 | Viewed by 1236
Abstract
Doppler radar for monitoring vital signals is an emerging tool, and how to remove the noise during the detection process and reconstruct the accurate respiration and heartbeat signals are hot issues in current research. In this paper, a novel radar vital signal separation [...] Read more.
Doppler radar for monitoring vital signals is an emerging tool, and how to remove the noise during the detection process and reconstruct the accurate respiration and heartbeat signals are hot issues in current research. In this paper, a novel radar vital signal separation and de-noising technique based on improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), sample entropy (SampEn), and wavelet threshold is proposed. First, the noisy radar signal was decomposed into a series of intrinsic mode functions (IMFs) using ICEEMDAN. Then, each IMF was analyzed using SampEn to find out the first few IMFs containing noise, and these IMFs were de-noised using the wavelet threshold. Finally, in order to extract accurate vital signals, spectrum analysis and Kullback–Leible (KL) divergence calculations were performed on all IMFs, and appropriate IMFs were selected to reconstruct respiration and heartbeat signals. Moreover, as far as we know, there is almost no previous research on radar vital signal de-noising based on the proposed technique. The effectiveness of the algorithm was verified using simulated and measured experiments. The results show that the proposed algorithm could effectively reduce the noise and was superior to the existing de-noising technologies, which is beneficial for extracting more accurate vital signals. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Article
Simultaneous EEG Acquisition System for Multiple Users: Development and Related Issues
Sensors 2019, 19(20), 4592; https://doi.org/10.3390/s19204592 - 22 Oct 2019
Cited by 3 | Viewed by 1635
Abstract
Social interaction is one of humans’ most important activities and many efforts have been made to understand the phenomenon. Recently, some investigators have attempted to apply advanced brain signal acquisition systems that allow dynamic brain activities to be measured simultaneously during social interactions. [...] Read more.
Social interaction is one of humans’ most important activities and many efforts have been made to understand the phenomenon. Recently, some investigators have attempted to apply advanced brain signal acquisition systems that allow dynamic brain activities to be measured simultaneously during social interactions. Most studies to date have investigated dyadic interactions, although multilateral interactions are more common in reality. However, it is believed that most studies have focused on such interactions because of methodological limitations, in that it is very difficult to design a well-controlled experiment for multiple users at a reasonable cost. Accordingly, there are few simultaneous acquisition systems for multiple users. In this study, we propose a design framework for an acquisition system that measures EEG data simultaneously in an environment with 10 or more people. Our proposed framework allowed us to acquire EEG data at up to 1 kHz frequency from up to 20 people simultaneously. Details of our acquisition system are described from hardware and software perspectives. In addition, various related issues that arose in the system’s development—such as synchronization techniques, system loads, electrodes, and applications—are discussed. In addition, simultaneous visual ERP experiments were conducted with a group of nine people to validate the EEG acquisition framework proposed. We found that our framework worked reasonably well with respect to less than 4 ms delay and average loss rates of 1%. It is expected that this system can be used in various hyperscanning studies, such as those on crowd psychology, large-scale human interactions, and collaborative brain–computer interface, among others. Full article
(This article belongs to the Special Issue Biomedical Signal Processing)
Show Figures

Figure 1

Back to TopTop