Biomedical Signals Research Articles

BDCDTA-based Reconfigurable Frequency Selective Filter Structures for Medium Wave Communication and Biomedical Signal Processing Applications

BDCDTA-based Reconfigurable Frequency Selective Filter Structures for Medium Wave Communication and Biomedical Signal Processing Applications

Predictive Analysis of Patient Risk of Death in ICU: A Bibliometric Analysis

This bibliometric analysis explores the synergy of artificial intelligence (AI), particularly machine learning, and biomedical signal processing in predicting patient mortality risk within the intensive care unit (ICU). Utilizing a comprehensive literature review, the study assesses the research landscape by applying these techniques to ICU data. Examining diverse data sources like vital signs and electronic health records, the analysis identifies trends and gaps in existing work, emphasizing AI’s potential for resource allocation and preventative care to enhance ICU outcomes. Structured within a bibliometric framework, the review encompasses methodological approaches, results, and discussions, while addressing clinical and ethical perspectives on mortality prediction. Challenges related to data, model performance, and fairness are evaluated through a bibliometric lens. The research questions underscore the importance of understanding past literature trends in predictive analysis for ICU patients. The review methodologically explores recent studies employing word representation models, impact assessments, and risk prediction of vital signs. Global research trends in AI for critical care are identified based on bibliographic data between 2013 and 2022. Noteworthy contributions, such as a sepsis dataset, are highlighted within the bibliometric analysis. In conclusion, this bibliometric analysis positions itself at the intersection of AI and critical care, emphasizing the importance of bibliographic data in understanding past trends, methodologies, and impactful contributions. It sets the stage for future directions in the evolving landscape of ICU predictive analytics within a bibliometric framework.

Tensor Methods in Biomedical Image Analysis.

In the past decade, tensors have become increasingly attractive in different aspects of signal and image processing areas. The main reason is the inefficiency of matrices in representing and analyzing multimodal and multidimensional datasets. Matrices cannot preserve the multidimensional correlation of elements in higher-order datasets and this highly reduces the effectiveness of matrix-based approaches in analyzing multidimensional datasets. Besides this, tensor-based approaches have demonstrated promising performances. These together, encouraged researchers to move from matrices to tensors. Among different signal and image processing applications, analyzing biomedical signals and images is of particular importance. This is due to the need for extracting accurate information from biomedical datasets which directly affects patient's health. In addition, in many cases, several datasets have been recorded simultaneously from a patient. A common example is recording electroencephalography (EEG) and functional magnetic resonance imaging (fMRI) of a patient with schizophrenia. In such a situation, tensors seem to be among the most effective methods for the simultaneous exploitation of two (or more) datasets. Therefore, several tensor-based methods have been developed for analyzing biomedical datasets. Considering this reality, in this paper, we aim to have a comprehensive review on tensor-based methods in biomedical image analysis. The presented study and classification between different methods and applications can show the importance of tensors in biomedical image enhancement and open new ways for future studies.

Biomedical Signal to Image Conversion and Classification using Flexible Deep Learning Techniques

Biomedical Signal to Image Conversion and Classification using Flexible Deep Learning Techniques

A new method for digital processing cardio signals using the wavelet function

Biomedical signal processing algorithms offer a variety of opportunities to improve performance. In this study, a new wavelet delta- function (WDF) method was proposed to effectively detect pathology from ECG signals. In this method, the delta function is determined for each value of the ECG signal. The coefficients 0, 1, and -1 are determined by summing this WDF. The level of detection of the difference between pathology and norm using data in the form of this vector allows changes in the diagnosis to be made more accurately than conventional methods. This is a new way of processing ECG signals by converting graphical data into vectors. The new method created a bar-code - like image. It has become possible to see myocardial infarction (MI), one of the diseases of the cardiovascular system, more effectively in real numbers of invisible peaks on the ECG. This allows for early detection and accurate diagnosis. The model we propose is an effective way to analyze an ECG. The WDF model we proposed can be used for early assessment of disease in biomedical signal processing.

Exploring Cutting-Edge Developments in Deep Learning for Biomedical Signal Processing

Exploring Cutting-Edge Developments in Deep Learning for Biomedical Signal Processing

ThermICA: Novel Approach for a Multivariate Analysis of Facial Thermal Responses.

Infrared Thermography (IRT) has been used to monitor skin temperature variation in a contactless manner, in both clinical medicine and psychophysiology. Here, we introduce a new methodology to obtain information about autonomic correlates related to perspiration, peripheral vasomotility, and respiration from infrared recordings. Our approach involves a model-based decomposition of facial thermograms using Independent Component Analysis (ICA) and an ad-hoc preprocessing procedure. We tested our approach on 30 healthy volunteers whose psychophysiological state was stimulated as part of an experimental protocol. Within-subject ICA analysis identified three independent components demonstrating correlations with the reference physiological signals. Moreover, a linear combination of independent components effectively predicted each physiological signal, achieving median correlations of 0.9 for electrodermal activity, 0.8 for respiration, and 0.73 for photoplethysmography peaks envelope. In addition, we performed a cross-validated inter-subject analysis, which allows to predict physiological signals from facial thermograms of unseen subjects. Our findings validate the efficacy of features extracted from both original and thermal-derived signals for differentiating experimental conditions. This outcome emphasizes the sensitivity and promise of our approach, advocating for expanded investigations into thermal imaging within biomedical signal analysis. It underscores its potential for enhancing objective assessments of emotional states.

A Review on Bio-Medical Signal Processing Using Machine Learning Techniques

A Review on Bio-Medical Signal Processing Using Machine Learning Techniques

Enhancing Fault Detection and Diagnosis in Grid-Connected PV Systems under Irradiance Variations: A Novel Approach Using New Data Normalization Techniques on RBFNN Algorithm

With the global shift towards renewable energy, the reliability and efficiency of photovoltaic (PV) systems have become paramount. A crucial aspect of this is the timely detection and accurate classification of faults within the system. In fact, accurate fault detection and classification in the diagnostic systems can prevent severe damages, enhance operational efficiency, and prolong the lifespan of the installations. This paper introduces a novel data normalization technique tailored for enhancing the performance of meta-heuristic algorithms (namely RBFNN) applied to single-phase inverter current signals for fault detection in PV systems. While conventional normalization technics have shown their limitations in capturing the nuances of PV system faults, our proposed strategy demonstrates a more effective approach in preserving fault-specific features in the data. The proposed method is evaluated using multiple datasets encompassing a variety of fault scenarios. Empirical results show a significant improvement in both fault detection rates and classification accuracy. This study not only presents a breakthrough in PV system fault diagnosis but also sheds light on the broader potential of specialized normalization techniques in all signal-processing field, such as biomedical signal processing, industrial process control, or financial time series analysis, and other domains. The supremacy of the proposed diagnostic in reducing false alarms and providing more clear-cut classifications is highlighted by several simulations under Matlab-Simulink.

Biomedical signal to image conversion and classification using flexible deep learning techniques

Biomedical signal to image conversion and classification using flexible deep learning techniques

A 1.2v ΔΣ ADC Modulator Using 4-bit SAR Quantizer for Biomedical Applications by using 65nm CMOS Technology

This research focuses on enhancing Sigma-Delta ADC modulators for biomedical applications by leveraging the working principle of Successive Approximation ADC circuits. The proposed modulator includes a comparator, DAC, successive approximation register, and control circuit. The operational process begins with the sample and holds circuit-initiating conversions by sampling the input signal, and then compared with the DAC output. Using a 4-bit example, the successive approximation register refines the DAC output through iterative bit adjustments until the closest digital code approximation to the input is voltage independent of input voltage, occurring incrementally one bit at a time. The proposed enhancement aims to optimize Sigma-Delta ADC modulator performance for biomedical applications, ensuring high resolution and speed. Typical conversion speeds range from 2 to 5 MSPS, with resolutions varying from 8 to 16 bits, contributing to improved precision and efficiency in capturing and digitizing biomedical signals.

Automatic Diagnosis of Schizophrenia in EEG Signals using CNN Models

This study uses convolutional neural networks (CNNs) to analyze electroencephalogram (EEG) signals to tackle the crucial problem of early schizophrenia diagnosis. In the study, two different CNN models with different architectural characteristics are compared and contrasted, with a focus on measures related to accuracy, loss, selectivity, and specificity. A meticulously selected dataset is obtained and preprocessed, containing EEG signals from people with and without schizophrenia. The chosen CNN architectures differ in terms of activation functions, filter sizes, and layer depth. The performance of the models is carefully assessed using metrics appropriate to the particulars of the problem, such as accuracy, loss, selectivity (true positive rate), and specificity (true negative rate), after they have undergone rigorous training on the preprocessed dataset. The goal of the comparison analysis is to offer a thorough grasp of how various architectural decisions affect the model’s capacity to correctly identify patterns linked to schizophrenia in EEG data. In addition to examining optimization and fine-tuning techniques to improve the model’s performance, the research also focuses on ethical issues to guarantee the responsible use of private health information. In the end, this work aims to further the development of deep learning-based EEG signal analysis diagnostic tools for schizophrenia, with a focus on the selection of assessment metrics that are important benchmarks for judging model performance. Keywords: schizophrenia, mental disorders, machine learning, biomedical signals, EEG signals, CNN

Pseudo-Resistor-Based ECG Amplifier: Design, Implementation and Temperature Characterization

Biomedical signal amplifiers are fundamental in various medical applications for acquiring crucial biological signals such as ECG, EEG, and EMG. The use of pseudo-resistors has been recently studied for biological amplifiers, mainly because of their fast recovery time after interference pulses, which are frequent in such applications. The previous studies on pseudo-resistors are limited to simulation, modeling, and implementing some narrow-bandwidth amplifiers. For the first time, this study uses the piecewise linear (PWL) model integrated with pseudo-resistors to design a tailored circuit for ECG applications, with 0.04 Hz to 2 kHz bandwidth for the full application temperature range. The circuit is fully modeled, simulated, and characterized, fine-tuning the feedback capacitance values to optimize performance within the crucial temperature range for biomedical applications. This full bandwidth amplifier represents a significant advancement in biomedical signal amplification technology, ensuring comprehensive signal fidelity allied to fast recovery response.

Approach and application of extracting matching features from E-nose signals for AI tasks

Machine learning algorithms involving feature engineering as their key steps play important roles in AI tasks. Both feature selection and extraction have their pros and cons, recent studies have tried to meet the expectation of obtaining advantages of both methods, and this strive is still ongoing. Here, we proposed an idea of matching features analysis (MFA) based on wavelets to extract features in one-dimensional signals. To evaluate the performance of this method, “breath-prints” with 8364 features from 109 lung cancer patients and 109 healthy controls are sampled by our self-developed e-nose system. Features extracted by our proposed method and 8 other conventional techniques are fed to 3 classifiers. Performances of these 27 classification models are then compared. It turns out that, by using features extracted by our proposed method, classifiers show the best performance in recognizing lung cancer patients from controls. Classification accuracy of 93% and AUC of 0.96 is finally achieved when using MFA-MLP. With relatively better interpretation and approximation, this matching feature analysis technique may have great potentials in features engineering of biomedical signals for AI tasks.

Optimized FIR Filter Using Genetic Algorithms: A Case Study of ECG Signals Filter Optimization

The advancement in technology and the availability of specialized digital signal processing chips have made digital filter design and implementation more feasible in a variety of fields, including biomedical engineering. This paper makes two key contributions. First, it uses a genetic algorithm to optimize the coefficients of finite impulse response (FIR) filters. Second, it conducts a case study on using genetic algorithms to optimize FIR filters for electrocardiogram (ECG) biomedical signal noise removal. The goal of the proposed filter design approach is to achieve the desired signal bandwidth while minimizing the side lobe level and eliminating unwanted signals using a genetic algorithm. The results of a comprehensive analysis show that the genetic algorithm-based filter is more effective than conventional filter designs in terms of noise removal efficiency.

The Study of Properties Savitzky-Golay Polynomial Smoothing Filter for Electrocardiogram Signal Processing

Many types of processing techniques have been proposed to improve the performance of biomedical signal with noise. The Savitzky-Golay (SG) filters is one of the techniques used in filtering noise which can smoothen out the signal without much destroying its original properties. Despite their exceptional features they were rarely used so far in the ECG signal processing. The principle behind S-G filter is to obtain the appropriate Polynomial degree fitting order and frame size properties since the performance of filter mostly depends on them. Thus, the appropriate properties of S-G filter in noisy signal needs to be examined. In this study, combination between band-pass filter and S-G filter is implemented. The implementation has been applied S-G filter on the noisy ECG signal with different Signal to noise ratio and artefacts. The aim of this paper is the investigation of S-G filter properties in detail from the ECG signal processing aspect. The comparison of properties of S-G filter on ECG signal with different signal of noise ratio are also discussed. The parameters which provide the highest correlation coefficient are considered for filter design.

EMG signal transmission system under RF schemes

With the rise in pathological conditions during the post-pandemic era, particularly concerning the management of biomedical signals, a significant surge has been observed. This research endeavors to develop a self-adaptive algorithm for the discretization and data encapsulation of electromyographic (EMG) signals. The synthetic signal used for analysis is acquired from the PhysioNet database, specifically focusing on the implementation of the tibialis anterior muscle. A transmission chain is established utilizing the AD9361 transceiver, while a power amplifier is employed for base radio applications, operating at a carrier frequency of 2.45 GHz. The spectral validation of this system reveals that the 16-QAM modulation, which is subjected to testing, yields an accuracy of -15.5 dB NMSE. As a further work, an EMG signal acquisition stage is proposed, based on a high-resolution analog-to-digital converter (ADC) card, alongside the exploration of higher order n-QAM schemes to enhance accuracy in the receiver stage.

Topological data analysis assisted automated sleep stage scoring using airflow signals

Objective:Breathing pattern variability (BPV), as a universal physiological feature, encodes rich health information. We aim to show that, a high-quality automatic sleep stage scoring based on a proper quantification of BPV extracting from the single airflow signal can be achieved. Methods:Topological data analysis (TDA) is applied to characterize BPV from the intrinsically nonstationary airflow signal. The extracted features from TDA are utilized to train an automatic sleep stage scoring model using the XGBoost learner. Additionally, the noise and artifacts that are typically present in the air flow signal are leveraged to improve the performance of the trained system. To evaluate the effectiveness of the proposed approach, a state-of-the-art method is implemented for comparison purposes. Results:A leave-one-subject-out cross-validation was conducted on a dataset comprising 30 whole-night polysomnogram signals with standard annotations. The results show that the proposed features outperform those considered in the state-of-the-art work in terms of overall accuracy (78.8% ± 8.7% vs. 75.0% ± 9.6%) and Cohen’s kappa (0.56 ± 0.15 vs. 0.50 ± 0.15) for automatically scoring wake, rapid eye movement (REM), and non-REM (NREM) stages. An external validation conducted on a dataset comprising 80 whole-night polysomnogram signals with standard annotations shows a result of overall accuracy 74.1%±11.6% and Cohen’s kappa 0.42±0.15, which again outperforms the state-of-the-art work. Furthermore, the analysis of feature importance reveals that the TDA features provide complementary information to the traditional features commonly used in the literature, and the respiratory quality index is identified as an essential component. Conclusion:The proposed TDA-assisted automatic annotation system can accurately distinguish wake, REM and NREM from the airflow signal. Significance:The utilization of a single air flow channel and the universality of BPV suggest the potential of TDA-assisted signal processing in addressing various biomedical signals and homecare issues beyond sleep stage annotation.

Biometric Analysis on Smart Textile Garment in Real Life Scenario

The rapid proliferation of wearable applications and technologies capable of acquiring biomedical signals has prompted the incorporation of biomedical signals, such as the electrocardiogram (ECG), for biometric purposes in wearable platforms. Most ECG biometric research utilises medical-grade sensors in clinical settings, which is unrealistic for wearable ECG-based biometric applications in the real world. Therefore, this research aims to examine the ECG biometric on smart textile garments in real life, collected from commercially available wearable Hexoskin Proshirt and HeartIn Fit shirts. ECG data were obtained from 22 participants who took part in this study. The raw ECG signal is initially pre-processed using noise-removal Butterworth filters in the time domain, followed by an effective QRS segmented feature extraction technique. Finally, around 2076 datasets were created for training and validation, while the remaining 501 datasets were employed to test the suggested recognition approach with 29 Machine Learning Classifiers. Subsequently, Quadratic SVM has the highest accuracy at 96.8% for ECG biometrics, followed by Narrow Neural Network with 95.8% and Wide Neural Network with 95.4%. Further improvement to the QSVM parameter improved the accuracy to 97.4% with an error rate of 2.6%, followed by a sensitivity of 97.4% with a precision of 97.7% and a false rejection rate of 2.6%. Thus, the results of this study further validate the feasibility of applying ECG biometrics for recognition in real-life scenarios utilising a smart textile shirt with different configurations and brand is possible.

A mathematical model for simulating photoacoustic signal generation and propagation in biological tissues

Photoacoustic (PA) medical imaging is a crossbred technique relying on light-induced ultrasonic waves due to the PA effect phenomenon recorded primarily in 1880 by A. G. Bell. Numerical simulation, also known as in-silico, studies assist scientists in minimizing incorrect PA experiments in both in-vitro and in-vivo. Numerical modeling techniques help to achieve a fast simulation process in contrast to pure mathematics alone. However, if a suitable facilitated mathematical model can be established prior to applying numerical modeling, it will be of great interest to the whole numeric model. Numerous mathematical equations, theorems, and propositions have been proposed to model the whole PA signal generation and propagation process in biological media. However, most of them are complicated and difficult to be understood by researchers, especially beginners. That’s why this paper was introduced. Our paper aims to simplify the understanding of the generation and propagation process of biomedical PA waves. We have developed a facilitated mathematical model for the entire process. The introduced developed mathematical model is based on three steps: (1) pulsed laser stimulation, (2) light diffusion, and (3) PA stress wave generation and propagation. The developed mathematical model has been implemented utilizing COMSOL Multiphysics, which relies on the finite element method (FEM) numerical modeling principle. The in-silico time-dependent study's results confirmed that the proposed mathematical model is a simple, efficient, accurate, and quick starting point for researchers to simulate biomedical PA signals' generation and propagation process utilizing any suitable software such as COMSOL multiphysics.