Biomedical Signal Processing Research Articles

Hybrid fuzzy deep neural network toward temporal-spatial-frequency features learning of motor imagery signals

Achieving an efficient and reliable method is essential to interpret a user’s brain wave and deliver an accurate response in biomedical signal processing. However, EEG patterns exhibit high variability across time and uncertainty due to noise and it is a significant problem to be addressed in mental task as motor imagery. Therefore, fuzzy components may help to enable a higher tolerance to noisy conditions. With the advent of Deep Learning and its considerable contributions to Artificial intelligence and data analysis, numerous efforts have been made to evaluate and analyze brain signals. In this study, to make use of neural activity phenomena, the feature extraction preprocessing is applied based on Multi-scale filter bank CSP. In the following, the hybrid series architecture named EEG-CLFCNet is proposed which extract the frequency and spatial features by Compact-CNN and the temporal features by the LSTM network. However, the classification results are evaluated by merging the fully connected network and fuzzy neural block. Here, the proposed method is further validated by the BCI competition IV-2a dataset and compare with two hyperparameter tuning methods, Coordinate-descent and Bayesian optimization algorithm. The proposed architecture that used fuzzy neural block and Bayesian optimization as tuning approach, results in better classification accuracy compared with the state-of-the-art literatures. As results shown, the remarkable performance of the proposed model, EEG-CLFCNet, and the general integration of fuzzy units to other classifiers would pave the way for enhanced MI-based BCI systems.

SsvEEGc: An efficient EEG clustering method using balance-constrained voting mechanism

With the increasing amount of unlabeled electroencephalography (EEG) trials in the brain–computer interface (BCI) domain, neurocognitive disorder diagnoses, and rehabilitation, etc., supervised EEG analysis that requires completely prior information of EEG labels has become unpractical. Although a few methods for unlabeled EEG clustering have recently emerged, their models or objective functions are pretty complex and time-consuming, which degrades the practicability in BCI or disease diagnosis that demands high efficiency of methods. To improve the performance of analyzing and clustering EEG trials for BCI applications, we simultaneously consider (1) the efficiency and efficacy, (2) the clustering balance and (3) the theoretical property satisfiability for partially labeled EEG trials in this paper. We propose an easily implemented and efficient EEG clustering method called ssvEEGc for partially labeled EEG trials by designing a high-efficiency and effective voting mechanism with clustering balance constraints. ssvEEGc satisfies 2 of 3 clustering theoretical properties and yields high-quality EEG clusters with low time consumption. Further, comprehensive experiments on 15 real-world EEG datasets demonstrate that ssvEEGc is superior to 11 state-of-the-art unsupervised clustering methods in terms of efficiency, effectiveness and theoretical property satisfiability. The results indicate that ssvEEGc can be applied to larger EEG datasets in biomedical signal processing and control application scenarios.

Educational trends in biomedical signal processing

Abstract Biomedical Engineering programs are present at many universities all over the world with an increasing trend. New generations of biomedical engineers have to face the challenges of health care systems round the world which need a large number of professionals not only to support the present technology in the health care system but to develop new devices and services. Biomedical Engineering supports patient diagnosis and treatment by installing, testing, calibrating and repairing biomedical equipment; training users; maintaining safe operations. Also, approves new equipment by conducting tests, ensuring adherence to codes and making modifications. This paper presents a solution for biomedical signal processing education, involving real signal acquisition and computer-based processing. The acquired signals also allow a lot of post processing procedures to be implemented in an educational form/way.

Implementation of Optimized Filter Order to the PSD Analysis of QRS Detected ECG Signal

Filtration of ECG signal is an important part in the analysis and signal processing of ECG signal. There are different types of digital and analog filters available for the filtration of an ECG signal. And choosing the right filter order for different filters has always been a tough task in biomedical signal processing. This study aims to solve this problem of filter order optimization by cascading digital filters and evaluating their performance based on SNR using ECG-ID Database from PHYSIONET. Besides, this optimized filter order has been applied to both normal and abnormal QRS detected ECG signals to choose the right filter order based on average power received from PSD analysis. QRS detection has been performed by differentiation technique. In this study, design of the filters has been carried out using MATLAB software-based FDA tool in both monitoring and diagnostic modes. This analysis has strong potential for analyzing low amplitude based biological signals like ECG or EEG.

A system for biomedical audio signal processing based on high performance computing techniques

In this paper, a noninvasive portable prototype is presented for biomedical audio signal processing. The proposed prototype is suitable for monitoring the health of patients. The proposed hardware setup consists of a cost-effective microphone, multipurpose microcontroller and computing node that could be a mobile phone or general-purpose computer. Using parallel and high-performance techniques, this setup allows one to register and wirelessly multicast the recorded biomedical signals to computing nodes in real time. The developed prototype was used as a case study to estimate the heart rate (HR) from the captured biomedical audio signal. In this regard, the developed algorithm for estimating HR comprises three stages: preprocessing, separation, and HR estimation. In the first stage, the signal captured by the microphone is adapted for processing. Subsequently, a separation stage was proposed to alleviate the acoustic interference between the lungs and heart. The separation is performed by combining a non-negative matrix factorization algorithm, clustering approach, and soft-filter strategy. Finally, HR estimation was obtained using a novel and efficient method based on the autocorrelation function. The developed prototype could be used not only for the estimation of the HR, but also for the retrieval of other biomedical information related to the recording of cardiac or respiratory audio signals. The proposed method was evaluated using well-known datasets and compared with state-of-the-art algorithms for source-separation. The results showed that it is possible to obtain an accurate separation and reliable real-time estimation in terms of source separation metrics and relative error in the tested scenarios by combining multi-core architectures with parallel and high-performance techniques. Finally, the proposed prototype was validated in a real-world scenario.

DeepPlayer: An open‐source SignalPlant plugin for deep learning inference

AbstractBackground and ObjectiveMachine learning has become a powerful tool in several computation domains. The most progressive way of machine learning, deep learning, has already surpassed several algorithms designed by human experts. It also applies to the field of biomedical signal processing. However, while many experts produce deep learning models, there is no software platform for signal processing, allowing the convenient use of pre‐trained deep learning models and evaluating them using any inspected signal. This may also hinder understanding, interpretation, and explanation of results. For these reasons, we designed DeepPlayer. It is a plugin for the free signal processing software SignalPlant. The plugin allows loading deep learning models saved in the Open Neural Network Exchange (ONNX) file format and evaluating them on any given signal.MethodsThe DeepPlayer plugin and its graphical user interface were designed in C# programming language and the .NET framework. We used the inference library OnnxRuntime, which supports graphics card acceleration. The inference is executed in asynchronous tasks for a live preview and evaluation of the signals. Model outputs can be exported back to SignalPlant for further processing, such as peak detection or thresholding.ResultsWe developed the DeepPlayer plugin to evaluate deep learning models in SignalPlant. The plugin keeps with SignalPlant's interactive work with signals, such as live preview or easy selection of associated signals. The plugin can load classification or regression models and allows standard pre‐processing and post‐processing methods. We prepared several deep learning models to test the plugin. Additionally, we provide a tutorial training script that outputs an ONNX format model with correctly set metadata information. These, and the source code of the DeepPlayer plugin, are publicly accessible via GitHub and Google Colab service.ConclusionThe DeepPlayer plugin allows running deep learning models easily and interactively. Therefore, experts and non‐AI experts alike can explore and apply deep learning models for (biomedical) signal processing. Its ease of use and interactivity might also contribute to a better understanding and acceptance of AI methods in biomedicine.

Blind Source Separation with Multi-Objective Optimization for Denoising

Blind Source Separation is an optimization method frequently used in statistical signal processing applications. There are many application areas such as ambient listening, denoising, signal detection, and so on. In this study, a new Strength Pareto Evolutionary Algorithm 2-based signal separation method is proposed, which combines Multi-Objective Optimization and Blind Source Separation algorithms. The proposed method has been tested for denoising, which is widely used in biomedical signal processing. That is, the Electrocardiogram (ECG) and White Gaussian Noise are mixed together with normally distributed random numbers and the original signals of the mixed signals are obtained again. To evaluate the performance of the proposed method and others (Multi-Objective Blind Source Separation and Independent Component Analysis), the Signal-to-Noise Ratio (SNR) of the ECG signal obtained from mixed signals has been measured. As a result of the simulation studies, it is seen that the performance of the proposed method is satisfactory.

Classification of ECG signal using FFT based improved Alexnet classifier.

Electrocardiograms (ECG) are extensively used for the diagnosis of cardiac arrhythmias. This paper investigates the use of machine learning classification algorithms for ECG analysis and arrhythmia detection. This is a crucial component of a conventional electronic health system, and it frequently necessitates ECG signal reduction for long-term data storage and remote transmission. Signal processing methods must be used to extract the function of the morphological properties of the ECG signal changing with time, which is difficult to discern in the typical visual depiction of the ECG signal. In biomedical research, signal processing and data analysis are commonly employed methodologies. This work proposes the use of an ECG arrhythmia classification method based on Fast Fourier Transform (FFT) for feature extraction and an improved AlexNet classifier to distinguish the difference between four types of arrhythmia conditions that were collected from records. The Convolutional Neural Network (CNN) algorithm's results are compared to those of other algorithms, and the simulation results prove that the proposed technique is more effective for various parameters. The final results of the proposed system show that its ability to find deviations is 20% better than that of traditional systems.

Digital Transformation in Epilepsy Diagnosis Using Raw Images and Transfer Learning in Electroencephalograms

Epilepsy diagnosis is a medical care process that requires considerable transformation, mainly in developed countries, to provide efficient and effective care services taking into consideration the low number of available neurologists, especially in rural areas. EEG remains the most common test used to diagnose epilepsy. In recent years, there has been an increase in deep learning techniques to analyze electroencephalograms (EEG) to detect epileptiform events. These types of techniques support the epilepsy diagnostic processes performed by neurologists. There have been several approaches such as biomedical signal processing, analysis of characteristics extracted from the signals, and image analysis to detect epileptiform events. Most of the works reported in the literature, which use images, transformed the signals into a two-dimensional space interpreted as an image. However, only a few of them use the raw EEG image. This paper presents a computational model for detecting epileptiform events from raw EEG images, using convolutional neural networks and a transfer learning approach. To perform this work, 100 pediatric EEGs were collected, noting six characteristics of epileptiform events in each exam: spikes, poly-spikes, spike-and-wave, sharp waves, periodic, and a combination of them. Then, pre-trained convolutional neural networks were used, which, through transfer learning techniques, were retrained to classify possible events. The model’s performance was evaluated in terms of precision, accuracy, and Mathews’ correlation coefficient. The model offered a performance above 95% accuracy for binary classification and above 87% for multi-class classification. These results demonstrated that identifying epileptiform events from raw EEG images combined with deep learning techniques such as transfer learning is feasible. Significance: The proposed method for the evaluation of EEG tests, as a support tool for the diagnosis of epilepsy, can help to reduce the time of reading EEGs, which is very important, especially in developing countries with a limitation of a specialist in neurology.

Gömülü ve Sarıcı Öznitelik Seçim Yöntemleri Kullanılarak Akciğer Rahatsızlıklarının Tespiti

Son yıllarda biyomedikal sinyal işleme alanındaki gelişmelere rağmen, akciğer rahatsızlıklarının tespiti üzerine hızlı ve yüksek doğrulukta çalışan teşhis sistemlerine duyulan ihtiyaç artmaktadır. Yapılan çalışmada fiziki muayene ile 94 farklı kişiden, solunum döngülerinin otomatik olarak tespit edilmesiyle elde edilen 150 adet normal ve 444 adet normal olmayan akciğer sesleri veri tabanı olarak kullanılmıştır. Sınıflandırma işleminde öznitelik olarak frekans ve zaman bölgesinde 12 farklı yöntem uygulanmıştır. Tüm veriler %80 eğitim %20 test aşamasında kullanılacak şekilde ikiye bölünmüştür. Elde edilen öznitelikler gömülü ve sarıcı öznitelik seçim yöntemleri kullanılarak değerlendirilmiştir. Bu yöntemler; özyinelemeli öznitelik eliminasyonu, uyarlanabilir yapı öğrenimi ile öznitelik seçimi, bağımlılık kılavuzlu denetimsiz öznitelik seçimi, sıralı yerellik ile denetimsiz öznitelik seçimi, içbükey küçültme yoluyla öznitelik seçimi, en küçük mutlak büzülme ve seçim operatörü öznitelik seçim yöntemleri olarak isimlendirilmektedir. İncelenen bu öznitelikler doğrusal destek vektör makineleri, k en yakın komşuluk, karar ağaçları ve naive bayes yöntemleri ile sınıflandırılmıştır. Sonuç olarak öznitelik sayısının sınırlandırılmadığı durum için, özyinelemeli öznitelik eliminasyonu yönteminin k en yakın komşuluk sınıflandırma ile beraber kullanıldığı durum için %97,3 doğruluk değerindeki başarıma ulaşılmaktadır. Öznitelik sayısının üç ile sınırlandırıldığı durumda ise uyarlanabilir yapı öğrenimi ile öznitelik seçimi yönteminin karar ağaçları yöntemi ile beraber kullanılması ile %91,4 değerinde başarıma ulaşılmıştır.

Intracardiac ECG pulse localization using overlapping block sparse reconstruction

The processing and analysis of multichannel signals which exhibit some synchronicity is of critical importance in biomedical signal processing. Though sparse reconstruction of such signals is well known, penalties enforcing both sparsity and partial synchronicity between channels have been less investigated. In this paper, we present an algorithm based on overlapping grouped LASSO to guarantee both sparsity and synchronicity for multichannel signals. We show that the proposed method can be implemented efficiently, using consensus learning approaches and recent work of the authors for accelerating the related optimization procedure. Results on synthetic data show the efficiency of the proposed approach. When applied on real intracardiac recordings, the proposed method succeeds in automatically detecting electrical pulses both for sinus rhythm and atrial fibrillation episodes.

Hardware Inspired Neural Network for Efficient Time-Resolved Biomedical Imaging.

Convolutional neural networks (CNN) have revealed exceptional performance for fluorescence lifetime imaging (FLIM). However, redundant parameters and complicated topologies make it challenging to implement such networks on embedded hardware to achieve real-time processing. We report a lightweight, quantized neural architecture that can offer fast FLIM imaging. The forward-propagation is significantly simplified by replacing matrix multiplications in each convolution layer with additions and data quantization using a low bit-width. We first used synthetic 3-D lifetime data with given lifetime ranges and photon counts to assure correct average lifetimes can be obtained. Afterwards, human prostatic cancer cells incubated with gold nanoprobes were utilized to validate the feasibility of the network for real-world data. The quantized network yielded a 37.8% compression ratio without performance degradation. Clinical relevance - This neural network can be applied to diagnose cancer early based on fluorescence lifetime in a non-invasive way. This approach brings high accuracy and accelerates diagnostic processes for clinicians who are not experts in biomedical signal processing.

CNN-based Two Step R Peak Detection Method: Combining Segmentation and Regression.

For semantic segmentation, U-Net provides an end-to-end trainable framework to detect multiple class objects from background. Due to its great achievements in computer vision tasks, U-Net has broadened its application to biomedical signal processing, especially, segmentation of waveforms in ECG signal. Despite its superior performance for QRS complex detection to other traditional signal processing methods, direct application of the U-Net to R peak detection has limitation since the U-Net structures tend to predict high probability around true peak. Such multiple detection results require additional process to determine a unique peak location in each QRS complex. In this study, we use a regression process to detect R peak instead of pixel-wise classification. Such regression process guarantees a unique peak location prediction. We collect data from resting ECG systems and wearable ECG devices as well as public ECG databases and the proposed model is trained on various combinations of the data sources. Especially, we investigate the robustness of the model for input data from the wearable devices when the model is trained by data from heterogeneous devices.

A computer‐aided educational device and toolbox for biomedical signal processing at the undergraduate level

AbstractEngineering education requires both a theoretical and practical basis; some aspects are better understood through practical examples. Providing practical experience in biomedical engineering is of great importance in terms of understanding concepts and assisting the retention of learning. Hands‐on experience can be particularly beneficial in supporting the theoretical explanation of the acquisition, processing, and displaying of biomedical signals. This study has developed an expansion board that can be plugged into Raspberry Pi boards to capture electroencephalography (EEG), electrooculography (EOG), electrocardiography (ECG), and electromyography (EMG) biomedical signals with a single‐channel amplifier circuit. A toolbox has been written in the Python programming language to; capture, process, filter, apply fast fourier transform, and display these signals. The device and laboratory applications were introduced in the curriculum of a final year module, “Introduction to Biomedical Engineering” in the Department of Electrical and Electronics Engineering at Gazi University. The pedagogical value of the application was assessed by administering a questionnaire to the students. Results show the use of measurement and display of biomedical signals increased the curiosity and motivation of the students in Biomedical Engineering.

Field programmable gate arrays implementation of different standard deviation estimation techniques

Additive white Gaussian noise level estimation has found its application in many fields such as biomedical signal processing, communication system, and image processing. Many methods have been proposed with different output accuracy, system complexity, power consumption, and speed. In this paper, three of the most well-known and largely used algorithms (median based, root mean square (RMS) based, and P84 based methods) have been implemented and investigated in a full comparison between them to find their advantage and disadvantage, and the suitability of each method for a specific application. The three designs are created using Xilinx system generator (XSG) and implemented on Xilinx field programmable gate arrays (FPGA) development board with Zynq series "XC7Z020-1CLG484", to evaluate the design's performance and the results are discussed in the paper.

Using biomedical signals with the help of fragmentary-wavelets on digital processing

This article is devoted to rebuilt for an important fragmentary of wavelet models of Biomedical Signal Processing. These models were built using Haar’s fragmentary-unchanged wavelets as well as Doubechi wavelets. The Haar’s fragmentary-unchanged wavelets models has a high accuracy for Biomedical signals on digital work, and this provides doctors for making any useful decisions about the patients diseases. For example, the first signal of Gastroenterology experimental information was took, and there were built on the basis of this information the of fragmentary-unchanged and Doubechi wavelet models and evaluated their errors. It is known that modification of signals using fragmentary wavelets results in formation of orthonormal wavelets, due to there will be sharp increase in errors along the signal graph, thus in order to reduce errors Doubechi wavelets were used and achieved the goal.

Using biomedical signals with the help of fragmentary-wavelets on digital processing

This article is devoted to rebuilt for an important fragmentary of wavelet models of Biomedical Signal Processing. These models were built using Haar’s fragmentary-unchanged wavelets as well as Doubechi wavelets. The Haar’s fragmentary-unchanged wavelets models has a high accuracy for Biomedical signals on digital work, and this provides doctors for making any useful decisions about the patients diseases. For example, the first signal of Gastroenterology experimental information was took, and there were built on the basis of this information the of fragmentary-unchanged and Doubechi wavelet models and evaluated their errors. It is known that modification of signals using fragmentary wavelets results in formation of orthonormal wavelets, due to there will be sharp increase in errors along the signal graph, thus in order to reduce errors Doubechi wavelets were used and achieved the goal.

Robust Identification of the QRS-Complexes in Electrocardiogram Signals Using Ramanujan Filter Bank-Based Periodicity Estimation Technique

Plausibly, the first computerized and automated electrocardiogram (ECG) signal processing algorithm was published in the literature in 1961, and since then, the number of algorithms that have been developed to-date for the detection of the QRS-complexes in ECG signals is countless. Both the digital signal processing and artificial intelligence-based techniques have been tested rigorously in many applications to achieve a high accuracy of the detection of the QRS-complexes in ECG signals. However, since the ECG signals are quasi-periodic in nature, a periodicity analysis-based technique would be an apt approach for the detection its QRS-complexes. Ramanujan filter bank (RFB)-based periodicity estimation technique is used in this research for the identification of the QRS-complexes in ECG signals. An added advantage of the proposed algorithm is that, at the instant of detection of a QRS-complex the algorithm can efficiently indicate whether it is a normal or a premature ventricular contraction or an atrial premature contraction QRS-complex. First, the ECG signal is preprocessed using Butterworth low and highpass filters followed by amplitude normalization. The normalized signal is then passed through a set of Ramanujan filters. Filtered signals from all the filters in the bank are then summed up to obtain a holistic time-domain representation of the ECG signal. Next, a Gaussian-weighted moving average filter is used to smooth the time-period-estimation data. Finally, the QRS-complexes are detected from the smoothed data using a peak-detection-based technique, and the abnormal ones are identified using a period thresholding-based technique. Performance of the proposed algorithm is tested on nine ECG databases (totaling a duration of 48.91 days) and is found to be highly competent compared to that of the state-of-the-art algorithms. To the best of our knowledge, such an RFB-based QRS-complex detection algorithm is reported here for the first time. The proposed algorithm can be adapted for the detection of other ECG waves, and also for the processing of other biomedical signals which exhibit periodic or quasi-periodic nature.

A Unified FPGA Realization for Fractional-Order Integrator and Differentiator

This paper proposes a generic FPGA realization of an IP core for fractional-order integration and differentiation based on the Grünwald–Letnikov approximation. All fractional-order dependent terms are approximated to simpler relations using curve fitting to enable an efficient hardware realization. Compared to previous works, the proposed design introduces enhancements in the fractional-order range covering both integration and differentiation. An error analysis between software and hardware results is presented for sine, triangle and sawtooth signals. The proposed generic design is realized on XC7A100T FPGA achieving frequency of 9.328 MHz and validated experimentally for a sine input signal on the oscilloscope. The proposed unified generic design is suitable for biomedical signal processing applications. In addition, it can be employed as a laboratory tool for fractional calculus education.

AppAxO : Designing App lication-specific A ppro x imate O perators for FPGA-based Embedded Systems

Approximate arithmetic operators, such as adders and multipliers, are increasingly used to satisfy the energy and performance requirements of resource-constrained embedded systems. However, most of the available approximate operators have an application-agnostic design methodology, and the efficacy of these operators can only be evaluated by employing them in the applications. Furthermore, the various available libraries of approximate operators do not share any standard approximation-induction policy to design new operators according to an application’s accuracy and performance constraints. These limitations also hinder the utilization of machine learning models to explore and determine approximate operators according to an application’s requirements. In this work, we present a generic design methodology for implementing FPGA-based application-specific approximate arithmetic operators. Our proposed technique utilizes lookup tables and carry-chains of FPGAs to implement approximate operators according to the input configurations. For instance, for an \( \text{M}\times \text{N} \) accurate multiplier utilizing K lookup tables, our methodology utilizes K -bit configurations to design \( 2^K \) approximate multipliers. We then utilize various machine learning models to evaluate and select configurations satisfying application accuracy and performance constraints. We have evaluated our proposed methodology for three benchmark applications, i.e., biomedical signal processing, image processing, and ANNs. We report more non-dominated approximate multipliers with better hypervolume contribution than state-of-the-art designs for these benchmark applications with the proposed design methodology.