Single-channel Signal Research Articles

Prediction of Increased Intracranial Pressure in Traumatic Brain Injury Using Quantitative Electroencephalogram in a Porcine Experimental Model.

Continuous and non-invasive measurement of intracranial pressure (ICP) in traumatic brain injury (TBI) is important to recognize increased ICP (IICP), which can reduce treatment delays. The purpose of this study was to develop an electroencephalogram (EEG)-based prediction model for IICP in a porcine TBI model. Thirty swine were anaesthetized and underwent IICP by inflating a Foley catheter in the intracranial space. Single-channel EEG data were collected every 6 min in 10 mmHg increments in the ICP from baseline to 50 mmHg. We developed EEG-based models to predict the IICP (equal or over 25 mmHg) using four algorithms: logistic regression (LR), naive Bayes (NB), support vector machine (SVM), and random forest (RF). We assessed the performance of each model based on the accuracy, sensitivity, specificity, and AUC values. The accuracy of each prediction model for IICP was 0.773 for SVM, 0.749 for NB, 0.746 for RF, and 0.706 for LR. The AUC of each model was 0.860 for SVM, 0.824 for NB, 0.802 for RF, and 0.748 for LR. We developed a machine learning prediction model for IICP using single-channel EEG signals in a swine TBI experimental model. The SVM model showed good predictive power with the highest AUC value.

An Automatic ECG Signal Quality Assessment Method Based on Resnet and Self-Attention

Electrocardiogram (ECG) signals are among the significant physiological signals that indicate the essential properties of the human body. In recent years, the measurement of ECG signals has become more portable thanks to the increasing usage of wearable health testing technology. However, the enormous amount of signal data gathered over a long period of time does impose a heavy load on medical professionals. In addition, false alarms might occur due to the potential for the detected signal to become jumbled with noise and motion perturbations. Therefore, analyzing the quality of the measured raw ECG signal automatically is a valuable task. In this paper, we propose a new single-channel ECG signal quality assessment method that combines the Resnet network structure and the principle of self-attention to extract ECG signal features using the principle of similarity between individual QRS heartbeats within a time slice of ten seconds. In addition, an improved self-attention module is introduced into the deep neural network to learn the similarity between features. Finally, the network distinguishes between acceptable and unacceptable ECG segments. The model test results indicate that the F1-score can approach 0.954, which leads to a more accurate assessment of the ECG signal quality.

Sparse Multichannel Decomposition of Electrodermal Activity With Physiological Priors.

Goal: Inferring autonomous nervous system (ANS) activity is a challenging issue and has critical applications in stress regulation. Sweat secretions caused by ANS activity influence the electrical conductance of the skin. Therefore, the variations in skin conductance (SC) measurements reflect the sudomotor nerve activity (SMNA) and can be used to infer the underlying ANS activity. These variations are strongly correlated with emotional arousal as well as thermoregulation. However, accurately recovering ANS activity and the corresponding state-space system from a single channel signal is difficult due to artifacts introduced by measurement noise. To minimize the impact of noise on inferring ANS activity, we utilize multiple channels of SC data. Methods: We model skin conductance using a second-order differential equation incorporating a time-shifted sparse impulse train input in combination with independent cubic basis spline functions. Finally, we develop a block coordinate descent method for SC signal decomposition by employing a generalized cross-validation sparse recovery approach while including physiological priors. Results: We analyze the experimental data to validate the performance of the proposed algorithm. We demonstrate its capacity to recover the ANS activations, the underlying physiological system parameters, and both tonic and phasic components. Finally, we present an overview of the algorithm's comparative performance under varying conditions and configurations to substantiate its ability to accurately model ANS activity. Our results show that our algorithm performs better in terms of multiple metrics like noise performance, AUC score, the goodness of fit of reconstructed signal, and lower missing impulses compared with the single channel decomposition approach. Conclusion: In this study, we highlight the challenges and benefits of concurrent decomposition and deconvolution of multichannel SC signals.

EEG Signal Epilepsy Detection with a Weighted Neighbour Graph Representation and Two-stream Graph-based Framework.

Epilepsy is one of the most common neurological diseases. Clinically, epileptic seizure detection is usually performed by analyzing electroencephalography (EEG) signals. At present, deep learning models have been widely used for single-channel EEG signal epilepsy detection, but this method is difficult to explain the classification results. Researchers have attempted to solve interpretive problems by combining graph representation of EEG signals with graph neural network models. Recently, the combination of graph representations and graph neural network (GNN) models has been increasingly applied to single-channel epilepsy detection. By this methodology, the raw EEG signal is transformed to its graph representation, and a GNN model is used to learn latent features and classify whether the data indicates an epileptic seizure episode. However, existing methods are faced with two major challenges. First, existing graph representations tend to have high time complexity as they generally require each vertex to traverse all other vertices to construct a graph structure. Some of them also have high space complexity for being dense. Second, while separate graph representations can be derived from a single-channel EEG signal in both time and frequency domains, existing GNN models for epilepsy detection can learn from a single graph representation, which makes it hard to let the information from the two domains complement each other. For addressing these challenges, we propose a Weighted Neighbour Graph (WNG) representation for EEG signals. Reducing the redundant edges of the existing graph, WNG can be both time and space-efficient, and as informative as its less efficient counterparts. We then propose a two-stream graph-based framework to simultaneously learn features from WNG in both time and frequency domain. Extensive experiments demonstrate the effectiveness and efficiency of the proposed methods.

Enhancing Performance of Single-Channel SSVEP-Based Visual Acuity Assessment via Mode Decomposition.

This study aimed to improve the performance of single-channel steady-state visual evoked potential (SSVEP)-based visual acuity assessment by mode decomposition methods. Using the SSVEP dataset induced by the vertical sinusoidal gratings at six spatial frequency steps from 11 subjects, 3-40-Hz band-pass filtering and other four mode decomposition methods, i.e., empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN), and variational mode decomposition (VMD), were used to preprocess the single-channel SSVEP signals from Oz electrode. After comparing the SSVEP signal characteristics corresponding to each mode decomposition method, the visual acuity threshold estimation criterion was used to obtain the final visual acuity results. The agreement between subjective Freiburg Visual Acuity and Contrast Test (FrACT) and SSVEP visual acuity for band-pass filtering (-0.095 logMAR), EMD (-0.112 logMAR), EEMD (-0.098 logMAR), ICEEMDAN (-0.093 logMAR), and VMD (-0.090 logMAR) was all pretty good, with an acceptable difference between FrACT and SSVEP acuity for band-pass filtering (0.129 logMAR), EMD (0.083 logMAR), EEMD (0.120 logMAR), ICEEMDAN (0.103 logMAR), and VMD (0.108 logMAR), finding that the visual acuity obtained by these four mode decompositions had a lower limit of agreement and a lower or close difference compared to the traditional band-pass filtering method. This study proved that the mode decomposition methods can enhance the performance of single-channel SSVEP-based visual acuity assessment, and also recommended ICEEEMDAN as the mode decomposition method for single-channel electroencephalography (EEG) signal denoising in the SSVEP visual acuity assessment.

Single-Channel sEMG-Based Estimation of Knee Joint Angle Using a Decomposition Algorithm With a State-Space Model.

Accurate human motion estimation is crucial for effective and safe human-robot interaction when using robotic devices for rehabilitation or performance enhancement. Although surface electromyography (sEMG) signals have been widely used to estimate human movements, conventional sEMG-based methods, which need sEMG signals measured from multiple relevant muscles, are usually subject to some limitations, including interference between sEMG sensors and wearable robots/environment, complicated calibration, as well as discomfort during long-term routine use. Few methods have been proposed to deal with these limitations by using single-channel sEMG (i.e., reducing the sEMG sensors as much as possible). The main challenge for developing single-channel sEMG-based estimation methods is that high estimation accuracy is difficult to be guaranteed. To address this problem, we proposed an sEMG-driven state-space model combined with an sEMG decomposition algorithm to improve the accuracy of knee joint movement estimation based on single-channel sEMG signals measured from gastrocnemius. The effectiveness of the method was evaluated via both single- and multi-speed walking experiments with seven and four healthy subjects, respectively. The results showed that the normal root-mean-squared error of the estimated knee joint angle using the method could be limited to 15%. Moreover, this method is robust with respect to variations in walking speeds. The estimation performance of this method was basically comparable to that of state-of-the-art studies using multi-channel sEMG.

Extracting Multi-Scale and Salient Features by MSE Based U-Structure and CBAM for Sleep Staging.

According to the World Health Organization, more and more people in the world are suffering from somnipathy. Automatic sleep staging is critical for assessing sleep quality and assisting in the diagnosis of psychiatric and neurological disorders caused by somnipathy. Many researchers employ deep learning methods for sleep stage classification and have achieved high performance. However, there are still no effective methods to modeling intrinsic characteristics of salient wave in different sleep stages from physiological signals. And transition rules hidden in signals from one to another sleep stage cannot be identified and captured. In addition, class imbalance problem in dataset is not conducive to building a robust classification model. To solve these problems, we construct a deep neural network combining MSE(Multi-Scale Extraction) based U-structure and CBAM (Convolutional Block Attention Module) to extract the multi-scale salient waves from single-channel EEG signals. The U-structured convolutional network with MSE is utilized to extract multi-scale features from raw EEG signals. After that, the CBAM is used to focus more on salient variation and then learn transition rules between successive sleep stages. Further, a class adaptive weight cross entropy loss function is proposed to solve the class imbalance problem. Experiments in three public datasets show that our model greatly outperform the state-of-the-art results compared with existing methods. The overall accuracy and macro F1-score (Sleep-EDF-39: 90.3%-86.2, Sleep-EDF-153: 89.7%-85.2, SHHS: 86.8%-83.5) on three public datasets suggest that the proposed model is very promising to completely take place of human experts for sleep staging.

Self-Supervised Representation Learning-Based OSA Detection Method Using Single-Channel ECG Signals

Sleep apnea(SA) is a pervasive and highly prevalent sleep disorder identified by recurrent breathing-related problems such as respiratory pauses for almost 10 seconds (called apnea events) during sleep. It is a strongly underdiagnosed problem because the person suffering from this disease is not aware of this situation. It may cause serious health issues and badly affect the quality of life. Therefore, the diagnosis of sleep is crucial to cure disease. Polysomnography(PSG) is a golden technique for diagnosing sleep disorders. In this technique, multiple sensors are used to collect specific physiological signals like Electroencephalogram(EEG), Electromyogram(EMG), electrooculogram(EOG), and many more. In regular clinical practice, medical experts need to manually analyze the signals of sleep hours which is a tedious process. Therefore, the automatic diagnosis tool is needed to simplify this process. Recently, many research groups have proposed deep-learning models for the automatic diagnosis of sleep apnea using physiological signals with good accuracy. However, all these models require a large amount of annotated data in the supervised training process, which limits the use of those models in real-time scenarios. However, annotating a huge amount of biomedical signals is challenging and requires lots of time and domain expertise. This study proposes a self-supervised representation learning method for detecting hypopnea events from single channel ECG signals. The proposed model is trained in two phases. In the first training phase, an encoder is trained to learn signal representation from the unlabeled data. In the second training phase, the classifier and the encoder are finetuned for the classification. Our proposed model performed well on the test data set with a per-segment classification accuracy of 85%, 89% and 92% by using only 1%, 10%, and 100% of training data with labels, respectively, for fine-tuning encoder along with the classifier. Also, our proposed model can identify a person suffering from the OSA with the accuracy of 100%, even when the encoder and classifier are fine-tuned using only 1% of training data with the label. The proposed model outperformed the state-of-the-art techniques and can be implemented offline or online for rapid and accurate diagnosis of the problem.

Prediction of Biceps Muscle Electromyogram Signal Using a NARX Neural Network.

This study was conducted to compare the response between the results of experimental data and the results achieved by the NARX neural network model to predict the electromyogram (EMG) signal on the biceps muscle in nonlinear stimulation conditions as a new stimulation model. This model is applied to design the controllers based on functional electrical stimulation (FES). To this end, the study was conducted in five stages, including skin preparation, placement of recording and stimulation electrodes, along with the position of the person to apply the stimulation signal and recording EMG, stimulation and recording of single-channel EMG signal, signal preprocessing, and training and validation of the NARX neural network. The electrical stimulation applied in this study is based on a chaotic equation derived from the Rossler equation and on the musculocutaneous nerve, and the response to this stimulation, i.e., the EMG signal, is from the biceps muscle as a single channel. The NARX neural network was trained, along with the stimulation signal and the response of each stimulation for 100 recorded signals from 10 individuals, and then validated and retested for trained data and new data after processing and synchronizing both signals. The results indicate that the Rossler equation can create nonlinear and unpredictable conditions for the muscle, and we also can predict the EMG signal with the NARX neural network as a predictive model. The proposed model appears to be a good method to predict control models based on FES and to diagnose some diseases.

EEG Signal Classification Automation using Novel Modified Random Forest Approach

Digitalization and automation are the two aspects in the medical industry that define compliance with industry 4.0. Automation is essential for speeding up the diagnosis process, while digitalization leads to smart medicine and efficient diagnosis. Epilepsy is one such disease that can use these automation techniques. The automatic monitoring of epilepsy EEG is of great significance in clinical medicine. Aiming at the non-stationary characteristics of EEG signals, the classification of EEG signals is based on the combination of overall empirical mode. It is proposed using the random forest method. The EEG signal data set has an epileptic interval over 200 single-channel signals with a seizure period. A total of 819,400 data are used as samples. First, the overall epileptic EEG signal modal is decomposed into multiple intrinsic modal functions. The effective features are extracted from the first-order intrinsic modal function. Finally, random forest and Least Square SVM (LS-SVM) are considered to classify the EEG signals characteristics. The correct recognition rate of random forest and LS-SVM is compared. The results show that random forest classification method has an ideal classification effect on epilepsy EEG signals during and between seizures. The recognition accuracy is 99% and 60%, which is higher than the accuracy of the LS-SVM. The proposed method improves clinical epilepsy. The efficiency of EEG signals analysis.

Research on Leakage Detection at the Joints of Diaphragm Walls of Foundation Pits Based on Ground Penetrating Radar

It is significant to monitor the leakage at the joints of the diaphragm walls of subway station foundation pits to check the weak links in the waterproof quality of the diaphragm wall structure. It is essential to take effective waterproof measurements timely to improve the overall waterproof quality of the diaphragm wall in the foundation pit to prevent accidents and reduce the operation and maintenance costs. This paper used ground penetrating radar (GPR) to detect the Lishan North Road Station section of Jinan Rail Transit Line R2 during construction. The abnormal waveform image is obtained after processing radar detection data with Reflexw software. This abnormal waveform image is used to identify the abnormal area. In order to accurately predict the location of leakage at the joint of diaphragm wall, MATLAB is used to calculate the average wave velocity amplitude and single channel signal of the electromagnetic wave velocity of geological radar at different mileages and draw the trend chart of average wave velocity amplitude with mileage and the corresponding relationship curve of electromagnetic wave amplitude and depth of radar. It is proposed that sudden changes in the area of the average wave velocity amplitude cause a change in the trend chart. Furthermore, the radar electromagnetic wave velocity amplitude curve is taken as the area where seepage may occur at the joints of the diaphragm wall, so as to determine the corresponding mileage and depth of the leakage area. On this basis, the grey correlation analysis for the analysis of the source of the water leakage at the joints of the diaphragm wall of the subway foundation pit is proposed. The research results show that the leakage water at the joints of the diaphragm wall of the subway foundation pit is not connected to the rivers around the foundation pit, which confirms that the construction of the subway station has not affected the groundwater resources around the station. The proposed approach has successfully predicted the location of the foundation pit leakage disaster and has been verified on the project site. The research results provide a reference for the monitoring and early warning of leakage at the joints of diaphragm walls in foundation pits with similar geological conditions.

Automatic Sleep Staging Based on Single-Channel EEG Signal Using Null Space Pursuit Decomposition Algorithm

Sleep quality is related to people’s physical and mental health, so an accurate assessment of sleep quality is key to recognizing sleep disorders and taking effective interventions. To address the shortcomings of traditional manual and automatic staging methods, such as being time-consuming and having low classification accuracy, an automatic sleep staging method based on the null space pursuit (NSP) decomposition algorithm of single-channel electroencephalographic (EEG) signals is proposed, which provides a new way for EEG signal decomposition and automatic identification of sleep stages. First, the single-channel EEG signal data from the Sleep-EDF database, DREAMS Subject database, and Sleep Heart Health Study database (SHHS), available on PhysioNet, were preprocessed, respectively. Second, the preprocessed single-channel EEG signals were decomposed by the NSP algorithm. Third, we extracted nine features in the time domain of the nonlinear dynamics and statistics from the original EEG signal and the six simple signals that were decomposed. Finally, the extreme gradient boosting (XGBOOST) algorithm was used to construct a classification model to classify and identify the 63 extracted EEG signal features for automatic sleep staging. The experimental results showed that, on the Sleep-EDF database, the accuracy of four and five categories were 93.59% and 92.89%, respectively; on the DREAMS Subject database, the accuracy rates of four and five categories were 91.32% and 90.01%, respectively; on the SHHS database, the accuracy rates of four and five categories were 90.25% and 88.37%, respectively. The experimental results show that the automatic sleep staging model proposed in this work has high classification accuracy and efficiency, as well as strong applicability and robustness.

Single-channel electroencephalogram signal used for sleep state recognition based on one-dimensional width kernel convolutional neural networks and long-short-term memory networks

Aiming at the problem that the unbalanced distribution of data in sleep electroencephalogram(EEG) signals and poor comfort in the process of polysomnography information collection will reduce the model's classification ability, this paper proposed a sleep state recognition method using single-channel EEG signals (WKCNN-LSTM) based on one-dimensional width kernel convolutional neural networks(WKCNN) and long-short-term memory networks (LSTM). Firstly, the wavelet denoising and synthetic minority over-sampling technique-Tomek link (SMOTE-Tomek) algorithm were used to preprocess the original sleep EEG signals. Secondly, one-dimensional sleep EEG signals were used as the input of the model, and WKCNN was used to extract frequency-domain features and suppress high-frequency noise. Then, the LSTM layer was used to learn the time-domain features. Finally, normalized exponential function was used on the full connection layer to realize sleep state. The experimental results showed that the classification accuracy of the one-dimensional WKCNN-LSTM model was 91.80% in this paper, which was better than that of similar studies in recent years, and the model had good generalization ability. This study improved classification accuracy of single-channel sleep EEG signals that can be easily utilized in portable sleep monitoring devices.

MLMRS-Net: Electroencephalography (EEG) motion artifacts removal using a multi-layer multi-resolution spatially pooled 1D signal reconstruction network

Electroencephalogram (EEG) signals suffer substantially from motion artifacts when recorded in ambulatory settings utilizing wearable sensors. Because the diagnosis of many neurological diseases is heavily reliant on clean EEG data, it is critical to eliminate motion artifacts from motion-corrupted EEG signals using reliable and robust algorithms. Although a few deep learning-based models have been proposed for the removal of ocular, muscle, and cardiac artifacts from EEG data to the best of our knowledge, there is no attempt has been made in removing motion artifacts from motion-corrupted EEG signals: In this paper, a novel 1D convolutional neural network (CNN) called multi-layer multi-resolution spatially pooled (MLMRS) network for signal reconstruction is proposed for EEG motion artifact removal. The performance of the proposed model was compared with ten other 1D CNN models: FPN, LinkNet, UNet, UNet+, UNetPP, UNet3+, AttentionUNet, MultiResUNet, DenseInceptionUNet, and AttentionUNet++ in removing motion artifacts from motion-contaminated single-channel EEG signal. All the eleven deep CNN models are trained and tested using a single-channel benchmark EEG dataset containing 23 sets of motion-corrupted and reference ground truth EEG signals from PhysioNet. Leave-one-out cross-validation method was used in this work. The performance of the deep learning models is measured using three well-known performance matrices viz. mean absolute error (MAE)-based construction error, the difference in the signal-to-noise ratio (ΔSNR), and percentage reduction in motion artifacts (η). The proposed MLMRS-Net model has shown the best denoising performance, producing an average ΔSNR, η, and MAE values of 26.64 dB, 90.52%, and 0.056, respectively, for all 23 sets of EEG recordings. The results reported using the proposed model outperformed all the existing state-of-the-art techniques in terms of average η improvement.

Fast Sleep Stage Classification Using Cascaded Support Vector Machines with Single-Channel EEG Signals.

Long-term sleep stage monitoring is very important for the diagnosis and treatment of insomnia. With the development of wearable electroencephalogram (EEG) devices, we developed a fast and accurate sleep stage classification method in this study with single-channel EEG signals for practical applications. The original sleep recordings were collected from the Sleep-EDF database. The wavelet threshold denoising (WTD) method and wavelet packet transformation (WPT) method were applied as signal preprocessing to extract six kinds of characteristic waves. With a comprehensive feature system including time, frequency, and nonlinear dynamics, we obtained the sleep stage classification results with different Support Vector Machine (SVM) models. We proposed a novel classification method based on cascaded SVM models with various features extracted from denoised EEG signals. To enhance the accuracy and generalization performance of this method, nonlinear dynamics features were taken into consideration. With nonlinear dynamics features included, the average classification accuracy was up to 88.11% using this method. In addition, with cascaded SVM models, the classification accuracy of the non-rapid eye movement sleep stage 1 (N1) was enhanced from 41.5% to 55.65% compared with the single SVM model, and the overall classification time for each epoch was less than 1.7 s. Moreover, we demonstrated that it was possible to apply this method for long-term sleep stage monitor applications.

Separating Inhibitory and Excitatory Responses of Epileptic Brain to Single-Pulse Electrical Stimulation.

To enable an accurate recognition of neuronal excitability in an epileptic brain for modeling or localization of epileptic zone, here the brain response to single-pulse electrical stimulation (SPES) has been decomposed into its constituent components using adaptive singular spectrum analysis (SSA). Given the response at neuronal level, these components are expected to be the inhibitory and excitatory components. The prime objective is to thoroughly investigate the nature of delayed responses (elicited between 100[Formula: see text]ms-1 s after SPES) for localization of the epileptic zone. SSA is a powerful subspace signal analysis method for separation of single channel signals into their constituent uncorrelated components. The consistency in the results for both early and delayed brain responses verifies the usability of the approach.

Single-Channel Blind Signal Separation of the MHD Linear Vibration Sensor Based on Singular Spectrum Analysis and Fast Independent Component Analysis.

An MHD vibration sensor, as a new type of sensor used for vibration measurements, meets the technical requirements for the low-noisy measurement of acceleration, velocity, and micro-vibration in spacecraft during their development, launch, and orbit operations. A linear vibration sensor with a runway type based on MHD was independently developed by a laboratory. In a practical test, its output signal was mixed with a large amount of noise, in which the continuous narrowband interference was particularly prominent, resulting in the inability to efficiently carry out the real-time detection of micro-vibration. Considering the high interference of narrowband noise in linear vibration signals, a single-channel blind signal separation method based on SSA and FastICA is proposed in this study, which provides a new strategy for linear vibration signals. Firstly, the singular spectrum of the linear vibration signal with noise was analyzed to suppress the narrowband interference in the collected signal. Then, a FastICA algorithm was used to separate the independent signal source. The experimental results show that the proposed method can effectively separate the useful linear vibration signals from the collected signals with low SNR, which is suitable for the separation of the MHD linear vibration sensor and other vibration measurement sensors. Compared with EEMD, VMD, and wavelet threshold denoising, the SNR of the separated signal is increased by 10 times on average. Through the verification of the actual acquisition of the linear vibration signal, this method has a good denoising effect.

Detection of active segments of lower limbs EMG signal based on time-domain variance combined with short-term energy

Using EMG signal to realize gesture recognition is a technical difficulty in the application of EMG signal. In order to solve this problem and ensure the accuracy and timeliness of action classification and recognition, it is proposed to use time-domain variance combined with short-term energy to set a double threshold algorithm to detect effective activity segments. Based on the short-term energy and the zero-crossing rate, the minimum energy threshold and the frame window data variance value are designed. Then the original signal is processed by frame length and frameshift, and the complete signal data is divided into several small Windows. Finally, the effective activity segment is intercepted after comparing the upper and lower limits of the time-domain feature extraction variance with the set threshold. The experimental results show that the algorithm is effective in realizing the detection and interception of the start and end points of actions when processing single-channel or multi-channel EMG signals.

A Dual Attention-Based Autoencoder Model for Fetal ECG Extraction From Abdominal Signals

Fetal electrocardiogram (FECG) signals contain important information about the conditions of the fetus during pregnancy. Currently, pure FECG signals can only be obtained through an invasive acquisition process, which is life threatening to both mother and fetus. In this study, single-channel ECG signals from the mother’s abdomen are analyzed with the aim of extracting the clean FECG waveform. This is a challenging task due to the very low amplitude of the FECG, various noises involved in the signal acquisition, and the overlap of R waves. To address this problem, we propose a novel convolutional autoencoder (AE) network architecture to learn and extract the FECG patterns. The proposed model is equipped with a dual attention mechanism, composed of squeeze-and-excitation and channel-wise (CW) modules, in the encoder and decoder blocks, respectively. It also benefits from a bidirectional long short-term memory (LSTM) layer. This unique combination allows the proposed network to accurately attend to and extract the FECG signals from abdominal data. Three well-established datasets are considered in our experiments. The obtained results of FECG extraction are promising and confirm the effectiveness of using attention modules within the deep learning model. The results also suggest that the proposed AE network can accurately extract the FECG signals where no information about maternal ECG (MECG) is available.

MRASleepNet: a multi-resolution attention network for sleep stage classification using single-channel EEG

Objective. Computerized classification of sleep stages based on single-lead electroencephalography (EEG) signals is important, but still challenging. In this paper, we proposed a deep neural network called MRASleepNet for automatic sleep stage classification using single-channel EEG signals. Approach. The proposed MRASleepNet model consisted of a feature extraction (FE) module, a multi-resolution attention (MRA) module, and a gated multilayer perceptron (gMLP) module, as well as a direct pathway for computing statistical features. The FE, MRA, and gMLP modules were used to extract features, establish feature attention, and obtain temporal relationships between features, respectively. EEG signals were normalized and cut into 30 s segments, and enhanced by incorporating contextual information from adjacent data segments. After data enhancement, the 40 s data segments were input to the MRASleepNet model. The model was evaluated on the SleepEDF and the cyclic alternating pattern (CAP) databases, using such metrics as the accuracy, Kappa, and macro-F1 (MF1). Main results. For the SleepEDF-20 database, the proposed model had an accuracy of 84.5%, an MF1 of 0.789, and a Kappa of 0.786. For the SleepEDF-78 database, the model had an accuracy of 81.4%, an MF1 of 0.754, and a Kappa of 0.743. For the CAP database, the model had an accuracy of 74.3%, an MF1 of 0.656, and a Kappa of 0.652. The proposed model achieved satisfactory performance in automatic sleep stage classification tasks. Significance. The time- and frequency-domain features extracted by the FE module and filtered by the MRA module, together with the temporal features extracted by the gMLP module and the statistical features extracted by the statistical highway, enabled the proposed model to obtain a satisfying performance in sleep staging. The proposed MRASleepNet model may be used as a new deep learning method for automatic sleep stage classification. The code of MRASleepNet will be made available publicly on https://github.com/YuRui8879/.