Classification Of Physiological Signals Research Articles

PSC-Net: Integration of Convolutional Neural Networks and transformers for Physiological Signal Classification

Objective:Physiological signals, such as electrocardiogram (ECG) and wrist pulse signals (WPS), play an important role in diagnosing and preventing cardiovascular and other physiological diseases. Therefore, accurate classification of physiological signals has become the key to assist physicians in diagnosis. However, this field still faces several prominent challenges, including limited availability of data, imbalanced datasets, convergence issues with loss functions, and the need for model architectures capable of accurately detecting waveform patterns. Methods:This study introduces the Physiological Signal Classification Network (PSC-Net), which combines the strengths of Convolutional Neural Networks (CNNs) and transformers for applications in medical artificial intelligence. Specifically, local temporal features are extracted using the GRWA-LSTM network (GLNet) proposed in this paper. Within the transformer, two GRU layers replace the fully-connected layer to enhance global feature extraction for physiological signal data. Residual connection integrates the outputs of GLNet and Transformer through global average pooling and weight settings. To address challenges related to small and imbalanced datasets, we propose an enhanced data augmentation algorithm based on SMOTE Tomek, along with an improved loss function. Additionally, automatic learning rates are optimized using the Dung Beetle Algorithm (DBA). Results:Our proposed method achieves superior accuracies of 83.33%, 100.0%, 95.74%, and 98.85% on four physiological signal datasets (including one clinical dataset): Five Types of Pulses Database, Coronary Heart Disease (CHD) database, MIT-BIH Arrhythmia Database, and MIT-BIH ST Change Database. These results attest to the model’s robust generalization capability and its promising application prospects in assisting diagnoses.

An Improved ConvNeXt with Multimodal Transformer for Physiological Signal Classification

An Improved ConvNeXt with Multimodal Transformer for Physiological Signal Classification

A federated learning and blockchain framework for physiological signal classification based on continual learning

A key challenge of physiological signal processing in the Internet of Medical Things is that physiological signals usually have dynamic distribution changes. Another challenge is that patients' data is vulnerable to disclosures. To address these problems, we propose a meta continual learning method, called MetaCL. MetaCL consists of a shared feature extractor, a knowledge base, a micro classifier module and a blockchain module. The shared feature extractor adopts a horizontal federated learning mechanism to prevent data leakage. The knowledge base is built and updated based on a Splite-based method to overcome catastrophic forgetting. The micro classifier module uses a mean-based model transfer method to adapt to the emergence of new classes. It integrates a Kullback-Leibler divergence regularization to the loss function to deal with fuzzy boundaries of classes. The blockchain module is designed based on the Alliance chain to protect the privacy of the classification results. Experiment results show that refinement classification performance of MetaCL is 98.35%, which outperforms the compared state-of-the-art works. The backward transfer under four increment scenarios is all within -2.6%. At last, a blockchain-based engineering application is presented to show that MetaCL can prevent privacy protection in the Internet of Medical Things (IoMT).

An Ensemble Learning Method for Emotion Charting Using Multimodal Physiological Signals

Emotion charting using multimodal signals has gained great demand for stroke-affected patients, for psychiatrists while examining patients, and for neuromarketing applications. Multimodal signals for emotion charting include electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, and galvanic skin response (GSR) signals. EEG, ECG, and GSR are also known as physiological signals, which can be used for identification of human emotions. Due to the unbiased nature of physiological signals, this field has become a great motivation in recent research as physiological signals are generated autonomously from human central nervous system. Researchers have developed multiple methods for the classification of these signals for emotion detection. However, due to the non-linear nature of these signals and the inclusion of noise, while recording, accurate classification of physiological signals is a challenge for emotion charting. Valence and arousal are two important states for emotion detection; therefore, this paper presents a novel ensemble learning method based on deep learning for the classification of four different emotional states including high valence and high arousal (HVHA), low valence and low arousal (LVLA), high valence and low arousal (HVLA) and low valence high arousal (LVHA). In the proposed method, multimodal signals (EEG, ECG, and GSR) are preprocessed using bandpass filtering and independent components analysis (ICA) for noise removal in EEG signals followed by discrete wavelet transform for time domain to frequency domain conversion. Discrete wavelet transform results in spectrograms of the physiological signal and then features are extracted using stacked autoencoders from those spectrograms. A feature vector is obtained from the bottleneck layer of the autoencoder and is fed to three classifiers SVM (support vector machine), RF (random forest), and LSTM (long short-term memory) followed by majority voting as ensemble classification. The proposed system is trained and tested on the AMIGOS dataset with k-fold cross-validation. The proposed system obtained the highest accuracy of 94.5% and shows improved results of the proposed method compared with other state-of-the-art methods.

Implementation of a sensor node for monitoring and classification of physiological signals in an edge computing system

We describe the design and development of sensor nodes, based on Edge computing technologies, for the processing and classification of events detected in physiological signals such as the electrocardiographic signal (ECG is the electrical signal of the heart), temperature, heart rate, and human movement. The edge device uses a 32-bit Tensilica microcontroller-based module with the ability to transmit data wirelessly using Wi-Fi. In addition, algorithms for classification and detection of movement patterns were implemented to be implemented in devices with limited resources and not only in high-performance computers. The Internet of Things and its application in smart environments can help non-intrusive monitoring of daily activities by implementing support vector machine (SVM is a machine learning algorithm) for implementation in embedded systems with low hardware resources. This paper shows experimental results obtained during the acquisition, transmission, and processing of physiological signals in a edge computing system and their visualization in a web application.

Time\u2013frequency time\u2013space LSTM for robust classification of physiological signals

Automated analysis of physiological time series is utilized for many clinical applications in medicine and life sciences. Long short-term memory (LSTM) is a deep recurrent neural network architecture used for classification of time-series data. Here time–frequency and time–space properties of time series are introduced as a robust tool for LSTM processing of long sequential data in physiology. Based on classification results obtained from two databases of sensor-induced physiological signals, the proposed approach has the potential for (1) achieving very high classification accuracy, (2) saving tremendous time for data learning, and (3) being cost-effective and user-comfortable for clinical trials by reducing multiple wearable sensors for data recording.

SleepPrintNet: A Multivariate Multimodal Neural Network Based on Physiological Time-Series for Automatic Sleep Staging

Sleep is one of the most fundamental physiological activities of human beings. Sleep assessment based on physiological time-series can efficiently assist human experts to diagnose the sleep health of people. However, most of the existing methods only considered one or two kinds of time-domain, frequency-domain, and spatial-domain information from electroencephalogram (EEG). Besides, existing deep learning methods share the feature extraction module of EEG with other modalities, which ignore the discriminative features of electrooculogram (EOG) and electromyography (EMG). Therefore, how to make full use of the complementarity of different features of EEG and capture the discriminative features from other modalities is challenging. To tackle this challenge, we design SleepPrintNet to capture the SleepPrint in physiological time-series, which represents the complementarity among different features of EEG and discriminative features from other modalities in different sleep stages. SleepPrintNet consists of an EEG temporal feature extraction module, an EEG spectral-spatial feature extraction module for the temporal-spectral-spatial representation of EEG signals, and two multimodal feature extraction modules including EOG and EMG feature extraction module. To the best of our knowledge, it is the first attempt to integrate EEG temporal-spectral-spatial as well as the multimodal features simultaneously in a unified model for sleep staging. Experiments on the benchmark dataset MASS-SS3 demonstrate that SleepPrintNet outperforms all baseline models. The implementation code of SleepPrintNet is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/xiyangcai/SleepPrintNet</uri> . <p xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><i>Impact Statement–</i> Sleep staging helps sleep experts assess sleep quality and diagnose sleep health. The polysomnography, which contains the physiological signal recordings during sleep, is a kind of multimodal multivariant physiological time-series for sleep staging. However, existing methods treat physiological time-series from different parts of the body equally, which ignore the abundant information in multimodal signals. The SleepPrintNet proposed in this article has improved the accuracy of sleep staging with the help of the discriminative characteristics from different physiological time-series, which is made up of several independent modules for the extraction of different modalities signals. SleepPrintNet is also a universal framework for the classification of multivariate and multimodal signals. It can be applied in the diagnosis and treatment of other diseases based on physiological signals. The high-accuracy classification of physiological signals has great significance in the field of intelligent medical diagnostics.

Attention Networks for Multi-Task Signal Analysis.

Recent advances in deep learning have enabled the development of automated frameworks for analysing medical images and signals. For analysis of physiological recordings, models based on temporal convolutional networks and recurrent neural networks have demonstrated encouraging results and an ability to capture complex patterns and dependencies in the data. However, representations that capture the entirety of the raw signal are suboptimal as not all portions of the signal are equally important. As such, attention mechanisms are proposed to divert focus to regions of interest, reducing computational cost and enhancing accuracy. Here, we evaluate attention-based frameworks for the classification of physiological signals in different clinical domains. We evaluated our methodology on three classification scenarios: neurogenerative disorders, neurological status and seizure type. We demonstrate that attention networks can outperform traditional deep learning models for sequence modelling by identifying the most relevant attributes of an input signal for decision making. This work highlights the benefits of attention-based models for analysing raw data in the field of biomedical research.

A Wearable Bio-signal Processing System with Ultra-low-power SoC and Collaborative Neural Network Classifier for Low Dimensional Data Communication.

In this paper, a real time physiological signal classification system with an integrated ultra-low power collaborative neural network classifier is presented. The developed system includes a specially designed system-on-chip (SoC) and a wireless communication module that transmits classification results to a smartphone app as a convenient user interface in real-time training. The customized SoC provides ultra-low-power and low-latency sensing and classification on physiological signals, e.g. EMG and ECG. A special collaborative neural network classifier was implemented to allow multiple chips to collaborate on classification. As a result, only low dimensional data is being transmitted over the network, significantly reducing data communication across multiple modules. A demonstration of EMG based gesture classification shows 1100X less power consumption from the developed SoC compared with conventional embedded solutions. The transmission of only low dimensional data from the collaborative neural network classifier leads to a 50X reduction of data communication and associated energy for multiple sensing cites.

P2438Deep learning model for atrial fibrillation detection based on single beat morphology

Abstract Background The electrocardiogram (ECG) is commonly used, but most recent rhythm discrimination algorithms still lack both specificity and sensitivity. Deep learning techniques have shown promising results in the classification of physiological signals like ECGs. Purpose To develop and test a deep learning (DL) model to discriminate between atrial fibrillation (AF) and sinus rhythm (SR). Methods For the development of the DL model we used 1499 ECGs sampled at 500 Hz of patients diagnosed with AF. All ECGs were labeled by two experienced investigators. Only ECGs labeled as SR or AF were included in the dataset. To simplify the learning process, solely the first ECG channel was used. The ECG waveforms were preprocessed using the Fourier cosine series to correct for baseline wander. Input data was generated by normalizing and scaling all different heartbeats by centralizing the R peak, leading to 15744 single heart beat samples of 80 data points (figure A). Multiple feedforward architectures were tested with different numbers of layers, filters and activation functions. The models were trained by equally splitting the data (50%SR, 50%AF) in a training (65%), validation (25%) and test set (15%). The best performing model was chosen based on the accuracy. Results A total of 1469 ECGs (1061 (72%)SR, 408 (28%)AF) were included. The model with the best performance was a feedforward model consisting three dense layers with ReLU activation and four dense layers with Linear activation. Training of the model was performed in 32 epochs. Validation of the model resulted in an accuracy of 96% (figure B), precision of 95% and recall of 96%. Conclusions The morphology based deep learning model developed in this study was able to discriminate atrial fibrillation from sinus rhythm with a fairly high accuracy using a limited size dataset and only one lead.

Classification of Physiological Signals for Emotion Recognition using IoT

Classification of Physiological Signals for Emotion Recognition using IoT

Classification of Physiological Signals for Emotion Recognition using IoT

Classification of Physiological Signals for Emotion Recognition using IoT

Probabilistic grammar-based neuroevolution for physiological signal classification of ventricular tachycardia

Ventricular tachycardia is a rapid heart rhythm that begins in the lower chambers of the heart. When it happens continuously, this may result in life-threatening cardiac arrest. In this paper, we apply deep learning techniques to tackle the problem of the physiological signal classification of ventricular tachycardia, since deep learning techniques can attain outstanding performance in many medical applications. Nevertheless, human engineers are required to manually design deep neural networks to handle different tasks. This can be challenging because of many possible deep neural network structures. Therefore, a method, called ADAG-DNE, is presented to automatically design deep neural network structures using deep neuroevolution. Our approach defines a set of structures using probabilistic grammar and searches for best network structures using Probabilistic Model Building Genetic Programming. ADAG-DNE takes advantages of the probabilistic dependencies found among the structures of networks. When applying ADAG-DNE to the classification problem, our discovered model achieves better accuracy than AlexNet, ResNet, and seven non-neural network classifiers. It also uses about 2% of parameters of AlexNet, which means the inference can be made quickly. To summarize, our method evolves a deep neural network, which can be implemented in expert systems. The deep neural network achieves high accuracy. Moreover, it is simpler than existing deep neural networks. Thus, computational efficiency and diagnosis accuracy of the expert system can be improved.

A comparative study of machine learning algorithms for physiological signal classification

The present work aims at the evaluation of the effectiveness of different machine learning algorithms on a variety of clinical data, derived from small, medium, and large publicly available databases. To this end, several algorithms were tested, and their performance, both in terms of accuracy and time required for the training and testing phases, are here reported. Sometimes a data preprocessing phase was also deemed necessary to improve the performance of the machine learning procedures, in order to reduce the problem size. In such cases a detailed analysis of the compression strategy and results is also presented.

Classification of physiological signals for wheel loader operators using Multi-scale Entropy analysis and case-based reasoning

Sensor signal fusion is becoming increasingly important in many areas including medical diagnosis and classification. Today, clinicians/experts often do the diagnosis of stress, sleepiness and tiredness on the basis of information collected from several physiological sensor signals. Since there are large individual variations when analyzing the sensor measurements and systems with single sensor, they could easily be vulnerable to uncertain noises/interferences in such domain; multiple sensors could provide more robust and reliable decision. Therefore, this paper presents a classification approach i.e. Multivariate Multiscale Entropy Analysis–Case-Based Reasoning (MMSE–CBR) that classifies physiological parameters of wheel loader operators by combining CBR approach with a data level fusion method named Multivariate Multiscale Entropy (MMSE). The MMSE algorithm supports complexity analysis of multivariate biological recordings by aggregating several sensor measurements e.g., Inter-beat-Interval (IBI) and Heart Rate (HR) from Electrocardiogram (ECG), Finger Temperature (FT), Skin Conductance (SC) and Respiration Rate (RR). Here, MMSE has been applied to extract features to formulate a case by fusing a number of physiological signals and the CBR approach is applied to classify the cases by retrieving most similar cases from the case library. Finally, the proposed approach i.e. MMSE–CBR has been evaluated with the data from professional drivers at Volvo Construction Equipment, Sweden. The results demonstrate that the proposed system that fuses information at data level could classify ‘stressed’ and ‘healthy’ subjects 83.33% correctly compare to an expert’s classification. Furthermore, with another data set the achieved accuracy (83.3%) indicates that it could also classify two different conditions ‘adapt’ (training) and ‘sharp’ (real-life driving) for the wheel loader operators. Thus, the new approach of MMSE–CBR could support in classification of operators and may be of interest to researchers developing systems based on information collected from different sensor sources.

Pairwise diversity ranking of polychotomous features for ensemble physiological signal classifiers

It is well known that fusion classifiers for physiological signal classification with diverse components (classifiers or data sets) outperform those with less diverse components. Determining component diversity, therefore, is of the utmost importance in the design of fusion classifiers that are often employed in clinical diagnostic and numerous other pattern recognition problems. In this article, a new pairwise diversity-based ranking strategy is introduced to select a subset of ensemble components, which when combined will be more diverse than any other component subset of the same size. The strategy is unified in the sense that the components can be classifiers or data sets. Moreover, the classifiers and data sets can be polychotomous. Classifier-fusion and data-fusion systems are formulated based on the diversity-based selection strategy, and the application of the two fusion strategies are demonstrated through the classification of multichannel event-related potentials. It is observed that for both classifier and data fusion, the classification accuracy tends to increase/decrease when the diversity of the component ensemble increases/decreases. For the four sets of 14-channel event-related potentials considered, it is shown that data fusion outperforms classifier fusion. Furthermore, it is demonstrated that the combination of data components that yield the best performance, in a relative sense, can be determined through the diversity-based selection strategy.