Physiological Signal Processing Research Articles

HybMED: A Hybrid Neural Network Training Processor with Multi-Sparsity Exploitation for Internet of Medical Things.

Cloud-based training and edge-based inference modes for Artificial Intelligence of Medical Things (AIoMT) applications suffer from accuracy degradation due to physiological signal variations among patients. On-chip learning can overcome this issue by online adaptation of neural network parameters for user-specific tasks. However, existing on-chip learning processors have limitations in terms of versatility, resource utilization, and energy efficiency. We propose HybMED, which is a novel neural signal processor that supports on-chip hybrid neural network training using a composite direct feedback alignment-based paradigm. HybMED is suitable for general-purpose health monitoring AIoMT devices. It improves resource utilization and area efficiency by the reconfigurable homogeneous core with heterogeneous data flow and enhances energy efficiency by exploiting sparsity at different granularities. The chip was fabricated by TSMC 40nm process and tested in multiple physiological signal processing tasks, demonstrating an average improvement in accuracy of 41.16% following online few-shot learning. The chip demonstrates an area efficiency of 1.17 GOPS/mm2 and an energy efficiency of 1.58 TOPS/W. Compared to the previous state-of-the-art physiological signal processors with on-chip learning, the chip achieves a 65× improvement in area efficiency and 1.48× improvement in energy efficiency, respectively.

Effect of Filters in Photoplethysmography Analog Signals Using Open-Source LTspice Software

Analog signal processing plays a crucial role in the realm of biomedical signal analysis. This study investigates the application of analog signal processing techniques in the domain of biomedical signals, focusing on enhancing the quality and reliability of recorded physiological data. The primary emphasis is on the implementation of analog filters and amplifiers to address challenges such as noise reduction, signal conditioning, and overall signal improvement. The processing of physiological signals, such as photoplethysmography (PPG), necessitates the use of amplifiers and filters within a range of 0.4 to 5Hz. Signal noise can stem from various sources, including the test subject’s muscle movement, respiration, humming, power line interference, or even from the device itself. The research methodology involves a comparison of 3 different order of Butterworth filter circuits and their impact on the signal. The test input signal is derived from an SpO$_2$ simulator, read by a standard PPG sensor, and processed by the internal 12-bit ADC of Nucleo-F429ZI. The resulting data is stored in CSV format for subsequent use in filter design simulations with SPICE. For analog circuit designers, the utilization of SPICE in the form of LTspice proves invaluable. This open software, LTspice, boasts a simple yet powerful interface, facilitating a focus on the conceptualization and performance of the design

Editorial: Physiological signal processing for wellness

Editorial: Physiological signal processing for wellness

Environmental enrichments and data-driven welfare indicators for sheltered dogs using telemetric physiological measures and signal processing.

Shelters are stressful environments for domestic dogs which are known to negatively impact their welfare. The introduction of outside stimuli for dogs in this environment can improve their welfare and life conditions. However, our current understanding of the influence of different stimuli on shelter dogs' welfare is limited and the data is still insufficient to draw conclusions. In this study, we collected 28days (four weeks) of telemetry data from eight male dogs housed in an Italian shelter for a long period of time. During this period, three types of enrichment were introduced into the dogs' pens for one week each: entertaining objects, intraspecific, and interspecific social enrichment, by means of the presence of female conspecifics and the presence of a human. To quantify their impact, we introduce novel metrics as indicators of sheltered dogs' welfare based on telemetry data: the variation of heart rate, muscle activity, and body temperature from an average baseline day, quality of sleep, and the regularity for cyclicity of the aforementioned parameters, based on the day-night cycle. Using these metrics, we show that while all three stimuli statistically improve the dogs' welfare, the variance between individual dogs is large. Moreover, our findings indicate that the presence of female conspecific is the best stimulus among the three explored options which improves both the quality of sleep and the parameters' cyclicity. Our results are consistent with previous research findings while providing novel data-driven welfare indicators that promote objectivity. Thus, this research provides some useful guidelines for managing shelters and improving dogs' welfare.

Ultra-Low Power Analog Folded Neural Network for Cardiovascular Health Monitoring.

Wearable sensors are increasingly used for continuous health monitoring, but their small size limits battery capacity, affecting user experience and monitoring capabilities. To overcome this, we introduce an ultra-low power analog Folded Neural Network (FNN) for physiological signal processing in a batteryless fashion. Our proposed FNN, by serializing computation, provides several benefits over traditional analog implementations, such as lower space, lower power consumption, and lower peak-to-average power ratio. We evaluate our method extensively using a dataset designed for ECG-based screening and diagnosis. Our analysis considers factors such as thermal noise, spatial requirements, and power consumption. Additionally, we evaluate detection performance, investigating various parameters of the proposed FNN. This evaluation provides insights into the optimal configuration for accurate anomaly detection. We observe a good trade-off for accuracy around 6 layers and a hidden size of 30 and further demonstrate that such architecture could be implemented in a wearable device and executed in a batteryless fashion.

Signal to Image Conversion and Convolutional Neural Networks for Physiological Signal Processing: A Review

Signal to Image Conversion and Convolutional Neural Networks for Physiological Signal Processing: A Review

Multiscale Diffusion Entropy Analysis for the Detection of Crucial Events in Cardiac Pathology.

The significance of crucial events in explaining the dynamics of a physiological system has only been recently emerging. Crucial events are yet to be fully understood and implemented in clinical applications of physiological signal processing. This paper proposes the application of modified diffusion entropy (MDEA) and novel multiscale diffusion entropy analyses (MSDEA) on measuring the temporal complexity of the ECG time series to improve crucial events detection performance. Thirty samples of each of three groups of ECG datasets from PhysioNet with recordings of cardiac arrhythmia (ARR), congestive heart failure (CHF) and normal sinus rhythm (NSR) were analyzed using MDEA with stripes followed by MSDEA. Healthy NSR ECGs showed an approximate 15% greater inverse power law (IPL) and scaling δ indices than pathologic CHF and ARR signals. Additionally, the scaling indices for the pathologic groups showed higher standard deviations, indicating that crucial events determined by MDEA reveal latent differences in ECG complexity that could better be investigated across multiple time scales of temporally decomposed signals using MSDEA which combines multiscale entropy (MSE) and MDEA. Hence, MSDEA showed an improved, clearer discrimination between the healthy and pathological cardiac signals (p<0.0005) characterized by a range of NSR complexity indices twice the range of the pathological values associated with ARR and CHF across twenty temporal scales as well as more reliable trend lines (R2>=0.95).Clinical Relevance- This research proposes a novel and enhanced diagnostic discrimination across healthy and pathologic cardiac conditions based on biomedical signal processing of ECG recordings utilizing the principle of crucial events detection.

Statistical Validation of An Automated Method for Calculating Time Domain Heart Rate Variability on The QT Dataset.

Heart rate variability measures calculated from electrocardiography recordings reflect social competence. Clinical assessments of social skills have found that reduced heart rate variability is related to differences in the development of social skills in children and increase the risk of mental disorders. Limited by widespread manual signal processing and R-peak detection in current clinical assessments, most literature reports only short-term baseline studies, with fewer studies reporting social interaction settings with prolonged recording. There is an urgent need for an automated physiological signal processing toolbox to detect R-peaks and perform heart rate variability measurements in social settings. This paper proposes a modified automated Neurokit2 toolbox with signal processing procedures similar to the MindWare software that requires manual inspection of R-peak locations. We calculate time domain heart rate variability metrics from the publicly available QT database by PhysioNet collected at resting states and under stress tests, mimicking social interaction stress scenarios. Statistical analysis conveys that heart rate variability metrics calculation applying both signal processing approaches using the Neurokit2 toolbox are statistically equivalent in comparison to the hand-labelled R-peaks from the QT database (n= 10 in the normal sinus rhythm group, and n= 6 in the ST Change group). Such validation results are crucial for the adoption of automated toolboxes for heart rate variability measures in social interaction assessments, where more movement and mood changes of participants are expected.Clinical Relevance- This contributes to the body of evidence of the reliability of the Neurokit2 toolbox for automatic cleaning of prolonged cardiac electrophysiological signals and calculation of heart rate variability in time-domain characterization in social interaction stress assessment.

A neuromorphic physiological signal processing system based on VO2 memristor for next-generation human-machine interface

Physiological signal processing plays a key role in next-generation human-machine interfaces as physiological signals provide rich cognition- and health-related information. However, the explosion of physiological signal data presents challenges for traditional systems. Here, we propose a highly efficient neuromorphic physiological signal processing system based on VO2 memristors. The volatile and positive/negative symmetric threshold switching characteristics of VO2 memristors are leveraged to construct a sparse-spiking yet high-fidelity asynchronous spike encoder for physiological signals. Besides, the dynamical behavior of VO2 memristors is utilized in compact Leaky Integrate and Fire (LIF) and Adaptive-LIF (ALIF) neurons, which are incorporated into a decision-making Long short-term memory Spiking Neural Network. The system demonstrates superior computing capabilities, needing only small-sized LSNNs to attain high accuracies of 95.83% and 99.79% in arrhythmia classification and epileptic seizure detection, respectively. This work highlights the potential of memristors in constructing efficient neuromorphic physiological signal processing systems and promoting next-generation human-machine interfaces.

From Nano to Macro: An overview of the IEEE Bio Image and Signal Processing Technical Committee

The Bio Image and Signal Processing (BISP) Technical Committee (TC) of the IEEE Signal Processing Society (SPS) promotes activities within the broad technical field of biomedical image and signal processing. Areas of interest include medical and biological imaging, digital pathology, molecular imaging, microscopy, and associated computational imaging, image analysis, and image-guided treatment, alongside physiological signal processing, computational biology, and bioinformatics.

Artificial Intelligence and Sensor Technologies the Future of Education Students with and without Intellectual and Developmental Disabilities

Abstract Learning environments such as classrooms and online systems for students with developmental or intellectual disabilities are typically dynamic, multisensory, and make use of top-down attention and working memory mechanisms to promote sense making by the student. However, the last five years have ushered a revolution in computational power, brain mapping, wearable sensors use, large scale data collection, generative artificial intelligence, and physiological signal processing techniques e.g., the 4th industrial revolution. Owing to the advent of inexpensive and highly accurate sensor technologies, generative artificial intelligence, and neurotechnologies, educators now have a new way to assess every student’s learning status, cognitive states, and promote adaption in a multi-modal and multi-dimensional way in real-time. Process data from sensors and neurotechnologies can be available for use by educators within milliseconds as opposed to minutes, hours, or days, as is the case for traditional educational data. Data from artificially intelligent systems can tracks students’ learning progressions using sensor-based data so that content adjustments and differentiation of instruction can meet a student’s needs in real-time. Keywords: Artificial Intelligence, Online Learning, Wearable Sensors, Special Education, Adaptive Learning.

Integrated Memristor Network for Physiological Signal Processing

AbstractHumans are complex organisms made by millions of physiological systems. Therefore, physiological activities can represent physical or mental states of the human body. Physiological signal processing is essential in monitoring human physiological features. For example, non‐invasive electroencephalography (EEG) signals can be used to reconstruct brain consciousness and detect eye movements for identity verification. However, physiological signal processing requires high resolution, high sensitivity, fast responses, and low power consumption, hindering practical hardware design for physiological signal processing. The bionic capability of memristor devices is very promising in the context of building physiological signal processing hardware and they have demonstrated a handful of advantages over the traditional Von Neumann architecture system in accelerating neural networks. Memristor networks can be integrated as a hardware system for physiological signal processing that can deliver higher energy efficiency and lower latency compared to traditional implementations. This review paper first introduces memristor characteristics, followed by a comprehensive literature study of memristor‐based networks. Physiology signal processing applications enabled by these integrated memristor networks are also presented in this review. In summary, this paper aims to provide a new perspective on physiological signal processing using integrated memristor networks.

Artificial Intelligence and Sensor Technologies the Future of Special Education for Students with Intellectual and Developmental Disabilities

Learning environments such as classrooms and online systems for students with developmental or intellectual disabilities are typically dynamic, multisensory, and make use of top-down attention and working memory mechanisms to promote sense making by the student. This is specifically true when the student with intellectual disabilities is mainstreamed into a general education classroom. The complex interactions between the classroom, the student, and the content creates serious difficulty in assessing a student’s understanding, particularly for students who are non-verbal or have deficits in communication. However, the last five years have ushered a revolution in computational power, brain mapping, wearable sensors use, large scale data collection, generative artificial intelligence, and physiological signal processing techniques e.g., the 4th industrial revolution

Compressed Sensing Approach for Physiological Signals: A Review

The immense progress in physiological signal acquisition and processing in health monitoring allowed a better understanding of patient disease detection and diagnosis. With the increase in data volume and power consumption, effective data compression, signal acquisition, transmission, and processing techniques are essential, especially in telemonitoring healthcare applications. An emerging research area focuses on integrating compressed sensing (CS) with physiological signals to deal with a massive amount of physiological data, transmission bandwidth, and power-saving purposes. A review of CS for physiological signals is presented in this article, including electroencephalography (EEG), electrocardiography (ECG), electromyography (EMG), and electrodermal activity (EDA), focusing on the pros and cons of CS in treating such signals and the suitability of CS for hardware implementation. Furthermore, we emphasize performance matrices, such as compression ratio (CR), signal-to-noise ratio (SNR), Percentage Root-mean-square Difference (PRD), and processing time to evaluate the performance of CS. We also investigate the current practices, challenges, and opportunities of using CS in healthcare applications.

A fast sample entropy for pulse rate variability analysis.

Sample entropy is an effective nonlinear index for analyzing pulse rate variability (PRV) signal, but it has problems with a large amount of calculation and time consumption. Therefore, this study proposes a fast sample entropy calculation method to analyze the PRV signal according to the microprocessor process of data updating and the principle of sample entropy. The simulated data and PRV signal are employed as experimental data to verify the accuracy and time consumption of the proposed method. The experimental results on simulated data display that the proposed improved sample entropy can improve the operation rate of the entropy value by a maximum of 47.6 times and an average of 28.6 times and keep the entropy value unchanged. Experimental results on PRV signal display that the proposed improved sample entropy has great potential in the real-time processing of physiological signals, which can increase approximately 35 times.

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).

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.

Cerebral Autoregulation Monitoring in Traumatic Brain Injury: An Overview of Recent Advances in Personalized Medicine.

Impaired cerebral autoregulation (CA) in moderate/severe traumatic brain injury (TBI) has been identified as a strong associate with poor long-term outcomes, with recent data highlighting its dominance over cerebral physiological dysfunction seen in the acute phase post-injury. With advances in bedside continuous cerebral physiological signal processing, continuously derived metrics of CA capacity have been described over the past two decades, leading to improvements in cerebral physiological insult detection and development of novel personalized approaches to TBI care in the intensive care unit (ICU). This narrative review focuses on highlighting the concept of continuous CA monitoring and consequences of impairment in moderate/severe TBI. Further, we provide a comprehensive description and overview of the main personalized cerebral physiological targets, based on CA monitoring, that are emerging as strong associates with patient outcomes. The CA-based personalized targets, such as optimal cerebral perfusion pressure (CPPopt), lower/upper limit of regulation (LLR/ULR), and individualized intracranial pressure (iICP) are positioned to change the way we care for patients with TBI in the ICU, moving away from the "one treatment fits all" paradigm of current guideline-based therapeutic approaches toward a true personalized medicine approach tailored to the individual patient. Future perspectives regarding research needs in this field are also discussed.

Diamond-like Carbon Coatings in the Biomedical Field: Properties, Applications and Future Development

Repairment and replacement of organs and tissues are part of the history of struggle against human diseases, in addition to the research and development (R&amp;D) of drugs. Acquisition and processing of specific substances and physiological signals are very important to understand the effects of pathology and treatment. These depend on the available biomedical materials. The family of diamond-like carbon coatings (DLCs) has been extensively applied in many industrial fields. DLCs have also been demonstrated to be biocompatible, both in vivo and in vitro. In many cases, the performance of biomedical devices can be effectively enhanced by coating them with DLCs, such as vascular stents, prosthetic heart valves and surgical instruments. However, the feasibility of the application of DLC in biomedicine remains under discussion. This review introduces the current state of research and application of DLCs in biomedical devices, their potential application in biosensors and urgent problems to be solved. It will be useful to build a bridge between DLC R&amp;D workers and biomedical workers in order to develop high-performance DLC films/coatings, promote their practical use and develop their potential applications in the biomedical field.

Standardizing continuous data classifications in a virtual T-maze using two-layer feedforward networks

There continues to be difficulties when it comes to replication of studies in the field of Psychology. In part, this may be caused by insufficiently standardized analysis methods that may be subject to state dependent variations in performance. In this work, we show how to easily adapt the two-layer feedforward neural network architecture provided by Huang1 to a behavioral classification problem as well as a physiological classification problem which would not be solvable in a standardized way using classical regression or “simple rule” approaches. In addition, we provide an example for a new research paradigm along with this standardized analysis method. This paradigm as well as the analysis method can be adjusted to any necessary modification or applied to other paradigms or research questions. Hence, we wanted to show that two-layer feedforward neural networks can be used to increase standardization as well as replicability and illustrate this with examples based on a virtual T-maze paradigm2–5 including free virtual movement via joystick and advanced physiological data signal processing.