Spike Analysis of the Neural Activities Across the Rats' Auditory Brain Structures

Tinnitus is a health condition that affects a large population. Clinical diagnosis and treatment have been developed for treating tinnitus for years. However, there are still limitations because researchers have yet to elucidate the mechanisms underlying how tinnitus neural signals develop in brain structures. Abnormal neural interactions among the brain areas are considered to play an important role in tinnitus generation. Researchers have been studying neural activities in the auditory brain structures, including the dorsal cochlear nucleus (DCN), inferior colliculus (IC), and auditory cortex (AC), to seek a better understanding of the information flow among these brain regions, especially in comparison with both health and tinnitus conditions. In this project, neural activities from the DCN, IC, and AC were collected and analyzed before and after the animals were noise-exposed and before and after their auditory cortices were electrically stimulated. These conditions in rats were used to estimate healthy animals, noise-trauma-induced tinnitus, and after auditory cortex electrical stimulation (ACES) treatment. The signal processing algorithms started with the raw measurement data and focused on the local field potentials (LFPs) and spikes in the time domain. The firing rate, shape of spikes, and time differences among channels were analyzed in the time domain, and phase-phase correlation was used to test the phase-frequency information. All the analysis results were summarized in plots and color-heat maps and also used to identify if any neural signal differs and cross-channel relation changes at various animal conditions and discussed.

Swept-source Raman spectroscopy of chemical and biological materials

Significance

Raman spectroscopy has been used as a powerful tool for chemical analysis, enabling the noninvasive acquisition of molecular fingerprints from various samples. Raman spectroscopy has proven to be valuable in numerous fields, including pharmaceutical, materials science, and biomedicine. Active research and development efforts are currently underway to bring this analytical instrument into the field, enabling in situ Raman measurements for a wider range of applications. Dispersive Raman spectroscopy using a fixed, narrowband source is a common method for acquiring Raman spectra. However, dispersive Raman spectroscopy requires a bulky spectrometer, which limits its field applicability. Therefore, there has been a tremendous need to develop a portable and sensitive Raman system.

Aim

We developed a compact swept-source Raman (SS-Raman) spectroscopy system and proposed a signal processing method to mitigate hardware limitations. We demonstrated the capabilities of the SS-Raman spectroscopy by acquiring Raman spectra from both chemical and biological samples. These spectra were then compared with Raman spectra obtained using a conventional dispersive Raman spectroscopy system.

Approach

The SS-Raman spectroscopy system used a wavelength-swept source laser (822 to 842 nm), a bandpass filter with a bandwidth of 1.5 nm, and a low-noise silicon photoreceiver. Raman spectra were acquired from various chemical samples, including phenylalanine, hydroxyapatite, glucose, and acetaminophen. A comparative analysis with the conventional dispersive Raman spectroscopy was conducted by calculating the correlation coefficients between the spectra from the SS-Raman spectroscopy and those from the conventional system. Furthermore, Raman mapping was obtained from cross-sections of swine tissue, demonstrating the applicability of the SS-Raman spectroscopy in biological samples.

Results

We developed a compact SS-Raman system and validated its performance by acquiring Raman spectra from both chemical and biological materials. Our straightforward signal processing method enhanced the quality of the Raman spectra without incurring high costs. Raman spectra in the range of 900 to 1200    cm - 1 were observed for phenylalanine, hydroxyapatite, glucose, and acetaminophen. The results were validated with correlation coefficients of 0.88, 0.84, 0.87, and 0.73, respectively, compared with those obtained from dispersive Raman spectroscopy. Furthermore, we performed scans across the cross-section of swine tissue to generate a biological tissue mapping plot, providing information about the composition of swine tissue.

Conclusions

We demonstrate the capabilities of the proposed compact SS-Raman spectroscopy system by obtaining Raman spectra of chemical and biological materials, utilizing straightforward signal processing. We anticipate that the SS-Raman spectroscopy will be utilized in various fields, including biomedical and chemical applications.

Combinatorial Quantification of Multi-Features of Coda Waves in Temperature-Affected Concrete Beams

Coda waves are highly sensitive to changes in medium properties and can serve as a tool for structural health monitoring (SHM). However, high sensitivity also makes them susceptible to noise, leading to excessive dispersion of monitoring results. In this paper, a coda wave multi-feature extraction method is proposed, in which three parameters, the time shift, the time stretch, and the amplitude variation of the wave trains within the time window, are totally derived. These three parameters are each mapped to the temperature variations of concrete beams, and then combined together with their optimal weight coefficients to give a best-fitted temperature-multi-parameter relationship that has the smallest errors. Coda wave signals were collected from an ultrasonic experiment on concrete beams within an environmental temperature range of 14 °C~21 °C to verify the effectiveness of the proposed method. The results indicate that the combination of multi-features derived from coda wave signals to quantify the medium temperature is feasible. Compared to the relationship established by a single parameter, the goodness-of-fit is improved. During identification, the method effectively reduces the dispersion of identification errors and mitigates the impact of noise interference on structural state assessment. Both the identification accuracy and stability are improved by more than 50%, and the order of magnitude of the identification accuracy is improved from 1 °C to 0.1 °C.

Peak frequency mapping of atypical atrial flutter

INTRODUCTION

Peak frequency (PF) mapping is a novel method that may identify critical portions of myocardial substrate supporting reentry. The aim of this study was to describe and evaluate PF mapping combined with omnipolar voltage mapping in the identification of critical isthmuses of left atrial (LA) atypical flutters.

METHODS AND RESULTS

LA omnipolar voltage and PF maps were generated in flutter using the Advisor HD-Grid catheter (Abbott) and EnSite Precision Mapping System (Abbott) in 12 patients. Normal voltage was defined as ≥0.5 mV, low-voltage as 0.1-0.5 mV, and scar as <0.1 mV. PF distributions were compared with ANOVA and post hoc Tukey analyses. The 1 cm radius from arrhythmia termination was compared to global myocardium with unpaired t-testing. The mean age was 65.8 ± 9.7 years and 50% of patients were female. Overall, 34 312 points were analyzed. Atypical flutters most frequently involved the mitral isthmus (58%) or anterior wall (25%). Mean PF varied significantly by myocardial voltage: normal (335.5 ± 115.0 Hz), low (274.6 ± 144.0 Hz), and scar (71.6 ± 140.5 Hz) (p < .0001 for all pairwise comparisons). All termination sites resided in low-voltage regions containing intermediate or high PF. Overall, mean voltage in the 1 cm radius from termination was significantly lower than the remaining myocardium (0.58 vs. 0.95 mV, p < .0001) and PF was significantly higher (326.4 vs. 245.1 Hz, p < .0001).

CONCLUSION

Low-voltage, high-PF areas may be critical targets during catheter ablation of atypical atrial flutter.

Calibrating Deep Learning Classifiers for Patient-Independent Electroencephalogram Seizure Forecasting

The recent scientific literature abounds in proposals of seizure forecasting methods that exploit machine learning to automatically analyze electroencephalogram (EEG) signals. Deep learning algorithms seem to achieve a particularly remarkable performance, suggesting that the implementation of clinical devices for seizure prediction might be within reach. However, most of the research evaluated the robustness of automatic forecasting methods through randomized cross-validation techniques, while clinical applications require much more stringent validation based on patient-independent testing. In this study, we show that automatic seizure forecasting can be performed, to some extent, even on independent patients who have never been seen during the training phase, thanks to the implementation of a simple calibration pipeline that can fine-tune deep learning models, even on a single epileptic event recorded from a new patient. We evaluate our calibration procedure using two datasets containing EEG signals recorded from a large cohort of epileptic subjects, demonstrating that the forecast accuracy of deep learning methods can increase on average by more than 20%, and that performance improves systematically in all independent patients. We further show that our calibration procedure works best for deep learning models, but can also be successfully applied to machine learning algorithms based on engineered signal features. Although our method still requires at least one epileptic event per patient to calibrate the forecasting model, we conclude that focusing on realistic validation methods allows to more reliably compare different machine learning approaches for seizure prediction, enabling the implementation of robust and effective forecasting systems that can be used in daily healthcare practice.

Experimental Evaluation of an SDR-Based UAV Localization System

UAV communications have seen a rapid rise in the last few years. The drone class of UAV has particularly become more widespread around the world, and illicit behavior using drones has become a problem. Therefore, localization, tracking, and even taking control of drones have also gained interest. Knowing the frequency of a target signal, its position can be determined (as the angle of arrival with respect to a fixed receiver point) using radio frequency-based localization techniques. One such technique is represented by the subspace-based algorithms that offer highly accurate results. This paper presents the implementation of the MUSIC algorithm on an SDR-based system using a uniform circular antenna array and its experimental evaluation in relevant outdoor environments for drone localization. The results show the capability of the system to indicate the AoA of the target signal. The results are compared with the actual direction computed from the log files of the drone application and validated with a professional direction-finding solution (i.e., Narda SignalShark equipped with the automatic direction-finding antenna).

Research on Online Monitoring Technology and Filtration Process of Inclusions in Aluminum Melt

Online monitoring and real-time feedback on inclusions in molten metal are essential for metal quality control. However, existing methods for detecting aluminum melt inclusions face challenges, including interference, prolonged processing times, and latency. This paper presents the design and development of an online monitoring system for molten metal inclusions. Initially, the system facilitates real-time adjustment of signal acquisition parameters through a multiplexer. Subsequently, it employs a detection algorithm capable of swiftly extracting pulse peaks, with this task integrated into our proprietary host computer software to ensure timely detection and data visualization. Ultimately, we developed a monitoring device integrated with this online monitoring system, enabling the online monitoring of the aluminum alloy filtration process. Our findings indicate that the system can accurately measure the size and concentration of inclusions during the filtration process in real time, offering enhanced detection speed and stability compared to the industrial LiMCA CM (liquid metal cleanliness analyzer continuous monitoring) standard. Furthermore, our evaluation of the filtration process demonstrates that the effectiveness of filtration significantly improves with the increase in inclusion sizes, and the synergistic effect of combining CFF (ceramic foam filter) and MCF (metallics cartridge filter) filtration methods exceeds the performance of the CFF method alone. This system thus provides valuable technical support for optimizing filtration processes and controlling inclusion quality.

Research on a Sound Source Localization Method for UAV Detection Based on Improved Empirical Mode Decomposition

To address the challenge of accurately locating unmanned aerial vehicles (UAVs) in situations where radar tracking is not feasible and visual observation is difficult, this paper proposes an innovative acoustic source localization method based on improved Empirical Mode Decomposition (EMD) within an adaptive frequency window. In this study, the collected flight signals of UAVs undergo smoothing filtering. Additionally, Robust Empirical Mode Decomposition (REMD) is applied to decompose the signals into Intrinsic Mode Function (IMF) components for spectrum analysis. We introduce a sliding frequency window with adjustable bandwidth, which is automatically determined using a Grey Wolf Optimizer (GWO) with a sliding index. This window is used to lock and extract specific frequencies from the IMFs. Based on predefined criteria, the extracted IMF components are reconstructed, and trigger signal times are analyzed and recorded from these reconstructed IMFs. The time differences between sensor receptions are then calculated. Furthermore, this study introduces the Chan-Taylor localization algorithm based on weighted least squares. This advanced algorithm takes sensor time delay parameters as input and solves a set of nonlinear equations to determine the target's location. Simulations and real-world signal tests are used to validate the robustness and performance of the proposed method. The results indicate that the localization error remains below 5% within a 15 m × 15 m measurement area. This provides an efficient and real-time method for detecting the location of small UAVs.

A real-time signal processing software package for the electrophysiology laboratory

BACKGROUND

Real-time signal processing has to date been difficult to implement in the clinical electrophysiology laboratory. To date, no open access software solutions are available in electrophysiology (EP) laboratories to facilitate real-time intraprocedural signal analysis. We aimed to develop an open access, scalable Python plug-in to allow real-time signal processing during human EP procedures.

METHODS AND RESULTS

A Python-based plug in for the widely available EnsiteX mapping system was developed. This plug-in utilized the LiveSync feature of the system to allow real-time signal analysis. An open access library was developed to allow end-users to implement real-time signal analysis using this platform, implemented in the Python programming language https://github.com/anand9176/WaveWatch5000Public.

CONCLUSION

We have developed and demonstrated the feasibility of a readily scalable and open-access Python-based plug in to an electroanatomic mapping system (EnSiteX) to allow real-time processing and display of electrogram (EGM) based information for the procedural electrophysiologist to view intraprocedurally in the electrophysiology laboratory. The availability, to the clinician, of traditional and novel EGM-based metrics at the time of intervention, such as atrial fibrillation ablation, allows for key mechanistic insights into critical unresolved questions regarding arrhythmia mechanism.

Emerging Data Processing Methods for Single-Entity Electrochemistry

Single-entity electrochemistry is a powerful tool that enables the study of electrochemical processes at interfaces and provides insights into the intrinsic chemical and structural heterogeneities of individual entities. Signal processing is a critical aspect of single-entity electrochemical measurements and can be used for data recognition, classification, and interpretation. In this review, we summarize the recent five-year advances in signal processing techniques for single-entity electrochemistry and highlight their importance in obtaining high-quality data and extracting effective features from electrochemical signals, which are generally applicable in single-entity electrochemistry. Moreover, we shed light on electrochemical noise analysis to obtain single-molecule frequency fingerprint spectra that can provide rich information about the ion networks at the interface. By incorporating advanced data analysis tools and artificial intelligence algorithms, single-entity electrochemical measurements would revolutionize the field of single-entity analysis, leading to new fundamental discoveries.

SALOS-A UWB Single-Anchor Indoor Localization System Based on a Statistical Multipath Propagation Model

Among other methods, UWB-based multi-anchor localization systems have been established for industrial indoor localization systems. However, multi-anchor systems have high costs and installation effort. By exploiting the multipath propagation of the UWB signal, the infrastructure and thus the costs of conventional systems can be reduced. Our UWB Single-Anchor Localization System (SALOS) successfully pursues this approach. The idea is to create a localization system with sophisticated signal modeling. Therefore, measured reference, like fingerprinting or training, is not required for position estimation. Although SALOS has already been implemented and tested successfully in an outdoor scenario with multipath propagation, it has not yet been evaluated in an indoor environment with challenging and hardly predictable multipath propagation. For this purpose, we have developed new algorithms for the existing hardware, mainly a three-dimensional statistical multipath propagation model for arbitrary spatial geometries. The signal propagation between the anchor and predefined candidate points for the tag position is modeled in path length and complex-valued receive amplitudes. For position estimation, these modeled signals are combined to multiple sets and compared to UWB measurements via a similarity metric. Finally, a majority decision of multiple position estimates is performed. For evaluation, we implement our localization system in a modular fashion and install the system in a building. For a fixed grid of 20 positions, the localization is evaluated in terms of position accuracy. The system results in correct position estimations for more than 73% of the measurements.

Advantages of Bistable Microwires in Digital Signal Processing

The advantageous applications of magnetic bistable microwires have emerged during long-lasting research. They have a wide range of applications in the scientific sphere or technical practice. They can be used for various applications, including magnetic memories, biomedicine, and sensors. This manuscript is focused on the last-mentioned application of microwires-sensors-discussing various digital signal processing techniques used in practical applications. Thanks to the highly sensitive properties of microwires and their two stable states of magnetization, it is possible to perform precise measurements with less demanding digital processing. The manuscript presents four practical signal-processing methods of microwire response using three different experiments. These experiments are focused on detecting the signal in a simple environment without an external magnetic background, measuring with the external background of a ferromagnetic core, and measuring in harsh conditions with a strong magnetic background. The experiments aim to propose the best method under various conditions, emphasizing the quality and signal processing speed of the microwire signal.

Rate of Change of Initial Intrinsicoid Deflection Predicts Endocardial Versus Epicardial Ventricular Tachycardia

BACKGROUND

Assessment of origin of ventricular tachycardias (VTs) arising from epicardial vs endocardial sites are largely challenged by the available criteria and etiology of cardiomyopathy. Current electrocardiographic (ECG) criteria based on 12-lead ECG have varying sensitivity and specificity based on site of origin and etiology of cardiomyopathy.

OBJECTIVES

This study sought to test the hypothesis that epicardial VT has a slower initial rate of depolarization than endocardial VT.

METHODS

We developed a method that takes advantage of the fact that electrical conduction is faster through the cardiac conduction system than the myocardium, and that the conduction system is primarily an endocardial structure. The technique calculated the rate of change in the initial VT depolarization from a signal-averaged 12-lead ECG. We hypothesized that the rate of change of depolarization in endocardial VT would be faster than epicardial. We assessed by applying this technique among 26 patients with VT in nonischemic cardiomyopathy patients.

RESULTS

When comparing patients with VTs ablated using epicardial and endocardial approaches, the rate of change of depolarization was found to be significantly slower in epicardial (mean ± SD 6.3 ± 3.1 mV/s vs 11.4 ± 3.7 mV/s; P < 0.05). Statistical significance was found when averaging all 12 ECG leads and the limb leads, but not the precordial leads. Follow up analysis by calculation of a receiver-operating characteristic curve demonstrated that this analysis provides a strong prediction if a VT is epicardial in origin (AUC range 0.72-0.88). Slower rate of change of depolarization had high sensitivity and specificity for prediction of epicardial VT.

CONCLUSIONS

This study demonstrates that depolarization rate analysis is a potential technique to predict if a VT is epicardial in nature.

A sleep stage estimation algorithm based on cardiorespiratory signals derived from a suprasternal pressure sensor

Automatic estimation of sleep structure is an important aspect in moving sleep monitoring from clinical laboratories to people's homes. However, the transition to more portable systems should not happen at the expense of important physiological signals, such as respiration. Here, we propose the use of cardiorespiratory signals obtained by a suprasternal pressure (SSP) sensor to estimate sleep stages. The sensor is already used for diagnosis of sleep-disordered breathing (SDB) conditions, but besides respiratory effort it can detect cardiac vibrations transmitted through the trachea. We collected the SSP sensor signal in 100 adults (57 male) undergoing clinical polysomnography for suspected sleep disorders, including sleep apnea syndrome, insomnia, and movement disorders. Here, we separate respiratory effort and cardiac activity related signals, then input these into a neural network trained to estimate sleep stages. Using the original mixed signal the results show a moderate agreement with manual scoring, with a Cohen's kappa of 0.53 in Wake/N1-N2/N3/rapid eye movement sleep discrimination and 0.62 in Wake/Sleep. We demonstrate that decoupling the two signals and using the cardiac signal to estimate the instantaneous heart rate improves the process considerably, reaching an agreement of 0.63 and 0.71. Our proposed method achieves high accuracy, specificity, and sensitivity across different sleep staging tasks. We also compare the total sleep time calculated with our method against manual scoring, with an average error of -1.83 min but a relatively large confidence interval of ±55 min. Compact systems that employ the SSP sensor information-rich signal may enable new ways of clinical assessments, such as night-to-night variability in obstructive sleep apnea and other sleep disorders.

Statistical Evaluation of ERG Responses: A New Method to Validate Cycle-by-Cycle Recordings in Advanced Retinal Degenerations

Purpose

To describe and evaluate a novel method to determine the validity of measurements made using cycle-by-cycle (CxC) recording techniques in patients with advanced retinal degenerations (RD) having low-amplitude flicker electroretinogram (ERG) responses.

Methods

The method extends the original CxC recording algorithm introduced by Sieving et al., retaining the original recording setup and the preliminary analysis of raw data. Novel features include extended use of spectrum analysis, reduction of errors due to known sources, and a comprehensive statistical assessment using three different tests. The method was applied to ERG recordings from seven patients with RD and two patients with CNGB3 achromatopsia.

Results

The method was implemented as a Windows application to processes raw data obtained from a commercial ERG system, and it features a computational toolkit for statistical assessment of ERG recordings with amplitudes as low as 1 µV, commonly found in advanced RD patients. When recorded using conditions specific for eliciting cone responses, none of the CNGB3 patients had a CxC validated response, indicating that no signal artifacts were present with our recording conditions. A comparison of the presented method with conventional 30 Hz ERG was performed. Bland-Altman plots indicated good agreement (mean difference, -0.045 µV; limits of agreement, 0.193 to -0.282 µV) between the resulting amplitudes. Within-session test-retest variability was 15%, comparing favorably to the variability of standard ERG amplitudes.

Conclusions

This novel method extracts highly reliable clinical recordings of low-amplitude flicker ERGs and effectively detects artifactual responses. It has potential value both as a cone outcome variable and planning tool in clinical trials on natural history and treatment of advanced RDs.

Seizure event detection using intravital two-photon calcium imaging data

Significance

Intravital cellular calcium imaging has emerged as a powerful tool to investigate how different types of neurons interact at the microcircuit level to produce seizure activity, with newfound potential to understand epilepsy. Although many methods exist to measure seizure-related activity in traditional electrophysiology, few yet exist for calcium imaging.

Aim

To demonstrate an automated algorithmic framework to detect seizure-related events using calcium imaging-including the detection of pre-ictal spike events, propagation of the seizure wavefront, and terminal spreading waves for both population-level activity and that of individual cells.

Approach

We developed an algorithm for precise recruitment detection of population and individual cells during seizure-associated events, which broadly leverages averaged population activity and high-magnitude slope features to detect single-cell pre-ictal spike and seizure recruitment. We applied this method to data recorded using awake in vivo two-photon calcium imaging during pentylenetetrazol-induced seizures in mice.

Results

We demonstrate that our detected recruitment times are concordant with visually identified labels provided by an expert reviewer and are sufficiently accurate to model the spatiotemporal progression of seizure-associated traveling waves.

Conclusions

Our algorithm enables accurate cell recruitment detection and will serve as a useful tool for researchers investigating seizure dynamics using calcium imaging.

The association of hypophysitis with immune checkpoint inhibitors use: Gaining insight through the FDA pharmacovigilance database

The use of immune checkpoint inhibitor (ICI) marked a revolutionary change in cancer treatment and opened new avenues for cancer therapy, but ICI can also trigger immune-related adverse events (irAEs). Here, we investigated the publicly available US Food and Drug Administration (FDA) Adverse Event Reporting System (FAERS) database to gain insight into the possible association between immune checkpoint inhibitors and hypophysitis. Data on adverse events (AEs) due to hypophysitisfor nivolumab, pembrolizumab, ipilimumab, and atezolizumab were collected from the US FDA Adverse Event Reporting System from the first quarter of 2004 to the second quarter of 2021, and the signals for hypophysitis associated with the four drugs were examined using the reporting odds ratio (ROR) method. The number of reported hypophysitis events ≥ 3 and the lower limit of the 95% confidence interval (CI) of the ROR > 1 were considered positive for hypophysitis signals. A total of 1252 AE reports of hypophysitis associated with nivolumab, pembrolizumab, ipilimumab, and atezolizumab were collected, including 419, 149, 643, and 41 cases, respectively. The RORs of hypophysitis were 289.58 (95% CI 258.49-324.40), 171.74 (95% CI 144.91-203.54), 2248.57 (95% CI 2025.31-2496.45), and 97.29 (95% CI 71.28-132.79), respectively. All four drugs were statistically correlated with the target AE, with the correlation being, in descending order, ipilimumab, nivolumab, pembrolizumab, and atezolizumab. Nivolumab, pembrolizumab, ipilimumab, and atezolizumab have all been associated with hypophysitis, which can negatively impact quality of life, and early recognition and management of immune checkpoint inhibitor-related hypophysitis is critical.

Towards Automating Personal Exercise Assessment and Guidance with Affordable Mobile Technology

Physical activity (PA) offers many benefits for human health. However, beginners often feel discouraged when introduced to basic exercise routines. Due to lack of experience and personal guidance, they might abandon efforts or experience musculoskeletal injuries. Additionally, due to phenomena such as pandemics and limited access to supervised exercise spaces, especially for the elderly, the need to develop personalized systems has become apparent. In this work, we develop a monitored physical exercise system that offers real-time guidance and recommendations during exercise, designed to assist users in their home environment. For this purpose, we used posture estimation interfaces that recognize body movement using a computer or smartphone camera. The chosen pose estimation model was BlazePose. Machine learning and signal processing techniques were used to identify the exercise currently being performed. The performances of three machine learning classifiers were evaluated for the exercise recognition task, achieving test-set accuracy between 94.76% and 100%. The research methodology included kinematic analysis (KA) of five selected exercises and statistical studies on performance and range of motion (ROM), which enabled the identification of deviations from the expected exercise execution to support guidance. To this end, data was collected from 57 volunteers, contributing to a comprehensive understanding of exercise performance. By leveraging the capabilities of the BlazePose model, an interactive tool for patients is proposed that could support rehabilitation programs remotely.

A supervised, externally validated machine learning model for artifact and drainage detection in high-resolution intracranial pressure monitoring data

OBJECTIVE

In neurocritical care, data from multiple biosensors are continuously measured, but only sporadically acknowledged by the attending physicians. In contrast, machine learning (ML) tools can analyze large amounts of data continuously, taking advantage of underlying information. However, the performance of such ML-based solutions is limited by different factors, for example, by patient motion, manipulation, or, as in the case of external ventricular drains (EVDs), the drainage of CSF to control intracranial pressure (ICP). The authors aimed to develop an ML-based algorithm that automatically classifies normal signals, artifacts, and drainages in high-resolution ICP monitoring data from EVDs, making the data suitable for real-time artifact removal and for future ML applications.

METHODS

In their 2-center retrospective cohort study, the authors used labeled ICP data from 40 patients in the first neurocritical care unit (University Hospital Zurich) for model development. The authors created 94 descriptive features that were used to train the model. They compared histogram-based gradient boosting with extremely randomized trees after building pipelines with principal component analysis, hyperparameter optimization via grid search, and sequential feature selection. Performance was measured with nested 5-fold cross-validation and multiclass area under the receiver operating characteristic curve (AUROC). Data from 20 patients in a second, independent neurocritical care unit (Charité - Universitätsmedizin Berlin) were used for external validation with bootstrapping technique and AUROC.

RESULTS

In cross-validation, the best-performing model achieved a mean AUROC of 0.945 (95% CI 0.92-0.969) on the development dataset. On the external validation dataset, the model performed with a mean AUROC of 0.928 (95% CI 0.908-0.946) in 100 bootstrapping validation cycles to classify normal signals, artifacts, and drainages.

CONCLUSIONS

Here, the authors developed a well-performing supervised model with external validation that can detect normal signals, artifacts, and drainages in ICP signals from patients in neurocritical care units. For future analyses, this is a powerful tool to discard artifacts or to detect drainage events in ICP monitoring signals.

Automated analysis and detection of epileptic seizures in video recordings using artificial intelligence

Introduction

Automated seizure detection promises to aid in the prevention of SUDEP and improve the quality of care by assisting in epilepsy diagnosis and treatment adjustment.

Methods

In this phase 2 exploratory study, the performance of a contactless, marker-free, video-based motor seizure detection system is assessed, considering video recordings of patients (age 0-80 years), in terms of sensitivity, specificity, and Receiver Operating Characteristic (ROC) curves, with respect to video-electroencephalographic monitoring (VEM) as the medical gold standard. Detection performances of five categories of motor epileptic seizures (tonic-clonic, hyperkinetic, tonic, unclassified motor, automatisms) and psychogenic non-epileptic seizures (PNES) with a motor behavioral component lasting for >10 s were assessed independently at different detection thresholds (rather than as a categorical classification problem). A total of 230 patients were recruited in the study, of which 334 in-scope (>10 s) motor seizures (out of 1,114 total seizures) were identified by VEM reported from 81 patients. We analyzed both daytime and nocturnal recordings. The control threshold was evaluated at a range of values to compare the sensitivity (n = 81 subjects with seizures) and false detection rate (FDR) (n = all 230 subjects).

Results

At optimal thresholds, the performance of seizure groups in terms of sensitivity (CI) and FDR/h (CI): tonic-clonic- 95.2% (82.4, 100%); 0.09 (0.077, 0.103), hyperkinetic- 92.9% (68.5, 98.7%); 0.64 (0.59, 0.69), tonic- 78.3% (64.4, 87.7%); 5.87 (5.51, 6.23), automatism- 86.7% (73.5, 97.7%); 3.34 (3.12, 3.58), unclassified motor seizures- 78% (65.4, 90.4%); 4.81 (4.50, 5.14), and PNES- 97.7% (97.7, 100%); 1.73 (1.61, 1.86). A generic threshold recommended for all motor seizures under study asserted 88% sensitivity and 6.48 FDR/h.

Discussion

These results indicate an achievable performance for major motor seizure detection that is clinically applicable for use as a seizure screening solution in diagnostic workflows.

Detecting central apneas using multichannel signals in premature infants

Objective. Monitoring of apnea of prematurity, performed in neonatal intensive care units by detecting central apneas (CAs) in the respiratory traces, is characterized by a high number of false alarms. A two-step approach consisting of a threshold-based apneic event detection algorithm followed by a machine learning model was recently presented in literature aiming to improve CA detection. However, since this is characterized by high complexity and low precision, we developed a new direct approach that only consists of a detection model based on machine learning directly working with multichannel signals.Approach. The dataset used in this study consisted of 48 h of ECG, chest impedance and peripheral oxygen saturation extracted from 10 premature infants. CAs were labeled by two clinical experts. 47 features were extracted from time series using 30 s moving windows with an overlap of 5 s and evaluated in sets of 4 consecutive moving windows, in a similar way to what was indicated for the two-step approach. An undersampling method was used to reduce imbalance in the training set while aiming at increasing precision. A detection model using logistic regression with elastic net penalty and leave-one-patient-out cross-validation was then tested on the full dataset.Main results. This detection model returned a mean area under the receiver operating characteristic curve value equal to 0.86 and, after the selection of a FPR equal to 0.1 and the use of smoothing, an increased precision (0.50 versus 0.42) at the expense of a decrease in recall (0.70 versus 0.78) compared to the two-step approach around suspected apneic events.Significance. The new direct approach guaranteed correct detections for more than 81% of CAs with lengthL≥ 20 s, which are considered among the most threatening apneic events for premature infants. These results require additional verifications using more extensive datasets but could lead to promising applications in clinical practice.

Preliminary Study of Novel Bio-Crypto Key Generation Using Clustering-Based Binarization of ECG Features

In modern society, the popularity of wearable devices has highlighted the need for data security. Bio-crypto keys (bio-keys), especially in the context of wearable devices, are gaining attention as a next-generation security method. Despite the theoretical advantages of bio-keys, implementing such systems poses practical challenges due to their need for flexibility and convenience. Electrocardiograms (ECGs) have emerged as a potential solution to these issues but face hurdles due to intra-individual variability. This study aims to evaluate the possibility of a stable, flexible, and convenient-to-use bio-key using ECGs. We propose an approach that minimizes biosignal variability using normalization, clustering-based binarization, and the fuzzy extractor, enabling the generation of personalized seeds and offering ease of use. The proposed method achieved a maximum entropy of 0.99 and an authentication accuracy of 95%. This study evaluated various parameter combinations for generating effective bio-keys for personal authentication and proposed the optimal combination. Our research holds potential for security technologies applicable to wearable devices and healthcare systems.

Deep Learning Model Using Continuous Skin Temperature Data Predicts Labor Onset

Background

Changes in body temperature anticipate labor onset in numerous mammals, yet this concept has not been explored in humans.

Methods

We evaluated patterns in continuous skin temperature data in 91 pregnant women using a wearable smart ring. Additionally, we collected daily steroid hormone samples leading up to labor in a subset of 28 pregnancies and analyzed relationships among hormones and body temperature trajectory. Finally, we developed a novel autoencoder long-short-term-memory (AE-LSTM) deep learning model to provide a daily estimation of days until labor onset.

Results

Features of temperature change leading up to labor were associated with urinary hormones and labor type. Spontaneous labors exhibited greater estriol to α-pregnanediol ratio, as well as lower body temperature and more stable circadian rhythms compared to pregnancies that did not undergo spontaneous labor. Skin temperature data from 54 pregnancies that underwent spontaneous labor between 34 and 42 weeks of gestation were included in training the AE-LSTM model, and an additional 40 pregnancies that underwent artificial induction of labor or Cesarean without labor were used for further testing. The model was trained only on aggregate 5-minute skin temperature data starting at a gestational age of 240 until labor onset. During cross-validation AE-LSTM average error (true - predicted) dropped below 2 days at 8 days before labor, independent of gestational age. Labor onset windows were calculated from the AE-LSTM output using a probabilistic distribution of model error. For these windows AE-LSTM correctly predicted labor start for 79% of the spontaneous labors within a 4.6-day window at 7 days before true labor, and 7.4-day window at 10 days before true labor.

Conclusion

Continuous skin temperature reflects progression toward labor and hormonal status during pregnancy. Deep learning using continuous temperature may provide clinically valuable tools for pregnancy care.

Missing Data Statistics Provide Causal Insights into Data Loss in Diabetes Health Monitoring by Wearable Sensors

BACKGROUND

Data loss in wearable sensors is an inevitable problem that leads to misrepresentation during diabetes health monitoring. We systematically investigated missing wearable sensors data to get causal insight into the mechanisms leading to missing data.

METHODS

Two-week-long data from a continuous glucose monitor and a Fitbit activity tracker recording heart rate (HR) and step count in free-living patients with type 2 diabetes mellitus were used. The gap size distribution was fitted with a Planck distribution to test for missing not at random (MNAR) and a difference between distributions was tested with a Chi-squared test. Significant missing data dispersion over time was tested with the Kruskal-Wallis test and Dunn post hoc analysis.

RESULTS

Data from 77 subjects resulted in 73 cleaned glucose, 70 HR and 68 step count recordings. The glucose gap sizes followed a Planck distribution. HR and step count gap frequency differed significantly (p < 0.001), and the missing data were therefore MNAR. In glucose, more missing data were found in the night (23:00-01:00), and in step count, more at measurement days 6 and 7 (p < 0.001). In both cases, missing data were caused by insufficient frequency of data synchronization.

CONCLUSIONS

Our novel approach of investigating missing data statistics revealed the mechanisms for missing data in Fitbit and CGM data.

Machine learning based hybrid anomaly detection technique for automatic diagnosis of cardiovascular diseases using cardiac sympathetic nerve activity and electrocardiogram

OBJECTIVES

Coronary artery diseases (CADs) are the leading cause of death worldwide and early diagnosis is crucial for timely treatment. To address this, our study presents a novel automated Artificial Intelligence (AI)-based Hybrid Anomaly Detection (AIHAD) technique that combines various signal processing, feature extraction, supervised, and unsupervised machine learning methods. By jointly and simultaneously analyzing 12-lead cardiac sympathetic nerve activity (CSNA) and electrocardiogram (ECG) data, the automated AIHAD technique performs fast, early, and accurate diagnosis of CADs.

METHODS

In order to develop and evaluate the proposed automated AIHAD technique, we utilized the fully labeled STAFF III and PTBD databases, which contain the 12-lead wideband raw recordings non-invasively acquired from 260 subjects. Using these wideband raw recordings, we developed a signal processing technique that simultaneously detects the 12-lead CSNA and ECG signals of all subjects. Using the pre-processed 12-lead CSNA and ECG signals, we developed a time-domain feature extraction technique that extracts the statistical CSNA and ECG features critical for the reliable diagnosis of CADs. Using the extracted discriminative features, we developed a supervised classification technique based on Artificial Neural Networks (ANNs) that simultaneously detects anomalies in the 12-lead CSNA and ECG data. Furthermore, we developed an unsupervised clustering technique based on Gaussian mixture models (GMMs) and Neyman-Pearson criterion, which robustly detects outliers corresponding to CADs.

RESULTS

Using the automated AIHAD technique, we have, for the first time, demonstrated a significant association between the increase in CSNA signals and anomalies in ECG signals during CADs. The AIHAD technique achieved highly reliable detection of CADs with a sensitivity of 98.48 %, specificity of 97.73 %, accuracy of 98.11 %, positive predictive value of 97.74 %, negative predictive value of 98.47 %, and F1-score of 98.11 %. Hence, the automated AIHAD technique demonstrates superior performance compared to the gold standard diagnostic test ECG in the diagnosis of CADs. Additionally, it outperforms other techniques developed in this study that separately utilize either only CSNA data or only ECG data. Therefore, it significantly increases the detection performance of CADs by taking advantage of the diversity in different data types and leveraging their strengths. Furthermore, its performance is comparatively better than that of most previously proposed machine and deep learning methods that exclusively used ECG data to diagnose or classify CADs. Additionally, it has a very low implementation time, which is highly desirable for real-time detection of CADs.

CONCLUSIONS

The proposed automated AIHAD technique may serve as an efficient decision-support system to increase physicians' success in fast, early, and accurate diagnosis of CADs. It may be highly beneficial and valuable, particularly for asymptomatic patients, for whom the diagnostic information provided by ECG alone is not sufficient to reliably diagnose the disease. Hence, it may significantly improve patient outcomes by enabling timely treatments and considerably reducing the mortality of cardiovascular diseases (CVDs).

Time Delay Study of Ultrasonic Gas Flowmeters Based on VMD-Hilbert Spectrum and Cross-Correlation

The accuracy of ultrasonic flowmeter time delay measurement is directly affected by the processing method of the ultrasonic echo signal. This paper proposes a method for estimating the time delay of the ultrasonic gas flowmeter based on the Variational Mode Decomposition (VMD)-Hilbert Spectrum and Cross-Correlation (CC). The method improves the accuracy of the ultrasonic gas flowmeter by enhancing the quality of the echo signal. To denoise forward and reverse ultrasonic echo signals collected at various wind speeds, a Butterworth filter is initially used. The ultrasonic echo signals are then analyzed by Empirical Mode De-composition (EMD) and VMD analysis to obtain the Intrinsic Mode Function (IMF) containing distinct center frequencies, respectively. The Hilbert spectrum time-frequency diagram is used to evaluate the results of the VMD and EMD decompositions. It is found that the IMF decomposed by VMD has a better filtering performance and better anti-interference performance. Therefore, the IMF with a better effect is selected for signal reconstruction. The ultrasonic time delay is then calculated using the Cross-Correlation algorithm. The self-developed ultrasonic gas flowmeter was tested on the experimental platform of the gas flow standard devices using this signal processing method. The results show a maximum indication error of 0.84% within the flow range of 60-606 m3/h, with a repeatability of no more than 0.29%. These results meet the 1-level accuracy requirements as outlined in the national ultrasonic flowmeters calibration regulation JJG1030-2007.

A deep learning dataset for sample preparation artefacts detection in multispectral high-content microscopy

High-content image-based screening is widely used in Drug Discovery and Systems Biology. However, sample preparation artefacts may significantly deteriorate the quality of image-based screening assays. While detection and circumvention of such artefacts could be addressed using modern-day machine learning and deep learning algorithms, this is widely impeded by the lack of suitable datasets. To address this, here we present a purpose-created open dataset of high-content microscopy sample preparation artefact. It consists of high-content microscopy of laboratory dust titrated on fixed cell culture specimens imaged with fluorescence filters covering the complete spectral range. To ensure this dataset is suitable for supervised machine learning tasks like image classification or segmentation we propose rule-based annotation strategies on categorical and pixel levels. We demonstrate the applicability of our dataset for deep learning by training a convolutional-neural-network-based classifier.

Convolutional Neural Networks for Raw Signal Classification in CNC Turning Process Monitoring

This study addresses the need for advanced machine learning-based process monitoring in smart manufacturing. A methodology is developed for near-real-time part quality prediction based on process-related data obtained from a CNC turning center. Instead of the manual feature extraction methods typically employed in signal processing, a novel one-dimensional convolutional architecture allows the trained model to autonomously extract pertinent features directly from the raw signals. Several signal channels are utilized, including vibrations, motor speeds, and motor torques. Three quality indicators-average roughness, peak-to-valley roughness, and diameter deviation-are monitored using a single model, resulting in a compact and efficient classifier. Training data are obtained via a small number of experiments designed to induce variability in the quality metrics by varying feed, cutting speed, and depth of cut. A sliding window technique augments the dataset and allows the model to seamlessly operate over the entire process. This is further facilitated by the model's ability to distinguish between cutting and non-cutting phases. The base model is evaluated via k-fold cross validation and achieves average F1 scores above 0.97 for all outputs. Consistent performance is exhibited by additional instances trained under various combinations of design parameters, validating the robustness of the proposed methodology.

Do Different Types of Microphones Affect Listening Effort in Cochlear Implant Recipients? A Pupillometry Study

BACKGROUND

It is known that subjects with a cochlear implant (CI) need to exert more listening effort to achieve adequate speech recognition compared to normal hearing subjects. One tool for assessing listening effort is pupillometry. The aim of this study is to evaluate the effectiveness of adaptive directional microphones in reducing listening effort for CI recipients.

METHODS

We evaluated listening in noise and listening effort degree (by pupillometry) in eight bimodal subjects with three types of CI microphones and in three sound configurations.

RESULTS

We found a correlation only between sound configurations and listening in noise score (p-value 0.0095). The evaluation of the microphone types shows worse scores in listening in noise with Opti Omni (+3.15 dB SNR) microphone than with Split Dir (+1.89 dB SNR) and Speech Omni (+1.43 dB SNR). No correlation was found between microphones and sound configurations and within the pupillometric data.

CONCLUSIONS

Different types of microphones have different effects on the listening of CI patients. The difference in the orientation of the sound source is a factor that has an impact on the listening effort results. However, the pupillometry measurements do not significantly correlate with the different microphone types.

Real-time prediction of bladder urine leakage using fuzzy inference system and dual Kalman filtering in cats

The use of electrical stimulation devices to manage bladder incontinence relies on the application of continuous inhibitory stimulation. However, continuous stimulation can result in tissue fatigue and increased delivered charge. Here, we employ a real-time algorithm to provide a short-time prediction of urine leakage using the high-resolution power spectrum of the bladder pressure during the presence of non-voiding contractions (NVC) in normal and overactive bladder (OAB) cats. The proposed method is threshold-free and does not require pre-training. The analysis revealed that there is a significant difference between voiding contraction (VC) and NVC pressures as well as band powers (0.5-5 Hz) during both normal and OAB conditions. Also, most of the first leakage points occurred after the maximum VC pressure, while all of them were observed subsequent to the maximum VC spectral power. Kalman-Fuzzy method predicted urine leakage on average 2.2 s and 1.6 s before its occurrence and an average of 2.0 s and 1.1 s after the contraction started with success rates of 94.2% and 100% in normal and OAB cats, respectively. This work presents a promising approach for developing a neuroprosthesis device, with on-demand stimulation to control bladder incontinence.

FFT-Based Simultaneous Calculations of Very Long Signal Multi-Resolution Spectra for Ultra-Wideband Digital Radio Frequency Receiver and Other Digital Sensor Applications

The discrete Fourier transform (DFT) is the most commonly used signal processing method in modern digital sensor design for signal study and analysis. It is often implemented in hardware, such as a field programmable gate array (FPGA), using the fast Fourier transform (FFT) algorithm. The frequency resolution (i.e., frequency bin size) is determined by the number of time samples used in the DFT, when the digital sensor's bandwidth is fixed. One can vary the sensitivity of a radio frequency receiver by changing the number of time samples used in the DFT. As the number of samples increases, the frequency bin width decreases, and the digital receiver sensitivity increases. In some applications, it is useful to compute an ensemble of FFT lengths; e.g., 2P-j for j=0, 1, 2, …, J, where j is defined as the spectrum level with frequency resolution 2j·Δf. Here Δf is the frequency resolution at j=0. However, calculating all of these spectra one by one using the conventional FFT method would be prohibitively time-consuming, even on a modern FPGA. This is especially true for large values of P; e.g., P≥20. The goal of this communication is to introduce a new method that can produce multi-resolution spectrum lines corresponding to sample lengths 2P-j for all J+1 levels, concurrently, while one long 2P-length FFT is being calculated. That is, the lower resolution spectra are generated naturally as by-products during the computation of the 2P-length FFT, so there is no need to perform additional calculations in order to obtain them.

Respiratory Diseases Diagnosis Using Audio Analysis and Artificial Intelligence: A Systematic Review

Respiratory diseases represent a significant global burden, necessitating efficient diagnostic methods for timely intervention. Digital biomarkers based on audio, acoustics, and sound from the upper and lower respiratory system, as well as the voice, have emerged as valuable indicators of respiratory functionality. Recent advancements in machine learning (ML) algorithms offer promising avenues for the identification and diagnosis of respiratory diseases through the analysis and processing of such audio-based biomarkers. An ever-increasing number of studies employ ML techniques to extract meaningful information from audio biomarkers. Beyond disease identification, these studies explore diverse aspects such as the recognition of cough sounds amidst environmental noise, the analysis of respiratory sounds to detect respiratory symptoms like wheezes and crackles, as well as the analysis of the voice/speech for the evaluation of human voice abnormalities. To provide a more in-depth analysis, this review examines 75 relevant audio analysis studies across three distinct areas of concern based on respiratory diseases' symptoms: (a) cough detection, (b) lower respiratory symptoms identification, and (c) diagnostics from the voice and speech. Furthermore, publicly available datasets commonly utilized in this domain are presented. It is observed that research trends are influenced by the pandemic, with a surge in studies on COVID-19 diagnosis, mobile data acquisition, and remote diagnosis systems.

Continuous Atrial Fibrillation Monitoring From Photoplethysmography: Comparison Between Supervised Deep Learning and Heuristic Signal Processing

BACKGROUND

Continuous monitoring for atrial fibrillation (AF) using photoplethysmography (PPG) from smartwatches or other wearables is challenging due to periods of poor signal quality during motion or suboptimal wearing. As a result, many consumer wearables sample infrequently and only analyze when the user is at rest, which limits the ability to perform continuous monitoring or to quantify AF.

OBJECTIVES

This study aimed to compare 2 methods of continuous monitoring for AF in free-living patients: a well-validated signal processing (SP) heuristic and a convolutional deep neural network (DNN) trained on raw signal.

METHODS

We collected 4 weeks of continuous PPG and electrocardiography signals in 204 free-living patients. Both SP and DNN models were developed and validated both on holdout patients and an external validation set.

RESULTS

The results show that the SP model demonstrated receiver-operating characteristic area under the curve (AUC) of 0.972 (sensitivity 99.6%, specificity: 94.4%), which was similar to the DNN receiver-operating characteristic AUC of 0.973 (sensitivity 92.2, specificity: 95.5%); however, the DNN classified significantly more data (95% vs 62%), revealing its superior tolerance of tracings prone to motion artifact. Explainability analysis revealed that the DNN automatically suppresses motion artifacts, evaluates irregularity, and learns natural AF interbeat variability. The DNN performed better and analyzed more signal in the external validation cohort using a different population and PPG sensor (AUC, 0.994; 97% analyzed vs AUC, 0.989; 88% analyzed).

CONCLUSIONS

DNNs perform at least as well as SP models, classify more data, and thus may be better for continuous PPG monitoring.

An Open-Source Mouse Chronic EEG Array System with High-Density MXene-Based Skull Surface Electrodes

Electroencephalography (EEG) is an indispensable tool in epilepsy, sleep, and behavioral research. In rodents, EEG recordings are typically performed with metal electrodes that traverse the skull into the epidural space. In addition to requiring major surgery, intracranial EEG is difficult to perform for more than a few electrodes, is time-intensive, and confounds experiments studying traumatic brain injury. Here, we describe an open-source cost-effective refinement of this technique for chronic mouse EEG recording. Our alternative two-channel (EEG2) and sixteen-channel high-density EEG (HdEEG) arrays use electrodes made of the novel, flexible 2D nanomaterial titanium carbide (Ti3C2T x ) MXene. The MXene electrodes are placed on the surface of the intact skull and establish an electrical connection without conductive gel or paste. Fabrication and implantation times of MXene EEG electrodes are significantly shorter than the standard approach, and recorded resting baseline and epileptiform EEG waveforms are similar to those obtained with traditional epidural electrodes. Applying HdEEG to a mild traumatic brain injury (mTBI) model in mice of both sexes revealed that mTBI significantly increased spike-wave discharge (SWD) preictal network connectivity with frequencies of interest in the β-spectral band (12-30 Hz). These findings indicate that the fabrication of MXene electrode arrays is a cost-effective, efficient technology for multichannel EEG recording in mice that obviates the need for skull-penetrating surgery. Moreover, increased preictal β-frequency network connectivity may contribute to the development of early post-mTBI SWDs.

General spectral characteristics of human activity and its inherent scale-free fluctuations

The scale-free nature of daily human activity has been observed in different aspects; however, the description of its spectral characteristics is incomplete. General findings are complicated by the fact that-although actigraphy is commonly used in many research areas-the activity calculation methods are not standardized; therefore, activity signals can be different. The presence of 1/f noise in activity or acceleration signals was mostly analysed for short time windows, and the complete spectral characteristic has only been examined in the case of certain types of them. To explore the general spectral nature of human activity in greater detail, we have performed Power Spectral Density (PSD) based examination and Detrended Fluctuation Analysis (DFA) on several-day-long, triaxial actigraphic acceleration signals of 42 healthy, free-living individuals. We generated different types of activity signals from these, using different acceleration preprocessing techniques and activity metrics. We revealed that the spectra of different types of activity signals generally follow a universal characteristic including 1/f noise over frequencies above the circadian rhythmicity. Moreover, we discovered that the PSD of the raw acceleration signal has the same characteristic. Our findings prove that the spectral scale-free nature is generally inherent to the motor activity of healthy, free-living humans, and is not limited to any particular activity calculation method.

Exploring Convolutional Neural Network Architectures for EEG Feature Extraction

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals.

An Intelligent Ball Bearing Fault Diagnosis System Using Enhanced Rotational Characteristics on Spectrogram

Faults in the ball bearing are a major cause of failure in rotating machinery where ball bearings are used. Therefore, there is a growing demand for ball bearing fault diagnosis to prevent failures in rotating machinery. Although studies on the fault diagnosis of bearing have been conducted using temperature measurements and sound monitoring, these methods have limitations, because they are affected by external noise. Therefore, many researchers have studied vibration monitoring for bearing fault diagnosis. Among these, mel-frequency cepstral coefficients (MFCCs) and 2D convolutional neural networks (CNNs) have attracted significant attention in vibration monitoring schemes. However, the MFCC in existing studies requires a high sampling rate and an expansive frequency band utilization. In addition, 2D CNNs are highly complex. In this study, a rotational characteristic emphasis (RCE) spectrogram process and an optimized CNN were proposed to solve these problems. The RCE spectrogram process analyzes a narrow frequency band and produces low-resolution images. The optimized CNN was designed with a shallow network structure. The experimental results showed an accuracy of 0.9974 for the proposed system. The optimized CNN model has parameters of 5.81 KB and FLOPs of 1.53×106. We demonstrate that the proposed ball bearing fault diagnosis system can achieve high accuracy with low complexity. Thus, we propose a ball bearing fault diagnosis scheme that is applicable to a low sampling rate and changing rotation frequency.

Sepsis Trajectory Prediction Using Privileged Information and Continuous Physiological Signals

The aim of this research is to apply the learning using privileged information paradigm to sepsis prognosis. We used signal processing of electrocardiogram and electronic health record data to construct support vector machines with and without privileged information to predict an increase in a given patient's quick-Sequential Organ Failure Assessment score, using a retrospective dataset. We applied this to both a small, critically ill cohort and a broader cohort of patients in the intensive care unit. Within the smaller cohort, privileged information proved helpful in a signal-informed model, and across both cohorts, electrocardiogram data proved to be informative to creating the prediction. Although learning using privileged information did not significantly improve results in this study, it is a paradigm worth studying further in the context of using signal processing for sepsis prognosis.

An Improved Spectral Subtraction Method for Eliminating Additive Noise in Condition Monitoring System Using Fiber Bragg Grating Sensors

The additive noise in the condition monitoring system using fiber Bragg grating (FBG) sensors, including white Gaussian noise and multifrequency interference, has a significantly negative influence on the fault diagnosis of rotating machinery. Spectral subtraction (SS) is an effective method for handling white Gaussian noise. However, the SS method exhibits poor performance in eliminating multifrequency interference because estimating the noise spectrum accurately is difficult, and it significantly weakens the useful information components in measured signals. In this study, an improved spectral subtraction (ISS) method is proposed to enhance its denoising performance. In the ISS method, a reference noise signal measured by the same sensing system without working loads is considered the estimated noise, the same sliding window is used to divide the power spectrums of the measured and reference noise signals into multiple frequency bands, and the formula of spectral subtraction in the standard SS method is modified. A simulation analysis and an experiment are executed by using simulated signals and establishing a vibration test rig based on the FBG sensor, respectively. The statistical results demonstrate the effectiveness and feasibility of the ISS method in simultaneously eliminating white Gaussian noise and multifrequency interference while well maintaining the useful information components.

Signal Processing for the Condition-Based Maintenance of Rotating Machines via Vibration Analysis: A Tutorial

One of the common methods for implementing the condition-based maintenance of rotating machinery is vibration analysis. This tutorial describes some of the important signal processing methods existing in the field, which are based on a profound understanding of the component's physical behavior. Furthermore, this tutorial provides Python and MATLAB code examples to demonstrate these methods alongside explanatory videos. The goal of this article is to serve as a practical tutorial, enabling interested individuals with a background in signal processing to quickly learn the important principles of condition-based maintenance of rotating machinery using vibration analysis.

Data-Driven Insights into Labor Progression with Gaussian Processes

Clinicians routinely perform pelvic examinations to assess the progress of labor. Clinical guidelines to interpret these examinations, using time-based models of cervical dilation, are not always followed and have not contributed to reducing cesarean-section rates. We present a novel Gaussian process model of labor progress, suitable for real-time use, that predicts cervical dilation and fetal station based on clinically relevant predictors available from the pelvic exam and cardiotocography. We show that the model is more accurate than a statistical approach using a mixed-effects model. In addition, it provides confidence estimates on the prediction, calibrated to the specific delivery. Finally, we show that predicting both dilation and station with a single Gaussian process model is more accurate than two separate models with single predictions.

Application of the Five-Step Phase-Shifting Method in Reflective Ghost Imaging for Efficient Phase Reconstruction

The conventional approach to phase reconstruction in Reflective Ghost Imaging (RGI) typically involves the introduction of three reference screens into the reference path, deeming the Fourier transform step indispensable. However, this method introduces complexity to the system and raises concerns regarding potential errors in phase retrieval. In response to these challenges, we advocate for adopting the Five-Step Phase-Shifting (FSPS) method in the RGI system. This method presents two key advantages over traditional approaches: (1) It streamlines the phase reconstruction process by eliminating the requirement for a Fourier inverse transform. (2) It avoids the need to insert objects into the reference optical path, simplifying the computation of reference optical path intensity and enabling seamless application to Computational Ghost Imaging (CGI), overcoming the constraints of Dual-Arm Ghost Imaging (DAGI). We substantiate the theoretical proposition through numerical simulations involving two intricate objects. Furthermore, our discussion delves into exploring the influence of varying reflective angles on the phase reconstruction performance.

A Selective Review on Information Criteria in Multiple Change Point Detection

Change points indicate significant shifts in the statistical properties in data streams at some time points. Detecting change points efficiently and effectively are essential for us to understand the underlying data-generating mechanism in modern data streams with versatile parameter-varying patterns. However, it becomes a highly challenging problem to locate multiple change points in the noisy data. Although the Bayesian information criterion has been proven to be an effective way of selecting multiple change points in an asymptotical sense, its finite sample performance could be deficient. In this article, we have reviewed a list of information criterion-based methods for multiple change point detection, including Akaike information criterion, Bayesian information criterion, minimum description length, and their variants, with the emphasis on their practical applications. Simulation studies are conducted to investigate the actual performance of different information criteria in detecting multiple change points with possible model mis-specification for the practitioners. A case study on the SCADA signals of wind turbines is conducted to demonstrate the actual change point detection power of different information criteria. Finally, some key challenges in the development and application of multiple change point detection are presented for future research work.

Home-based monitoring of persons with advanced Parkinson's disease using smartwatch-smartphone technology

Movement deterioration is the hallmark of Parkinson's disease (PD), characterized by levodopa-induced motor-fluctuations (i.e., symptoms' variability related to the medication cycle) in advanced stages. However, motor symptoms are typically too sporadically and/or subjectively assessed, ultimately preventing the effective monitoring of their progression, and thus leading to suboptimal treatment/therapeutic choices. Smartwatches (SW) enable a quantitative-oriented approach to motor-symptoms evaluation, namely home-based monitoring (HBM) using an embedded inertial measurement unit. Studies validated such approach against in-clinic evaluations. In this work, we aimed at delineating personalized motor-fluctuations' profiles, thus capturing individual differences. 21 advanced PD patients with motor fluctuations were monitored for 2 weeks using a SW and a smartphone-dedicated app (Intel Pharma Analytics Platform). The SW continuously collected passive data (tremor, dyskinesia, level of activity using dedicated algorithms) and active data, i.e., time-up-and-go, finger tapping, hand tremor and hand rotation carried out daily, once in OFF and once in ON levodopa periods. We observed overall high compliance with the protocol. Furthermore, we observed striking differences among the individual patterns of symptoms' levodopa-related variations across the HBM, allowing to divide our participants among four data-driven, motor-fluctuations' profiles. This highlights the potential of HBM using SW technology for revolutionizing clinical practices.

Novel Entropy-Based Metrics for Long-Term Atrial Fibrillation Recurrence Prediction Following Surgical Ablation: Insights from Preoperative Electrocardiographic Analysis

Atrial fibrillation (AF) is a prevalent cardiac arrhythmia often treated concomitantly with other cardiac interventions through the Cox-Maze procedure. This highly invasive intervention is still linked to a long-term recurrence rate of approximately 35% in permanent AF patients. The aim of this study is to preoperatively predict long-term AF recurrence post-surgery through the analysis of atrial activity (AA) organization from non-invasive electrocardiographic (ECG) recordings. A dataset comprising ECGs from 53 patients with permanent AF who had undergone Cox-Maze concomitant surgery was analyzed. The AA was extracted from the lead V1 of these recordings and then characterized using novel predictors, such as the mean and standard deviation of the relative wavelet energy (RWEm and RWEs) across different scales, and an entropy-based metric that computes the stationary wavelet entropy variability (SWEnV). The individual predictors exhibited limited predictive capabilities to anticipate the outcome of the procedure, with the SWEnV yielding a classification accuracy (Acc) of 68.07%. However, the assessment of the RWEs for the seventh scale (RWEs7), which encompassed frequencies associated with the AA, stood out as the most promising individual predictor, with sensitivity (Se) and specificity (Sp) values of 80.83% and 67.09%, respectively, and an Acc of almost 75%. Diverse multivariate decision tree-based models were constructed for prediction, giving priority to simplicity in the interpretation of the forecasting methodology. In fact, the combination of the SWEnV and RWEs7 consistently outperformed the individual predictors and excelled in predicting post-surgery outcomes one year after the Cox-Maze procedure, with Se, Sp, and Acc values of approximately 80%, thus surpassing the results of previous studies based on anatomical predictors associated with atrial function or clinical data. These findings emphasize the crucial role of preoperative patient-specific ECG signal analysis in tailoring post-surgical care, enhancing clinical decision making, and improving long-term clinical outcomes.

Semi-Supervised Clustering-Based DANA Algorithm for Data Gathering and Disease Detection in Healthcare Wireless Sensor Networks (WSN)

Wireless sensor networks (WSNs) have emerged as a promising technology in healthcare, enabling continuous patient monitoring and early disease detection. This study introduces an innovative approach to WSN data collection tailored for disease detection through signal processing in healthcare scenarios. The proposed strategy leverages the DANA (data aggregation using neighborhood analysis) algorithm and a semi-supervised clustering-based model to enhance the precision and effectiveness of data collection in healthcare WSNs. The DANA algorithm optimizes energy consumption and prolongs sensor node lifetimes by dynamically adjusting communication routes based on the network's real-time conditions. Additionally, the semi-supervised clustering model utilizes both labeled and unlabeled data to create a more robust and adaptable clustering technique. Through extensive simulations and practical deployments, our experimental assessments demonstrate the remarkable efficacy of the proposed method and model. We conducted a comparative analysis of data collection efficiency, energy utilization, and disease detection accuracy against conventional techniques, revealing significant improvements in data quality, energy efficiency, and rapid disease diagnosis. This combined approach of the DANA algorithm and the semi-supervised clustering-based model offers healthcare WSNs a compelling solution to enhance responsiveness and reliability in disease diagnosis through signal processing. This research contributes to the advancement of healthcare monitoring systems by offering a promising avenue for early diagnosis and improved patient care, ultimately transforming the landscape of healthcare through enhanced signal processing capabilities.

Temporal segmentation of EEG based on functional connectivity network structure

In the study of brain functional connectivity networks, it is assumed that a network is built from a data window in which activity is stationary. However, brain activity is non-stationary over sufficiently large time periods. Addressing the analysis electroencephalograph (EEG) data, we propose a data segmentation method based on functional connectivity network structure. The goal of segmentation is to ensure that within a window of analysis, there is similar network structure. We designed an intuitive and flexible graph distance measure to quantify the difference in network structure between two analysis windows. This measure is modular: a variety of node importance indices can be plugged into it. We use a reference window versus sliding window comparison approach to detect changes, as indicated by outliers in the distribution of graph distance values. Performance of our segmentation method was tested in simulated EEG data and real EEG data from a drone piloting experiment (using correlation or phase-locking value as the functional connectivity strength metric). We compared our method under various node importance measures and against matrix-based dissimilarity metrics that use singular value decomposition on the connectivity matrix. The results show the graph distance approach worked better than matrix-based approaches; graph distance based on partial node centrality was most sensitive to network structural changes, especially when connectivity matrix values change little. The proposed method provides EEG data segmentation tailored for detecting changes in terms of functional connectivity networks. Our study provides a new perspective on EEG segmentation, one that is based on functional connectivity network structure differences.

A Comprehensive Study on Pain Assessment from Multimodal Sensor Data

Pain assessment is a critical aspect of healthcare, influencing timely interventions and patient well-being. Traditional pain evaluation methods often rely on subjective patient reports, leading to inaccuracies and disparities in treatment, especially for patients who present difficulties to communicate due to cognitive impairments. Our contributions are three-fold. Firstly, we analyze the correlations of the data extracted from biomedical sensors. Then, we use state-of-the-art computer vision techniques to analyze videos focusing on the facial expressions of the patients, both per-frame and using the temporal context. We compare them and provide a baseline for pain assessment methods using two popular benchmarks: UNBC-McMaster Shoulder Pain Expression Archive Database and BioVid Heat Pain Database. We achieved an accuracy of over 96% and over 94% for the F1 Score, recall and precision metrics in pain estimation using single frames with the UNBC-McMaster dataset, employing state-of-the-art computer vision techniques such as Transformer-based architectures for vision tasks. In addition, from the conclusions drawn from the study, future lines of work in this area are discussed.