Electroretinogram (ERG) signals show distinctive patterns in neurodevelopmental disorders including autism spectrum disorder (ASD) and attention deficit/hyperactivity disorder (ADHD). Traditional ERG analysis relies primarily on time-domain features, limiting the capture of complex nonlinear relationships. We propose ERG-Graph, a novel graph signal processing approach that transforms ERG signals into graph networks to extract topological features for improved classification. Using 5,838 ERG recordings from 278 subjects across four groups (Control, ADHD, ASD, ASD+ADHD), we applied quantization and k-nearest neighbor graph construction to create ERG-graphs and extracted 25 graph-level features including centrality measures, spectral properties, and connectivity metrics. Seven machine learning algorithms were evaluated with leave-one-subject-out cross-validation, achieving balanced accuracies of 0.77 for ADHD vs. Control and 0.76 for ASD vs. Control using Random Forest, outperforming traditional ERG features. ERG-Graph demonstrates superior performance in multi-class scenarios and captures subtle topological patterns associated with neurodevelopmental conditions, offering a promising advancement in automated ERG-based diagnosis.

Electrodermal activity (EDA), an electrical manifestation of the sympathetic innervation of the sweat glands, is widely used in long-term physiological monitoring, including sleep, stress, and cognitive studies. DC-source devices are more commonly used for recording EDA due to their simplicity, while AC alternatives are less adopted because of their perceived complexity. However, maintaining low noise and ensuring signal stability over extended durations remains a significant challenge. This study uses LTspice simulations to compare AC and DC constant current EDA circuits under identical conditions. The electrode–skin interface is modeled using a Randles cell, and real EDA recordings are time-compressed to modulate tissue resistance. Results show that both AC and DC circuits perform comparably well in short-term recordings; however, over time, DC signals degrade due to electrode polarization in the Randles cell model, while AC remains stable and continues to capture EDA reliably.

Inappropriate driver behavior is a leading cause of traffic accidents, contributing to 94% of crashes, according to the National Motor Vehicle Crash Causation Survey. Factors such as individual driving styles, risk-taking tendencies, and noncompliance with traffic regulations increase the likelihood of conflicts and accidents, emphasizing the need for a deeper understanding of driver behavior. Despite existing studies on driving behavior, there is a lack of precise and comprehensive classification methods that effectively correlate physiological signals with driving actions. Current models do not fully capture the cognitive aspects of driving, limiting their applicability in enhancing traffic safety and accident prevention. The primary goal of this study is to identify the most relevant features that contribute to analyzing driving behavior and utilize them to classify driver actions accurately. We conducted feature extraction using 52 distinct features to analyze driving behavior. Following this, feature selection was performed using the Random Forest Recursive Feature Elimination method to identify the 10 most significant features. These important features were then used for driver behavior classification with machine learning models, ensuring improved accuracy and efficiency in identifying different driving patterns.

This study introduces a novel Graph Signal Processing (GSP) method to analyze Electrodermal Activity (EDA) signals for emotional state detection. EDA, influenced by the sympathetic nervous system, is a sensitive indicator of emotional states but is characterized by complex nonstationary and nonlinear properties. Our novel approach transforms EDA signals into graphical networks, termed EDA-graphs, using GSP to unravel intricate relationships in time-series data. We used the CASE dataset and created EDA-graphs by quantizing the signals and grouping values based on Euclidean distances between nearest neighbors. From the EDA-graphs we computed and analyzed graph-based features including Total Load Centrality (TLC), Total Harmonic Centrality (THC) and Number of Cliques (NoC). These features were compared with those derived from traditional EDA processing techniques for emotional state detection. The results showed that EDA-graph features (TLC, THC and NoC), exhibited more significant differences across the five emotional states considered in this study (Neutral, Amused, Bored, Relaxed, and Scared) compared to traditional features of EDA, demonstrating the potential of our GSP approach in enhancing emotional state detection using EDA.

Electroretinography (ERG) devices use brief light flashes to measure electrical responses near the eye. In recent studies, this was found to indicate that the patient may have certain neurodevelopmental disorders, like autism spectrum disorder (ASD) and attention deficit hyperactivity disorder (ADHD). However, these devices costly and scarce. The proposed smartphone-based solution aims to address this, enabling affordable ERG readings. By using a smartphone flashlight, the device processes ERG signals through a signal processing circuit to a microcontroller on a PCB, then sends data to an Android phone for averaging and display. The ERG signals are finally visualized on the smartphone screen that is accessed through a smartphone app. The ease with which the ERG test is performed could enhance the number of evaluations and monitoring of the patients by a doctor.

The continuous detection of emotional states has many applications in mental health, marketing, human-computer interaction, and assistive robotics. Electrodermal activity (EDA), a signal modulated by sympathetic nervous system activity, provides continuous insight into emotional states. However, EDA possesses intricate nonstationary and nonlinear characteristics, making the extraction of emotion-relevant information challenging. We propose a novel graph signal processing (GSP) approach to model EDA signals as graphical networks, termed EDA-graph. The GSP leverages graph theory concepts to capture complex relationships in time-series data. To test the usefulness of EDA-graphs to detect emotions, we processed EDA recordings from the CASE emotion dataset using GSP by quantizing and linking values based on the Euclidean distance between the nearest neighbors. From these EDA-graphs, we computed the features of graph analysis, including total load centrality (TLC), total harmonic centrality (THC), number of cliques (GNC), diameter, and graph radius, and compared those features with features obtained using traditional EDA processing techniques. EDA-graph features encompassing TLC, THC, GNC, diameter, and radius demonstrated significant differences (p < 0.05) between five emotional states (Neutral, Amused, Bored, Relaxed, and Scared). Using machine learning models for classifying emotional states evaluated using leave-one-subject-out cross-validation, we achieved a five-class F1 score of up to 0.68.

The electroretinogram (ERG) is a mass electrical response from the retina, evoked by a brief flash of light. The ERG is composed of electrical potentials contributed by different cell types within the retina, and the stimulus conditions can elicit stronger responses from certain components. Clinically, ERG has been used mainly for the diagnosis of retinal diseases. However, recent studies have found that ERG can be used for early diagnosis of neurodevelopmental and neurodegenerative disorders like autism spectrum disorder, attention-deficit/hyperactivity disorder, and Alzheimer’s disease, among others. Neurodevelopmental disorders affect approximately 1 in 100 children globally. Therefore, early diagnosis to support appropriate Early assessment for those disorders is deemed to be very important. However, ERG is only accessible in clinical settings, and a portable and inexpensive ERG system would enable early screening of neurodiversity and timely intervention. Technically, ERG requires a flash with controlled light strength, electrodes placed on the skin beneath the eye to measure retinal responses, and the processing of the signal. In this study, we have tested the feasibility of developing an ERG system using the capabilities of a Smartphone (flashlight, camera) and a circuit to collect the evoked ERG signals and flash strength and transfer the data to the phone for signal processing. Our results show that a Smartphone-based ERG system is feasible. This technology could contribute to the early detection of neurodiversity.

Data visualization is critical to unraveling hidden information from complex and high-dimensional data. Interpretable visualization methods are critical, especially in the biology and medical fields, however, there are limited effective visualization methods for large genetic data. Current visualization methods are limited to lower-dimensional data and their performance suffers if there is missing data. In this study, we propose a literature-based visualization method to reduce high-dimensional data without compromising the dynamics of the single nucleotide polymorphisms (SNP) and textual interpretability. Our method is innovative because it is shown to (1) preserves both global and local structures of SNP while reducing the dimension of the data using literature text representations, and (2) enables interpretable visualizations using textual information. For performance evaluations, we examined the proposed approach to classify various classification categories including race, myocardial infarction event age groups, and sex using several machine learning models on the literature-derived SNP data. We used visualization approaches to examine clustering of data as well as quantitative performance metrics for the classification of the risk factors examined above. Our method outperformed all popular dimensionality reduction and visualization methods for both classification and visualization, and it is robust against missing and higher-dimensional data. Moreover, we found it feasible to incorporate both genetic and other risk information obtained from literature with our method.

The current method for assessing pain in clinical practice is subjective and relies on self-reported scales. An objective and accurate method of pain assessment is needed for physicians to prescribe the proper medication dosage, which could reduce addiction to opioids. Hence, many works have used electrodermal activity (EDA) as a suitable signal for detecting pain. Previous studies have used machine learning and deep learning to detect pain responses, but none have used a sequence-to-sequence deep learning approach to continuously detect acute pain from EDA signals, as well as accurate detection of pain onset. In this study, we evaluated deep learning models including 1-dimensional convolutional neural networks (1D-CNN), long short-term memory networks (LSTM), and three hybrid CNN-LSTM architectures for continuous pain detection using phasic EDA features. We used a database consisting of 36 healthy volunteers who underwent pain stimuli induced by a thermal grill. We extracted the phasic component, phasic drivers, and time-frequency spectrum of the phasic EDA (TFS-phEDA), which was found to be the most discerning physiomarker. The best model was a parallel hybrid architecture of a temporal convolutional neural network and a stacked bi-directional and uni-directional LSTM, which obtained a F1-score of 77.8% and was able to correctly detect pain in 15-second signals. The model was evaluated using 37 independent subjects from the BioVid Heat Pain Database and outperformed other approaches in recognizing higher pain levels compared to baseline with an accuracy of 91.5%. The results show the feasibility of continuous pain detection using deep learning and EDA.

In conditions of pressure and temperature associated with immersion in water, humans are more susceptible to severe stress, challenging the human physiological control systems. Reliable tools for the assessment of the stress underwater are needed. Electrodermal activity (EDA) is considered a promising alternative for the assessment of the level of stress in humans. EDA is a measure of the changes in conductance at the skin surface related to sweat production. In normal humidity conditions, EDA changes in response to stress in three main ways: the skin conductance level (SCL) is increased, the occurrence of non-specific skin conductance responses (NS.SCRs) increases, and the normalized spectral power in the band from (EDASympn) 0.045 to 0.25 Hz is elevated. When skin is immersed in water, the humidity blocks the sweat glands, changing the dynamics of EDA. For this reason, we have tested the measures of EDA for subjects immersed in water, as response to cognitive stress. Four subjects were recruited for the experiment. Subjects remained four minutes underwater, prior to performing the Stroop task, a test utilized to induce cognitive stress. The SCL and NS.SCRs, didn't exhibit significant differences due to cognitive stress, compared to baseline measurements. EDASymp exhibited significant differences due to cognitive stress. We conclude that the only measure of EDA sensitive to cognitive stress under water is the EDASymp, and it can be potentially used to assess cognitive stress level in divers.

In this paper, a new method for systolic peak detection of pulse wave signals is presented. This method is based on the detection of each peak by the correlation with adaptive Gaussian function template (GFT). The point of maximum correlation is selected as a systolic peak. Its accuracy and noise robustness were evaluated over a set of annotated signals (arterial blood pressure) from CSL database. The GFT method showed an error respect to trained observers less than 5.5 ± 4.2 ms. Furthermore, this method has an error of 8.99 ± 25.09 ms for several noise realization at 9 dB of signal-noise ratio. The results suggest that this method could be used in the measurement of heart rate and pulse transit time, and in the study of autonomic function.