Differential Entropy Research Articles

Electroencephalography Emotion Recognition Based on Rhythm Information Entropy Extraction

Electroencephalography (EEG) is a physiological signal directly generated by the central nervous system. Brain rhythm is closely related to a person’s emotional state and is widely used for EEG emotion recognition. In previous studies, the rhythm specificity between different brain channels was seldom explored. In this paper, the rhythm specificity of brain channels is studied to improve the accuracy of EEG emotion recognition. Variational mode decomposition is used to decompose rhythm signals and enhance features, and two kinds of information entropy, i.e., differential entropy (DE) and dispersion entropy (DispEn) are extracted. The rhythm being used to get the best result of single channel emotion recognition is selected as the representative rhythm, and the remove one method is employed to obtain rhythm information entropy feature. In the experiment, the DEAP database was used for EEG emotion recognition in valence-arousal space. The results showed that the best result of rhythm DE feature classification in the valence dimension is 77.04%, and the best result of rhythm DispEn feature classification in the arousal dimension is 79.25%.

Machine learning based classification of presence utilizing psychophysiological signals in immersive virtual environments

In Virtual Reality (VR), a higher level of presence positively influences the experience and engagement of a user. There are several parameters that are responsible for generating different levels of presence in VR, including but not limited to, graphical fidelity, multi-sensory stimuli, and embodiment. However, standard methods of measuring presence, including self-reported questionnaires, are biased. This research focuses on developing a robust model, via machine learning, to detect different levels of presence in VR using multimodal neurological and physiological signals, including electroencephalography and electrodermal activity. An experiment has been undertaken whereby participants (N = 22) were each exposed to three different levels of presence (high, medium, and low) in a random order in VR. Four parameters within each level, including graphics fidelity, audio cues, latency, and embodiment with haptic feedback, were systematically manipulated to differentiate the levels. A number of multi-class classifiers were evaluated within a three-class classification problem, using a One-vs-Rest approach, including Support Vector Machine, k-Nearest Neighbour, Extra Gradient Boosting, Random Forest, Logistic Regression, and Multiple Layer Perceptron. Results demonstrated that the Multiple Layer Perceptron model obtained the highest macro average accuracy of 93±0.03%\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$93\\pm 0.03\\%$$\\end{document}. Posthoc analysis revealed that relative band power, which is expressed as the ratio of power in a specific frequency band to the total baseline power, in both the frontal and parietal regions, including beta over theta and alpha ratio, and differential entropy were most significant in detecting different levels of presence.

Introduction of a general class of entropy-based control charts: The Φ-chart

We introduce a new class of Shewhart control charts, namely the f-chart. This new class is based on the cumulative paired f-divergence that generalizes both the cumulative (residual) entropy and the differential entropy. The f-chart contains several subclasses; of which one has a special case, the G-chart, which uses Gini’s mean difference as a measure of dispersion. We investigate the performance of three of the subclasses of f-charts in a showcase scenario, comparing its average run length under the Gaussian and several alternative distributions relevant to process control. We find especially the new Leik control chart to outperform classical Shewhart charts, which are based on ranks, standard deviation, or Gini’s mean difference. The results imply that monitoring a production process using f-charts results in faster detection of out-of-control processes, which can be crucial for a variety of application areas.

Study of moisture sorption thermodynamic in canola oilseed and drying energy requirement considerations

AbstractThe objective of this study is to derive the thermodynamic characteristics from sorption isotherm data for canola. The semi‐gravimetric method was utilized at three different temperatures (25, 40, and 55°C) and seven air relative humidity levels within the range of 11%–90%. The observed data indicated that the equilibrium moisture content of the sample decreased as the temperature increased. The “GAB and BET” models were applied to fit the empirical data, which demonstrated a Type III isotherm, and the monolayer water content was subsequently determined using these models. Thermodynamic properties such as “isosteric heat,” “net isosteric heat,” “differential entropy,” “net integral entropy,” and “net integral enthalpy” were determined from isothermal sorption curves. The results show that as moisture content increases, both the sorption isosteric heat and the differential entropy of sorption decrease. This indicates that at higher moisture levels, the energy required for additional moisture adsorption and the changes in entropy are reduced. Similarly, the net isosteric heat of sorption and the net integral enthalpy of sorption also decrease with increasing moisture content, consistent with the observed reductions in isosteric heat and differential entropy. The specific absorption surface area for each temperature was determined by calculating the monolayer moisture content using both the “GAB and BET models.” The net integral entropy had an increasing trend in the range of 4%–4.5% (db%), while it decreased in the range of 4.5%–6.8% of moisture content. In addition, the spreading pressure at three levels of temperature was reported. Finally, an empirical relation was employed to illustrate the cumulative energy requirement for drying versus moisture content. The results indicated that at low moisture content levels, the drying process required significantly higher energy.Practical applicationsMoisture sorption isotherms are essential for understanding the interaction between water and food ingredients. This knowledge is vital for improving food processing methods such as drying, mixing, cooling, and storage. In industry, isotherms can help determine the best drying method to maintain food quality, identify the optimal mixing conditions to ensure consistency, establish cooling protocols to prevent spoilage, and set storage guidelines to extend shelf life. In addition, understanding thermodynamic properties is crucial for regulating moisture absorption and release, achieving the desired food texture, managing surface characteristics, and calculating the energy needed for effective dehydration processes.

MVEB: Self-Supervised Learning With Multi-View Entropy Bottleneck.

Self-supervised learning aims to learn representation that can be effectively generalized to downstream tasks. Many self-supervised approaches regard two views of an image as both the input and the self-supervised signals, assuming that either view contains the same task-relevant information and the shared information is (approximately) sufficient for predicting downstream tasks. Recent studies show that discarding superfluous information not shared between the views can improve generalization. Hence, the ideal representation is sufficient for downstream tasks and contains minimal superfluous information, termed minimal sufficient representation. One can learn this representation by maximizing the mutual information between the representation and the supervised view while eliminating superfluous information. Nevertheless, the computation of mutual information is notoriously intractable. In this work, we propose an objective termed multi-view entropy bottleneck (MVEB) to learn minimal sufficient representation effectively. MVEB simplifies the minimal sufficient learning to maximizing both the agreement between the embeddings of two views and the differential entropy of the embedding distribution. Our experiments confirm that MVEB significantly improves performance. For example, it achieves top-1 accuracy of 76.9% on ImageNet with a vanilla ResNet-50 backbone on linear evaluation. To the best of our knowledge, this is the new state-of-the-art result with ResNet-50.

Distribution pattern analysis of passing and receiving locations during the 2022 FIFA World Cup using the measure of spatial entropy

ABSTRACT The study aimed to investigate the spatial distribution patterns of passing and receiving locations during the 2022 FIFA World Cup in different match stages, playing positions and team possession types. Eighteen types of spatial entropy were proposed to evaluate the heterogeneity of passing and receiving locations in 64 matches. T-tests of these entropies were made between teams at the group and knockout stages, and between distinct playing positions. The K-means clustering of each team’s ball-possession per match was employed to divide all matches into two categories, and their differences in entropies were then analysed using one-way ANOVA. Results showed that the teams at the group and knockout stages had significant differences only in goalkeeper entropy (ES = 0.368). The spatial entropy of the goalkeeper exhibited significant differences in comparison to the other positions (ES: −6.71 ~ -4.69). Low ball-possession teams were significantly lower in 8 types of spatial entropies (ES: −1.02 ~ -0.41) compared to their high ball-possession counterparts. Furthermore, only two types of spatial entropies (ES: −0.58 ~ -0.54) differed significantly in the comparison between high and low ball-possession teams. These findings may provide coaches with guidance for implementing targeted defensive strategies and enhancing the team’s passing performance.

The effect of the loop on the thermodynamic and kinetic of single base pair in pseudoknot.

RNA pseudoknots are RNA molecules with specialized three-dimensional structures that play important roles in various biological processes. To understand the functions and mechanisms of pseudoknots, it is essential to elucidate their structures and folding pathways. The most fundamental step in RNA folding is the opening and closing of a base pair. The effect of flexible loops on the base pair in pseudoknots remains unclear. In this work, we use molecular dynamics simulations and Markov state model to study the configurations, thermodynamic and kinetic of single base pair in pseudoknots. We find that the presence of the loop leads to a trap state. In addition, the rate-limiting step for the formation of base pair is the disruption of the trap state, rather than the open state to the closed state, which is quite different from the previous studies on non-pseudoknot RNA. For the thermodynamic parameters in pseudoknots, we find that the entropy difference upon opening the base pair between this simulation and the nearest-neighbor model results from the different entropy of different lengths of loop in solution. The thermodynamic parameters of the stack in pseudoknot are close to the nearest-neighbor parameters. The bases on the loop have different distribution patterns in different states, and the slow transition states of the loop are determined by the orientation of the bases.

Exploring the possibility of a complex-valued non-Gaussianity measure for quantum states of light

We consider a quantity that is the differential relative entropy between a generic Wigner function and a Gaussian one. We prove that said quantity is minimized with respect to its Gaussian argument, if both Wigner functions in the argument of the Wigner differential entropy have the same first and second moments, i.e., if the Gaussian argument is the Gaussian associate of the other, generic Wigner function. Therefore, we introduce the differential relative entropy between any Wigner function and its Gaussian associate and we examine its potential as a non-Gaussianity measure. The proposed, phase-space based non-Gaussianity measure is complex-valued, with its imaginary part possessing the physical meaning of the Wigner function’s negative volume. At the same time, the real part of this measure provides an extra layer of information, rendering the complex-valued quantity a measure of non-Gaussianity, instead of a quantity pertaining only to the negativity of the Wigner function. We prove that the measure (both the real and imaginary parts) is faithful, invariant under Gaussian unitary operations, and find a sufficient condition on its monotonic behavior under Gaussian channels. We provide numerical results supporting the aforesaid condition. In addition, we examine the measure’s usefulness to non-Gaussian quantum state engineering with partial measurements.

Estimation of average differential entropy for a stationary ergodic space-time random field on a bounded area

Estimation of average differential entropy for a stationary ergodic space-time random field on a bounded area

Subject-independent auditory spatial attention detection based on brain topology modeling and feature distribution alignment

Auditory spatial attention detection (ASAD) seeks to determine which speaker in a surround sound field a listener is focusing on based on the one’s brain biosignals. Although existing studies have achieved ASAD from a single-trial electroencephalogram (EEG), the huge inter-subject variability makes them generally perform poorly in cross-subject scenarios. Besides, most ASAD methods do not take full advantage of topological relationships between EEG channels, which are crucial for high-quality ASAD. Recently, some advanced studies have introduced graph-based brain topology modeling into ASAD, but how to calculate edge weights in a graph to better capture actual brain connectivity is worthy of further investigation. To address these issues, we propose a new ASAD method in this paper. First, we model a multi-channel EEG segment as a graph, where differential entropy serves as the node feature, and a static adjacency matrix is generated based on inter-channel mutual information to quantify brain functional connectivity. Then, different subjects’ EEG graphs are encoded into a shared embedding space through a total variation graph neural network. Meanwhile, feature distribution alignment based on multi-kernel maximum mean discrepancy is adopted to learn subject-invariant patterns. Note that we align EEG embeddings of different subjects to reference distributions rather than align them to each other for the purpose of privacy preservation. A series of experiments on open datasets demonstrate that the proposed model outperforms state-of-the-art ASAD models in cross-subject scenarios with relatively low computational complexity, and feature distribution alignment improves the generalizability of the proposed model to a new subject.

Computationally Efficient IMplicit Training Strategy for UNrolled NEtworks (IMUNNE): A preliminary analysis using accelerated real-time cardiac cine MRI.

Highly-undersampled, dynamic MRI reconstruction, particularly in multi-coil scenarios, is a challenging inverse problem. Unrolled networks achieve state-of-the-art performance in MRI reconstruction but suffer from long training times and extensive GPU memory cost. In this work, we propose a novel training strategy for IMplicit UNrolled NEtworks (IMUNNE) for highly-undersampled, multi-coil dynamic MRI reconstruction. It formulates the MRI reconstruction problem as an implicit fixed-point equation and leverages gradient approximation for backpropagation, enabling training of deep architectures with fixed memory cost. This study represents the first application of implicit network theory in the context of real-time cine MRI. The proposed method is evaluated using a prospectively undersampled, real-time cine dataset using radial k-space sampling, comprising balanced steady-state free precession (b-SSFP) readouts. Experiments include a hyperparameter search, head-to-head comparisons with a complex U-Net (CU-Net) and an alternating unrolled network (Alt-UN), and an analysis of robustness under noise perturbations; peak signal-to-noise ratio, structural similarity index, normalized root mean-square error, spatio-temporal entropic difference, and a blur metric were used. IMUNNE produced significantly and slightly better image quality compared to CU-Net and Alt-UN, respectively. Compared with Alt-UN, IMUNNE significantly reduced training and inference times, making it a promising approach for highly-accelerated, multi-coil real-time cine MRI reconstruction. IMUNNE strategy successfully applies unrolled networks to image reconstruction of highly-accelerated, real-time radial cine MRI. Implicit training enables rapid, high-quality, and cost-effective CMR exams by reducing training and inference times and lowering memory cost associated with advanced reconstruction methods.

Ultrasound normalized cumulative residual entropy imaging: Theory, methodology, and application

Background and Objective:Ultrasound information entropy imaging is an emerging quantitative ultrasound technique for characterizing local tissue scatterer concentrations and arrangements. However, the commonly used ultrasound Shannon entropy imaging based on histogram-derived discrete probability estimation suffers from the drawbacks of histogram settings dependence and unknown estimator performance. In this paper, we introduced the information-theoretic cumulative residual entropy (CRE) defined in a continuous distribution of cumulative distribution functions as a new entropy measure of ultrasound backscatter envelope uncertainty or complexity, and proposed ultrasound CRE imaging for tissue characterization. Methods:We theoretically analyzed the CRE for Rayleigh and Nakagami distributions and proposed a normalized CRE for characterizing scatterer distribution patterns. We proposed a method based on an empirical cumulative distribution function estimator and a trapezoidal numerical integration for estimating the normalized CRE from ultrasound backscatter envelope signals. We presented an ultrasound normalized CRE imaging scheme based on the normalized CRE estimator and the parallel computation technique. We also conducted theoretical analysis of the differential entropy which is an extension of the Shannon entropy to a continuous distribution, and introduced a method for ultrasound differential entropy estimation and imaging. Monte-Carlo simulation experiments were performed to evaluate the estimation accuracy of the normalized CRE and differential entropy estimators. Phantom simulation and clinical experiments were conducted to evaluate the performance of the proposed normalized CRE imaging in characterizing scatterer concentrations and hepatic steatosis (n = 204), respectively. Results:The theoretical normalized CRE for the Rayleigh distribution was π/4, corresponding to the case where there were ≥10 randomly distributed scatterers within the resolution cell of an ultrasound transducer. The theoretical normalized CRE for the Nakagami distribution decreased as the Nakagami parameter m increased, corresponding to that the ultrasound backscattered statistics varied from pre-Rayleigh to Rayleigh and to post-Rayleigh distributions. Monte-Carlo simulation experiments showed that the proposed normalized CRE and differential entropy estimators can produce a satisfying estimation accuracy even when the size of the test samples is small. Phantom simulation experiments showed that the proposed normalized CRE and differential entropy imaging can characterize scatterer concentrations. Clinical experiments showed that the proposed ultrasound normalized CRE imaging is capable to quantitatively characterize hepatic steatosis, outperforming ultrasound differential entropy imaging and being comparable to ultrasound Shannon entropy and Nakagami imaging. Conclusion:This study sheds light on the theory and methodology of ultrasound normalized CRE. The proposed ultrasound normalized CRE can serve as a new, flexible quantitative ultrasound envelope statistics parameter. The proposed ultrasound normalized CRE imaging may find applications in quantified characterization of biological tissues. Our code will be made available publicly at https://github.com/zhouzhuhuang.

Emotion Detection from EEG Signals Using Machine Deep Learning Models.

Detecting emotions is a growing field aiming to comprehend and interpret human emotions from various data sources, including text, voice, and physiological signals. Electroencephalogram (EEG) is a unique and promising approach among these sources. EEG is a non-invasive monitoring technique that records the brain's electrical activity through electrodes placed on the scalp's surface. It is used in clinical and research contexts to explore how the human brain responds to emotions and cognitive stimuli. Recently, its use has gained interest in real-time emotion detection, offering a direct approach independent of facial expressions or voice. This is particularly useful in resource-limited scenarios, such as brain-computer interfaces supporting mental health. The objective of this work is to evaluate the classification of emotions (positive, negative, and neutral) in EEG signals using machine learning and deep learning, focusing on Graph Convolutional Neural Networks (GCNN), based on the analysis of critical attributes of the EEG signal (Differential Entropy (DE), Power Spectral Density (PSD), Differential Asymmetry (DASM), Rational Asymmetry (RASM), Asymmetry (ASM), Differential Causality (DCAU)). The electroencephalography dataset used in the research was the public SEED dataset (SJTU Emotion EEG Dataset), obtained through auditory and visual stimuli in segments from Chinese emotional movies. The experiment employed to evaluate the model results was "subject-dependent". In this method, the Deep Neural Network (DNN) achieved an accuracy of 86.08%, surpassing SVM, albeit with significant processing time due to the optimization characteristics inherent to the algorithm. The GCNN algorithm achieved an average accuracy of 89.97% in the subject-dependent experiment. This work contributes to emotion detection in EEG, emphasizing the effectiveness of different models and underscoring the importance of selecting appropriate features and the ethical use of these technologies in practical applications. The GCNN emerges as the most promising methodology for future research.

The rising entropy of English in the attention economy

We present evidence that the word entropy of American English has been rising steadily since around 1900. We also find differences in word entropy between media categories, with short-form media such as news and magazines having higher entropy than long-form media, and social media feeds having higher entropy still. To explain these results we develop an ecological model of the attention economy that combines ideas from Zipf’s law and information foraging. In this model, media consumers maximize information utility rate taking into account the costs of information search, while media producers adapt to technologies that reduce search costs, driving them to generate higher entropy content in increasingly shorter formats.

SFT-Net: A Network for Detecting Fatigue From EEG Signals by Combining 4D Feature Flow and Attention Mechanism.

Fatigued driving is a leading cause of traffic accidents, and accurately predicting driver fatigue can significantly reduce their occurrence. However, modern fatigue detection models based on neural networks often face challenges such as poor interpretability and insufficient input feature dimensions. This article proposes a novel Spatial-Frequency-Temporal Network (SFT-Net) method for detecting driver fatigue using electroencephalogram (EEG) data. Our approach integrates EEG signals' spatial, frequency, and temporal information to improve recognition performance. We transform the differential entropy of five frequency bands of EEG signals into a 4D feature tensor to preserve these three types of information. An attention module is then used to recalibrate the spatial and frequency information of each input 4D feature tensor time slice. The output of this module is fed into a depthwise separable convolution (DSC) module, which extracts spatial and frequency features after attention fusion. Finally, long short-term memory (LSTM) is used to extract the temporal dependence of the sequence, and the final features are output through a linear layer. We validate the effectiveness of our model on the SEED-VIG dataset, and experimental results demonstrate that SFT-Net outperforms other popular models for EEG fatigue detection. Interpretability analysis supports the claim that our model has a certain level of interpretability. Our work addresses the challenge of detecting driver fatigue from EEG data and highlights the importance of integrating spatial, frequency, and temporal information.

Average Entropy of Gaussian Mixtures.

We calculate the average differential entropy of a q-component Gaussian mixture in Rn. For simplicity, all components have covariance matrix σ21, while the means {Wi}i=1q are i.i.d. Gaussian vectors with zero mean and covariance s21. We obtain a series expansion in μ=s2/σ2 for the average differential entropy up to order O(μ2), and we provide a recipe to calculate higher-order terms. Our result provides an analytic approximation with a quantifiable order of magnitude for the error, which is not achieved in previous literature.

Entanglement structures from modified IR geometry

We investigate a new proposal connecting the geometry at various radial scales in asymptotic AdS spacetime with entanglement structure at corresponding real-space length scales of the boundary theory. With this proposal, the bulk IR geometry encodes the long-scale entanglement structure of the dual quantum system. We consider two distinct types of IR geometries, namely the spherical case and the hyperbolic case, which are intimately related to the physics of differential entropy and brane-world holography separately. We explore the corresponding change in the dual long-scale entanglement structures, utilizing the tools of the Ryu-Takayanagi formula, conditional mutual information, and partial entanglement entropy. The results indicate that modifying the IR geometry leads to a redistribution of entanglement at scales longer than a critical length determined by the location of the IR region, with the two modified IR geometries corresponding to two opposite ways of redistribution. Furthermore, we establish the maximum amount of entanglement that can be modified, which is proportional to the area of the IR region.

High-Accuracy Classification of Multiple Distinct Human Emotions Using EEG Differential Entropy Features and ResNet18

The high-accuracy detection of multiple distinct human emotions is crucial for advancing affective computing, mental health diagnostics, and human–computer interaction. The integration of deep learning networks with entropy measures holds significant potential in neuroscience and medicine, especially for analyzing EEG-based emotion states. This study proposes a method combining ResNet18 with differential entropy to identify five types of human emotions (happiness, sadness, fear, disgust, and neutral) from EEG signals. Our approach first calculates the differential entropy of EEG signals to capture the complexity and variability of the emotional states. Then, the ResNet18 network is employed to learn feature representations from the differential entropy measures, which effectively captures the intricate spatiotemporal dynamics inherent in emotional EEG patterns using residual connections. To validate the efficacy of our method, we conducted experiments on the SEED-V dataset, achieving an average accuracy of 95.61%. Our findings demonstrate that the combination of ResNet18 with differential entropy is highly effective in classifying multiple distinct human emotions from EEG signals. This method shows robust generalization and broad applicability, indicating its potential for extension to various pattern recognition tasks across different domains.

EEG emotion recognition using EEG-SWTNS neural network through EEG spectral image

The rapid development in deep learning models provide considerable advancements in emotion recognition by electroencephalogram (EEG). However, existing approaches primarily focus on temporal and frequency domain features of EEG signals, neglecting spatial domain features in model information integration. Therefore, this study proposed a novel EEG input format, called EEG spectral image (ESI), which integrates spatial domain features using Azimuthal Equidistant Projection (AEP) and frequency domain features through differential entropy (DE). To better utilize this fine-grained data format, we propose the EEG Swin Transformer (EEG-SWTNS), which combines the window attention mechanism with shifted window partitioning. Window attention mechanism can concentrate on affective information within various regions and use shifted window partitioning to disrupt aggregated emotional representations for more granular features. Different from traditional graph neural networks, this method leverages the spatial locality of region information, leading to enhanced performance in EEG-based emotion recognition. Experiments conducted on SEED and SEED IV datasets demonstrate superior performance compared to baseline methods and the state-of-the-art models. Relative improvements of 0.6% and 0.08% are observed in subject-dependent experiments, while accuracies of 80.07% and 66.72% are achieved in subject-independent experiments without utilizing transfer learning techniques.

Measuring cognitive effort using tabular transformer-based language models of electronic health record-based audit log action sequences.

To develop and validate a novel measure, action entropy, for assessing the cognitive effort associated with electronic health record (EHR)-based work activities. EHR-based audit logs of attending physicians and advanced practice providers (APPs) from four surgical intensive care units in 2019 were included. Neural language models (LMs) were trained and validated separately for attendings' and APPs' action sequences. Action entropy was calculated as the cross-entropy associated with the predicted probability of the next action, based on prior actions. To validate the measure, a matched pairs study was conducted to assess the difference in action entropy during known high cognitive effort scenarios, namely, attention switching between patients and to or from the EHR inbox. Sixty-five clinicians performing 5904429 EHR-based audit log actions on 8956 unique patients were included. All attention switching scenarios were associated with a higher action entropy compared to non-switching scenarios (P < .001), except for the from-inbox switching scenario among APPs. The highest difference among attendings was for the from-inbox attention switching: Action entropy was 1.288 (95% CI, 1.256-1.320) standard deviations (SDs) higher for switching compared to non-switching scenarios. For APPs, the highest difference was for the to-inbox switching, where action entropy was 2.354 (95% CI, 2.311-2.397) SDs higher for switching compared to non-switching scenarios. We developed a LM-based metric, action entropy, for assessing cognitive burden associated with EHR-based actions. The metric showed discriminant validity and statistical significance when evaluated against known situations of high cognitive effort (ie, attention switching). With additional validation, this metric can potentially be used as a screening tool for assessing behavioral action phenotypes that are associated with higher cognitive burden. An LM-based action entropy metric-relying on sequences of EHR actions-offers opportunities for assessing cognitive effort in EHR-based workflows.