Lempel-Ziv Complexity Research Articles

Automated recognition of mental cognitive workload through nonlinear EEG analysis

Nowadays, with the remarkable advancements in detection instruments and artificial intelligence, there has been extensive utilization of human mental state monitoring in various domains. Few studies have explored how nonlinear analysis methods can detect cognitive workload despite the complex nature of EEG signals and advancements in signal processing techniques. In addition, the fuzziness of human mental conditions makes the need to use fuzzy engineering tools tangible in this field. Therefore, this investigation aimed to develop a decision support algorithm to improve previous efforts for the classification of task EEG and resting through machine learning algorithms. Various nonlinear features were calculated from all 19 EEG channels: Hurst exponent, Lempel–Ziv complexity, detrended fluctuation analysis, Higuchi fractal dimension, Katz fractal dimension, permutation entropy, singular value decomposition entropy, Petrosian fractal dimension, sample entropy, and Lyapunov exponent. During the classification step, a newly developed EPC-FC (Expert per Class Fuzzy Classifier) is introduced, utilizing an ensemble framework with specialized sub-classifiers for identifying a particular condition. By training sub-classifiers with the negative correlation learning (NCL) approach, the EPC-FC is designed to be exceptionally adaptable. Additionally, the separation of sub-classifiers within each class provides versatility and clarity to the system’s design. The proposed approach based on fuzzy systems and nonlinear analyses was applied to EEG data for mental workload recognition, which provides an excellent accuracy of 98.50% and an F1-score of 98.56% which is much higher than previous findings in this field. Also, the obtained results indicate that utilizing the proposed EPC-FC classifier maintains a consistently high accuracy exceeding 90% across various levels of SNRs. The obtained results proved the high potential of nonlinear analysis to detect cognitive states of the brain, which is consistent with the nonlinear and fuzzy nature of EEG data. Other nonlinear approaches should be considered for future studies to improve the current results.

Research on aquatic biological signal recognition based on mode decomposition and deep learning

Abstract As an important research content in the field of marine biology and ecology, aquatic biological signal (ABS) recognition is of great significance for understanding marine ecosystems, protecting biodiversity, and monitoring environmental changes. To improve the recognition accuracy of ABS, this paper proposes a new ABS recognition method based on mode decomposition and deep learning. First, real ABS data were obtained from the public website, and some data were selected for the simulation experiment. Secondly, the signal is decomposed using improved variational mode decomposition by human evolutionary optimization algorithm (HEOA-VMD), and the decomposed intrinsic mode function (IMF) set is classified into low complexity and high complexity IMF using improved Lempel-Ziv complexity (ILZC) and reverse permutation entropy (RPE). Then, mutual information (MI) is used to select double eigenvectors from low and high complexity IMF, respectively, and recognition is performed based on the double eigenvectors using weighted-convolutional neural network (CNN)-bidirectional gate recurrent unit (BIGRU)-Attention model. Finally, the proposed ABS recognition method is applied to both chaotic and real signals, and additional proof of universality is performed using real signals. The result of the study shows that the accuracy of the proposed method for the recognition of chaotic and real signals is as high as 97.3% and 98.0%. In conclusion, the research on ABS recognition in this paper is successful and has a broad application prospect.

Dispersion network-transition entropy: A metric for characterizing the complexity of nonlinear signals.

Extracting meaningful information from signals has always been a challenge. Due to the influence of environmental noise, collected signals often exhibit nonlinear characteristics, rendering traditional metrics inadequate in capturing the dynamic properties and complex structures of signals. To address this challenge, this study proposes an innovative metric for quantifying signal complexity-dispersion network-transition entropy (DNTE), which integrates the concepts of complex networks and information entropy. Specifically, we assign single cumulative distribution function values to network nodes and utilize Markov chains to represent links, transforming nonlinear signals into weighted directed complex networks. Subsequently, we assess the importance of network nodes and links, and employ the mathematical expression of information entropy to calculate the DNTE value, quantifying the complexity of the original signal. Next, through extensive experiments on simulated chaotic models and real underwater acoustic signals, we confirm the outstanding performance of DNTE. The results indicate that, compared to Lempel-Ziv complexity, permutation entropy, and dispersion entropy, DNTE not only more accurately reflects changes in signal complexity but also exhibits higher computational efficiency. Importantly, DNTE demonstrates optimal performance in distinguishing different categories of chaotic models, ships, and modulation signals, showcasing its significant potential in extracting effective information from signals.

UAV propeller fault diagnosis using deep learning of non-traditional χ2-selected Taguchi method-tested Lempel–Ziv complexity and Teager–Kaiser energy features

Fault detection and isolation in unmanned aerial vehicle (UAV) propellers are critical for operational safety and efficiency. Most existing fault diagnosis techniques rely basically on traditional statistical-based methods that necessitate better approaches. This study explores the application of untraditional feature extraction methodologies, namely Permutation Entropy (PE), Lempel–Ziv Complexity (LZC), and Teager–Kaiser Energy Operator (TKEO), on the PADRE dataset, which encapsulates various rotor fault configurations. The extracted features were subjected to a Chi-Square (χ2) feature selection process to identify the most significant features for input into a Deep Neural Network. The Taguchi method was utilized to test the performance of the recorded features, correspondingly. Performance metrics, including Accuracy, F1-Score, Precision, and Recall, were employed to evaluate the model’s effectiveness before and after the feature selection. The achieved accuracy has increased by 0.9% when compared with results utilizing traditional statistical methods. Comparative analysis with prior research reveals that the proposed untraditional features surpass traditional methods in diagnosing UAV propeller faults. It resulted in improved performance metrics with Accuracy, F1-Score, Precision, and Recall reaching 99.6%, 99.5%, 99.5%, and 99.5%, respectively. The results suggest promising directions for future research in UAV maintenance and safety protocols.

Complex Function-Based Fault Detection: A New Method to Measure the Complexity of Nonlinear Time Series

In this paper, we propose a new complexity computation based on the complex function. This measure exploits the dispersion Lempel–Ziv complexity (DLZC) and the dispersion statistical complexity measure based on Jensen–Shannon divergence (DCJS) of the analytic signal and constructs the binary complex function, called complex number complexity (CNC). The statistical measure depicts the complex system from different angle and mines more potential information. Through simulation experiments, we prove that the proposed method is able to detect data fluctuations more sensitively and accurately. For an application, the CNC is applied to fault detection which has different fault diameters and rotational speeds. The results deliver that the CNC measure can well represent the complexity of faulty bearings and has significant differences in any two fault types. The technique is effective to characterize different fault.

Breathwork-induced psychedelic experiences modulate neural dynamics.

Breathwork is an understudied school of practices involving intentional respiratory modulation to induce an altered state of consciousness (ASC). We simultaneously investigate the phenomenological and neural dynamics of breathwork by combining Temporal Experience Tracing, a quantitative methodology that preserves the temporal dynamics of subjective experience, with low-density portable EEG devices. Fourteen novice participants completed a course of up to 28 breathwork sessions-of 20, 40, or 60min-in 28days, yielding a neurophenomenological dataset of 301 breathwork sessions. Using hypothesis-driven and data-driven approaches, we found that "psychedelic-like" subjective experiences were associated with increased neural Lempel-Ziv complexity during breathwork. Exploratory analyses showed that the aperiodic exponent of the power spectral density-but not oscillatory alpha power-yielded similar neurophenomenological associations. Non-linear neural features, like complexity and the aperiodic exponent, neurally map both a multidimensional data-driven composite of positive experiences, and hypothesis-driven aspects of psychedelic-like experience states such as high bliss.

Study protocol for "Psilocybin in patients with fibromyalgia: brain biomarkers of action".

Chronic pain is a leading cause of disability worldwide. Fibromyalgia is a particularly debilitating form of widespread chronic pain. Fibromyalgia remains poorly understood, and treatment options are limited or moderately effective at best. Here, we present a protocol for a mechanistic study investigating the effects of psychedelic-assisted-therapy in a fibromyalgia population. The principal focus of this trial is the central mechanism(s) of psilocybin-therapy i.e., in the brain and on associated mental schemata, primarily captured by electroencephalography (EEG) recordings of the acute psychedelic state, plus pre and post Magnetic Resonance Imaging (MRI). Twenty participants with fibromyalgia will complete 8 study visits over 8 weeks. This will include two dosing sessions where participants will receive psilocybin at least once, with doses varying up to 25mg. Our primary outcomes are 1) Lempel-Ziv complexity (LZc) recorded acutely using EEG, and the 2) the (Brief Experiential Avoidance Questionnaire (BEAQ) measured at baseline and primary endpoint. Secondary outcomes will aim to capture broad aspects of the pain experience and related features through neuroimaging, self-report measures, behavioural paradigms, and qualitative interviews. Pain Symptomatology will be measured using the Brief Pain Inventory Interference Subscale (BPI-IS), physical and mental health-related function will be measured using the 36-Item Short Form Health Survey (SF-36). Further neurobiological investigations will include functional MRI (fMRI) and diffusion tensor imaging (changes from baseline to primary endpoint), and acute changes in pre- vs post-acute spontaneous brain activity - plus event-related potential functional plasticity markers, captured via EEG. The results of this study will provide valuable insight into the brain mechanisms involved in the action of psilocybin-therapy for fibromyalgia with potential implications for the therapeutic action of psychedelic-therapy more broadly. It will also deliver essential data to inform the design of a potential subsequent RCT.

Dorsal and median raphe neuronal firing dynamics characterized by nonlinear measures.

The dorsal (DRN) and median (MRN) raphe are important nuclei involved in similar functions, including mood and sleep, but playing distinct roles. These nuclei have a different composition of neuronal types and set of neuronal connections, which among other factors, determine their neuronal dynamics. Most works characterize the neuronal dynamics using classic measures, such as using the average spiking frequency (FR), the coefficient of variation (CV), and action potential duration (APD). In the current study, to refine the characterization of neuronal firing profiles, we examined the neurons within the raphe nuclei. Through the utilization of nonlinear measures, our objective was to discern the redundancy and complementarity of these measures, particularly in comparison with classic methods. To do this, we analyzed the neuronal basal firing profile in both nuclei of urethane-anesthetized rats using the Shannon entropy (Bins Entropy) of the inter-spike intervals, permutation entropy of ordinal patterns (OP Entropy), and Permutation Lempel-Ziv Complexity (PLZC). Firstly, we found that classic (i.e., FR, CV, and APD) and nonlinear measures fail to distinguish between the dynamics of DRN and MRN neurons, except for the OP Entropy. We also found strong relationships between measures, including the CV with FR, CV with Bins entropy, and FR with PLZC, which imply redundant information. However, APD and OP Entropy have either a weak or no relationship with the rest of the measures tested, suggesting that they provide complementary information to the characterization of the neuronal firing profiles. Secondly, we studied how these measures are affected by the oscillatory properties of the firing patterns, including rhythmicity, bursting patterns, and clock-like behavior. We found that all measures are sensitive to rhythmicity, except for the OP Entropy. Overall, our work highlights OP Entropy as a powerful and useful quantity for the characterization of neuronal discharge patterns.

Unraveling the complexity of rapid eye movement microstates: insights from nonlinear EEG analysis.

Although rapid eye movement (REM) sleep is conventionally treated as a unified state, it comprises two distinct microstates: phasic and tonic REM. Recent research emphasizes the importance of understanding the interplay between these microstates, hypothesizing their role in transient shifts between sensory detachment and external awareness. Previous studies primarily employed linear metrics to probe cognitive states, such as oscillatory power, while in this study, we adopt Lempel-Ziv Complexity (LZC), to examine the nonlinear features of electroencephalographic (EEG) data from the REM microstates and to gain complementary insights into neural dynamics during REM sleep. Our findings demonstrate a noteworthy reduction in LZC during phasic REM compared to tonic REM states, signifying diminished EEG complexity in the former. Additionally, we noted a negative correlation between decreased LZC and delta band power, along with a positive correlation with alpha band power. This study highlights the potential of nonlinear EEG metrics, particularly LZC, in elucidating the distinct features of REM microstates. Overall, this research contributes to advancing our understanding of the complex dynamics within REM sleep and opens new avenues for exploring its implications in both clinical and nonclinical contexts.

Major depressive disorder recognition by quantifying EEG signal complexity using proposed APLZC and AWPLZC

BackgroundSeeking objective quantitative indicators is important for accurately recognizing major depressive disorder (MDD). Lempel-Ziv complexity (LZC), employed to characterize neurological disorders, faces limitations in tracking dynamic changes in EEG signals due to defects in the coarse-graining process, hindering its precision for MDD objective quantitative indicators. MethodsThis work proposed Adaptive Permutation Lempel-Ziv Complexity (APLZC) and Adaptive Weighted Permutation Lempel-Ziv Complexity (AWPLZC) algorithms by refining the coarse-graining process and introducing weight factors to effectively improve the precision of LZC in characterizing EEGs and further distinguish MDD patients better. APLZC incorporated the ordinal pattern, while False Nearest Neighbor and Mutual Information algorithms were introduced to determine and adjust key parameters adaptively. Furthermore, we proposed AWPLZC by assigning different weights to each pattern based on APLZC. Thirty MDD patients and 30 healthy controls (HCs) were recruited and their 64-channel resting EEG signals were collected. The complexities of gamma oscillations were then separately computed using LZC, APLZC, and AWPLZC algorithms. Subsequently, a multi-channel adaptive K-nearest neighbor model was constructed for identifying MDD patients and HCs. ResultsLZC, APLZC, and AWPLZC algorithms achieved accuracy rates of 78.29 %, 90.32 %, and 95.13 %, respectively. Sensitivities reached 67.96 %, 85.04 %, and 98.86 %, while specificities were 88.62 %, 95.35 %, and 89.92 %, respectively. Notably, AWPLZC achieved the best performance in accuracy and sensitivity, with a specificity limitation. LimitationThe sample size is relatively small. ConclusionAPLZC and AWPLZC algorithms, particularly AWPLZC, demonstrate superior effectiveness in differentiating MDD patients from HCs compared with LZC. These findings hold significant clinical implications for MDD diagnosis.

Urban Meteorology, Pollutants, Geomorphology, Fractality, and Anomalous Diffusion

The measurements, recorded as time series (TS), of urban meteorology, including temperature (T), relative humidity (RH), wind speed (WS), and pollutants (PM10, PM2.5, and CO), in three different geographical morphologies (basin, mountain range, and coast) are analyzed through chaos theory. The parameters calculated at TS, including the Lyapunov exponent (λ > 0), the correlation dimension (DC < 5), Kolmogorov entropy (SK > 0), the Hurst exponent (0.5 < H < 1), Lempel–Ziv complexity (LZ > 0), the loss of information (<ΔI> < 0), and the fractal dimension (D), show that they are chaotic. For the different locations of data recording, CK is constructed, which is a proportion between the sum of the Kolmogorov entropies of urban meteorology and the sum of the Kolmogorov entropies of the pollutants. It is shown that, for the three morphologies studied, the numerical value of the CK quotient is compatible with the values of the exponent α of time t in the expression of anomalous diffusion applied to the diffusive behavior of atmospheric pollutants in basins, mountain ranges, and coasts. Through the Fréchet heavy tail study, it is possible to define, in each morphology, whether urban meteorology or pollutants exert the greatest influence on the diffusion processes.

The Effects of Lockdown, Urban Meteorology, Pollutants, and Anomalous Diffusion on the SARS-CoV-2 Pandemic in Santiago de Chile

A study was carried out in Santiago de Chile, located in a geographic basin, on the sustainability and diffusion of the recent SARS-CoV-2 pandemic. Hourly measurements were used (carried out for 3.25 years in seven communes of the city) to quantify the accumulated sick (AS) population, urban meteorology variables (MVs) (temperature (T), relative humidity (RH), and magnitude of wind speed (WS)), and air pollution (P) (PM10, PM2.5, 03). Time series (TS) were constructed for each commune, which related AS to MVs, called AS/VM, and to P, noted AS/P. Chaos theory was applied to each TS, requiring the following variables: the Lyapunov exponent (λ > 0), the correlation dimension (DC < 5), Kolmogorov entropy (SK > 0), the Hurst exponent (H, such that 0 < H < 1), Lempel–Ziv complexity (LZ > 0), and information loss (<ΔI> < 0). Every TS complied with chaos theory. For each commune, CK was calculated as a quotient between the sum of AS/T, AS/WS, and AS/RH entropies and the sum of AS/PM10, AS/PM2.5, and AS/O3 entropies. The results show that the entropy for the AS/P ratio is lower than that of the AS/VM ratio in three of the seven communes, since between 2020 and early 2022, the population was confined, reducing pollution. The TS of the AS/P ratio is more persistent and complex. The predictability times of the ratios are comparable in four of the seven communes. The TS of the AS/MV ratios shows greater information loss and chaos. According to the calculated CK values, it is possible to relate it to anomalous diffusion (sub/super-diffusion) and the context that favored the expansion of the pandemic: urban densification, pollution, urban meteorology, population density, etc. Using Fréchet heavy-tailed probability, the compatibility of the results with CK is verified.

A gender recognition method based on EEG microstates

BackgroundGender carries important information related to male and female characteristics, and a large number of studies have attempted to use physiological measurement methods for gender classification. Although previous studies have shown that there exist statistical differences in some Electroencephalographic (EEG) microstate parameters between males and females, it is still unknown that whether these microstate parameters can be used as potential biomarkers for gender classification based on machine learning. MethodsWe used two independent resting-state EEG datasets: the first dataset included 74 females and matched 74 males, and the second one included 42 males and matched 42 females. EEG microstate analysis based on modified k-means clustering method was applied, and temporal parameter and nonlinear characteristics (sample entropy and Lempel–Ziv complexity) of EEG microstate sequences were extracted to compare between males and females. More importantly, these microstate temporal parameters and complexity were tried to train six machine learning methods for gender classification. ResultsWe obtained five common microstates for each dataset and each group. Compared with the male group, the female group has significantly higher temporal parameters of microstate B, C, E and lower temporal parameters of microstate A and D, and higher complexity of microstate sequence. When using combination of microstate temporal parameters and complexity or only microstate temporal parameters as classification features in an independent test set (the second dataset), we achieved 95.2% classification accuracy. ConclusionOur research findings indicate that the dynamics of microstate have considerable Gender-specific alteration. EEG microstates can be used as neurophysiological biomarkers for gender classification.

Spectral Slope and Lempel-Ziv Complexity as Robust Markers of Brain States during Sleep and Wakefulness.

Nonoscillatory measures of brain activity such as the spectral slope and Lempel-Ziv complexity are affected by many neurological disorders and modulated by sleep. A multitude of frequency ranges, particularly a broadband (encompassing the full spectrum) and a narrowband approach, have been used especially for estimating the spectral slope. However, the effects of choosing different frequency ranges have not yet been explored in detail. Here, we evaluated the impact of sleep stage and task engagement (resting, attention, and memory) on slope and complexity in a narrowband (30-45 Hz) and broadband (1-45 Hz) frequency range in 28 healthy male human subjects (21.54 ± 1.90 years) using a within-subject design over 2 weeks with three recording nights and days per subject. We strived to determine how different brain states and frequency ranges affect slope and complexity and how the two measures perform in comparison. In the broadband range, the slope steepened, and complexity decreased continuously from wakefulness to N3 sleep. REM sleep, however, was best discriminated by the narrowband slope. Importantly, slope and complexity also differed between tasks during wakefulness. While narrowband complexity decreased with task engagement, the slope flattened in both frequency ranges. Interestingly, only the narrowband slope was positively correlated with task performance. Our results show that slope and complexity are sensitive indices of brain state variations during wakefulness and sleep. However, the spectral slope yields more information and could be used for a greater variety of research questions than Lempel-Ziv complexity, especially when a narrowband frequency range is used.

Construction of machine learning models for recognizing comorbid anxiety in epilepsy patients based on their clinical and quantitative EEG features

BackgroundThis study aimed to construct prediction models for the recognizing of anxiety disorders (AD) in patients with epilepsy (PWEs) by combining clinical features with quantitative electroencephalogram (qEEG) features and using machine learning (ML). MethodsNineteen clinical features and 20-min resting-state EEG were collected from 71 PWEs comorbid with AD and another 60 PWEs without AD who met the inclusion-exclusion criteria of this study. The EEG were preprocessed and 684 Phase Locking Value (PLV) and 76 Lempel–Ziv Complexity (LZC) features on four bands were extracted. The Fisher score method was used to rank all the derived features. We constructed four models for recognizing AD in PWEs, whether PWEs based on different combinations of features using eXtreme gradient boosting (XGboost) and evaluated these models using the five-fold cross-validation method. ResultsThe prediction model constructed by combining the clinical, PLV, and LZC features showed the best performance, with an accuracy of 96.18%, precision of 94.29%, sensitivity of 98.33%, F1-score of 96.06%, and Area Under the Curve (AUC) of 0.96. The Fisher score ranking results displayed that the top ten features were depression, educational attainment, α_P3LZC, α_T6-PzPLV, α_F7LZC, β_Fp2-O1PLV, θ_T4-CzPLV, θ_F7-PzPLV, α_Fp2LZC, and θ_T4-PzPLV. ConclusionsThe model, constructed by combining the clinical and qEEG features PLV and LZC, efficiently identified the presence of AD comorbidity in PWEs and might have the potential to complement the clinical diagnosis. Our findings suggest that LZC features in the α band and PLV features in Fp2-O1 may be potential biomarkers for diagnosing AD in PWEs.

Metastability indexes global changes in the dynamic working point of the brain following brain stimulation.

Several studies have shown that coordination among neural ensembles is a key to understand human cognition. A well charted path is to identify coordination states associated with cognitive functions from spectral changes in the oscillations of EEG or MEG. A growing number of studies suggest that the tendency to switch between coordination states, sculpts the dynamic repertoire of the brain and can be indexed by a measure known as metastability. In this article, we characterize perturbations in the metastability of global brain network dynamics following Transcranial Magnetic Stimulation that could quantify the duration for which information processing is altered. Thus allowing researchers to understand the network effects of brain stimulation, standardize stimulation protocols and design experimental tasks. We demonstrate the effect empirically using publicly available datasets and use a digital twin (a whole brain connectome model) to understand the dynamic principles that generate such observations. We observed a significant reduction in metastability, concurrent with an increase in coherence following single-pulse TMS reflecting the existence of a window where neural coordination is altered. The reduction in complexity was validated by an additional measure based on the Lempel-Ziv complexity of microstate labeled EEG data. Interestingly, higher frequencies in the EEG signal showed faster recovery in metastability than lower frequencies. The digital twin shed light on how the phase resetting introduced by the single-pulse TMS in local cortical networks can propagate globally, giving rise to changes in metastability and coherence.

Mindfulness meditation styles differently modulate source-level MEG microstate dynamics and complexity.

The investigation of mindfulness meditation practice, classically divided into focused attention meditation (FAM), and open monitoring meditation (OMM) styles, has seen a long tradition of theoretical, affective, neurophysiological and clinical studies. In particular, the high temporal resolution of magnetoencephalography (MEG) or electroencephalography (EEG) has been exploited to fill the gap between the personal experience of meditation practice and its neural correlates. Mounting evidence, in fact, shows that human brain activity is highly dynamic, transiting between different brain states (microstates). In this study, we aimed at exploring MEG microstates at source-level during FAM, OMM and in the resting state, as well as the complexity and criticality of dynamic transitions between microstates. Ten right-handed Theravada Buddhist monks with a meditative expertise of minimum 2,265 h participated in the experiment. MEG data were acquired during a randomized block design task (6 min FAM, 6 min OMM, with each meditative block preceded and followed by 3 min resting state). Source reconstruction was performed using eLORETA on individual cortical space, and then parcellated according to the Human Connect Project atlas. Microstate analysis was then applied to parcel level signals in order to derive microstate topographies and indices. In addition, from microstate sequences, the Hurst exponent and the Lempel-Ziv complexity (LZC) were computed. Our results show that the coverage and occurrence of specific microstates are modulated either by being in a meditative state or by performing a specific meditation style. Hurst exponent values in both meditation conditions are reduced with respect to the value observed during rest, LZC shows significant differences between OMM, FAM, and REST, with a progressive increase from REST to FAM to OMM. Importantly, we report changes in brain criticality indices during meditation and between meditation styles, in line with a state-like effect of meditation on cognitive performance. In line with previous reports, we suggest that the change in cognitive state experienced in meditation is paralleled by a shift with respect to critical points in brain dynamics.

Assessment of visual fatigue in SSVEP-based brain-computer interface: a comprehensive study.

Fatigue deteriorates the performance of a brain-computer interface (BCI) system; thus, reliable detection of fatigue is the first step to counter this problem. The fatigue evaluated by means of electroencephalographic (EEG) signals has been studied in many research projects, but widely different results have been reported. Moreover, there is scant research when considering the fatigue on steady-state visually evoked potential (SSVEP)-based BCI. Therefore, nowadays, fatigue detection is not a completely solved topic. In the current work, the issues found in the literature that led to the differences in the results are identified and saved by performing a new experiment on an SSVEP-based BCI system. The experiment was long enough to produce fatigue in the users, and different SSVEP stimulation ranges were used. Additionally, the EEG features commonly reported in the literature (EEG rhythms powers, SNR, etc.) were calculated as well as newly proposed features (spectral features and Lempel-Ziv complexity). The analysis was carried out on O1, Oz and O2 channels. This work found a tendency of displacement from high-frequency rhythms to low-frequency ones, and thus, better EEG features should present a similar behaviour. Then, the 'relative power' of EEG rhythms, the rates (θ + α)/β, α/β and θ/β, some spectral features (central and mean frequencies, asymmetry and kurtosis coefficients, etc.) and Lempel-Ziv complexity are proposed as reliable EEG features for fatigue detection. Hence, this set of features may be used to construct a more trustworthy fatigue index.

Investigating the Impact of Local Manipulations on Spontaneous and Evoked Brain Complexity Indices: A Large-Scale Computational Model

Brain complexity relies on the integrity of structural and functional brain networks, where specialized areas synergistically cooperate on a large scale. Local alterations within these areas can lead to widespread consequences, leading to a reduction in overall network complexity. Investigating the mechanisms governing this occurrence and exploring potential compensatory interventions is a pressing research focus. In this study, we employed a whole-brain in silico model to simulate the large-scale impact of local node alterations. These were assessed by network complexity metrics derived from both the model’s spontaneous activity (i.e., Lempel–Ziv complexity (LZc)) and its responses to simulated local perturbations (i.e., the Perturbational Complexity Index (PCI)). Compared to LZc, local node silencing of distinct brain regions induced large-scale alterations that were paralleled by a systematic drop of PCI. Specifically, while the intact model engaged in complex interactions closely resembling those obtained in empirical studies, it displayed reduced PCI values across all local manipulations. This approach also revealed the heterogeneous impact of different local manipulations on network alterations, emphasizing the importance of posterior hubs in sustaining brain complexity. This work marks an initial stride toward a comprehensive exploration of the mechanisms underlying the loss and recovery of brain complexity across different conditions.

Predicting the therapeutic response to valproic acid in childhood absence epilepsy through electroencephalogram analysis using machine learning

Childhood absence epilepsy (CAE) is a common type of idiopathic generalized epilepsy, manifesting as daily multiple absence seizures. Although seizures in most patients can be adequately controlled with first-line antiseizure medication (ASM), approximately 25 % of patients respond poorly to first-line ASM. In addition, an accurate method for predicting first-line medication responsiveness is lacking. We used the quantitative electroencephalogram (QEEG) features of patients with CAE along with machine learning to predict the therapeutic effects of valproic acid in this population. We enrolled 25 patients with CAE from multiple medical centers. Twelve patients who required additional medication for seizure control or who were shifted to another ASM and 13 patients who achieved seizure freedom with valproic acid within 6 months served as the nonresponder and responder groups. Using machine learning, we analyzed the interictal background EEG data without epileptiform discharge before ASM. The following features were analyzed: EEG frequency bands, Hjorth parameters, detrended fluctuation analysis, Higuchi fractal dimension, Lempel–Ziv complexity (LZC), Petrosian fractal dimension, and sample entropy (SE). We applied leave-one-out cross-validation with support vector machine, K-nearest neighbor (KNN), random forest, decision tree, Ada boost, and extreme gradient boosting, and we tested the performance of these models. The responders had significantly higher alpha band power and lower delta band power than the nonresponders. The Hjorth mobility, LZC, and SE values in the temporal, parietal, and occipital lobes were higher in the responders than in the nonresponders. Hjorth complexity was higher in the nonresponders than in the responders in almost all the brain regions, except for the leads FP1 and FP2. Using KNN classification with theta band power in the temporal lobe yielded optimal performance, with sensitivity of 92.31 %, specificity of 76.92 %, accuracy of 84.62 %, and area under the curve of 88.46 %.We used various EEG features along with machine learning to accurately predict whether patients with CAE would respond to valproic acid. Our method could provide valuable assistance for pediatric neurologists in selecting suitable ASM.