RESUMO
This work presents open-source software that incorporates detection and delineation algorithms of characteristic points of QRS complexes and P and T waves in ECG recordings. The tool facilitates the identification of significant points in the ECG waves, allowing manual correction of the results based on user criteria, exporting the detected points, and a simultaneous visualization of the recordings and the obtained points. The main objective is to improve the management of long- and short-term recordings by reducing detection errors caused by noise, interference, and artifacts, while also providing the capability for manual results correction. To achieve these objectives, the software uses an SQL Server database, which efficiently manages the data, and detection and delineation algorithms based on the continuous wavelet transform with splines, along with alternatives to optimize processing time. The QRS complex detection algorithm was validated in a previous work with the manually annotated ECG databases: MIT-BIH Arrhythmia, European ST-T, and QT. The QRS detector obtained a Se = 99.91% and a P+= 99.62% on the first channel of the MIT-BIH, ST-T and QT databases over the 986,930 QRS complexes analyzed. To evaluate the delineation algorithms of the characteristic points of QRS, P and T waves, the QT and PTB databases were used. The mean and standard deviations of the differences between the automatic and manual annotations by CSE experts were calculated. The mean errors range obtained was smaller than one sample (4 ms) to around two samples (8 ms); and the mean standard deviations range was around of two samples (8 ms) to six samples (24 ms).
Assuntos
Algoritmos , Eletrocardiografia , Software , Análise de Ondaletas , Eletrocardiografia/métodos , Humanos , Bases de Dados Factuais , Processamento de Sinais Assistido por Computador , Arritmias Cardíacas/diagnóstico , Reprodutibilidade dos Testes , ArtefatosRESUMO
Intracranial hypertension (ICH) is a common and critical condition in neurocritical care, often requiring immediate intervention. Current methods for continuous intracranial pressure (ICP) monitoring are invasive and costly, limiting their use in resource-limited settings. This study investigates the potential of the electroencephalography (EEG) as a non-invasive alternative for ICP monitoring. Using a generalized additive model (GAM) applied to porcine models, we analyzed the correlation between ICP and EEG features, including total EEG energy and the slope of the EEG power spectral density. Our model achieved moderate specificity (0.75) and sensitivity (0.73), accurately identifying 85% of ICH episodes with a 3-second window. These findings support the feasibility of using the EEG to detect ICH, particularly in low-resource environments. While further validation in human subjects is needed, our approach offers a promising, cost-effective method for non-invasive continuous ICP monitoring, enhancing ICH detection where traditional methods are impractical or inaccessible.
Assuntos
Eletroencefalografia , Hipertensão Intracraniana , Pressão Intracraniana , Suínos , Pressão Intracraniana/fisiologia , Projetos Piloto , Animais , Eletroencefalografia/métodos , Hipertensão Intracraniana/fisiopatologia , Hipertensão Intracraniana/diagnóstico , Monitorização Fisiológica/métodos , Humanos , Processamento de Sinais Assistido por ComputadorRESUMO
Objective.Continuous monitoring of the hemodynamic coherence between macro and microcirculation is difficult at the bedside. We tested the role of photoplethysmography (PPG) to real-time assessment of microcirculation during extreme manipulation of macrohemodynamics induced by the cardiopulmonary bypass (CPB).Approach.We analyzed the alternating (AC) and direct (DC) components of the finger PPG in 12 patients undergoing cardiac surgery with CPB at five moments: (1) before-CPB; (2) CPB-start, at the transition from pulsatile to non-pulsatile blood flow; (3) CPB-aortic clamping, at a sudden decrease in pump blood flow and volemia.; (4) CPB-weaning, during step-wise 20% decreases in pump blood flow and opposite proportional increases in native pulsatile blood flow; and (5) after-CPB.Main results.Nine Caucasian men and three women were included for analysis. Macrohemodynamic changes during CPB had an immediate impact on the PPG at all studied moments. Before-CPB the AC signal amplitude showed a median and IQR values of 0.0023(0.0013). The AC signal completely disappeared at CPB-start and at CPB-aortic clamping. During CPB weaning its amplitude progressively increased but remained lower than before CPB, at 80% [0.0008 (0.0005);p< 0.001], 60% [0.0010(0.0006);p< 0.001], and 40% [0.0013(0.0009);p= 0.011] of CPB flow. The AC amplitude returned close to Before-CPB values at 20% of CPB flow [0.0015(0.0008);p= 0.081], when CPB was completely stopped [0.0019 (0.0009);p= 0.348], and at after-CPB [0.0021(0.0009);p= 0.687]. The DC signal Before-CPB [0.95(0.02)] did not differ statistically from CPB-start, CPB-weaning and After-CPB. However, at CPB-aortic clamping, at no flow and a sudden drop in volemia, the DC signal decreased from [0.96(0.01)] to [0.94(0.02);p= 0.002].Significance.The macrohemodynamic alterations brought on by CPB were consistent with changes in the finger's microcirculation. PPG described local pulsatile blood flow (AC) as well as non-pulsatile blood flow and volemia (DC) in the finger. These findings provide plausibility to the use of PPG in ongoing hemodynamic coherence monitoring.
Assuntos
Ponte Cardiopulmonar , Dedos , Microcirculação , Fotopletismografia , Humanos , Fotopletismografia/métodos , Masculino , Feminino , Microcirculação/fisiologia , Dedos/irrigação sanguínea , Idoso , Pessoa de Meia-Idade , Processamento de Sinais Assistido por Computador , Hemodinâmica/fisiologiaRESUMO
The prediction of subject traits using brain data is an important goal in neuroscience, with relevant applications in clinical research, as well as in the study of differential psychology and cognition. While previous prediction work has predominantly been done on neuroimaging data, our focus is on electroencephalography (EEG), a relatively inexpensive, widely available and non-invasive data modality. However, EEG data is complex and needs some form of feature extraction for subsequent prediction. This process is sometimes done manually, risking biases and suboptimal decisions. Here we investigate the use of data-driven Kernel methods for prediction from single channels using the EEG spectrogram, which reflects macro-scale neural oscillations in the brain. Specifically, we introduce the idea of reinterpreting the spectrogram of each channel as a probability distribution, so that we can leverage advanced machine learning techniques that can handle probability distributions with mathematical rigour and without the need for manual feature extraction. We explore how the resulting technique, Kernel mean embedding regression, compares to a standard application of Kernel ridge regression as well as to a non-Kernelised approach. Overall, we found that the Kernel methods exhibit improved performance thanks to their capacity to handle nonlinearities in the relation between the EEG spectrogram and the trait of interest. We leveraged this method to predict biological age in a multinational EEG data set, HarMNqEEG, showing the method's capacity to generalise across experiments and acquisition setups.
Assuntos
Envelhecimento , Encéfalo , Eletroencefalografia , Humanos , Eletroencefalografia/métodos , Envelhecimento/fisiologia , Encéfalo/fisiologia , Encéfalo/diagnóstico por imagem , Adulto , Aprendizado de Máquina , Feminino , Masculino , Adulto Jovem , Pessoa de Meia-Idade , Idoso , Processamento de Sinais Assistido por Computador , Ondas Encefálicas/fisiologiaRESUMO
Electromyography (EMG) stands out as an accessible and inexpensive method for identifying muscle contractions on the surface and within deeper muscle tissues. Using specialized electronic circuits for amplification and filtering can help develop simple but effective systems for detecting and analyzing these signals. However, EMG devices developed by research teams frequently lack rigorous methodologies for validating the quality of the signals they record compared to those obtained by commercial systems that have undergone extensive testing and regulatory approval for market release. This underscores the critical need for standardized validation techniques to reliably assess the performance of experimental devices relative to established commercial equipment. Hence, this study introduces a methodology for the development and statistical validation of a laboratory EMG circuit compared with a professional device available on the market. The experiment simultaneously recorded the muscle electrical activity of 18 volunteers using two biosignal acquisition devices-a prototype EMG and a commercial system-both applied in parallel at the same recording site. Volunteers performed a series of finger and wrist extension movements to elicit myoelectric activity in these forearm muscles. To achieve this, it was necessary to develop not only the EMG signal conditioning board, but also two additional interface boards: one for enabling parallel recording on both devices and another for synchronizing the devices with the task programmatically controlled in Python that the volunteers were required to perform. The EMG signals generated during these tasks were recorded simultaneously by both devices. Subsequently, 22 feature indices commonly used for classifying muscular activity patterns were calculated from two-second temporal windows of the recordings to extract detailed temporal and spatial characteristics. Finally, the Mean Absolute Percentage Error (MAPE) was computed to compare the indices from the prototype with those from the commercial device, using this method as a validation system to assess the quality of the signals recorded by the prototype relative to the commercial equipment. A concordance of 87.6% was observed between the feature indices calculated from the recordings of both devices, suggesting high effectiveness and reliability of the EMG signals recorded by the prototype compared to the commercial device. These results validate the efficacy of our EMG prototype device and provide a solid foundation for the future evaluation of similar devices, ensuring their reliability, accuracy, and suitability for research or clinical applications.
Assuntos
Eletromiografia , Processamento de Sinais Assistido por Computador , Eletromiografia/métodos , Eletromiografia/instrumentação , Humanos , Adulto , Masculino , Contração Muscular/fisiologia , Feminino , Músculo Esquelético/fisiologia , Adulto JovemRESUMO
We propose a novel 1-D median estimator specifically designed for the online detection of threshold-crossing signals, such as spikes in extracellular neural recordings. Compared to state-of-the-art algorithms, our method reduces estimator variance by up to eight times for a given buffer length. Likewise, for a given estimator variance, it requires a buffer length that is up to eight times smaller. This results in three significant advantages: the footprint area decreases by more than eight times, leading to reduced power consumption and a faster response to non-stationary signals.
Assuntos
Potenciais de Ação , Algoritmos , Potenciais de Ação/fisiologia , Humanos , Neurônios/fisiologia , Processamento de Sinais Assistido por ComputadorRESUMO
Machine learning algorithms have brought remarkable advancements in detecting motion artifacts (MAs) from the photoplethysmogram (PPG) with no measured or synthetic reference data. However, no study has provided a synthesis of these methods, let alone an in-depth discussion to aid in deciding which one is more suitable for a specific purpose. This narrative review examines the application of machine learning techniques for the reference signal-less detection of MAs in PPG signals. We did not consider articles introducing signal filtering or decomposition algorithms without previous identification of corrupted segments. Studies on MA-detecting approaches utilizing multiple channels and additional sensors such as accelerometers were also excluded. Despite its promising results, the literature on this topic shows several limitations and inconsistencies, particularly those regarding the model development and testing process and the measures used by authors to support the method's suitability for real-time applications. Moreover, there is a need for broader exploration and validation across different body parts and a standardized set of experiments specifically designed to test and validate MA detection approaches. It is essential to provide enough elements to enable researchers and developers to objectively assess the reliability and applicability of these methods and, therefore, obtain the most out of them.
Assuntos
Algoritmos , Artefatos , Aprendizado de Máquina , Fotopletismografia , Processamento de Sinais Assistido por Computador , Fotopletismografia/métodos , Humanos , Movimento (Física)RESUMO
Objective.This study proposes a closed-loop brain-machine interface (BMI) based on spinal cord stimulation to inhibit epileptic seizures, applying a semi-supervised machine learning approach that learns from Local Field Potential (LFP) patterns acquired on the pre-ictal (preceding the seizure) condition.Approach.LFP epochs from the hippocampus and motor cortex are band-pass filtered from 1 to 13 Hz, to obtain the time-frequency representation using the continuous Wavelet transform, and successively calculate the phase lock values (PLV). As a novelty, theZ-score-based PLV normalization using both modifiedk-means and Davies-Bouldin's measure for clustering is proposed here. Consequently, a generic seizure's detector is calibrated for detecting seizures on the normalized PLV, and enables the spinal cord stimulation for periods of 30 s in a closed-loop, while the BMI system detects seizure events. To calibrate the proposed BMI, a dataset with LFP signals recorded on five Wistar rats during basal state and epileptic crisis was used. The epileptic crisis was induced by injecting pentylenetetrazol (PTZ). Afterwards, two experiments without/with our BMI were carried out, inducing epileptic crisis by PTZ in Wistar rats.Main results.Stronger seizure events of high LFP amplitudes and long time periods were observed in the rat, when the BMI system was not used. In contrast, short-time seizure events of relative low intensity were observed in the rat, using the proposed BMI. The proposed system detected on unseen data the synchronized seizure activity in the hippocampus and motor cortex, provided stimulation appropriately, and consequently decreased seizure symptoms.Significance.Low-frequency LFP signals from the hippocampus and motor cortex, and cord spinal stimulation can be used to develop accurate closed-loop BMIs for early epileptic seizures inhibition, as an alternative treatment.
Assuntos
Interfaces Cérebro-Computador , Epilepsia , Ratos Wistar , Convulsões , Animais , Ratos , Convulsões/terapia , Epilepsia/terapia , Medula Espinal , Córtex Motor/fisiopatologia , Hipocampo , Masculino , Estimulação da Medula Espinal/métodos , Algoritmos , Aprendizado de Máquina , Pentilenotetrazol , Estimulação Elétrica/métodos , Eletroencefalografia/métodos , Processamento de Sinais Assistido por Computador , Análise de OndaletasRESUMO
Human-robot collaboration will play an important role in the fourth industrial revolution in applications related to hostile environments, mining, industry, forestry, education, natural disaster and defense. Effective collaboration requires robots to understand human intentions and tasks, which involves advanced user profiling. Voice-based communication, rich in complex information, is key to this. Beamforming, a technology that enhances speech signals, can help robots extract semantic, emotional, or health-related information from speech. This paper describes the implementation of a system that provides substantially improved signal-to-noise ratio (SNR) and speech recognition accuracy to a moving robotic platform for use in human-robot interaction (HRI) applications in static and dynamic contexts. This study focuses on training deep learning-based beamformers using acoustic model-based multi-style training with measured room impulse responses (RIRs). The results show that this approach outperforms training with simulated RIRs or matched measured RIRs, especially in dynamic conditions involving robot motion. The findings suggest that training with a broad range of measured RIRs is sufficient for effective HRI in various environments, making additional data recording or augmentation unnecessary. This research demonstrates that deep learning-based beamforming can significantly improve HRI performance, particularly in challenging acoustic environments, surpassing traditional beamforming methods.
Assuntos
Acústica , Robótica , Humanos , Robótica/métodos , Aprendizado Profundo , Razão Sinal-Ruído , Processamento de Sinais Assistido por ComputadorRESUMO
Objective.This study aims to use recurrence quantification analysis (RQA) of uterine vectormyometriogram (VMG) created from the slow wave (SW) and high wave (HW) bands of electrohysterogram (EHG) signals and assess the directionality of the EHG activity (horizontal orX, vertical orY) in normal-weight (NW) and overweight (OW) women during the first stage of labor.Approach. The study involved 41 parturient women (NW = 21 and OW = 20) during the first stage of labor, all of whom were attended at the Gynecology and Obstetrics Hospital of the Maternal and Child Institute of the State of Mexico in Toluca, Mexico. Twenty-minute EHG signals were analyzed in horizontal and vertical directions. Linear and nonlinear indices such as dominant frequency (Dom), Sample Entropy (SampEn), and RQA measures of VMG were computed for SW and HW bands.Main results. Significant differences in SampEn and Dom were observed in the SW band between NW and OW in bothXandYdirections, indicating more regular dynamics of electrical uterine activity and a higher Dom in NW parturient women compared to OW women. Additionally, the RQA indices calculated from the VMG of SW were consistent and revealed that NW women exhibit more regular dynamics compared to OW women.Significance. The study demonstrates that RQA of VMG signals and EHG directionality differentiate uterine activity between NW and OW women during the first stage of labor. These findings suggest that the uterine vector may become more periodic, predictable, and stable in NW women compared to OW women. This highlights the importance of tailored clinical strategies for managing labor in OW women to improve maternal and infant outcomes.
Assuntos
Sobrepeso , Humanos , Feminino , Adulto , Sobrepeso/fisiopatologia , Gravidez , Útero/diagnóstico por imagem , Adulto Jovem , Parto , Recidiva , Peso Corporal , Processamento de Sinais Assistido por ComputadorRESUMO
There are two widely used methods to measure the cardiac cycle and obtain heart rate measurements: the electrocardiogram (ECG) and the photoplethysmogram (PPG). The sensors used in these methods have gained great popularity in wearable devices, which have extended cardiac monitoring beyond the hospital environment. However, the continuous monitoring of ECG signals via mobile devices is challenging, as it requires users to keep their fingers pressed on the device during data collection, making it unfeasible in the long term. On the other hand, the PPG does not contain this limitation. However, the medical knowledge to diagnose these anomalies from this sign is limited by the need for familiarity, since the ECG is studied and used in the literature as the gold standard. To minimize this problem, this work proposes a method, PPG2ECG, that uses the correlation between the domains of PPG and ECG signals to infer from the PPG signal the waveform of the ECG signal. PPG2ECG consists of mapping between domains by applying a set of convolution filters, learning to transform a PPG input signal into an ECG output signal using a U-net inception neural network architecture. We assessed our proposed method using two evaluation strategies based on personalized and generalized models and achieved mean error values of 0.015 and 0.026, respectively. Our method overcomes the limitations of previous approaches by providing an accurate and feasible method for continuous monitoring of ECG signals through PPG signals. The short distances between the infer-red ECG and the original ECG demonstrate the feasibility and potential of our method to assist in the early identification of heart diseases.
Assuntos
Eletrocardiografia , Frequência Cardíaca , Redes Neurais de Computação , Fotopletismografia , Processamento de Sinais Assistido por Computador , Humanos , Eletrocardiografia/métodos , Fotopletismografia/métodos , Frequência Cardíaca/fisiologia , Algoritmos , Dispositivos Eletrônicos VestíveisRESUMO
BACKGROUND: Knee ligament rupture is one of the most common injuries, but the diagnosis of its severity tends to require the use of complex methods and analyses that are not always available to patients. AIM: The objective of this research is the investigation and development of a diagnostic aid system to analyze and determine patterns that characterize the presence of the injury and its degree of severity. METHODS: Implement a novel proposal of a framework based on stacked auto-encoder (SAE) for ground reaction force (GRF) signals analysis, coming from the GaitRec database. Analysis of the raw data is used to determine the main features that allow us to diagnose the presence of a knee ligament rupture and classify its severity as high, mid or mild. RESULTS: The process is divided into two stages to determine the presence of the lesion and, if necessary, evaluate variations in features to classify the degree of severity as high, mid, and mild. The framework presents an accuracy of 87 % and a F1-Score of 90 % for detecting ligament rupture and an accuracy of 86.5 % and a F1-Score of 87 % for classifying severity. CONCLUSION: This new methodology aims to demonstrate the potential of SAE in physiotherapy applications as an evaluation and diagnostic tool, identifying irregularities associated with ligament rupture and its degree of severity, thus providing updated information to the specialist during the rehabilitation process.
Assuntos
Traumatismos do Joelho , Humanos , Ruptura , Traumatismos do Joelho/diagnóstico por imagem , Traumatismos do Joelho/classificação , Masculino , Feminino , Adulto , Processamento de Sinais Assistido por ComputadorRESUMO
This study focuses on the acoustic classification of delphinid species at the southern continental slope of Brazil. Recordings were collected between 2013 and 2015 using towed arrays and were processed using a classifier to identify the species in the recordings. Using Raven Pro 1.6 software (Cornell Laboratory of Ornithology, Ithaca, NY), we analyzed whistles for species identification. The random forest algorithm in R facilitates classification analysis based on acoustic parameters, including low, high, delta, center, beginning, and ending frequencies, and duration. Evaluation metrics, such as correct and incorrect classification percentages, global accuracy, balanced accuracy, and p-values, were employed. Receiver operating characteristic curves and area-under-the-curve (AUC) values demonstrated well-fitting models (AUC ≥ 0.7) for species definition. Duration and delta frequency emerged as crucial parameters for classification, as indicated by the decrease in mean accuracy. Multivariate dispersion plots visualized the proximity between acoustic and visual match data and exclusively acoustic encounter (EAE) data. The EAE results classified as Delphinus delphis (n = 6), Stenella frontalis (n = 3), and Stenella longirostris (n = 2) provide valuable insights into the presence of these species between approximately 23° and 34° S in Brazil. This study demonstrates the effectiveness of acousting classification in discriminating delphinids through whistle parameters.
Assuntos
Acústica , Golfinhos , Vocalização Animal , Animais , Vocalização Animal/classificação , Oceano Atlântico , Golfinhos/classificação , Golfinhos/fisiologia , Espectrografia do Som , Brasil , Especificidade da Espécie , Processamento de Sinais Assistido por ComputadorRESUMO
Independent vector analysis (IVA) can be viewed as an extension of independent component analysis (ICA) to multiple datasets. It exploits the statistical dependency between different datasets through mutual information. In the context of motor imagery classification based on electroencephalogram (EEG) signals for the brain-computer interface (BCI), several methods have been proposed to extract features efficiently, mainly based on common spatial patterns, filter banks, and deep learning. However, most methods use only one dataset at a time, which may not be sufficient for dealing with a multi-source retrieving problem in certain scenarios. From this perspective, this paper proposes an original approach for feature extraction through multiple datasets based on IVA to improve the classification of EEG-based motor imagery movements. The IVA components were used as features to classify imagined movements using consolidated classifiers (support vector machines and K-nearest neighbors) and deep classifiers (EEGNet and EEGInception). The results show an interesting performance concerning the clustering of MI-based BCI patients, and the proposed method reached an average accuracy of 86.7%.
Assuntos
Interfaces Cérebro-Computador , Eletroencefalografia , Movimento , Máquina de Vetores de Suporte , Humanos , Eletroencefalografia/métodos , Movimento/fisiologia , Imaginação/fisiologia , Processamento de Sinais Assistido por Computador , AlgoritmosRESUMO
Recognizing user intention in reach-to-grasp motions is a critical challenge in rehabilitation engineering. To address this, a Machine Learning (ML) algorithm based on the Extreme Learning Machine (ELM) was developed for identifying motor actions using surface Electromyography (sEMG) during continuous reach-to-grasp movements, involving multiple Degrees of Freedom (DoFs). This study explores feature extraction methods based on time domain and autoregressive models to evaluate ELM performance under different conditions. The experimental setup encompassed variations in neuron size, time windows, validation with each muscle, increase in the number of features, comparison with five conventional ML-based classifiers, inter-subjects variability, and temporal dynamic response. To evaluate the efficacy of the proposed ELM-based method, an openly available sEMG dataset containing data from 12 participants was used. Results highlight the method's performance, achieving Accuracy above 85%, F-score above 90%, Recall above 85%, Area Under the Curve of approximately 84% and compilation times (computational cost) of less than 1 ms. These metrics significantly outperform standard methods (p < 0.05). Additionally, specific trends were found in increasing and decreasing performance in identifying specific tasks, as well as variations in the continuous transitions in the temporal dynamics response. Thus, the ELM-based method effectively identifies continuous reach-to-grasp motions through myoelectric data. These findings hold promise for practical applications. The method's success prompts future research into implementing it for more reliable and effective Human-Machine Interface (HMI) control. This can revolutionize real-time upper limb rehabilitation, enabling natural and complex Activities of Daily Living (ADLs) like object manipulation. The robust results encourages further research and innovative solutions to improve people's quality of life through more effective interventions.
Assuntos
Algoritmos , Eletromiografia , Força da Mão , Aprendizado de Máquina , Movimento , Humanos , Masculino , Força da Mão/fisiologia , Movimento/fisiologia , Feminino , Adulto , Processamento de Sinais Assistido por Computador , Adulto JovemRESUMO
Eye movement during blinking can be a significant artifact in Event-Related Potentials (ERP) analysis. Blinks produce a positive potential in the vertical electrooculogram (VEOG), spreading towards the posterior direction. Two methods are frequently used to suppress VEOGs: linear regression to subtract the VEOG signal from the electroencephalogram (EEG) and Independent Component Analysis (ICA). However, some information is lost in both. The present algorithm (1) statistically identifies the position of VEOGs in the frontopolar channels; (2) performs EEG averaging for each channel, which results in 'blink templates'; (3) subtracts each template from the respective EEG at each VEOG position, only when the linear correlation index between the template and the segment is greater than a chosen threshold L. The signals from twenty subjects were acquired using a behavioral test and were treated using FilterBlink for subsequent ERP analysis. A model was designed to test the method for each subject using twenty copies of the EEG signal from the subject's mid-central channel (with nearly no VEOG) representing the EEG channels and their respective blink templates. At the same 200 equidistant time points (marks), a signal (2.5 sinusoidal cycles at 1050 ms emulating an ERP) was mixed with each model channel and the respective blink template of that channel, between 500 to 1200 ms after each mark. According to the model, VEOGs interfered with both ERPs and the ongoing EEG, mainly on the anterior medial leads, and no significant effect was observed on the mid-central channel (Cz). FilterBlink recovered approximately 90% (Fp1) to 98% (Fz) of the original ERP and EEG signals for L = 0.1. The method reduced the VEOG effect on the EEG after ERP and blink-artifact averaging in analyzing real signals. The method is straightforward and effective for VEOG attenuation without significant distortion in the EEG signal and embedded ERPs.
Assuntos
Algoritmos , Artefatos , Piscadela , Eletroencefalografia , Eletroculografia , Humanos , Eletroencefalografia/métodos , Eletroculografia/métodos , Piscadela/fisiologia , Masculino , Feminino , Adulto , Processamento de Sinais Assistido por Computador , Potenciais Evocados/fisiologia , Adulto Jovem , Movimentos Oculares/fisiologiaRESUMO
Stroke is a neurological condition that usually results in the loss of voluntary control of body movements, making it difficult for individuals to perform activities of daily living (ADLs). Brain-computer interfaces (BCIs) integrated into robotic systems, such as motorized mini exercise bikes (MMEBs), have been demonstrated to be suitable for restoring gait-related functions. However, kinematic estimation of continuous motion in BCI systems based on electroencephalography (EEG) remains a challenge for the scientific community. This study proposes a comparative analysis to evaluate two artificial neural network (ANN)-based decoders to estimate three lower-limb kinematic parameters: x- and y-axis position of the ankle and knee joint angle during pedaling tasks. Long short-term memory (LSTM) was used as a recurrent neural network (RNN), which reached Pearson correlation coefficient (PCC) scores close to 0.58 by reconstructing kinematic parameters from the EEG features on the delta band using a time window of 250 ms. These estimates were evaluated through kinematic variance analysis, where our proposed algorithm showed promising results for identifying pedaling and rest periods, which could increase the usability of classification tasks. Additionally, negative linear correlations were found between pedaling speed and decoder performance, thereby indicating that kinematic parameters between slower speeds may be easier to estimate. The results allow concluding that the use of deep learning (DL)-based methods is feasible for the estimation of lower-limb kinematic parameters during pedaling tasks using EEG signals. This study opens new possibilities for implementing controllers most robust for MMEBs and BCIs based on continuous decoding, which may allow for maximizing the degrees of freedom and personalized rehabilitation.
Assuntos
Aprendizado Profundo , Eletroencefalografia , Extremidade Inferior , Humanos , Eletroencefalografia/métodos , Fenômenos Biomecânicos , Masculino , Extremidade Inferior/fisiologia , Adulto , Feminino , Interfaces Cérebro-Computador , Ciclismo/fisiologia , Redes Neurais de Computação , Adulto Jovem , Algoritmos , Processamento de Sinais Assistido por ComputadorRESUMO
This work addresses the challenge of classifying multiclass visual EEG signals into 40 classes for brain-computer interface applications using deep learning architectures. The visual multiclass classification approach offers BCI applications a significant advantage since it allows the supervision of more than one BCI interaction, considering that each class label supervises a BCI task. However, because of the nonlinearity and nonstationarity of EEG signals, using multiclass classification based on EEG features remains a significant challenge for BCI systems. In the present work, mutual information-based discriminant channel selection and minimum-norm estimate algorithms were implemented to select discriminant channels and enhance the EEG data. Hence, deep EEGNet and convolutional recurrent neural networks were separately implemented to classify the EEG data for image visualization into 40 labels. Using the k-fold cross-validation approach, average classification accuracies of 94.8% and 89.8% were obtained by implementing the aforementioned network architectures. The satisfactory results obtained with this method offer a new implementation opportunity for multitask embedded BCI applications utilizing a reduced number of both channels (<50%) and network parameters (<110 K).
Assuntos
Algoritmos , Interfaces Cérebro-Computador , Aprendizado Profundo , Eletroencefalografia , Redes Neurais de Computação , Eletroencefalografia/métodos , Humanos , Processamento de Sinais Assistido por ComputadorRESUMO
The integration of artificial intelligence (AI) models in the classification of electromyographic (EMG) signals represents a significant advancement in the design of control systems for prostheses. This study explores the development of a portable system that classifies the electrical activity of three shoulder muscles in real time for actuator control, marking a milestone in the autonomy of prosthetic devices. Utilizing low-power microcontrollers, the system ensures continuous EMG signal recording, enhancing user mobility. Focusing on a case study-a 42-year-old man with left shoulder disarticulation-EMG activity was recorded over two days using a specifically designed electronic board. Data processing was performed using the Edge Impulse platform, renowned for its effectiveness in implementing AI on edge devices. The first day was dedicated to a training session with 150 repetitions spread across 30 trials and three different movements. Based on these data, the second day tested the AI model's ability to classify EMG signals in new movement executions in real time. The results demonstrate the potential of portable AI-based systems for prosthetic control, offering accurate and swift EMG signal classification that enhances prosthetic user functionality and experience. This study not only underscores the feasibility of real-time EMG signal classification but also paves the way for future research on practical applications and improvements in the quality of life for prosthetic users.
Assuntos
Eletromiografia , Aprendizado de Máquina , Ombro , Humanos , Eletromiografia/métodos , Adulto , Masculino , Ombro/fisiologia , Músculo Esquelético/fisiologia , Processamento de Sinais Assistido por ComputadorRESUMO
We use a multiscale symbolic approach to study the complex dynamics of temporal lobe refractory epilepsy employing high-resolution intracranial electroencephalogram (iEEG). We consider the basal and preictal phases and meticulously analyze the dynamics across frequency bands, focusing on high-frequency oscillations up to 240 Hz. Our results reveal significant periodicities and critical time scales within neural dynamics across frequency bands. By bandpass filtering neural signals into delta, theta, alpha, beta, gamma, and ripple high-frequency bands (HFO), each associated with specific neural processes, we examine the distinct nonlinear dynamics. Our method introduces a reliable approach to pinpoint intrinsic time lag scales τ within frequency bands of the basal and preictal signals, which are crucial for the study of refractory epilepsy. Using metrics such as permutation entropy (H), Fisher information (F), and complexity (C), we explore nonlinear patterns within iEEG signals. We reveal the intrinsic τmax that maximize complexity within each frequency band, unveiling the nonlinear subtle patterns of the temporal structures within the basal and preictal signal. Examining the H×F and C×F values allows us to identify differences in the delta band and a band between 200 and 220 Hz (HFO 6) when comparing basal and preictal signals. Differences in Fisher information in the delta and HFO 6 bands before seizures highlight their role in capturing important system dynamics. This offers new perspectives on the intricate relationship between delta oscillations and HFO waves in patients with focal epilepsy, highlighting the importance of these patterns and their potential as biomarkers.