Power-based Features Research Articles

Assessment of Different Feature Extraction Methods for Discriminating Expressed Emotions during Music Performance towards BCMI Application.

A Brain-Computer Music Interface (BCMI) system may be designed to harness electroencephalography (EEG) signals for control over musical outputs in the context of emotionally expressive performance. To develop a real-time BCMI system, accurate and computationally efficient emotional biomarkers should first be identified. In the current study, we evaluated the ability of various features to discriminate between emotions expressed during music performance with the aim of developing a BCMI system. EEG data was recorded while subjects performed simple piano music with contrasting emotional cues and rated their success in communicating the intended emotion. Power spectra and connectivity features (Magnitude Square Coherence (MSC) and Granger Causality (GC)) were extracted from the signals. Two different approaches of feature selection were used to assess the contribution of neutral baselines in detection accuracies; 1- utilizing the baselines to normalize the features, 2- not taking them into account (non-normalized features). Finally, the Support Vector Machine (SVM) has been used to evaluate and compare the capability of various features for emotion detection. Best detection accuracies were obtained from the non-normalized MSC-based features equal to 85.57 ± 2.34, 84.93 ± 1.67, and 87.16 ± 0.55 for arousal, valence, and emotional conditions respectively, while the power-based features had the lowest accuracies. Both connectivity features show acceptable accuracy while requiring short processing time and thus are potential candidates for the development of a real-time BCMI system.

Discriminative sEMG-based features to assess damping ability and interpret activation patterns in lower-limb muscles of ACLR athletes

ObjectiveThe main goal of the athletes who undergo anterior cruciate ligament reconstruction (ACLR) surgery is a successful return-to-sport. At this stage, identifying muscular deficits becomes important. Hence, in this study, three discriminative features based on surface electromyographic signals (sEMG) acquired in a dynamic protocol are introduced to assess the damping ability and interpret activation patterns in lower-limb muscles of ACLR athletes. MethodsThe features include the median frequency of the power spectrum density (PSD), the relative percentage of the equivalent damping or equivalent stiffness derived from the median frequency, and the energy of the signals in the time–frequency plane of the pseudo-Wigner-Ville distribution (PWVD). To evaluate the features, 11 healthy and 11 ACLR athletes (6 months post-reconstruction surgery) were recruited to acquire the sEMG signals from the medial and the lateral parts of the hamstrings, quadriceps, and gastrocnemius muscles in pre- and post-fatigue single-leg landings. ResultsA significant damping deficiency is observed in the hamstring muscles of ACLR athletes by evaluating the proposed features. This deficiency indicates that more attention should be paid to this muscle of ACLR athletes in pre-return-to-sport rehabilitations. ConclusionThe quality of electromyography-based pre-return-to-sport assessments on ACLR subjects depends on the sEMG acquisition protocol, as well as the type and nature of the extracted features. Hence, combinatorial application of both energy-based features (derived from the PWVD) and power-based features (derived from the PSD) could facilitate the assessment process by providing additional biomechanical information regarding the behavior of the muscles surrounding the knee.

Mental State Classification Using Multi-Graph Features.

We consider the problem of extracting features from passive, multi-channel electroencephalogram (EEG) devices for downstream inference tasks related to high-level mental states such as stress and cognitive load. Our proposed feature extraction method uses recently developed spectral-based multi-graph tools and applies them to the time series of graphs implied by the statistical dependence structure (e.g., correlation) amongst the multiple sensors. We study the features in the context of two datasets each consisting of at least 30 participants and recorded using multi-channel EEG systems. We compare the classification performance of a classifier trained on the proposed features to a classifier trained on the traditional band power-based features in three settings and find that the two feature sets offer complementary predictive information. We conclude by showing that the importance of particular channels and pairs of channels for classification when using the proposed features is neuroscientifically valid.

Functional Connectivity and Frequency Power Alterations during P300 Task as a Result of Amyotrophic Lateral Sclerosis.

Amyotrophic Lateral Sclerosis (ALS) is one of the most aggressive neurodegenerative diseases and is now recognized as a multisystem network disorder with impaired connectivity. Further research for the understanding of the nature of its cognitive affections is necessary to monitor and detect the disease, so this work provides insight into the neural alterations occurring in ALS patients during a cognitive task (P300 oddball paradigm) by measuring connectivity and the power and latency of the frequency-specific EEG activity of 12 ALS patients and 16 healthy subjects recorded during the use of a P300-based BCI to command a robotic arm. For ALS patients, in comparison to Controls, the results (p < 0.05) were: an increment in latency of the peak ERP in the Delta range (OZ) and Alpha range (PO7), and a decreased power in the Beta band among most electrodes; connectivity alterations among all bands, especially in the Alpha band between PO7 and the channels above the motor cortex. The evolution observed over months of an advanced-state patient backs up these findings. These results were used to compute connectivity- and power-based features to discriminate between ALS and Control groups using Support Vector Machine (SVM). Cross-validation achieved a 100% in specificity and 75% in sensitivity, with an overall 89% success.

Cross-participant prediction of vigilance stages through the combined use of wPLI and wSMI EEG functional connectivity metrics.

Functional connectivity (FC) metrics describe brain inter-regional interactions and may complement information provided by common power-based analyses. Here, we investigated whether the FC-metrics weighted Phase Lag Index (wPLI) and weighted Symbolic Mutual Information (wSMI) may unveil functional differences across four stages of vigilance-wakefulness (W), NREM-N2, NREM-N3, and REM sleep-with respect to each other and to power-based features. Moreover, we explored their possible contribution in identifying differences between stages characterized by distinct levels of consciousness (REM+W vs. N2+N3) or sensory disconnection (REM vs. W). Overnight sleep and resting-state wakefulness recordings from 24 healthy participants (27 ± 6 years, 13F) were analyzed to extract power and FC-based features in six classical frequency bands. Cross-validated linear discriminant analyses (LDA) were applied to investigate the ability of extracted features to discriminate (1) the four vigilance stages, (2) W+REM vs. N2+N3, and (3) W vs. REM. For the four-way vigilance stages classification, combining features based on power and both connectivity metrics significantly increased accuracy relative to considering only power, wPLI, or wSMI features. Delta-power and connectivity (0.5-4 Hz) represented the most relevant features for all the tested classifications, in line with a possible involvement of slow waves in consciousness and sensory disconnection. Sigma-FC, but not sigma-power (12-16 Hz), was found to strongly contribute to the differentiation between states characterized by higher (W+REM) and lower (N2+N3) probabilities of conscious experiences. Finally, alpha-FC resulted as the most relevant FC-feature for distinguishing among wakefulness and REM sleep and may thus reflect the level of disconnection from the external environment.

Agent‐based situational awareness system for severity in closeness of voltage instability occurrence

In this study, on the basis of a new agent-based situational awareness platform, the amount of severity in closeness to voltage instability occurrence is determined. In the proposed platform (with the aid of the agents of the disturbance detection unit that are responsible for perception of environmental events and understanding the current situation and the agents of the early enough instability prediction unit that predicts instability occurrence), the novelty is in creating the agents of clustering units that are responsible for prediction of the future status, i.e. severity in closeness to voltage instability occurrence through determining the severity class. This clustering unit maps the reactive power-based features obtained from unconstrained power flow analyses, to the instability time; without any need of post-disturbance data, i.e. the method belongs to just-after-disturbance algorithms. Then, it estimates the severity of the closeness to instability for any test scenario according to its membership degree related to the pre-defined severity clusters. The simulation results show acceptable overall accuracy (up to 99%) in performing early warning task for operators of power systems.

Early Prediction of Sepsis From Clinical Data Using Ratio and Power-Based Features

Early prediction of sepsis is of utmost importance to provide optimal care at an early stage. This work aims to deploy soft-computing and machine learning techniques for early prediction of sepsis. An algorithm for early identification of sepsis using ratio and power-based feature transformation of easily obtainable clinical data. PhysioNet Challenge 2019 provided ICU data from three separate hospital systems. Publicly shared data from two hospital systems are used for training and validation purposes, whereas sequestered data from all the three systems is used for testing. Over 60,000 ICU patients with up to 40 clinical variables are sourced for each hour of their ICU stay. The Sepsis-3 criterion is applied for annotation. None. The clinical feature exploration for early prediction of sepsis is achieved using the proposed framework named genetic algorithm optimized ratio and power-based expert algorithm. An optimal feature set containing 46 ratio and power-based features is computed from the given patient covariates using genetic algorithm optimized ratio and power-based expert and grouped with identified 17 raw features and 55 statistical features to form a final feature set of 118 clinical features to predict the onset of sepsis in the proceeding 6 hours. The obtained features are fed to a hybrid Random Under-Sampling-Boosting algorithm, called RUSBoost for alleviating the involved class imbalance. The optimal RUSBoost model has achieved a normalized utility score of 0.318 on full test data. The proposed study supports the realization of a hospital-specific customized solution in the form of an early-warning system for sepsis. However, an extended analysis is necessary to apply this framework for hospital-independent diagnosis of sepsis in general. Nevertheless, the clinical utility of hospital-specific customized solutions based on the proposed method across a wide range of hospital systems needs to be studied.

Channel-Wise Characterization of High Frequency Oscillations for Automated Identification of the Seizure Onset Zone

High frequency oscillations (HFOs) in intracranial electroencephalography (iEEG) recordings are a promising clinical biomarker that can help define the epileptogenic regions in the brain. The aim of this study is to characterize the spatial and temporal distribution of HFOs in channel-wise instead of event-level as usual and to develop an automated the seizure onset zone (SOZ) identification by using a support vector machine (SVM) approach on the channel-wise features in a short-term recording. In this work, five consecutive patients with medically intractable epilepsy were enrolled. For each patient, ten-minute segments were defined from two hours of iEEG recordings during sleep state. A total of 17 channel-wise features including 6 rate-based, 6 duration-based, 3 amplitude-based, and 2 power-based features of HFOs were extracted from each 10-min segment, which including ripples (Rs, 80-250 Hz) and fast ripples (FRs, 250-500Hz) were detected automatically using validated detectors. Each channel-wise feature was ranked by using the Student's t-test method and the most distinctive features were selected to explore the characteristics of HFOs in each channel. A supervised-learning based SVM classifier with the selected channel-wise features or their combinations was developed to identify each channel within the independently clinician-defined SOZ or not. Over 3,816 chanel-10-min segments of iEEG recordings, the evaluated accuracy, sensitivity, and specificity of the proposed approach with the optimal combination of top five ranked features for SOZ identification are 86.6%, 73.0%, and 94.1%, respectively, for ten-fold cross-validation, and 86.0%, 79.2 %, and 91.8%, respectively, for the leave-1-out cross-validation. Compared with the recently reported SOZ detectors based on event-wise feature of HFOs, the channel-wise features and the combination with machine learning approach demonstrate its feasibility in SOZ identification with a relative higher performance and potentially reduce the time needed currently for long-term recording and manual inspection.

Cross-participant prediction of vigilance stages through the combined use of wPLI and wSMI EEG functional connectivity metrics

Functional connectivity (FC) metrics describe brain inter-regional interactions and may complement information provided by common power-based analyses. Here, we investigated whether the FC-metrics weighted Phase Lag Index (wPLI) and weighted Symbolic Mutual Information (wSMI) may unveil functional differences across four stages of vigilance-wakefulness (W), NREM-N2, NREM-N3, and REM sleep-with respect to each other and to power-based features. Moreover, we explored their possible contribution in identifying differences between stages characterized by distinct levels of consciousness (REM+W vs. N2+N3) or sensory disconnection (REM vs. W). Overnight sleep and resting-state wakefulness recordings from 24 healthy participants (27 ± 6 years, 13F) were analyzed to extract power and FC-based features in six classical frequency bands. Cross-validated linear discriminant analyses (LDA) were applied to investigate the ability of extracted features to discriminate (1) the four vigilance stages, (2) W+REM vs. N2+N3, and (3) W vs. REM. For the four-way vigilance stages classification, combining features based on power and both connectivity metrics significantly increased accuracy relative to considering only power, wPLI, or wSMI features. Delta-power and connectivity (0.5-4 Hz) represented the most relevant features for all the tested classifications, in line with a possible involvement of slow waves in consciousness and sensory disconnection. Sigma-FC, but not sigma-power (12-16 Hz), was found to strongly contribute to the differentiation between states characterized by higher (W+REM) and lower (N2+N3) probabilities of conscious experiences. Finally, alpha-FC resulted as the most relevant FC-feature for distinguishing among wakefulness and REM sleep and may thus reflect the level of disconnection from the external environment.

Emotion recognition from single-trial EEG based on kernel Fisher's emotion pattern and imbalanced quasiconformal kernel support vector machine.

Electroencephalogram-based emotion recognition (EEG-ER) has received increasing attention in the fields of health care, affective computing, and brain-computer interface (BCI). However, satisfactory ER performance within a bi-dimensional and non-discrete emotional space using single-trial EEG data remains a challenging task. To address this issue, we propose a three-layer scheme for single-trial EEG-ER. In the first layer, a set of spectral powers of different EEG frequency bands are extracted from multi-channel single-trial EEG signals. In the second layer, the kernel Fisher's discriminant analysis method is applied to further extract features with better discrimination ability from the EEG spectral powers. The feature vector produced by layer 2 is called a kernel Fisher's emotion pattern (KFEP), and is sent into layer 3 for further classification where the proposed imbalanced quasiconformal kernel support vector machine (IQK-SVM) serves as the emotion classifier. The outputs of the three layer EEG-ER system include labels of emotional valence and arousal. Furthermore, to collect effective training and testing datasets for the current EEG-ER system, we also use an emotion-induction paradigm in which a set of pictures selected from the International Affective Picture System (IAPS) are employed as emotion induction stimuli. The performance of the proposed three-layer solution is compared with that of other EEG spectral power-based features and emotion classifiers. Results on 10 healthy participants indicate that the proposed KFEP feature performs better than other spectral power features, and IQK-SVM outperforms traditional SVM in terms of the EEG-ER accuracy. Our findings also show that the proposed EEG-ER scheme achieves the highest classification accuracies of valence (82.68%) and arousal (84.79%) among all testing methods.