A hybrid model to predict the pressure gradient for the liquid-liquid flow in both horizontal and inclined pipes for unknown flow patterns.

Accurate prediction of the pressure gradient (PG) for the oil-water flow requires identification of the flow pattern (FP), which is usually achieved by using either an expensive measurement system or time-consuming manual observations. This study proposes a hybrid scheme where two machine-learning (ML) models are coupled in a series to predict the PG value without any conclusive FP information. The first model (M1) determines the oil-water FP, whereas the second model (M2) predicts the oil-water PG. 1637 experimental data points for the oil-water flow in both horizontal and inclined pipes are used to develop the models. The important feature subset is identified using the modified Binary Grey Wolf Optimization Particle Swarm Optimization (BGWOPSO) algorithm. The MLs' performance is evaluated using metrics including accuracy, sensitivity, specificity, and F1-score for the M1, and coefficient of variation of root mean squared error, mean absolute percentage error (MAPE), and median absolute percentage error for the M2. The evaluation metrics are cross-validated using a repeated train-test split strategy. The results showed that the overall FP classification accuracy is greater than 91%, with 90.61% sensitivity and 98.53% specificity using the weighted majority voting for M1. With the Gaussian Process regression for M2, the evaluation metrics for the PG prediction were found to be 10.65%, 86.26 Pa/m, and 0.96 for MAPE, root mean square error, and adjusted coefficient of determination, respectively. Statistical analysis showed that the selected features for liquids' and pipe's properties using the BGWOPSO algorithm were adequate to attain superior performance for both models. The achieved MAPE using the proposed hybrid model is superior to existing mechanistic or correlation-based models reported in the literature (between 26 and 69%). The proposed hybrid scheme can significantly reduce the costs associated with identifying the oil-water flow profile and be critical in designing energy-efficient transportation of liquid-liquid flow.

Development of Machine-Learning Algorithms for Recognition of Subjects' Upper Limb Movement Intention Using Electroencephalogram Signals.

This study aims to classify rest and upper limb movements execution and intention using electroencephalogram (EEG) signals by developing machine-learning (ML) algorithms. Five different MLs are implemented, including k-Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA), Naïve Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF). The EEG data from fifteen healthy subjects during motor execution (ME) and motor imagination (MI) are preprocessed with Independent Component Analysis (ICA) to reduce eye-blinking associated artifacts. A sliding window technique varying from 1 s to 2 s is used to segment the signals. The majority voting (MV) strategy is employed during the post-processing stage. The results show that the application of ICA increases the accuracy of MI up to 6%, which is improved further by 1-2% using the MV (p<0.05). However, the improvement in the accuracies is more significant in MI (>5%) than in ME (<1%), indicating a more significant influence of eye-blinking artifacts in the EEG signals during MI than ME. Among the MLs, both RF and SVM consistently produced better accuracies in both ME and MI. Using RF, the 2 s window size produced the highest accuracies in both ME and MI than the smaller window sizes.

A Multi-Window Majority Voting Strategy to Improve Hand Gesture Recognition Accuracies Using Electromyography Signal.

The electromyography (EMG) signal has great potential to determine the hand gestures automatically before the actual move begins. However, parameters of the sliding window along with the EMG signal, such as window size and overlapping size, as well as the number of votes in post-processing, such as majority voting, can significantly influence the gesture recognition accuracy. These phenomena have been investigated only in a few studies on a small number of subjects. The aim of this study is two-fold. First, to determine the influence of different window and overlapping sizes on the machine-learning performance using a large database consists of forty healthy subjects. Second, to develop a novel multi-window scheme to accumulate a large number of votes compared to the conventional single-window majority voting to improve gesture recognition accuracy. A large publicly available EMG dataset was used in this study. The window and overlapping sizes were varied between 50ms and 500ms, and between 0% and 80%, respectively. Six machine-learning algorithms, including k-Nearest Neighbor, Linear Discriminant Analysis, Logistic Regression, Naïve Bayes, Support Vector Machine, and Random Forest were used to classify six different hand gestures. Results show that the overall classification accuracy can be substantially improved by increasing the window size, overlapping size, and the number of votes in the majority voting strategy (p < 0.05). The maximum accuracy was achieved using the Random Forest algorithm. The two-way repeated measure analysis of variance shows that the proposed multi-window scheme substantially improved the overall accuracy of the machine-learning algorithms compared to the conventional majority voting. The proposed method can be instrumental for efficient control of prosthetic or exoskeleton devices.

Design and kinematic analysis of a novel upper limb exoskeleton for rehabilitation of stroke patients.

This paper details the design process and features of a novel upper limb rehabilitation exoskeleton named CLEVER (Compact, Low-weight, Ergonomic, Virtual/Augmented Reality Enhanced Rehabilitation) ARM. The research effort is focused on designing a lightweight and ergonomic upper-limb rehabilitation exoskeleton capable of producing diverse and perceptually rich training scenarios. To this end, the knowledge available in the literature of rehabilitation robotics is used along with formal conceptual design techniques. This paper briefly reviews the systematic approach used for design of the exoskeleton, and elaborates on the specific details of the proposed design concept and its advantages over other design possibilities. The kinematic structure of CLEVER ARM has eight degrees of freedom supporting the motion of shoulder girdle, glenohumeral joint, elbow and wrist. Six degrees of freedom of the exoskeleton are active, and the two degrees of freedom supporting the wrist motion are passive. Kinematics of the proposed design is studied analytically and experimentally with the aid of a 3D printed prototype. The paper is concluded by some remarks on the optimization of the design, motorization of device, and the fabrication challenges.

Enhanced automated sleep spindle detection algorithm based on synchrosqueezing.

Detection of sleep spindles is of major importance in the field of sleep research. However, manual scoring of spindles on prolonged recordings is very laborious and time-consuming. In this paper, we introduce a new algorithm based on synchrosqueezing transform for detection of sleep spindles. Synchrosqueezing is a powerful time-frequency analysis tool that provides precise frequency representation of a multicomponent signal through mode decomposition. Subsequently, the proposed algorithm extracts and compares the basic features of a spindle-like activity with its surrounding, thus adapting to an expert's visual criteria for spindle scoring. The performance of the algorithm was assessed against the spindle scoring of one expert on continuous electroencephalogram sleep recordings from two subjects. Through appropriate choice of synchrosqueezing parameters, our proposed algorithm obtained a maximum sensitivity of 96.5% with 98.1% specificity. Compared to previously published works, our algorithm has shown improved performance by enhancing the quality of sleep spindle detection.

Improved spindle detection through intuitive pre-processing of electroencephalogram.

BACKGROUND: Numerous signal processing techniques have been proposed for automated spindle detection on EEG recordings with varying degrees of success. While the latest techniques usually introduce computational complexity and/or vagueness, the conventional techniques attempted in literature have led to poor results. This study presents a spindle detection approach which relies on intuitive pre-processing of the EEG prior to spindle detection, thus resulting in higher accuracy even with standard techniques. NEW METHOD: The pre-processing techniques proposed include applying the derivative operator on the EEG, suppressing the background activity using Empirical Mode Decomposition and shortlisting candidate EEG segments based on eye-movements on the EOG. RESULTS/COMPARISON: Results show that standard signal processing tools such as wavelets and Fourier transforms perform much better when coupled with apt pre-processing techniques. The developed algorithm also relies on data-driven thresholds ensuring its adaptability to inter-subject and inter-scorer variability. When tested on sample EEG segments scored by multiple experts, the algorithm identified spindles with average sensitivities of 96.14 and 92.85% and specificities of 87.59 and 84.85% for Fourier transform and wavelets respectively. These results are found to be on par with results obtained by other recent studies in this area.

Effect of resistive inspiratory and expiratory loading on cardio-respiratory interaction in healthy subjects.

Resistive loading affects the breathing pattern and causes an increase in negative intrathoracic pressure. The aim of this paper was to study the influence inspiratory and expiratory loading on cardio-respiratory interaction. We recorded electrocardiogram (ECG) and respiratory inductance plethysmogram (RIP) in 11 healthy male subjects under normal and resistive loading conditions. The R-R time series were extracted from the ECG and respiratory phases were calculated from the ribcage and abdominal RIP using the Hilbert transform. Both the series were transformed into ternary symbol vectors based on the changes between two successive R-R intervals or respiratory phases, respectively. Subsequently, words of length `3 digits' were formed and the correspondence between words of the two series was determined to quantify cardio-respiratory interaction. Adding inspiratory and expiratory resistive loads resulted in an increase in inspiratory and expiatory time, respectively. Furthermore, we observed a significant increase in cardio-respiratory interaction during inspiratory resistive loading as compared to expiratory resistive loading (ribcage: 22.1±7.2 vs. 12.5±4.3 %, p<;0.0001; abdomen: 18.8±8.5 vs. 12.1±3.1 %, p<;0.05, respectively). Further studies may aid in better understanding the underlying physiological mechanisms and management of patients with breathing disorders.

Predicting epileptic seizures in scalp EEG based on a variational Bayesian Gaussian mixture model of zero-crossing intervals.

A novel patient-specific seizure prediction method based on the analysis of positive zero-crossing intervals in scalp electroencephalogram (EEG) is proposed. In a moving-window analysis, the histogram of these intervals for the current EEG epoch is computed, and the values corresponding to specific bins are selected as an observation. Then, the set of observations from the last 5 min is compared with two reference sets of data points (preictal and interictal) through novel measures of similarity and dissimilarity based on a variational Bayesian Gaussian mixture model of the data. A combined index is then computed and compared with a patient-specific threshold, resulting in a cumulative measure which is utilized to form an alarm sequence for each channel. Finally, this channel-based information is used to generate a seizure prediction alarm. The proposed method was evaluated using ∼ 561 h of scalp EEG including a total of 86 seizures in 20 patients. A high sensitivity of 88.34 % was achieved with a false prediction rate of 0.155 h⁻¹ and an average prediction time of 22.5 min for the test dataset. The proposed method was also tested against a Poisson-based random predictor.

Detection of epileptic seizures in scalp electroencephalogram: an automated real-time wavelet-based approach.

This study evaluates a new automated patient-specific method for epileptic seizure detection using scalp electroencephalogram (EEG). The method relies on a normalized wavelet-based index, named the combined seizure index (CSI), and requires a seizure example and a nonseizure EEG interval as reference. The CSI is derived for every epoch in each EEG channel and is sensitive to both the rhythmicity and relative energy of that epoch and the consistency of EEG patterns among different channels. Increasing significantly as seizures occur, the CSI is monitored using a one-sided cumulative sum test to generate appropriate alarms in each channel. A seizure alarm is finally generated according to channel-based information. The proposed method was evaluated using the scalp EEG test data of approximately 236 hours from 26 patients with a total of 79 focal seizures, achieving a high sensitivity of approximately 91% with a false detection rate of 0.33 per hour and a median detection latency of 7 seconds. In addition, statistical analysis revealed that the average CSI around the onset on the side of the focus in patients with temporal lobe epilepsy (TLE) is significantly greater than that of the opposite side (P < 0.001), indicating the capability of this index in lateralizing the seizure focus in this type of epilepsy.

Specific change in spectral power of fetal heart rate variability related to fetal acidemia during labor: comparison between preterm and term fetuses.

BACKGROUND: Spectral analysis of fetal heart rate (FHR) variability is a useful method to assess fetal condition. There have been several studies involving the change in spectral power related to fetal acidemia, but the results have been inconsistent. AIMS: To determine the change in spectral power related to fetal umbilical arterial pH at birth, dividing cases into preterm (31-36 weeks) and term (≥37 weeks) gestations. STUDY DESIGN: Case-control study. The 514 cases of deliveries were divided into a low-pH group (an umbilical arterial pH <7.2) and a control group (pH≥7.2). SUBJECTS: FHR recorded on cardiotocography during the last 2h of labor. OUTCOME MEASURES: The spectral powers in various bands of FHR variability. RESULTS: In preterm fetuses, the total, low (LF), and movement (MF) frequency spectral powers and LF/HF ratio were significantly lower in the low-pH group than the control group (all P<0.05). In contrast, in term fetuses, the total frequency, LF, and MF powers were significantly higher in the low-pH group than the control group (all P<0.05). The area under the receiver operating characteristic of LF power to detect a low pH at birth was 0.794 in preterm fetuses and 0.595 in term fetuses. The specificity was 86.8% and 93.3% in preterm and term fetuses, respectively. CONCLUSIONS: The changes in spectral power responding to a low pH are different between term and preterm fetuses. Spectral analysis of FHR variability may be useful fetal monitoring for early detection of fetal acidemia.

Epileptic seizure prediction using variational mixture of Gaussians.

We propose a novel patient-specific method for predicting epileptic seizures by analysis of positive zero-crossing intervals in scalp electroencephalogram (EEG). In real-time analysis, the histogram of these intervals for the current EEG epoch is computed, and the values which correspond to the bins discriminating between interictal and preictal references are selected as an observation. Then, the set of observations from the last 5 min is compared with two reference sets of data points (interictal and preictal) using a variational Gaussian mixture model (GMM) of the data, and a combined index is computed. Comparing this index with a patient-specific threshold, an alarm sequence is produced for each channel. Finally, a seizure prediction alarm is generated according to channel-based information. The proposed method was evaluated using ~40.3 h of scalp EEG recordings from 6 patients with total of 28 partial seizures. A high sensitivity of 95% was achieved with a false prediction rate of 0.134/h and an average prediction time of 22.8 min for the test dataset.

Predicting temporal lobe epileptic seizures based on zero-crossing interval analysis in scalp EEG.

A novel real-time patient-specific algorithm to predict epileptic seizures is proposed. The method is based on the analysis of the positive zero-crossing intervals in the scalp electroencephalogram (EEG), describing the brain dynamics. In a moving-window analysis, the histogram of these intervals in each EEG epoch is computed, and the distribution of the histogram value in specific bins, selected using interictal and preictal references, is estimated based on the values obtained from the current epoch and the epochs of the last 5 min. The resulting distribution for each selected bin is then compared to two reference distributions (interictal and preictal), and a seizure prediction index is developed. Comparing this index with a patient-specific threshold for all EEG channels, a seizure prediction alarm is finally generated. The algorithm was tested on approximately 15.5 hours of multichannel scalp EEG recordings from three patients with temporal lobe epilepsy, including 14 seizures. 86% of seizures were predicted with an average prediction time of 20.8 min and a false prediction rate of 0.12/hr.

Automated real-time epileptic seizure detection in scalp EEG recordings using an algorithm based on wavelet packet transform.

A novel wavelet-based algorithm for real-time detection of epileptic seizures using scalp EEG is proposed. In a moving-window analysis, the EEG from each channel is decomposed by wavelet packet transform. Using wavelet coefficients from seizure and nonseizure references, a patient-specific measure is developed to quantify the separation between seizure and nonseizure states for the frequency range of 1-30 Hz. Utilizing this measure, a frequency band representing the maximum separation between the two states is determined and employed to develop a normalized index, called combined seizure index (CSI). CSI is derived for each epoch of every EEG channel based on both rhythmicity and relative energy of that epoch as well as consistency among different channels. Increasing significantly during ictal states, CSI is inspected using one-sided cumulative sum test to generate proper channel alarms. Analyzing alarms from all channels, a seizure alarm is finally generated. The algorithm was tested on scalp EEG recordings from 14 patients, totaling approximately 75.8 h with 63 seizures. Results revealed a high sensitivity of 90.5%, a false detection rate of 0.51 h(-1) and a median detection delay of 7 s. The algorithm could also lateralize the focus side for patients with temporal lobe epilepsy.

An entropy-based approach to predict seizures in temporal lobe epilepsy using scalp EEG.

We describe a novel algorithm for the prediction of epileptic seizures using scalp EEG. The method is based on the analysis of the positive zero-crossing interval series of the EEG signal and its first and second derivatives as a measure of brain dynamics. In a moving-window analysis, we estimated the probability density of these intervals and computed the differential entropy. The resultant entropy time series were then inspected using the cumulative sum (CUSUM) procedure to detect decreases as precursors of upcoming seizures. In the next step, the alarm sequences resulting from analysis of the EEG waveform and its derivatives were combined. Finally, a seizure prediction index was generated based on the spatio-temporal processing of the combined CUSUM alarms. We evaluated our algorithm using a dataset of approximately 21.5 hours of multichannel scalp EEG recordings from four patients with temporal lobe epilepsy, resulting in 87.5% sensitivity, a false prediction rate of 0.28/hr, and an average prediction time of 25 min.

An automatic sleep spindle detector based on wavelets and the teager energy operator.

Sleep spindles are one of the most important short-lasting rhythmic events occurring in the EEG during Non-Rapid Eye Movement sleep. Their accurate identification in a polysomnographic signal is essential for sleep professionals to help them mark Stage 2 sleep. Visual spindle scoring however is a tedious workload, as there are often a thousand spindles in an all-night recording. In this paper a novel approach for the automatic detection of sleep spindles based upon the Teager Energy Operator and wavelet packets has been presented. The Teager operator was found to accurately enhance periodic activity in epochs of the EEG containing spindles. The wavelet packet transform proved effective in accurately locating spindles in the time-frequency domain. The autocorrelation function of the resultant Teager signal and the wavelet packet energy ratio were used to identify epochs with spindles. These two features were integrated into a spindle detection algorithm which achieved an accuracy of 93.7%.

A novel wavelet-based index to detect epileptic seizures using scalp EEG signals.

In this paper, we propose a novel wavelet-based algorithm for the detection of epileptic seizures. The algorithm is based on the recognition of rhythmic activities associated with ictal states in surface EEG recordings. Using a moving-window analysis, we first decomposed each EEG segment into a wavelet packet tree. Then, we extracted the coefficients corresponding to the frequency band of interest defined for rhythmic activities. Finally, a normalized index sensitive to both the rhythmicity and energy of the EEG signal was derived, based on the resulting coefficients. In our study, we evaluated this combined index for real-time detection of epileptic seizures using a dataset of approximately 11.5 hours of multichannel scalp EEG recordings from three patients and compared it to our previously proposed wavelet-based index. In this dataset, the novel combined index detected all epileptic seizures with a false detection rate of 0.52/hr.

Electroconvulsive therapy: a model for seizure detection by a wavelet packet algorithm.

Electroconvulsive therapy (ECT) is an effective treatment for severe depression. In this paper, we have used an algorithm based on wavelet packet (WP) analysis of EEG signals to detect seizures induced by ECT. After determining dominant frequency bands in the ictal period during ECT, the energy ratio of these bands was computed using the corresponding WP coefficients. This ratio was then used as an index to recognize seizure periods. Four different approaches to detect ECT seizures were employed in 41 EEG recordings from nine patients. Sensitivity in ECT seizure detection ranged from 76 to 95% while the false detection rate ranged from 6 to 13.

Seizure detection by a novel wavelet packet method.

We describe a novel wavelet-based method for the detection of seizure in patients with temporal lobe epilepsy. This method uses local discriminant bases and cross- data entropy algorithms to identify nodes of a wavelet packet dictionary that best discriminate preictal from ictal EEG signals. The algorithms are based on relative entropy criterion as a measure of discrepancy between different classes of signals. The frequency bands associated with these nodes were in the range of interest for seizure events. After selecting two bands, we determined the ratio of energies at the level of wavelet packet chosen by the cross-data entropy algorithm. Preliminary results demonstrate that the wavelet packet energy ratio could serve as a robust criterion in seizure detection.