A Minimal and Multi-Source Recording Setup for Ankle Joint Kinematics Estimation During Walking Using Only Proximal Information From Lower Limb.

In this study, a minimal setup for the ankle joint kinematics estimation is proposed relying only on proximal information of the lower-limb, i.e. thigh muscles activity and joint kinematics. To this purpose, myoelectric activity of Rectus Femoris (RF), Biceps Femoris (BF), and Vastus Medialis (VM) were recorded by surface electromyography (sEMG) from six healthy subjects during unconstrained walking task. For each subject, the angular kinematics of hip and ankle joints were synchronously recorded with sEMG signal for a total of 288 gait cycles. Two feature sets were extracted from sEMG signals, i.e. time domain (TD) and wavelet (WT) and compared to have a compromise between the reliability and computational capacity, they were used for feeding three regression models, i.e. Artificial Neural Networks, Random Forest, and Least Squares - Support Vector Machine (LS-SVM). BF together with LS-SVM provided the best ankle angle estimation in both TD and WT domains (RMSE < 5.6 deg). The inclusion of Hip joint trajectory significantly enhanced the regression performances of the model (RMSE < 4.5 deg). Results showed the feasibility of estimating the ankle trajectory using only proximal and limited information from the lower limb which would maximize a potential transfemoral amputee user's comfortability while facing the challenge of having a small amount of information thus requiring robust data-driven models. These findings represent a significant step towards the development of a minimal setup useful for the control design of ankle active prosthetics and rehabilitative solutions.

Hand Force Estimation from Acoustic Myography Using Deep Wavelet Scattering Transform and Long Short-Term Memory.

The ability to estimate user intention from surface electromyogram (sEMG) signals is a crucial aspect in the design of powered prosthetics. Recently, researchers have been using regression techniques to connect the user's intent, as expressed through sEMG signals, to the force applied at the fingertips in order to achieve a natural and accurate form of control. However, there are still challenges associated with processing sEMG signals that need to be overcome to allow for widespread and clinical implementation of upper limb prostheses. As a result, alternative modalities functioning as promising control signals have been proposed as source of control input rather than the sEMG, such as Acoustic Myography (AMG). In this study, six high sensitivity array microphones were used to acquire AMG signals, with custom-built 3D printed microphone housing. To tackle the challenge of extracting the relevant information from AMG signals, the Wavelet Scattering Transform (WST) was utilized. alongside a Long Short-Term Memory (LSTM) neural network model for predicting the force from the AMG. The subjects were asked to use a hand dynamometer to measure the changes in force and correlate that to the force predicted by using the AMG features. Seven subjects were recruited for data collection in this study, using hardware designed by the research team. the performance results showed that the WST-LSTM model can be robustly utilized across varying window sizes and testing schemes, to achieve average NRMSE results of approximately 8%. These pioneering results suggest that AMG signals can be utilized to reliably estimate the force levels that the muscles are applying.Clinical Relevance- This research presents a new method for controlling upper limb prostheses using Acoustic Myography (AMG) signals. A novel method mapping the AMG signals to force applied by the corresponding muscles is developed. The presented findings have the potential to lead to the development of more natural and accurate control of human-machine interfaces.

A Deep Feature Fusion of Improved Suspected Keratoconus Detection with Deep Learning.

Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose a deep learning (DL) model to address this challenge. We first used Xception and InceptionResNetV2 DL architectures to extract features from three different corneal maps collected from 1371 eyes examined in an eye clinic in Egypt. We then fused features using Xception and InceptionResNetV2 to detect subclinical forms of KCN more accurately and robustly. We obtained an area under the receiver operating characteristic curves (AUC) of 0.99 and an accuracy range of 97-100% to distinguish normal eyes from eyes with subclinical and established KCN. We further validated the model based on an independent dataset with 213 eyes examined in Iraq and obtained AUCs of 0.91-0.92 and an accuracy range of 88-92%. The proposed model is a step toward improving the detection of clinical and subclinical forms of KCN.

An integrated entropy-spatial framework for automatic gender recognition enhancement of emotion-based EEGs.

Investigating gender differences based on emotional changes using electroencephalogram (EEG) is essential to understand various human behavior in the individual situation in our daily life. However, gender differences based on EEG and emotional states are not thoroughly investigated. The main novelty of this paper is twofold. First, it aims to propose an automated gender recognition system through the investigation of five entropies which were integrated as a set of entropy domain descriptors (EDDs) to illustrate the changes in the complexity of EEGs. Second, the combination EDD set was used to develop a customized EEG framework by estimating the entropy-spatial descriptors (ESDs) set for identifying gender from emotional-based EEGs. The proposed methods were validated on EEGs of 30 participants who examined short emotional video clips with four audio-visual stimuli (anger, happiness, sadness, and neutral). The individual performance of computed entropies was statistically examined using analysis of variance (ANOVA) to identify a gender role in the brain emotions. Finally, the proposed ESD framework performance was evaluated using three classifiers: support vector machine (SVM), k-nearest neighbors (kNN) and random forest (RF), and long short-term memory (LSTM) deep learning model. The results illustrated the effect of individual EDD features as remarkable indices for investigating gender while studying the relationship between EEG brain activity and emotional state changes. Moreover, the proposed ESD achieved significant enhancement in classification accuracy with SVM indicating that ESD may offer a helpful path for reliable improvement of the gender detection from emotional-based EEGs.

A Hybrid Deep Learning Construct for Detecting Keratoconus From Corneal Maps.

Purpose: To develop and assess the accuracy of a hybrid deep learning construct for detecting keratoconus (KCN) based on corneal topographic maps. Methods: We collected 3794 corneal images from 542 eyes of 280 subjects and developed seven deep learning models based on anterior and posterior eccentricity, anterior and posterior elevation, anterior and posterior sagittal curvature, and corneal thickness maps to extract deep corneal features. An independent subset with 1050 images collected from 150 eyes of 85 subjects from a separate center was used to validate models. We developed a hybrid deep learning model to detect KCN. We visualized deep features of corneal parameters to assess the quality of learning subjectively and computed area under the receiver operating characteristic curve (AUC), confusion matrices, accuracy, and F1 score to evaluate models objectively. Results: In the development dataset, 204 eyes were normal, 123 eyes were suspected KCN, and 215 eyes had KCN. In the independent validation dataset, 50 eyes were normal, 50 eyes were suspected KCN, and 50 eyes were KCN. Images were annotated by three corneal specialists. The AUC of the models for the two-class and three-class problems based on the development set were 0.99 and 0.93, respectively. Conclusions: The hybrid deep learning model achieved high accuracy in identifying KCN based on corneal maps and provided a time-efficient framework with low computational complexity. Translational Relevance: Deep learning can detect KCN from non-invasive corneal images with high accuracy, suggesting potential application in research and clinical practice to identify KCN.

Improved hand prostheses control for transradial amputees based on hybrid of voice recognition and electromyography.

The control of prostheses and their complexities is one of the greatest challenges limiting wide amputees' use of upper limb prostheses. The main challenges include the difficulty of extracting signals for controlling the prostheses, limited number of degrees of freedom (DoF), and cost-prohibitive for complex controlling systems. In this study, a real-time hybrid control system, based on electromyography (EMG) and voice commands (VC) is designed to render the prosthesis more dexterous with the ability to accomplish amputee's daily activities proficiently. The voice and EMG systems were combined in three proposed hybrid strategies, each strategy had different number of movements depending on the combination protocol between voice and EMG control systems. Furthermore, the designed control system might serve a large number of amputees with different amputation levels, and since it has a reasonable cost and be easy to use. The performance of the proposed control system, based on hybrid strategies, was tested by intact-limbed and amputee participants for controlling the HANDi hand. The results showed that the proposed hybrid control system was robust, feasible, with an accuracy of 94%, 98%, and 99% for Strategies 1, 2, and 3, respectively. It was possible to specify the grip force applied to the prosthetic hand within three gripping forces. The amputees participated in this study preferred combination Strategy 3 where the voice and EMG are working concurrently, with an accuracy of 99%.

Recurrent Fusion of Time-Domain Descriptors Improves EMG-based Hand Movement Recognition.

Controlling powered prostheses with myoelectric pattern recognition (PR) provides a natural human-robot interfacing scheme for amputees who lost their limbs. Research in this direction reveals that the challenges prohibiting reliable clinical translation of myoelectric interfaces are mainly driven by the quality of the extracted features. Hence, developing accurate and reliable feature extraction techniques is of vital importance for facilitating clinical implementation of Electromyogram (EMG) PR systems. To overcome this challenge, we proposed a combination of Range Spatial Filtering (RSF) and Recurrent Fusion of Time Domain Descriptors (RFTDD) in order to improve the classifier performance and make the prosthetic hand control more appropriate for clinical applications. RSF is used to increase the number of EMG signals available for feature extraction by focusing on the spatial information between all possible logical combinations of the physical EMG channels. RFTDD is then used to capture the temporal information by applying a recurrent data fusion process on the resulting orientation-based time-domain (TD) features, with a sigmoidal function to limit the features range and overcome the vanishing amplitudes problem. The main advantages of the proposed method include 1) its potential in capturing the temporal-spatial dependencies of the EMG signals, leading to reduced classification errors, and 2) the simplicity with which the features are extracted, as any kind of simple TD features can be adopted with this method. The performance of the proposed RFTDD is then benchmarked across many well-known TD features individually and as sets to prove the power of the RFTDD method on two EMG datasets with a total of 31 subjects. Testing results revealed an approximate reduction of 12% in classification errors across all subjects when using the proposed method against traditional feature extraction methods.Clinical Relevance-Establishing significance and importance of RFTDD, with simple time-domain features, for robust and low-cost clinical applications.

Adaptive Windowing Framework for Surface Electromyogram-Based Pattern Recognition System for Transradial Amputees.

Electromyogram (EMG)-based Pattern Recognition (PR) systems for upper-limb prosthesis control provide promising ways to enable an intuitive control of the prostheses with multiple degrees of freedom and fast reaction times. However, the lack of robustness of the PR systems may limit their usability. In this paper, a novel adaptive time windowing framework is proposed to enhance the performance of the PR systems by focusing on their windowing and classification steps. The proposed framework estimates the output probabilities of each class and outputs a movement only if a decision with a probability above a certain threshold is achieved. Otherwise (i.e., all probability values are below the threshold), the window size of the EMG signal increases. We demonstrate our framework utilizing EMG datasets collected from nine transradial amputees who performed nine movement classes with Time Domain Power Spectral Descriptors (TD-PSD), Wavelet and Time Domain (TD) feature extraction (FE) methods and a Linear Discriminant Analysis (LDA) classifier. Nonetheless, the concept can be applied to other types of features and classifiers. In addition, the proposed framework is validated with different movement and EMG channel combinations. The results indicate that the proposed framework works well with different FE methods and movement/channel combinations with classification error rates of approximately 13% with TD-PSD FE. Thus, we expect our proposed framework to be a straightforward, yet important, step towards the improvement of the control methods for upper-limb prostheses.

Complexity analysis of spontaneous brain activity in mood disorders: A magnetoencephalography study of bipolar disorder and major depression.

BACKGROUND AND PURPOSE: The lack of a biomarker for Bipolar Disorder (BD) causes problems in the differential diagnosis with other mood disorders such as major depression (MD), and misdiagnosis frequently occurs. Bearing this in mind, we investigated non-linear magnetoencephalography (MEG) patterns in BD and MD. METHODS: Lempel-Ziv Complexity (LZC) was used to evaluate the resting-state MEG activity in a cross-sectional sample of 60 subjects, including 20 patients with MD, 16 patients with BD type-I, and 24 control (CON) subjects. Particular attention was paid to the role of age. The results were aggregated by scalp region. RESULTS: Overall, MD patients showed significantly higher LZC scores than BD patients and CONs. Linear regression analyses demonstrated distinct tendencies of complexity progression as a function of age, with BD patients showing a divergent tendency as compared with MD and CON groups. Logistic regressions confirmed such distinct relationship with age, which allowed the classification of diagnostic groups. CONCLUSIONS: The patterns of neural complexity in BD and MD showed not only quantitative differences in their non-linear MEG characteristics but also divergent trajectories of progression as a function of age. Moreover, neural complexity patterns in BD patients resembled those previously observed in schizophrenia, thus supporting preceding evidence of common neuropathological processes.

A Framework of Temporal-Spatial Descriptors-Based Feature Extraction for Improved Myoelectric Pattern Recognition.

The extraction of the accurate and efficient descriptors of muscular activity plays an important role in tackling the challenging problem of myoelectric control of powered prostheses. In this paper, we present a new feature extraction framework that aims to give an enhanced representation of muscular activities through increasing the amount of information that can be extracted from individual and combined electromyogram (EMG) channels. We propose to use time-domain descriptors (TDDs) in estimating the EMG signal power spectrum characteristics; a step that preserves the computational power required for the construction of spectral features. Subsequently, TDD is used in a process that involves: 1) representing the temporal evolution of the EMG signals by progressively tracking the correlation between the TDD extracted from each analysis time window and a nonlinearly mapped version of it across the same EMG channel and 2) representing the spatial coherence between the different EMG channels, which is achieved by calculating the correlation between the TDD extracted from the differences of all possible combinations of pairs of channels and their nonlinearly mapped versions. The proposed temporal-spatial descriptors (TSDs) are validated on multiple sparse and high-density (HD) EMG data sets collected from a number of intact-limbed and amputees performing a large number of hand and finger movements. Classification results showed significant reductions in the achieved error rates in comparison to other methods, with the improvement of at least 8% on average across all subjects. Additionally, the proposed TSDs achieved significantly well in problems with HD-EMG with average classification errors of <5% across all subjects using windows lengths of 50 ms only.

Selecting the optimal movement subset with different pattern recognition based EMG control algorithms.

Pattern Recognition (PR)-based EMG controllers of multi-functional upper-limb prostheses have been recently deployed on commercial state-of-the-art prostheses, offering intuitive control with the ability to control large number of movements with fast reaction time. Current challenges with such PR systems include the lack of training and deployment protocols that can help optimize the system's performance based on amputees' needs. Selecting the best subset of movements that each individual amputee can perform will help to exclude movements that have poor performance so that a subject-specific training can be achieved. In this paper, we propose to select the best set of movements that each amputee can perform as well as identifying the movements for which the PR system would have the worst performance and, therefore, would require further training. Unlike previous studies in this direction, different feature extraction and classification methods were utilized to examine if the choice of features/classifiers could affect the best movements subset selection. We performed our experiments on EMG signals collected from four transradial amputees with an accuracy > 97.5% on average across all subjects for the selection of best subset of movements.

Improving the Performance Against Force Variation of EMG Controlled Multifunctional Upper-Limb Prostheses for Transradial Amputees.

We investigate the problem of achieving robust control of hand prostheses by the electromyogram (EMG) of transradial amputees in the presence of variable force levels, as these variations can have a substantial impact on the robustness of the control of the prostheses. We also propose a novel set of features that aim at reducing the impact of force level variations on the prosthesis controlled by amputees. These features characterize the EMG activity by means of the orientation between a set of spectral moments descriptors extracted from the EMG signal and a nonlinearly mapped version of it. At the same time, our feature extraction method processes the EMG signals directly from the time-domain to reduce computational cost. The performance of the proposed features is tested on EMG data collected from nine transradial amputees performing six classes of movements each with three force levels. Our results indicate that the proposed features can achieve significant reductions in classification error rates in comparison to other well-known feature extraction methods, achieving improvements of ≈ 6% to 8% in the average classification performance across all subjects and force levels, when training with all forces.

Transradial Amputee Gesture Classification Using an Optimal Number of sEMG Sensors: An Approach Using ICA Clustering.

Surface electromyography (sEMG)-based pattern recognition studies have been widely used to improve the classification accuracy of upper limb gestures. Information extracted from multiple sensors of the sEMG recording sites can be used as inputs to control powered upper limb prostheses. However, usage of multiple EMG sensors on the prosthetic hand is not practical and makes it difficult for amputees due to electrode shift/movement, and often amputees feel discomfort in wearing sEMG sensor array. Instead, using fewer numbers of sensors would greatly improve the controllability of prosthetic devices and it would add dexterity and flexibility in their operation. In this paper, we propose a novel myoelectric control technique for identification of various gestures using the minimum number of sensors based on independent component analysis (ICA) and Icasso clustering. The proposed method is a model-based approach where a combination of source separation and Icasso clustering was utilized to improve the classification performance of independent finger movements for transradial amputee subjects. Two sEMG sensor combinations were investigated based on the muscle morphology and Icasso clustering and compared to Sequential Forward Selection (SFS) and greedy search algorithm. The performance of the proposed method has been validated with five transradial amputees, which reports a higher classification accuracy ( > 95%). The outcome of this study encourages possible extension of the proposed approach to real time prosthetic applications.

Spectral analysis of resting state magnetoencephalogram activity in patients with bipolar disorder.

We analyzed the frequency spectrum of magnetoencephalogram (MEG) background activity in 16 bipolar disorder (BD) patients and 24 age-matched healthy control. Median frequency (MF), spectral entropy (SpEn), and relative power in delta (RPδ), theta (RPθ), alpha (RPα), beta (RPß), and gamma (RPγ) bands were computed for all 148 MEG channels. Significant differences between the two groups were found in the average level of MF, RPδ, and RPθ in the posterior region of the scalp. Moreover, the MF, SpEn, RPδ, and RPß values of BD patients had a different dependence on age as compared with the results of control subjects, which may suggest that BD affects how the brain activity develops with age. We conclude that the spectral analysis of the background MEG in BD patients may give insights into how this condition affects the brain activity.

A preliminary investigation of the effect of force variation for myoelectric control of hand prosthesis.

The myoelectric control of prostheses has been an important area of research for the past 40 years. Significant advances have been achieved with Pattern Recognition (PR) systems regarding the number of movements to be classified with high accuracy. However, practical robustness still needs further research. This paper focuses on investigating the effect of the change in force levels by transradial amputee persons on the performance of PR systems. Two below-elbow amputee persons participated in the study. Three levels of forces (low, medium, and high) were recorded for different hand grips with the help of visual feedback from the Electromyography (EMG) signals. Results showed that changing the force level degraded the performance of the myoelectric control system by up to 60% with 12 EMG channels for 4 hand grips and a rest position. We investigated different EMG feature sets in combination with a Linear Discriminant Analysis (LDA) classifier. The performance was slightly better with Time Domain (TD) features compared to Auto Regression (AR) coefficients and Root Mean Square (RMS) features. Finally, the error of the classification was considerably reduced to approximately 17% when the PR system was trained with all force levels.

Protocol for site selection and movement assessment for the myoelectric control of a multi-functional upper-limb prosthesis.

Although there have been many advances in electromyography (EMG) signal processing and pattern recognition (PR) for the control of multi-functional upper-limb prostheses, some the outstanding problems need to be solved before practical PR-based prostheses can be put into service. Some of these are the lack of training and deployment protocols and the provision of the tools required. Therefore, we present a preliminary procedure to personalize the prosthesis deployment. In the first step, we record the demographic information of each individual amputee person and their background. In the second step of the protocol, the EMG signals are acquired. PR algorithms and parameters will be chosen in the 3(rd) step of the protocol. In the 4(th) step, the best number of EMG sensors to achieve the maximal performance with a full set of gestures is identified. The final step involves finding the best set of movements that the amputee person can produce with an accuracy > 95% as well as identifying the movements with the worst performance, which would require further training. This proposed approach is validated with 2 transradial amputees.

Classification of finger movements for the dexterous hand prosthesis control with surface electromyography.

A method for the classification of finger movements for dexterous control of prosthetic hands is proposed. Previous research was mainly devoted to identify hand movements as these actions generate strong electromyography (EMG) signals recorded from the forearm. In contrast, in this paper, we assess the use of multichannel surface electromyography (sEMG) to classify individual and combined finger movements for dexterous prosthetic control. sEMG channels were recorded from ten intact-limbed and six below-elbow amputee persons. Offline processing was used to evaluate the classification performance. The results show that high classification accuracies can be achieved with a processing chain consisting of time domain-autoregression feature extraction, orthogonal fuzzy neighborhood discriminant analysis for feature reduction, and linear discriminant analysis for classification. We show that finger and thumb movements can be decoded accurately with high accuracy with latencies as short as 200 ms. Thumb abduction was decoded successfully with high accuracy for six amputee persons for the first time. We also found that subsets of six EMG channels provide accuracy values similar to those computed with the full set of EMG channels (98% accuracy over ten intact-limbed subjects for the classification of 15 classes of different finger movements and 90% accuracy over six amputee persons for the classification of 12 classes of individual finger movements). These accuracy values are higher than previous studies, whereas we typically employed half the number of EMG channels per identified movement.

A note on the probability distribution function of the surface electromyogram signal.

The probability density function (PDF) of the surface electromyogram (EMG) signals has been modelled with Gaussian and Laplacian distribution functions. However, a general consensus upon the PDF of the EMG signals is yet to be reached, because not only are there several biological factors that can influence this distribution function, but also different analysis techniques can lead to contradicting results. Here, we recorded the EMG signal at different isometric muscle contraction levels and characterised the probability distribution of the surface EMG signal with two statistical measures: bicoherence and kurtosis. Bicoherence analysis did not help to infer the PDF of measured EMG signals. In contrast, with kurtosis analysis we demonstrated that the EMG PDF at isometric, non-fatiguing, low contraction levels is super-Gaussian. Moreover, kurtosis analysis showed that as the contraction force increases the surface EMG PDF tends to a Gaussian distribution.

Single channel-based myoelectric control of hand movements with Empirical Mode Decomposition.

Myoelectric control has been an important area of research for the past 40 years for prosthetic control, since it targets amputees who lost their body limbs. Advances were achieved concerning the number of movements to be classified with high accuracy. Hence, not much research was done to extract information from single channel Electromyogram (EMG). This paper presents Empirical Mode Decomposition (EMD) for Feature Extraction (FE) from single-channel EMG for ten class wrist movements and handgrips. Two classification schemes were applied based on Time Domain-Auto Regression (TDAR) features (a commonly used approach in the Literature) and EMD, with Principle Component Analysis (PCA) for dimensionality reduction, and Support Vector Machine (SVM) for classification. With the use of only one single-channel EMG, the EMD achieved an improvement in the classification rate for a single flexor and extensor EMG channel of 11.2% (from 83.7% to 94.4%) and 13% (from 80.16% to 93.16%), respectively. The results suggested that EMD remarkably improves the classification performance for a single-channel EMG over the traditional time domain FE technique. This will reduce the computational cost of applying only one channel EMG and facilitates the acquisition of the EMG. The main drawback of using EMD technique is that it is not suitable for real time processing of prosthetic control.