Classification Accuracy Of Movements Research Articles

Application of Deep Learning to Enhance Finger Movement Classification Accuracy from UHD-EEG Signals

Application of Deep Learning to Enhance Finger Movement Classification Accuracy from UHD-EEG Signals

A novel sEMG data augmentation based on WGAN-GP

The classification of sEMG signals is fundamental in applications that use mechanical prostheses, making it necessary to work with generalist databases that improve the accuracy of those classifications. Therefore, synthetic signal generation can be beneficial in enriching a database to make it more generalist. This work proposes using a variant of generative adversarial networks to produce synthetic biosignals of sEMG. A convolutional neural network (CNN) was used to classify the movements. The results showed good performance with an increase of 4.07% in a set of movement classification accuracy when 200 synthetic samples were included for each movement. We compared our results to other methodologies, such as Magnitude Warping and Scaling. Both methodologies did not have the same performance in the classification.

Proposal of a Wearable Multimodal Sensing-Based Serious Games Approach for Hand Movement Training After Stroke

Stroke often leads to hand motor dysfunction, and effective rehabilitation requires keeping patients engaged and motivated. Among the existing automated rehabilitation approaches, data glove-based systems are not easy to wear for patients due to spasticity, and single sensor-based approaches generally provided prohibitively limited information. We thus propose a wearable multimodal serious games approach for hand movement training after stroke. A force myography (FMG), electromyography (EMG), and inertial measurement unit (IMU)-based multi-sensor fusion model was proposed for hand movement classification, which was worn on the user’s affected arm. Two movement recognition-based serious games were developed for hand movement and cognition training. Ten stroke patients with mild to moderate motor impairments (Brunnstrom Stage for Hand II-VI) performed experiments while playing interactive serious games requiring 12 activities-of-daily-living (ADLs) hand movements taken from the Fugl Meyer Assessment. Feasibility was evaluated by movement classification accuracy and qualitative patient questionnaires. The offline classification accuracy using combined FMG-EMG-IMU was 81.0% for the 12 movements, which was significantly higher than any single sensing modality; only EMG, only FMG, and only IMU were 69.6, 63.2, and 47.8%, respectively. Patients reported that they were more enthusiastic about hand movement training while playing the serious games as compared to conventional methods and strongly agreed that they subjectively felt that the proposed training could be beneficial for improving upper limb motor function. These results showed that multimodal-sensor fusion improved hand gesture classification accuracy for stroke patients and demonstrated the potential of this proposed approach to be used as upper limb movement training after stroke.

The Human Tic Detector: An automatic approach to tic characterization using wearable sensors

ObjectiveCurrent rating scales for Tourette syndrome (TS) are limited by recollection bias or brief assessment periods. This proof-of-concept study aimed to develop a sensor-based paradigm to detect and classify tics. MethodsWe recorded both electromyogram and acceleration data from seventeen TS patients, either when voluntarily moving or experiencing tics and during the modified Rush Video Tic Rating Scale (mRVTRS). Spectral properties of voluntary and tic movements from the sensor that captured the dominant tic were calculated and used as features in a support vector machine (SVM) to detect and classify movements retrospectively. ResultsAcross patients, the SVM had an accuracy, sensitivity, and specificity of 96.69 ± 4.84%, 98.24 ± 4.79%, and 96.03 ± 6.04%, respectively, when classifying movements in the test dataset. Furthermore, each patient’s SVM was validated using data collected during the mRVTRS. Compared to the expert consensus, the tic detection accuracy was 85.63 ± 15.28% during the mRVTRS, while overall movement classification accuracy was 94.23 ± 5.97%. ConclusionsThese results demonstrate that wearable sensors can capture physiological differences between tic and voluntary movements and are comparable to expert consensus. SignificanceUltimately, wearables could individualize and improve care for people with TS, provide a robust and objective measure of tics, and allow data collection in real-world settings.

Optimization of Data Quality Related EMG Feature Extraction Parameters to Increase Hand Movement Classification Accuracy.

Many biomedical robotic interfaces (e.g., prostheses, exoskeletons) classify or estimate user movement intent based on features extracted from measured electromyograms (EMG). In most cases, the parameters of feature extraction are determined heuristically or assigned arbitrary values. We propose a more rigorous method, numerical optimization, to systematically identify parameters that maximize classification accuracy based on EMG signal characteristics. In this study, we used simulated annealing, a common global numerical optimization method, to find the optimal values of three feature extraction parameters based on the root mean square (rms) magnitude of the EMG signal. The EMG data, obtained from a public database, had been measured from 2 muscles (one hand flexor and one hand extensor) of 5 able-bodied participants performing 6 different movement tasks. Using optimization, we increased the offline movement classification accuracy by 3-5% for each participant and from 79.91% to 92.25% overall. The value of one optimized parameter (threshold of Wilson amplitude) was strongly correlated with the rms magnitude of the EMG signal (R2=0.81). Other parameters were suspected to be related to signal noise, since no strong correlation with rms magnitude was observed. Future studies will refine the optimization approach and test its practicality and effectiveness for improving online classification accuracy with robotic interfaces.

HD-EMG Electrode Count and Feature Selection Influence on Pattern-based Movement Classification Accuracy.

Control schemes that rely on electromyography (EMG) pattern classification have shown to improve their accuracy when coupled with an increasing number of electrodes. In this study, HD-EMG signals from the hand and forearm of volunteers performing a series of movements were recorded. Different amounts of input EMG channels were selected and time-domain features were extracted to train several SVM classifiers. Detailed comparisons were made to evaluate the impact of electrode count and feature selection over the overall classification accuracy of 17 different movements. The increased resolution achieved from higher electrode counts yielded significant improvements in classification accuracy; however, these improvements were marginal when the number of channels utilized surpassed 100 electrodes.Clinical relevance- Pattern-based EMG classification is a widely used control method for a range of prosthetic devices and robotic interfaces. This work studies the optimal number of simultaneous HD-EMG channels and features that must be considered for accurate myoelectric control using this method.

Hand movement classification from measured scattering parameters using deep convolutional neural network

Human body movement analysis aids in implementing the physical rehabilitation process to regain the diminished motor abilities. In this work, the feasibility of using antennas and no dedicated sensors for movement identification is explored. Compact dual-band transmitting and receiving antennas of size 37.6 mm × 27 mm with frequency accuracy of 87% at lower band and 76% at higher band are simulated, fabricated and placed on the body of ten healthy subjects with normal BMI (18.5–24.9) kg/m2. Subjects are made to demonstrate five different hand movements. The dataset for each hand movement is experimentally measured using a Vector Network Analyzer (VNA). Measurement results reveal that the Reflection and Transmission coefficients (S11 and S21) of on-body antennas for each hand movement exhibit unique channel functionalities with respect to frequency. The uniqueness of the exhibited parameters aids in identifying the hand movements. Classification of hand movements based on measured data set is carried out using Deep Convolutional Neural Network (DCNN). The classification accuracy of movement comes out to be 93.32% when classifying using S11 parameters, and an accuracy of 98.67% when classifying using S21 parameters.

Portable Electromyography: A Case Study on Ballistic Finger Movement Recognition

In the neuromuscular analysis, electromyography (EMG) is typically used to analyze aggregate action potential (AP) signals to detect medical abnormalities, activation levels, and recruitment order, or analyze biomechanics. In our previous work, we compared the performance of these off-the-shelf solutions to research-grade EMG machines and found that due to their rigid electrode placement, low sampling rate, and data transmission medium, they are ill-suited for research use, in which data collection must be robust and accurate. We present XTREMIS: a low-cost and portable EMG platform with a small form factor (55 mm $\times$ 35 mm) that has a sample rate comparable to research-grade EMG machines. Indeed, the experiments on eight subjects have shown that not only does XTREMIS functionally outperform technologies, but also its signal quality is high enough to achieve finger movement classification accuracy similar to research-grade EMG machines, making it a suitable platform for research.

Training in Use of Brain-Machine Interface-Controlled Robotic Hand Improves Accuracy Decoding Two Types of Hand Movements.

Objective: Brain-machine interfaces (BMIs) are useful for inducing plastic changes in cortical representation. A BMI first decodes hand movements using cortical signals and then converts the decoded information into movements of a robotic hand. By using the BMI robotic hand, the cortical representation decoded by the BMI is modulated to improve decoding accuracy. We developed a BMI based on real-time magnetoencephalography (MEG) signals to control a robotic hand using decoded hand movements. Subjects were trained to use the BMI robotic hand freely for 10 min to evaluate plastic changes in the cortical representation due to the training.Method: We trained nine young healthy subjects with normal motor function. In open-loop conditions, they were instructed to grasp or open their right hands during MEG recording. Time-averaged MEG signals were then used to train a real decoder to control the robotic arm in real time. Then, subjects were instructed to control the BMI-controlled robotic hand by moving their right hands for 10 min while watching the robot's movement. During this closed-loop session, subjects tried to improve their ability to control the robot. Finally, subjects performed the same offline task to compare cortical activities related to the hand movements. As a control, we used a random decoder trained by the MEG signals with shuffled movement labels. We performed the same experiments with the random decoder as a crossover trial. To evaluate the cortical representation, cortical currents were estimated using a source localization technique. Hand movements were also decoded by a support vector machine using the MEG signals during the offline task. The classification accuracy of the movements was compared among offline tasks.Results: During the BMI training with the real decoder, the subjects succeeded in improving their accuracy in controlling the BMI robotic hand with correct rates of 0.28 ± 0.13 to 0.50 ± 0.11 (p = 0.017, n = 8, paired Student's t-test). Moreover, the classification accuracy of hand movements during the offline task was significantly increased after BMI training with the real decoder from 62.7 ± 6.5 to 70.0 ± 11.1% (p = 0.022, n = 8, t(7) = 2.93, paired Student's t-test), whereas accuracy did not significantly change after BMI training with the random decoder from 63.0 ± 8.8 to 66.4 ± 9.0% (p = 0.225, n = 8, t(7) = 1.33).Conclusion: BMI training is a useful tool to train the cortical activity necessary for BMI control and to induce some plastic changes in the activity.

Repeatability of grasp recognition for robotic hand prosthesis control based on sEMG data.

Control methods based on sEMG obtained promising results for hand prosthetics. Control system robustness is still often inadequate and does not allow the amputees to perform a large number of movements useful for everyday life. Only few studies analyzed the repeatability of sEMG classification of hand grasps. The main goals of this paper are to explore repeatability in sEMG data and to release a repeatability database with the recorded experiments. The data are recorded from 10 intact subjects repeating 7 grasps 12 times, twice a day for 5 days. The data are publicly available on the Ninapro web page. The analysis for the repeatability is based on the comparison of movement classification accuracy in several data acquisitions and for different subjects. The analysis is performed using mean absolute value and waveform length features and a Random Forest classifier. The accuracy obtained by training and testing on acquisitions at different times is on average 27.03% lower than training and testing on the same acquisition. The results obtained by training and testing on different acquisitions suggest that previous acquisitions can be used to train the classification algorithms. The inter-subject variability is remarkable, suggesting that specific characteristics of the subjects can affect repeatibility and sEMG classification accuracy. In conclusion, the results of this paper can contribute to develop more robust control systems for hand prostheses, while the presented data allows researchers to test repeatability in further analyses.

A two-stage four-class BCI based on imaginary movements of the left and the right wrist

This paper presents a new concept of a two-modality, four-class brain–computer interface (BCI) classifier based on motor imagination of the left and the right wrist. The noninvasive BCI combines classification of movements of the same limb (wrist flexion and extension) with classification of movements of different limbs, i.e., left and right wrist. Results were obtained from ten right-handed neurologically healthy volunteers. Subjects were not allowed to practice real movements before performing movement imagination. The mean classification accuracy for four different classes was 63±10%. Classification accuracy in four out of ten subjects was ≥70%. A two-stage four-class classifier showed significantly better classification results (p=0.014) than a single four-class classifier. Classifiers were based on Elman's neural networks and features were a selected set of absolute values of Gabor coefficients (GCs), calculated from the Independent Components, rather than the EEG signals’ time series. The most representative features for classification between movements of different limbs were in the alpha and the beta range, while for classification between movements of the same limb they were in the delta and the gamma range. There was no statistically significant difference between classification accuracy of movements of the right vs. the left wrist.

Multi-view human movement recognition based on fuzzy distances and linear discriminant analysis

In this paper, a novel multi-view human movement recognition method is presented. A novel representation of multi-view human movement videos is proposed that is based on learning basic multi-view human movement primitives, called multi-view dynemes. The movement video is represented in a new feature space (called dyneme space) using these multi-view dynemes, thus producing a time invariant multi-view movement representation. Fuzzy distances from the multi-view dynemes are used to represent the human body postures in the dyneme space. Three variants of Linear Discriminant Analysis (LDA) are evaluated to achieve a discriminant movement representation in a low dimensionality space. The view identification problem is solved either by using a circular block shift procedure followed by the evaluation of the minimum Euclidean distance from any dyneme, or by exploiting the circular shift invariance property of the Discrete Fourier Transform (DFT). The discriminant movement representation combined with camera viewpoint identification and a nearest centroid classification step leads to a high human movement classification accuracy.