Optimizing the performance of convolutional neural network for enhanced gesture recognition using sEMG.

Deep neural networks (DNNs) have demonstrated higher performance results when compared to traditional approaches for implementing robust myoelectric control (MEC) systems. However, the delay induced by optimising a MEC remains a concern for real-time applications. As a result, an optimised DNN architecture based on fine-tuned hyperparameters is required. This study investigates the optimal configuration of convolutional neural network (CNN)-based MEC by proposing an effective data segmentation technique and a generalised set of hyperparameters. Firstly, two segmentation strategies (disjoint and overlap) and various segment and overlap sizes were studied to optimise segmentation parameters. Secondly, to address the challenge of optimising the hyperparameters of a DNN-based MEC system, the problem has been abstracted as an optimisation problem, and Bayesian optimisation has been used to solve it. From 20 healthy people, ten surface electromyography (sEMG) grasping movements abstracted from daily life were chosen as the target gesture set. With an ideal segment size of 200 ms and an overlap size of 80%, the results show that the overlap segmentation technique outperforms the disjoint segmentation technique (p-value < 0.05). In comparison to manual (12.76 ± 4.66), grid (0.10 ± 0.03), and random (0.12 ± 0.05) search hyperparameters optimisation strategies, the proposed optimisation technique resulted in a mean classification error rate (CER) of 0.08 ± 0.03 across all subjects. In addition, a generalised CNN architecture with an optimal set of hyperparameters is proposed. When tested separately on all individuals, the single generalised CNN architecture produced an overall CER of 0.09 ± 0.03. This study's significance lies in its contribution to the field of EMG signal processing by demonstrating the superiority of the overlap segmentation technique, optimizing CNN hyperparameters through Bayesian optimization, and offering practical insights for improving prosthetic control and human-computer interfaces.

Memorability-based multimedia analytics for robotic interestingness prediction system using trimmed Q-learning algorithm.

Mobile robots are increasingly employed in today's environment. Perceiving the environment to perform a task plays a major role in the robots. The service robots are wisely employed in the fully (or) partially known user's environment. The exploration and exploitation of the unknown environment is a tedious task. This paper introduces a novel Trimmed Q-learning algorithm to predict interesting scenes via efficient memorability-oriented robotic behavioral scene activity training. The training process involves three stages: online learning and short-term and long-term learning modules. It is helpful for autonomous exploration and making wiser decisions about the environment. A simplified three-stage learning framework is introduced to train and predict interesting scenes using memorability. A proficient visual memory schema (VMS) is designed to tune the learning parameters. A role-based profile arrangement is made to explore the unknown environment for a long-term learning process. The online and short-term learning frameworks are designed using a novel Trimmed Q-learning algorithm. The underestimated bias in robotic actions must be minimized by introducing a refined set of practical candidate actions. Finally, the recalling ability of each learning module is estimated to predict the interesting scenes. Experiments conducted on public datasets, SubT, and SUN databases demonstrate the proposed technique's efficacy. The proposed framework has yielded better memorability scores in short-term and online learning at 72.84% and in long-term learning at 68.63%.

Deploying efficient net batch normalizations (BNs) for grading diabetic retinopathy severity levels from fundus images.

Diabetic retinopathy (DR) is one of the main causes of blindness in people around the world. Early diagnosis and treatment of DR can be accomplished by organizing large regular screening programs. Still, it is difficult to spot diabetic retinopathy timely because the situation might not indicate signs in the primary stages of the disease. Due to a drastic increase in diabetic patients, there is an urgent need for efficient diabetic retinopathy detecting systems. Auto-encoders, sparse coding, and limited Boltzmann machines were used as a few past deep learning (DL) techniques and features for the classification of DR. Convolutional Neural Networks (CNN) have been identified as a promising solution for detecting and classifying DR. We employ the deep learning capabilities of efficient net batch normalization (BNs) pre-trained models to automatically acquire discriminative features from fundus images. However, we successfully achieved F1 scores above 80% on all efficient net BNs in the EYE-PACS dataset (calculated F1 score for DeepDRiD another dataset) and the results are better than previous studies. In this paper, we improved the accuracy and F1 score of the efficient net BNs pre-trained models on the EYE-PACS dataset by applying a Gaussian Smooth filter and data augmentation transforms. Using our proposed technique, we have achieved F1 scores of 84% and 87% for EYE-PACS and DeepDRiD.

The effects of surface inclination on gastrocnemius, soleus and tibialis anterior muscle activation during gait.

BACKGROUND: Inclined walking is associated with multiple musculoskeletal benefits and is considered a therapeutic exercise. Various patterns of increased and decreased muscle activation with inclined surfaces have been observed in normal muscles, with more focus on the proximal lower limb musculature. OBJECTIVE: The aim of this study was to assess the differences in electromyographic activation of gastrocnemius, soleus, and tibialis anterior at various inclined surfaces during gait. METHODS: Fourteen healthy male participants aged between 17-30 years walked at a self-selected speed at motor driven treadmill on 0, 2 and 4 degrees of inclination. EMG activity of the muscles was recorded using the Delsys Trigno surface EMG system. RESULTS: Results showed that muscular activation of tibialis anterior significantly decreased with increase in the level of inclination (p< 0.05). However, soleus, gastrocnemius medialis and gastrocnemius lateralis showed no significant differences (p> 0.05) in their muscular activation, and no noticeable trends were found. Furthermore, no significant difference was found between all the muscles at ground level and inclined level 2 and 4. CONCLUSION: These differences in activation patterns found in distal extremity can be useful for designing rehabilitation protocols in sports training and for patients with neurological and musculoskeletal pathologies.

A Low-Cost Device for Measurement of Exhaled Breath for the Detection of Obstructive Lung Disease.

Breath sensor technology can be used in medical diagnostics. This study aimed to build a device to measure the level of hydrogen sulfide, ammonia, acetone and alcohol in exhaled breath of patients as well as healthy individuals. The purpose was to determine the efficacy of these gases for detection of obstructive lung disease. This study was conducted on a total of 105 subjects, where 60 subjects were patients of obstructive lung disease and 45 subjects were healthy individuals. Patients were screened by means of the Pulmonary Function Test (PFT) by a pulmonologist. The gases present in the exhaled breath of all subjects were measured. The level of ammonia (32.29 ± 20.83 ppb), (68.83 ± 35.25 ppb), hydrogen sulfide (0.50 ± 0.26 ppm), (62.71 ± 22.20 ppb), and acetone (103.49 ± 35.01 ppb), (0.66 ± 0.31 ppm) in exhaled breath were significantly different (p < 0.05) between obstructive lung disease patients and healthy individuals, except alcohol, with a p-value greater than 0.05. Positive correlation was found between ammonia w.r.t Forced Expiratory Volume in 1 s (FEV1) (r = 0.74), Forced Vital Capacity (FVC) (r = 0.61) and Forced Expiratory Flow (FEF) (r = 0.63) and hydrogen sulfide w.r.t FEV1 (r = 0.54), FVC (r = 0.41) and FEF (r = 0.37). Whereas, weak correlation was found for acetone and alcohol w.r.t FEV1, FVC and PEF. Therefore, the level of ammonia and hydrogen sulfide are useful breath markers for detection of obstructive lung disease.

Reply to Morone, G.; Giansanti, D. Comment on "Anwer et al. Rehabilitation of Upper Limb Motor Impairment in Stroke: A Narrative Review on the Prevalence, Risk Factors, and Economic Statistics of Stroke and State of the Art Therapies. Healthcare 2022, 10, 190".

Thank you so much for your kind remarks [...].

Melanoma segmentation using deep learning with test-time augmentations and conditional random fields.

In a computer-aided diagnostic (CAD) system for skin lesion segmentation, variations in shape and size of the skin lesion makes the segmentation task more challenging. Lesion segmentation is an initial step in CAD schemes as it leads to low error rates in quantification of the structure, boundary, and scale of the skin lesion. Subjective clinical assessment of the skin lesion segmentation results provided by current state-of-the-art deep learning segmentation techniques does not offer the required results as per the inter-observer agreement of expert dermatologists. This study proposes a novel deep learning-based, fully automated approach to skin lesion segmentation, including sophisticated pre and postprocessing approaches. We use three deep learning models, including UNet, deep residual U-Net (ResUNet), and improved ResUNet (ResUNet++). The preprocessing phase combines morphological filters with an inpainting algorithm to eliminate unnecessary hair structures from the dermoscopic images. Finally, we used test time augmentation (TTA) and conditional random field (CRF) in the postprocessing stage to improve segmentation accuracy. The proposed method was trained and evaluated on ISIC-2016 and ISIC-2017 skin lesion datasets. It achieved an average Jaccard Index of 85.96% and 80.05% for ISIC-2016 and ISIC-2017 datasets, when trained individually. When trained on combined dataset (ISIC-2016 and ISIC-2017), the proposed method achieved an average Jaccard Index of 80.73% and 90.02% on ISIC-2017 and ISIC-2016 testing datasets. The proposed methodological framework can be used to design a fully automated computer-aided skin lesion diagnostic system due to its high scalability and robustness.

Rehabilitation of Upper Limb Motor Impairment in Stroke: A Narrative Review on the Prevalence, Risk Factors, and Economic Statistics of Stroke and State of the Art Therapies.

Stroke has been one of the leading causes of disability worldwide and is still a social health issue. Keeping in view the importance of physical rehabilitation of stroke patients, an analytical review has been compiled in which different therapies have been reviewed for their effectiveness, such as functional electric stimulation (FES), noninvasive brain stimulation (NIBS) including transcranial direct current stimulation (t-DCS) and transcranial magnetic stimulation (t-MS), invasive epidural cortical stimulation, virtual reality (VR) rehabilitation, task-oriented therapy, robot-assisted training, tele rehabilitation, and cerebral plasticity for the rehabilitation of upper extremity motor impairment. New therapeutic rehabilitation techniques are also being investigated, such as VR. This literature review mainly focuses on the randomized controlled studies, reviews, and statistical meta-analyses associated with motor rehabilitation after stroke. Moreover, with the increasing prevalence rate and the adverse socio-economic consequences of stroke, a statistical analysis covering its economic factors such as treatment, medication and post-stroke care services, and risk factors (modifiable and non-modifiable) have also been discussed. This review suggests that if the prevalence rate of the disease remains persistent, a considerable increase in the stroke population is expected by 2025, causing a substantial economic burden on society, as the survival rate of stroke is high compared to other diseases. Compared to all the other therapies, VR has now emerged as the modern approach towards rehabilitation motor activity of impaired limbs. A range of randomized controlled studies and experimental trials were reviewed to analyse the effectiveness of VR as a rehabilitative treatment with considerable satisfactory results. However, more clinical controlled trials are required to establish a strong evidence base for VR to be widely accepted as a preferred rehabilitation therapy for stroke.

Automatic detection of pathological myopia using machine learning.

Pathological myopia is a severe case of myopia, i.e., nearsightedness. Pathological myopia is also known as degenerative myopia because it ultimately leads to blindness. In pathological myopia, certain myopia-specific pathologies occur at the eye's posterior i.e., Foster-Fuchs's spot, Cystoid degeneration, Liquefaction, Macular degeneration, Vitreous opacities, Weiss's reflex, Posterior staphyloma, etc. This research is aimed at developing a machine learning (ML) approach for the automatic detection of pathological myopia based on fundus images. A deep learning technique of convolutional neural network (CNN) is employed for this purpose. A CNN model is developed in Spyder. The fundus images are first preprocessed. The preprocessed images are then fed to the designed CNN model. The CNN model automatically extracts the features from the input images and classifies the images i.e., normal image or pathological myopia. The best performing CNN model achieved an AUC score of 0.9845. The best validation loss obtained is 0.1457. The results show that the model can be successfully employed to detect pathological myopia from the fundus images.

Predicting Risk of Antenatal Depression and Anxiety Using Multi-Layer Perceptrons and Support Vector Machines.

Perinatal depression and anxiety are defined to be the mental health problems a woman faces during pregnancy, around childbirth, and after child delivery. While this often occurs in women and affects all family members including the infant, it can easily go undetected and underdiagnosed. The prevalence rates of antenatal depression and anxiety worldwide, especially in low-income countries, are extremely high. The wide majority suffers from mild to moderate depression with the risk of leading to impaired child-mother relationship and infant health, few women end up taking their own lives. Owing to high costs and non-availability of resources, it is almost impossible to diagnose every pregnant woman for depression/anxiety whereas under-detection can have a lasting impact on mother and child's health. This work proposes a multi-layer perceptron based neural network (MLP-NN) classifier to predict the risk of depression and anxiety in pregnant women. We trained and evaluated our proposed system on a Pakistani dataset of 500 women in their antenatal period. ReliefF was used for feature selection before classifier training. Evaluation metrics such as accuracy, sensitivity, specificity, precision, F1 score, and area under the receiver operating characteristic curve were used to evaluate the performance of the trained model. Multilayer perceptron and support vector classifier achieved an area under the receiving operating characteristic curve of 88% and 80% for antenatal depression and 85% and 77% for antenatal anxiety, respectively. The system can be used as a facilitator for screening women during their routine visits in the hospital's gynecology and obstetrics departments.

Decoding of Ankle Joint Movements in Stroke Patients Using Surface Electromyography.

Stroke is a cerebrovascular disease (CVD), which results in hemiplegia, paralysis, or death. Conventionally, a stroke patient requires prolonged sessions with physical therapists for the recovery of motor function. Various home-based rehabilitative devices are also available for upper limbs and require minimal or no assistance from a physiotherapist. However, there is no clinically proven device available for functional recovery of a lower limb. In this study, we explored the potential use of surface electromyography (sEMG) as a controlling mechanism for the development of a home-based lower limb rehabilitative device for stroke patients. In this experiment, three channels of sEMG were used to record data from 11 stroke patients while performing ankle joint movements. The movements were then decoded from the sEMG data and their correlation with the level of motor impairment was investigated. The impairment level was quantified using the Fugl-Meyer Assessment (FMA) scale. During the analysis, Hudgins time-domain features were extracted and classified using linear discriminant analysis (LDA) and artificial neural network (ANN). On average, 63.86% ± 4.3% and 67.1% ± 7.9% of the movements were accurately classified in an offline analysis by LDA and ANN, respectively. We found that in both classifiers, some motions outperformed others (p < 0.001 for LDA and p = 0.014 for ANN). The Spearman correlation (ρ) was calculated between the FMA scores and classification accuracies. The results indicate that there is a moderately positive correlation (ρ = 0.75 for LDA and ρ = 0.55 for ANN) between the two of them. The findings of this study suggest that a home-based EMG system can be developed to provide customized therapy for the improvement of functional lower limb motion in stroke patients.

Evaluation of windowing techniques for intramuscular EMG-based diagnostic, rehabilitative and assistive devices.

Objective.Intramuscular electromyography (iEMG) signals, invasively recorded, directly from the muscles are used to diagnose various neuromuscular disorders/diseases and to control rehabilitative and assistive robotic devices. iEMG signals are potentially being used in neurology, kinesiology, rehabilitation and ergonomics, to detect/diagnose various diseases/disorders. Electromyography-based classification and analysis systems are being designed and tested for the classification of various neuromuscular disorders and to control rehabilitative and assistive robotic devices. Many studies have explored parameters such as the pre-processing, feature extraction and selection of classifiers that can affect the performance and efficacy of iEMG-based classification systems. The pre-processing stage includes the removal of any unwanted noise from the original signal and windowing of the signal.Approach.This study investigated and presented the optimum windowing configurations for robust control and better performance results of an iEMG-based analysis system based on the stationarity rate (SR) and classification accuracy. Both disjoint and overlap, windowing techniques with varying window and overlap sizes have been investigated using a machine learning-based classification algorithm called linear discriminant analysis.Main results.The optimum window size ranges are from 200-300 ms for the disjoint and 225-300 ms for the overlap windowing technique, respectively. The inferred results show that for the overlap windowing technique the optimum range of overlap size is from 10%-30% of the length of window size. The mean classification accuracy (MCA) and mean stationarity rate (MSR) were found to be lower in the disjoint windowing technique compared to overlap windowing at all investigated overlap sizes. Statistical analysis (two-way analysis of variance test) showed that the MSR and MCA of the overlap windowing technique was significantly different at overlap sizes of 10%-30% (p-values < 0.05).Significance.The presented results can be used to achieve the best possible classification results and SR for any iEMG-based real-time diagnosis, detection and control system, which can enhance the performance of the system significantly.

Decoding Attempted Hand Movements in Stroke Patients Using Surface Electromyography.

Brain- and muscle-triggered exoskeletons have been proposed as a means for motor training after a stroke. With the possibility of performing different movement types with an exoskeleton, it is possible to introduce task variability in training. It is difficult to decode different movement types simultaneously from brain activity, but it may be possible from residual muscle activity that many patients have or quickly regain. This study investigates whether nine different motion classes of the hand and forearm could be decoded from forearm EMG in 15 stroke patients. This study also evaluates the test-retest reliability of a classical, but simple, classifier (linear discriminant analysis) and advanced, but more computationally intensive, classifiers (autoencoders and convolutional neural networks). Moreover, the association between the level of motor impairment and classification accuracy was tested. Three channels of surface EMG were recorded during the following motion classes: Hand Close, Hand Open, Wrist Extension, Wrist Flexion, Supination, Pronation, Lateral Grasp, Pinch Grasp, and Rest. Six repetitions of each motion class were performed on two different days. Hudgins time-domain features were extracted and classified using linear discriminant analysis and autoencoders, and raw EMG was classified with convolutional neural networks. On average, 79 ± 12% and 80 ± 12% (autoencoders) of the movements were correctly classified for days 1 and 2, respectively, with an intraclass correlation coefficient of 0.88. No association was found between the level of motor impairment and classification accuracy (Spearman correlation: 0.24). It was shown that nine motion classes could be decoded from residual EMG, with autoencoders being the best classification approach, and that the results were reliable across days; this may have implications for the development of EMG-controlled exoskeletons for training in the patient's home.

Skin Lesion Segmentation from Dermoscopic Images Using Convolutional Neural Network.

Clinical treatment of skin lesion is primarily dependent on timely detection and delimitation of lesion boundaries for accurate cancerous region localization. Prevalence of skin cancer is on the higher side, especially that of melanoma, which is aggressive in nature due to its high metastasis rate. Therefore, timely diagnosis is critical for its treatment before the onset of malignancy. To address this problem, medical imaging is used for the analysis and segmentation of lesion boundaries from dermoscopic images. Various methods have been used, ranging from visual inspection to the textural analysis of the images. However, accuracy of these methods is low for proper clinical treatment because of the sensitivity involved in surgical procedures or drug application. This presents an opportunity to develop an automated model with good accuracy so that it may be used in a clinical setting. This paper proposes an automated method for segmenting lesion boundaries that combines two architectures, the U-Net and the ResNet, collectively called Res-Unet. Moreover, we also used image inpainting for hair removal, which improved the segmentation results significantly. We trained our model on the ISIC 2017 dataset and validated it on the ISIC 2017 test set as well as the PH2 dataset. Our proposed model attained a Jaccard Index of 0.772 on the ISIC 2017 test set and 0.854 on the PH2 dataset, which are comparable results to the current available state-of-the-art techniques.

Performance Evaluation of Convolutional Neural Network for Hand Gesture Recognition Using EMG.

Electromyography (EMG) is a measure of electrical activity generated by the contraction of muscles. Non-invasive surface EMG (sEMG)-based pattern recognition methods have shown the potential for upper limb prosthesis control. However, it is still insufficient for natural control. Recent advancements in deep learning have shown tremendous progress in biosignal processing. Multiple architectures have been proposed yielding high accuracies (>95%) for offline analysis, yet the delay caused due to optimization of the system remains a challenge for its real-time application. From this arises a need for optimized deep learning architecture based on fine-tuned hyper-parameters. Although the chance of achieving convergence is random, however, it is important to observe that the performance gain made is significant enough to justify extra computation. In this study, the convolutional neural network (CNN) was implemented to decode hand gestures from the sEMG data recorded from 18 subjects to investigate the effect of hyper-parameters on each hand gesture. Results showed that the learning rate set to either 0.0001 or 0.001 with 80-100 epochs significantly outperformed (p < 0.05) other considerations. In addition, it was observed that regardless of network configuration some motions (close hand, flex hand, extend the hand and fine grip) performed better (83.7% ± 13.5%, 71.2% ± 20.2%, 82.6% ± 13.9% and 74.6% ± 15%, respectively) throughout the course of study. So, a robust and stable myoelectric control can be designed on the basis of the best performing hand motions. With improved recognition and uniform gain in performance, the deep learning-based approach has the potential to be a more robust alternative to traditional machine learning algorithms.

Classification of Overt and Covert Speech for Near-Infrared Spectroscopy-Based Brain Computer Interface.

People suffering from neuromuscular disorders such as locked-in syndrome (LIS) are left in a paralyzed state with preserved awareness and cognition. In this study, it was hypothesized that changes in local hemodynamic activity, due to the activation of Broca's area during overt/covert speech, can be harnessed to create an intuitive Brain Computer Interface based on Near-Infrared Spectroscopy (NIRS). A 12-channel square template was used to cover inferior frontal gyrus and changes in hemoglobin concentration corresponding to six aloud (overtly) and six silently (covertly) spoken words were collected from eight healthy participants. An unsupervised feature extraction algorithm was implemented with an optimized support vector machine for classification. For all participants, when considering overt and covert classes regardless of words, classification accuracy of 92.88 ± 18.49% was achieved with oxy-hemoglobin (O2Hb) and 95.14 ± 5.39% with deoxy-hemoglobin (HHb) as a chromophore. For a six-active-class problem of overtly spoken words, 88.19 ± 7.12% accuracy was achieved for O2Hb and 78.82 ± 15.76% for HHb. Similarly, for a six-active-class classification of covertly spoken words, 79.17 ± 14.30% accuracy was achieved with O2Hb and 86.81 ± 9.90% with HHb as an absorber. These results indicate that a control paradigm based on covert speech can be reliably implemented into future Brain⁻Computer Interfaces (BCIs) based on NIRS.

Multiday EMG-Based Classification of Hand Motions with Deep Learning Techniques.

Pattern recognition of electromyography (EMG) signals can potentially improve the performance of myoelectric control for upper limb prostheses with respect to current clinical approaches based on direct control. However, the choice of features for classification is challenging and impacts long-term performance. Here, we propose the use of EMG raw signals as direct inputs to deep networks with intrinsic feature extraction capabilities recorded over multiple days. Seven able-bodied subjects performed six active motions (plus rest), and EMG signals were recorded for 15 consecutive days with two sessions per day using the MYO armband (MYB, a wearable EMG sensor). The classification was performed by a convolutional neural network (CNN) with raw bipolar EMG samples as the inputs, and the performance was compared with linear discriminant analysis (LDA) and stacked sparse autoencoders with features (SSAE-f) and raw samples (SSAE-r) as inputs. CNN outperformed (lower classification error) both LDA and SSAE-r in the within-session, between sessions on same day, between the pair of days, and leave-out one-day evaluation (p < 0.001) analyses. However, no significant difference was found between CNN and SSAE-f. These results demonstrated that CNN significantly improved performance and increased robustness over time compared with standard LDA with associated handcrafted features. This data-driven features extraction approach may overcome the problem of the feature calibration and selection in myoelectric control.

Parallel programming of saccades during natural scene viewing: evidence from eye movement positions.

Previous studies have shown that saccade plans during natural scene viewing can be programmed in parallel. This evidence comes mainly from temporal indicators, i.e., fixation durations and latencies. In the current study, we asked whether eye movement positions recorded during scene viewing also reflect parallel programming of saccades. As participants viewed scenes in preparation for a memory task, their inspection of the scene was suddenly disrupted by a transition to another scene. We examined whether saccades after the transition were invariably directed immediately toward the center or were contingent on saccade onset times relative to the transition. The results, which showed a dissociation in eye movement behavior between two groups of saccades after the scene transition, supported the parallel programming account. Saccades with relatively long onset times (>100 ms) after the transition were directed immediately toward the center of the scene, probably to restart scene exploration. Saccades with short onset times (<100 ms) moved to the center only one saccade later. Our data on eye movement positions provide novel evidence of parallel programming of saccades during scene viewing. Additionally, results from the analyses of intersaccadic intervals were also consistent with the parallel programming hypothesis.