A5066206447- Muscle activation and electromyography studies
- EEG and Brain-Computer Interfaces
- Neuroscience and Neural Engineering
- Advanced Sensor and Energy Harvesting Materials
- Corneal surgery and disorders
- Ocular Surface and Contact Lens
- Prosthetics and Rehabilitation Robotics
- Glaucoma and retinal disorders
- Neural dynamics and brain function
- Hand Gesture Recognition Systems
- COVID-19 diagnosis using AI
- Ophthalmology and Visual Impairment Studies
- Stroke Rehabilitation and Recovery
- Infrared Thermography in Medicine
- AI in cancer detection
- Functional Brain Connectivity Studies
- Corneal Surgery and Treatments
- Artificial Intelligence in Healthcare
- Medical Imaging and Analysis
- Motor Control and Adaptation
- Diabetic Foot Ulcer Assessment and Management
- Traditional Chinese Medicine Studies
- Bipolar Disorder and Treatment
- Neural Networks and Applications
- Biometric Identification and Security
University of Baghdad
2015-2024
University of Plymouth
2012-2023
Abstract Data scarcity is a major challenge when training deep learning (DL) models. DL demands large amount of data to achieve exceptional performance. Unfortunately, many applications have small or inadequate train frameworks. Usually, manual labeling needed provide labeled data, which typically involves human annotators with vast background knowledge. This annotation process costly, time-consuming, and error-prone. every framework fed by significant automatically learn representations....
A method for the classification of finger movements dexterous control prosthetic hands is proposed. Previous research was mainly devoted to identify hand as these actions generate strong electromyography (EMG) signals recorded from forearm. In contrast, in this paper, we assess use multichannel surface (sEMG) classify individual and combined control. sEMG channels were ten intact-limbed six below-elbow amputee persons. Offline processing used evaluate performance. The results show that high...
We investigate the problem of achieving robust control hand prostheses by electromyogram (EMG) transradial amputees in presence variable force levels, as these variations can have a substantial impact on robustness prostheses. also propose novel set features that aim at reducing level prosthesis controlled amputees. These characterize EMG activity means orientation between spectral moments descriptors extracted from signal and nonlinearly mapped version it. At same time, our feature...
The performance of intelligent electromyogram (EMG)-driven prostheses, functioning as artificial alternatives to missing limbs, is influenced by several dynamic factors including: electrode position shift, varying muscle contraction level, forearm orientation, and limb position. impact these on EMG pattern recognition has been previously studied in isolation, with the combined effect being understudied. However, it likely that a combination influences accuracy. We investigated two factors,...
In this study, a minimal setup for the ankle joint kinematics estimation is proposed relying only on proximal information of lower-limb, i.e. thigh muscles activity and kinematics. To purpose, myoelectric Rectus Femoris (RF), Biceps (BF), Vastus Medialis (VM) were recorded by surface electromyography (sEMG) from six healthy subjects during unconstrained walking task. For each subject, angular hip joints synchronously with sEMG signal total 288 gait cycles. Two feature sets extracted signals,...
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 sEMG recording sites can be as inputs control powered prostheses. However, usage EMG on prosthetic hand is not practical and makes it difficult for amputees due electrode shift/movement, often feel discomfort in wearing sensor array. Instead, using fewer numbers would greatly controllability devices...
Upper-limb amputation imposes significant burden on amputees thereby restricting them from fully exploring their environments during activities of daily living. The use intelligent learning algorithm for electromyogram-pattern recognition (EMG-PR)-based control in upper-limb prostheses is considered as an important clinical option. Though the existing EMG-PR could discriminate multiple degrees freedom (DOF) limb movements, transition to clinically viable option still being challenged by some...
The extraction of the accurate and efficient descriptors muscular activity plays an important role in tackling challenging problem myoelectric control powered prostheses. In this paper, we present a new feature framework that aims to give enhanced representation activities through increasing amount information can be extracted from individual combined electromyogram (EMG) channels. We propose use time-domain (TDDs) estimating EMG signal power spectrum characteristics; step preserves...
Gait phase recognition systems based on surface electromyographic signals (EMGs) are crucial for developing advanced myoelectric control schemes that enhance the interaction between humans and lower limb assistive devices. However, machine learning models used in this context, such as Linear Discriminant Analysis (LDA) Support Vector Machine (SVM), typically experience performance degradation when modeling gait cycle with more than just stance swing phases. This study introduces a...
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 PDF EMG is yet to be reached, because not only are there several biological factors that can influence this function, but also different analysis techniques lead contradicting results.Here, we recorded signal at isometric muscle contraction levels characterised two statistical measures: bicoherence...
The use of surface electromyographic (sEMG) signals, alongside pattern recognition (PR) systems, is fundamental in the design and control assistive technologies. Transient sEMG signal epochs at early beginning movement provide important information for upper-limb intent motion recognition. However, only few studies investigated role transient myoelectric architectures. Therefore, this work, focus was given to signals intact-limb (IL) subjects transhumeral amputees (AMP), who performed a...
Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose deep learning (DL) model to address challenge. We first used Xception and InceptionResNetV2 DL architectures extract features from three different corneal maps collected 1371 eyes examined in an eye clinic Egypt. then fused using detect subclinical forms KCN more accurately robustly. obtained area under the receiver operating characteristic curves (AUC) 0.99 accuracy...
Abstract Clinical keratoconus (KCN) detection is a challenging and time-consuming task. In the diagnosis process, ophthalmologists must revise demographic clinical ophthalmic examinations. The latter include slit-lamb, corneal topographic maps, Pentacam indices (PI). We propose an Ensemble of Deep Transfer Learning (EDTL) based on maps. consider four pretrained networks, SqueezeNet (SqN), AlexNet (AN), ShuffleNet (SfN), MobileNet-v2 (MN), fine-tune them dataset KCN normal cases, each...
The role of feature extraction in electromyogram (EMG) based pattern recognition has recently been emphasized with several publications promoting deep learning (DL) solutions that outperform traditional methods. It shown the ability DL models to extract temporal, spatial, and spatio–temporal information provides significant enhancements performance generalizability myoelectric control. Despite these advancements, it can be argued are computationally very expensive, requiring long training...
The myoelectric control of prostheses has been an important area research for the past 40 years. Significant advances have achieved with Pattern Recognition (PR) systems regarding number movements to be classified high accuracy. However, practical robustness still needs further research. This paper focuses on investigating effect change in force levels by transradial amputee persons performance PR systems. Two below-elbow participated study. Three forces (low, medium, and high) were recorded...
This paper presents a new feature extraction algorithm for the challenging problem of classification myoelectric signals prostheses control. The employs orientation between set descriptors muscular activities and nonlinearly mapped version them. It incorporates information about Electromyogram (EMG) signal power spectrum characteristics derived from each analysis window while correlating that with previous windows robust activity recognition. proposed idea can be summarized in following...
The design of pattern recognition-based myoelectric interfaces has been heavily explored and contested in the research literature. A considerable proportion performance these linked to quality feature extraction (FE) stage used describe underlying signal. In this paper, we address two important factors FE that have not fully exploited; 1) Spatial focus - traditional methods mainly on concatenation features extracted from individual channels 2) Temporal available are cross-sectional nature,...
To develop and assess the accuracy of a hybrid deep learning construct for detecting keratoconus (KCN) based on corneal topographic maps.We collected 3794 images from 542 eyes 280 subjects developed seven models anterior posterior eccentricity, elevation, sagittal curvature, thickness maps to extract features. An independent subset with 1050 150 85 separate center was used validate models. We model detect KCN. visualized features parameters quality subjectively computed area under receiver...
Electromyogram (EMG)-based Pattern Recognition (PR) systems for upper-limb prosthesis control provide promising ways to enable an intuitive of the prostheses with multiple degrees freedom and fast reaction times. However, lack robustness PR may limit their usability. In this paper, a novel adaptive time windowing framework is proposed enhance performance by focusing on classification steps. The estimates output probabilities each class outputs movement only if decision probability above...
Difficulties accessing amputee populations has resulted in the widespread adoption of able-bodied subjects virtual environments for development myoelectric prostheses. Factors such as scar tissue, different physiologies or surgical outcomes, and reduced visual proprioceptive feedback, however, may contribute to differences electromyogram (EMG) patterns between these groups. As such, studies have consistently found worse results when comparing performance that their counterparts under same...