A5102830803- Non-Invasive Vital Sign Monitoring
- COVID-19 epidemiological studies
- Diabetes Management and Research
- Neural Networks and Applications
- Smart Grid Security and Resilience
- COVID-19 diagnosis using AI
- Anomaly Detection Techniques and Applications
- Pelvic floor disorders treatments
- Energy Load and Power Forecasting
- User Authentication and Security Systems
- Heart Rate Variability and Autonomic Control
- EEG and Brain-Computer Interfaces
- Data-Driven Disease Surveillance
- ECG Monitoring and Analysis
- COVID-19 Pandemic Impacts
- Healthcare Technology and Patient Monitoring
- Bone and Dental Protein Studies
- Smart Grid Energy Management
- Advanced Data and IoT Technologies
- Pregnancy-related medical research
- Oral microbiology and periodontitis research
- Connexins and lens biology
- Computational Geometry and Mesh Generation
- Privacy-Preserving Technologies in Data
- Electric Vehicles and Infrastructure
Qatar University
2020-2025
Al-Azhar University
2023
Cairo University
2022
To assist policymakers in making adequate decisions to stop the spread of COVID-19 pandemic, accurate forecasting disease propagation is paramount importance. This paper presents a deep learning approach forecast cumulative number cases using bidirectional Long Short-Term Memory (Bi-LSTM) network applied multivariate time series. Unlike other techniques, our proposed first groups countries having similar demographic and socioeconomic aspects health sector indicators K-means clustering...
Cardiac autonomic neuropathy (CAN) has been suggested to be associated with hypoglycemia and impaired unawareness. We have assessed the relationship between CAN extensive measures of glucose variability (GV) in patients type 1 2 diabetes.Participants diabetes underwent continuous monitoring (CGM) obtain GV extent hyperglycemia cardiovascular reflex testing.Of 40 participants (20 T1DM 20 T2DM) (aged 40.70 ± 13.73 years, duration 14.43 7.35 HbA1c 8.85 1.70%), 23 (57.5%) had CAN. Despite a...
ABSTRACT Background Hyperglycemia is a major driver of diabetic peripheral neuropathy (DPN) in type 1 diabetes mellitus (T1DM). Advanced hybrid closed‐loop (AHCL) technologies improve glycemic control and reduce variability may DPN. Methods Patients with T1DM treated for 9.8 ± 0.32 months the 780G SmartGuard system ( n = 14) were compared patients on MDI 20) healthy controls 15). Time range (TIR), time above (TAR), below (TBR), variability, HbA 1c evaluated, corneal confocal microscopy (CCM)...
To reduce the impact of COVID-19 pandemic most countries have implemented several counter-measures to control virus spread including school and border closing, shutting down public transport workplace restrictions on gathering. In this research work, we propose a deep-learning prediction model for evaluating predicting various lockdown policies daily cases. This is achieved by first clustering having similar policies, then training based cases in each cluster along with data describing their...
Continuous glucose monitoring (CGM) has revealed that glycemic variability and low time in range are associated with albuminuria retinopathy. We have investigated the relationship between metrics derived from CGM a highly sensitive measure of neuropathy using corneal confocal microscopy participants type 1 2 diabetes.A total 40 diabetes 28 healthy controls underwent quantification nerve fiber density (CNFD), branch (CNBD), length (CNFL) inferior whorl (IWL) those for four consecutive...
In this paper, we propose a novel session-based continuous authentication model using photoplethysmography (PPG). Unlike previous PPG-based techniques that generate user signatures only during the initial interaction, our approach tackles inter session PPG drifting by generating signature at start of each session. Our is composed two modules: Firstly, heavy deep autoencoders (AE) are utilized for feature extraction and, secondly, lightweight Local Outlier Factor (LOF) employed...
Hyperbolic space has garnered attention for its unique properties and efficient representation of hierarchical structures. Recent studies have explored hyperbolic alternatives to hyperplane-based classifiers, such as logistic regression support vector machines. They even fused into random forests by constructing data splits with horosphere, which proved effective datasets. However, the existing incorporation horosphere leads substantial computation times, diverting from application on most...
Glucose monitoring is key to the management of diabetes mellitus maintain optimal glucose control whilst avoiding hypoglycemia. Non-invasive continuous techniques have evolved considerably replace finger prick testing, but still require sensor insertion. Physiological variables, such as heart rate and pulse pressure, change with blood glucose, especially during hypoglycemia, could be used predict To validate this approach, clinical studies that contemporaneously acquire physiological...
The Smart Grid Advanced Metering Infrastructure (AMI) has revolutionized the smart grid network, generating vast amounts of data that can be utilized for diverse objectives, one which is Household Characteristics Classification (HCC). This help utility provider profile their customers and tailor services to meet customer needs. To accomplish this task, we evaluated multiple Machine learning HCC models, with a focus on CNN-based models due wide popularity in field signal classification. We 1D...
This paper introduces a novel residual-based model to identify households with Battery Electric Vehicles (EVs) under high Air Conditioning (AC) load. The considerable energy demands of AC units can obscure charging events for EVs. In this work we propose residual based which leverages the distinctive characteristics EV patterns, marked by unpredictable spikes in consumption, and more predictable nature Our proposed approach involves training lightweight forecasting predict overall house-hold...
<p>In this paper, we propose a novel session-based continuous authentication scheme using photoplethysmography (PPG). The supporting model is developed in two phases: first, utilize deep autoencoders to extract features from PPG signals, and later adopt Local Outlier Factor (LOF) authenticate the user. LOF trained only on legitimate user data, making it practical for real-world scenarios. In detail, data generates signatures at beginning of each session with short buffer duration....
This paper investigates the potential privacy risks associated with forecasting models, specific emphasis on their application in context of smart grids. While machine learning and deep algorithms offer valuable utility, concerns arise regarding exposure sensitive information. Previous studies have focused classification overlooking models. Deep based such as Long Short Term Memory (LSTM), play a crucial role several applications including optimizing grid systems but also introduce risks....
The introduction of smart grids allows utility providers to collect detailed data about consumers, which can be utilized enhance grid efficiency and reliability. However, this collection also raises privacy concerns. To protect user privacy, some studies suggest using battery-based load hiding. Nevertheless, the impact widespread adoption approach on remain unclear. Our paper seeks evaluate effects hiding two critical operations: profiling anomaly detection. findings reveal that inclusion...
Background: To assist policy makers in taking adequate decisions to stop the spread of COVID-19 pandemic, accurate forecasting disease propagation is paramount importance. Materials and Methods: This paper presents a deep learning approach forecast cumulative number cases using Bidirectional Long Short-Term Memory (Bi-LSTM) network applied multivariate time series. Unlike other techniques, our proposed first groups countries having similar demographic socioeconomic aspects health sector...
<p>In this paper, we propose a novel session-based continuous authentication model using photoplethysmography (PPG). Unlike previous PPG-based techniques that generate user signatures only during the initial interaction, our approach tackles inter session PPG drifting by generating signature at start of each session. Our is composed two modules: Firstly, heavy deep autoencoders (AE) are utilized for feature extraction and, secondly, lightweight Local Outlier Factor (LOF) employed...