A5033655491- Hydrocarbon exploration and reservoir analysis
- Hydraulic Fracturing and Reservoir Analysis
- Hepatocellular Carcinoma Treatment and Prognosis
- AI in cancer detection
- Liver Disease Diagnosis and Treatment
- Spectroscopy Techniques in Biomedical and Chemical Research
- Enhanced Oil Recovery Techniques
- Paleopathology and ancient diseases
- Infrastructure Maintenance and Monitoring
- Auction Theory and Applications
- Transportation and Mobility Innovations
- ECG Monitoring and Analysis
- Mobile Ad Hoc Networks
- Lattice Boltzmann Simulation Studies
- Advanced X-ray and CT Imaging
- Energy Efficient Wireless Sensor Networks
- Geochemistry and Geologic Mapping
- Millimeter-Wave Propagation and Modeling
- Groundwater and Watershed Analysis
- Drilling and Well Engineering
- Cell Image Analysis Techniques
- Radiomics and Machine Learning in Medical Imaging
- Blockchain Technology Applications and Security
- Indoor and Outdoor Localization Technologies
- Speech and Audio Processing
Texas A&M University at Qatar
2022-2025
Qatar Foundation
2025
Université Ibn Zohr
2024
Mitchell Institute
2022-2024
Texas A&M University
2022-2024
Hamad Medical Corporation
2022
Carnegie Mellon University Qatar
2021
Clinical imaging (e.g., magnetic resonance and computed tomography) is a crucial adjunct for clinicians, aiding in the diagnosis of diseases planning appropriate interventions. This especially true malignant conditions such as hepatocellular carcinoma (HCC), where image segmentation (such accurate delineation liver tumor) preliminary step taken by clinicians to optimize diagnosis, staging, treatment intervention transplantation, surgical resection, radiotherapy, PVE, embolization, etc)....
Abstract Understanding ancient organisms and their interactions with paleoenvironments through the study of body fossils is a central tenet paleontology. Advances in digital image capture now allow for efficient accurate documentation, curation, interrogation fossil forms structures two three dimensions, extending from microfossils to larger specimens. Despite these developments, key processing analysis tasks, such as segmentation classification, still require significant user intervention,...
Abstract Petrographic observations are vital for carbonate pore‐typing, linking geological frameworks to petrophysical behavior. However, current petrographic pore typing is manual, with the qualitative semi‐quantitative results not easily fitted into quantitative subsurface characterization. Some recent studies have automated this process using supervised machine learning (ML) and deep (DL), focusing on simple morphological features, reported high classification accuracies several complex...
In our research, we address the problem of coordination and planning in heterogeneous multi-robot systems for missions that consist spatially localized tasks. Conventionally, this has been framed as a task allocation maps tasks to robots. However, all previous work assumes are atomic procedures. work, relax assumption adopt non-atomic model enables robots accomplish mission incrementally over disjoint periods, precisely account possibility having serviced by numerous individual contributions...
GeoCrack is the first large-scale open source annotated dataset of fracture traces from geological outcrops, enabling deep learning-based segmentation, setting a new standard for natural characterization datasets. contains images photogrammetric surveys fractured rock exposures across 11 sites in Europe and Middle East, capturing diverse lithologies tectonic settings. Each image was cleaned, normalized, manually segmented, followed by recursive annotation vetting process to ensure quality...
With significant advancements in Machine Learning and Deep Learning, Convolutional Neural Networks (CNNs) have shown promising results handling classification regression problems. We present 3DRSSNet, a model that can predict the signal strength of an Access point 3-D environment based on floor map building. Our deep CNN approach differs from previous work (i) it generalize to unseen environments, (ii) best our knowledge, is first utilize 3D maps build prediction validate its using actual...
The first study to propose a binary framing for machine learning driven petrographic pore typing• Linear and non-linear models perform equally well idealized microfractures pores• We highlight the need greater scrutiny in AI typing
In this paper, we present an approach to model the stochastic spread of malware within a wireless sensor network (WSN).The is characterized as reduced scale-free topology, exhibiting just two average degrees.Our work delves into realm epidemic modeling building upon its deterministic counterpart [19].We leverage distinct methodologies, namely discrete-time Markov chain (DTMC) and Stochastic Differential Equation (SDE) techniques, explore temporal dynamics our proposed model.Our investigation...
<title>Abstract</title> Understanding ancient organisms and their paleo-environments through the study of body fossils represents a central tenet paleontology. Advances in digital image capture over past several decades now allow for efficient accurate documentation, curation interrogation fossil anatomy disparate length scales. Despite these developments, key processing analysis tasks, such as segmentation classification still require significant user intervention, which can be...
Abstract Medical images (e.g., magnetic resonance imaging (MRI) and computed tomography (CT)) provide critical information to the clinicians in order diagnose pathology plan interventions. Image segmentation is first foremost step taken by while optimizing analytic diagnosis treatment planning for interventions transplantation complete resection) therapeutic procedures radiotherapy, PVE, embolization approaches), especially hepatocellular carcinoma. Thus, techniques certainly impact...