A5076741438- Probabilistic and Robust Engineering Design
- Statistical Methods and Inference
- Thermochemical Biomass Conversion Processes
- Heat transfer and supercritical fluids
- Neural Networks and Applications
- Context-Aware Activity Recognition Systems
- Model Reduction and Neural Networks
- Adversarial Robustness in Machine Learning
- Stroke Rehabilitation and Recovery
- Green IT and Sustainability
- Cerebrovascular and Carotid Artery Diseases
- Forecasting Techniques and Applications
- Phase Equilibria and Thermodynamics
- Machine Learning and Data Classification
- Human Mobility and Location-Based Analysis
- Acute Ischemic Stroke Management
RWTH Aachen University
2020-2024
University of Engineering and Technology Lahore
2023
Khwaja Fareed University of Engineering and Information Technology
2020
CentraCare Health System
2018
This paper presents a comprehensive step-wise methodology for implementing industry 4.0 in functional coal power plant. The overall efficiency of 660 MWe supercritical coal-fired plant using real operational data is considered the study. Conventional and advanced AI-based techniques are used to present visualization. Monte-Carlo experimentation on artificial neural network (ANN) least square support vector machine (LSSVM) process models interval adjoint significance analysis (IASA) performed...
The increasing use of stochastic models for describing complex phenomena warrants surrogate that capture the reference model characteristics at a fraction computational cost, foregoing potentially expensive Monte Carlo simulation. predominant approach fitting large neural network and then pruning it to reduced size has commonly neglected shortcomings. produced often will not sensitivities uncertainties inherent in original model. In particular, (higher-order) derivative information such...
Background: Most studies recruiting patients with acute ischemic stroke ascertain the final functional status at 3 months post symptom onset. The rates and predictors of late improvement (>3 months) in has not been systemically studied. Methods: We analyzed data from three phase-III randomized multicenter clinical trials that recruited within or 5 hours symptoms Late was defined by an 1 more grade modified Rankin scale between ascertainments performed 12 randomization. groups patients;...
Abstract The use of smartphones and their applications is expanding rapidly, thereby increasing the demand computational power other hardware resources smartphones. On hand, these small devices can have limited computation power, battery backup, RAM memory, storage space due to size. These need reconcile resource hungry applications. This research focuses on solving issues efficiency smart by adapting intelligently mobile usage profiling user intelligently. Our designed architecture makes a...
The increasing use of stochastic models for describing complex phenomena warrants surrogate that capture the reference model characteristics at a fraction computational cost, foregoing potentially expensive Monte Carlo simulation. predominant approach fitting large neural network and then pruning it to reduced size has commonly neglected shortcomings. produced often will not sensitivities uncertainties inherent in original model. In particular, (higher-order) derivative information such...