A5101480699- Parallel Computing and Optimization Techniques
- COVID-19 diagnosis using AI
- Low-power high-performance VLSI design
- Ferroelectric and Negative Capacitance Devices
- Artificial Intelligence in Healthcare
- Caching and Content Delivery
- Imbalanced Data Classification Techniques
- Retinal Imaging and Analysis
- Power System Reliability and Maintenance
- Power Transformer Diagnostics and Insulation
- Thermal Analysis in Power Transmission
- Cloud Computing and Resource Management
- IoT and Edge/Fog Computing
- Advanced X-ray and CT Imaging
- Radiomics and Machine Learning in Medical Imaging
- Image Retrieval and Classification Techniques
- Multi-Criteria Decision Making
- Algorithms and Data Compression
- Fuzzy Systems and Optimization
- Advanced Neural Network Applications
- Brain Tumor Detection and Classification
Guru Nanak Dev University
2024
Universidad Internacional
2022
Ibero-American University Puebla
2022
Ibero American University
2022
Graphic Era University
2022
Lebanese American University
2022
University of California, San Diego
2006-2009
Brain tumors are the 10th leading reason for death which is common among adults and children. On basis of texture, region, shape there exists various types tumor, each one has chances survival very low. The wrong classification can lead to worse consequences. As a result, these had be properly divided into many classes or grades, where multiclass comes play. Magnetic resonance imaging (MRI) pictures most acceptable manner method representing human brain identifying tumors. Recent...
Tuberculosis (TB) is an airborne disease caused by Mycobacterium tuberculosis. It imperative to detect cases of TB as early possible because if left untreated, there a 70% chance patient dying within 10 years. The necessity for supplementary tools has increased in mid low-income countries due the rise automation healthcare sectors. already limited resources are being heavily allocated towards controlling other dangerous diseases. Modern digital radiography (DR) machines, used screening chest...
In this paper, we propose a novel online-learning algorithm for system-level power management. We formulate both dynamic management (DPM) and voltage-frequency scaling problems as one of workload characterization selection solve them using our algorithm. The is done among set experts, which refers to DPM policies settings, leveraging the fact that different experts outperform each other under workloads device leakage characteristics. adapts changes in characteristics guarantees fast...
Dynamic power management (DPM) work proposed to date places inactive components into low states using a single DPM policy. In contrast, we instead dynamically select among set of policies with machine learning algorithm. We leverage the fact that different outperform each other under workloads and devices. Our algorithm adapts changes in guarantees quick convergence best performing policy for workload. performed experiments representing state art on hard disk drive WLAN card. results show...
Diabetes is a rapidly spreading disease. When the pancreas produces insufficient insulin or body cannot utilise it effectively. Diabetic Retinopathy (DR) and blindness are two major issues for diabetics. patients increase amount of data collected about DR. To extract important information undiscovered knowledge from data, mining techniques required. DM necessary in DR to improve society's health. Our study focuses on early detection using patient information. approaches used these numeric...
One of the main technologies for big data networking framework is online multihoming optimization that large-scale dimension table association technology in a distributed environment. It often used applications like real-time suggestion and research. Big concerned with quality large datasets are distributed. These demand sophisticated network to adequately transmit massive share files. Dimension process integrating stream offline stored executing processing using novel frameworks, as...
This study examines a demand-constant inventory-fuzzy-model and shortages are tolerated. In the proposed inventory model, our main motive is to reduce costs as much possible. So, optimization method used optimize cost. Due uncertainty some parameters of model contains fuzzy nature. which cost function also goal convert them into crisp one. Various defuzzification methods utilized for this purpose triangular numbers (TFN). Several analyzed numerically. The research concludes with sensitivity analysis.