A5101957301- Scientific Computing and Data Management
- IoT and GPS-based Vehicle Safety Systems
- Machine Learning and Data Classification
- EEG and Brain-Computer Interfaces
- IoT-based Smart Home Systems
- Advanced Proteomics Techniques and Applications
- Biochemical effects in animals
- Metabolomics and Mass Spectrometry Studies
- Aerospace Engineering and Energy Systems
- Advanced Neuroimaging Techniques and Applications
- Mass Spectrometry Techniques and Applications
- Aerospace and Aviation Technology
- Infrared Thermography in Medicine
- Fire Detection and Safety Systems
- Blind Source Separation Techniques
- Cloud Computing and Resource Management
- Brain Tumor Detection and Classification
- Neurological Disease Mechanisms and Treatments
- ECG Monitoring and Analysis
- IoT and Edge/Fog Computing
- Visual perception and processing mechanisms
- Functional Brain Connectivity Studies
- Planetary Science and Exploration
- Alzheimer's disease research and treatments
- Inertial Sensor and Navigation
Indian Institute of Technology Madras
2024-2025
American International University-Bangladesh
2024
National Institute of Technology Calicut
2021
Lahore University of Management Sciences
2021
BRAC University
2019-2020
University of Engineering and Technology Taxila
2020
Defence Electronics Research Laboratory
2020
An airship model is made-up of aerostatic, aerodynamic, dynamic, and propulsive forces torques. Besides others, the computation aerodynamic torques difficult. Usually, wind tunnel experimentation potential flow theory are used for their calculations. However, limitations these methods pose difficulties in accurate calculation. In this work, an online estimation scheme based on unscented Kalman filter (UKF) proposed The method introduces six auxiliary states complete model. UKF uses extended...
The evolutionary process of modern robotics helps the military forces to revamp their aged systems with today's advanced technology. For defending any kind criminal activities like hostage situation created by extremist or a militant group uses all terrain assistance robot has increased from past time. In this paper we have approached stair climbing some creative features which can assist complete mission achieve milestone. We focused on reliable designs and unique mechanisms detection...
In today's production machine learning (ML) systems, models are continuously trained, improved, and deployed. ML design training becoming a continuous workflow of various tasks that have dynamic resource demands. Serverless computing is an emerging cloud paradigm provides transparent management scaling for users has the potential to revolutionize routine training. However, hosting modern workflows on existing serverless platforms non-trivial challenges due their intrinsic limitations such as...
Proper implementation of internet things (IoT) can help the people developing countries to turn their conventional life style into a smart one. In this following research paper an IoT based LPG cylinder monitoring system has been approached for smoothing uses procedure with proper safety. Robust model custom designed PCB helps device be adjusted existing without any major changes. Mobile application unique design and versatile functionality along central server connect user through IoT. Uses...
PERCEPTRON is a next-generation freely available web-based proteoform identification and characterization platform for top-down proteomics (TDP). search pipeline brings together algorithms (i) intact protein mass tuning, (ii) de novo sequence tags-based filtering, (iii) of terminal as well post-translational modifications, (iv) truncated proteoforms, (v) in silico spectral comparison, (vi) weight-based candidate scoring. High-throughput performance achieved through the execution optimized...
Abstract Alzheimer’s disease (AD) is a progressive neurodegenerative brain disorder that primarily affects elderly individuals. Mild cognitive impairment (MCI) represents an intermediate stage between normal functioning and the onset of AD. During this transition state, various subanatomic structures brain, including fornix, undergo pathological changes. In study, attempt has been made to analyse structural variations in fornix region MCI AD using invariant moments. For purpose, T1- weighted...
In detecting brain activity and behavior, the Electroencephalogram (EEG) plays a key role. The EEG signals recorded are almost always corrupted by artifacts hence affect signal analysis. Therefore, it is highly essential to devise techniques extract noise-free data from signals. performance efficiency of two variation denoising methods: Simultaneous Low-Pass Filtering/Total Variation Denoising(LPF/TVD) Transient Artifact Reduction Algorithm (TARA) in artifact removal Schizophrenia (SZ)...
Extremely high data rates at modern synchrotron and X-ray free-electron laser light source beamlines motivate the use of machine learning methods for reduction, feature detection, other purposes. Regardless application, basic concept is same: collected in early stages an experiment, from past similar experiments, and/or simulated upcoming experiment are used to train models that, effect, learn specific characteristics those data; these then process subsequent more efficiently than would...
Extracting actionable information rapidly from data produced by instruments such as the Linac Coherent Light Source (LCLS-II) and Advanced Photon Upgrade (APS-U) is becoming ever more challenging due to high (up TB/s) rates. Conventional physics-based retrieval methods are hard-pressed detect interesting events fast enough enable timely focusing on a rare event or correction of an error. Machine learning~(ML) that learn cheap surrogate classifiers present promising alternative, but can fail...