A5033894707- COVID-19 diagnosis using AI
- Radiomics and Machine Learning in Medical Imaging
- Statistical Distribution Estimation and Applications
- Astro and Planetary Science
- Atmospheric Ozone and Climate
- Multi-Criteria Decision Making
- Lung Cancer Diagnosis and Treatment
- Isotope Analysis in Ecology
- Artificial Intelligence in Healthcare and Education
- Planetary Science and Exploration
- Bayesian Methods and Mixture Models
- Advanced Vision and Imaging
- EEG and Brain-Computer Interfaces
- Noise Effects and Management
- Probabilistic and Robust Engineering Design
- Hydrology and Drought Analysis
- Video Surveillance and Tracking Methods
- Video Coding and Compression Technologies
- Bayesian Modeling and Causal Inference
- Remote-Sensing Image Classification
- AI in cancer detection
- Big Data and Business Intelligence
- Statistical Methods and Bayesian Inference
- Remote Sensing and LiDAR Applications
- Anomaly Detection Techniques and Applications
University of New England
2021-2025
University of Technology Sydney
2019-2025
Griffith University
2023-2025
Dibrugarh University
2024
UNSW Sydney
2024
Ramakrishna Mission Vivekananda Educational and Research Institute
2024
Indian Institute of Engineering Science and Technology, Shibpur
2010-2022
University of California, San Diego
2003-2022
Indian Institute of Technology Kanpur
2022
Saroj Gupta Cancer Centre & Research Institute
2022
Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how transfer learning from deep models can be used to perform detection using images three most commonly medical imaging modes X-Ray, Ultrasound, CT scan. The aim is provide over-stressed professionals a second pair of eyes through intelligent image classification models. We identify suitable <italic xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Selection of an appropriate Multiple Attribute Decision Making (MADM) method for providing a solution to given MADM problem is always challenging endeavour. The challenge even greater situations where specific there exist multiple methods with similar degree suitability. Technique Order Preference by Similarity Ideal Solution (TOPSIS) and its dominant variant the Modified TOPSIS are two very applicable same type problems. This study provides extensive simulation-based comparisons...
Ensuring health worker job satisfaction and motivation are important if workers to be retained effectively deliver services in many developing countries, whether they work the public or private sector. The objectives of paper identify aspects two Indian states working sectors. Cross-sectional surveys 1916 sector Andhra Pradesh Uttar Pradesh, India, were conducted using a standardized instrument workers' with key factors related motivation. Ratings compared how consider these factors. There...
Detecting COVID-19 early may help in devising an appropriate treatment plan and disease containment decisions. In this study, we demonstrate how pre-trained deep learning models can be adopted to perform detection using X-Ray images. The aim is provide over-stressed medical professionals a second pair of eyes through intelligent image classification models. We highlight the challenges (including dataset size quality) utilising current publicly available datasets for developing useful propose...
The COVID-19 pandemic has triggered an urgent call to contribute the fight against immense threat human population. Computer Vision, as a subfield of artificial intelligence, enjoyed recent success in solving various complex problems health care and potential controlling COVID-19. In response this call, computer vision researchers are putting their knowledge base at test devise effective ways counter challenge serve global community. New contributions being shared with every passing day. It...
Climate change already challenges people’s livelihood globally and it also affects plant health. Rising temperatures facilitate the introduction establishment of unwanted organisms, including arthropods, pathogens, weeds (hereafter collectively called pests). For example, a single, unusually warm winter under temperate climatic conditions may be sufficient to assist invasive pests, which otherwise would not able establish. In addition, increased market globalization related transport recent...
Objective: In this paper, we explore the correlation between performance reporting and development of inclusive AI solutions for biomedical problems. Our study examines critical aspects bias noise in context medical decision support, aiming to provide actionable solutions. Contributions: A key contribution our work is recognition that measurement processes introduce arising from human data interpretation selection. We concept “noise-bias cascade” explain their interconnected nature. While...
Multiattribute decision making (MADM) uses a normalization procedure to transform performance ratings with different data measurement units in matrix into compatible unit. MADM methods generally use one particular without justifying its suitability. The technique for order preference by similarity ideal solution (TOPSIS) is of the most popular and widely applied methods. This study compares four commonly known procedures terms their ranking consistency weight sensitivity when used TOPSIS...
Abstract High-velocity data streams present a challenge to deep learning-based computer vision models due the resources needed retrain for new incremental data. This study presents novel staggered training approach using an ensemble model comprising following: (i) resource-intensive high-accuracy transformer; and (ii) fast training, but less accurate, low parameter-count convolutional neural network. The transformer provides scalable accurate base model. A network (CNN) quickly incorporates...
The objectives of the study were to monitor and assess road traffic noise in its spatial-temporal aspect an urban area. paper discusses observations, results their interpretation based on study. Noise recordings from site, collected April 2006 March 2006, used for statistical analysis generation various indices. maps also created impact formulation Risk Zones. Mean Ldn value ranged between 55.1 87.3 dB (A). Day time Leq level 51.2 89.0 (A), where it 43.5 81.9 (A) during night. reveals that...
Historically, the physical chemistry of isotope effects and precise measurements in samples from nature have provided information on processes that could not been obtained otherwise. With discovery a mass-independent isotopic fractionation during formation ozone, new chemical basis for required development. Combined theoretical experimental developments broadened this understanding extended range systems where these unique occur. Simultaneously, application to an extensive both terrestrial...
Nitrogen isotopic distributions in the solar system extend across an enormous range, from -400‰, wind and Jovian atmosphere, to about 5,000‰ organic matter carbonaceous chondrites. Distributions such as these require complex processing of nitrogen reservoirs extraordinary isotope effects. While theoretical models invoke ion-neutral exchange reactions outside protoplanetary disk photochemical self-shielding on surface explain variations, there are no experiments substantiate models....
Terrestrial features extraction, such as roads and buildings from aerial images using an automatic system, has many usages in extensive range of fields, including disaster management, change detection, land cover assessment, urban planning. This task is commonly tough because complex scenes, where road objects are surrounded by shadows, vehicles, trees, etc., which appear heterogeneous forms with lower inter-class higher intra-class contrasts. Moreover, extraction time-consuming expensive to...
This article's main contributions are twofold: 1) to demonstrate how apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice domain of healthcare and 2) investigate research question what does "trustworthy AI" mean at time COVID-19 pandemic. To this end, we present results a post-hoc self-assessment evaluate trustworthiness an system predicting multiregional score conveying degree lung compromise patients, developed verified by...