Mohammad Ali Moni
183
Publications
0
Followers
0
Following
0
Questions
About
Dr Moni holds a PhD in Artificial Intelligence & Data Science in 2014 from the University of Cambridge, UK followed by postdoctoral training at the University of New South Wales, University of Sydney Vice-chancellor fellowship, and Senior Data Scientist at the University of Oxford. Dr Moni then joined UQ in 2021. He also worked as an assistant professor and lecturer in two universities (PUST and JKKNIU) from 2007 to 2011. He is an Artificial Intelligence, Computer Vision & Machine learning, Digital Health Data Science, Health Informatics and Bioinformatics researcher developing interpretable and clinical applicable machine learning and deep learning models to increase the performance and transparency of AI-based automated decision-making systems.
His research interests include quantifying and extracting actionable knowledge from data to solve real-world problems and giving humans explainable AI models through feature visualisation and attribution methods. He has applied these techniques to various multi-disciplinary applications such as medical imaging including stroke MRI/fMRI imaging, real-time cancer imaging. He led and managed significant research programs in developing machine-learning, deep-learning and translational data science models, and software tools to aid the diagnosis and prediction of disease outcomes, particularly for hard-to-manage complex and chronic diseases. His research interest also includes developing Data Science, machine learning and deep learning algorithms, models and software tools utilizing different types of data, especially medical images, neuroimaging (MRI, fMRI, Ultrasound, X-Ray), EEG, ECG, Bioinformatics, and secondary usage of routinely collected data.
Skills & Expertise
Text Mining
Artificial Intelligence
Data Mining
Computer Vision
Matlab
Data Science
Bioinformatics
Mathematical Modeling
Natural Language Processing (NLP)
Machine learning
Medical Image Analysis
R
Medical Imaging and Informatics
Computational Biology
Digital Health
Deep-Learning
Neuro Imaging
Health Informatics
Clinical Informatics
Systems Biology
Research Interests
Artificial Intelligence
Machine Learning
nanotechnology
psychology
Data Science
Data Management
Haematology
Health Sciences
Neurosciences
Biomedical engineering
Applications in life sciences
Applied computing
Biological Sciences
Biomedical and Clinical Sciences
Cardiovascular medicine
Clinical sciences
Cognitive and computational psychology
Computer vision and multimedia computation
Cybersecurity and privacy
Distributed computing
systems software
Engineering
Human-centred computing
Information and Computing Sciences
Informetrics
Library and information studies
Medical biotechnology
Mobile computing
Sports science and exercise
Connect With Me
Experience
Honorary Senior Research Fellow
Senior Lecturer
USyd Fellow
Postdoctoral Research Fellow
Associate Lecturer
Postdoctoral Researcher
Education
University of Cambridge
Islamic University, Kushtia (IU)
Islamic University, Kushtia (IU)
Projects
develop AI-based health-care related software products
Seed funding from two companies Karte Ltd (Japan) and iHealthOmics Ltd (Hong Kong) to develop AI-based health-care related software products. Received seed funding ($40,000) from Karte Ltd. 2018-2020
AI-based based model development for Magnetic Resonance Imaging
Deep Learning models to solve inverse problems utiling MRI/fMRI image
Deep Leaning Model to identify Neuroimaging biomarkers
Deep learning models development and application to the Neuro Imaging (MRI and fMRI)
Magnetic resonance (MR) imaging has become an important non-invasive radiological modality for various clinical applications, such as stoke and cancer. Extracting meaningful clinical information without human interaction is a challenging task. Developing such automatic methods are important in order to reduce human errors and the time taken by clinicians.
In this project, the student will develop novel deep learning algorithms to solve segmentation and detection problems from imaging that could possibly be deployed to MRI & fMRI scanners and may eventually used for diagnostic purposes. The project will involve applying computer vision and deep learning techniques to MR image processing and analysis.
The Garvan Research Foundation & Ridley Corporation award
Statistical Bioinformatics and Machine-Learning Methods for Diagnosis and Prognosis of ovarian cancer empowered by integrated Next Generation Sequencing (NGS)
Eleven outstanding early career researchers from around the world will join the University of Sydney in 2017 under the University of Sydney Fellowship scheme.
Now in its 21st year, Sydney Fellows was the first scheme of its kind in Australia when launched in 1996. It aims to recruit promising young scholars in order to enhance the research strengths and culture of the University and enable them to contribute to its thriving intellectual life.
This year, the scheme focused on recruiting talented recent doctoral graduates who can contribute to our whole-of-university multidisciplinary initiatives, including the Charles Perkins Centre, the Brain and Mind Centre and the China Studies Centre.
Conferences & Seminars (1)
Real-time human activity recognition using non-intrusive sensing and continual learning
With a rapid increase in the ageing population across the globe, there is an urgent need for the development of affordable and sustainable solutions to provide aged care support services. Recent advancements in sensor technologies coupled with the use of artificial intelligence (AI) make it possible to monitor and classify the activities of daily living (ADL) of residents in aged care settings, making it easier to detect and predict any potential health problems. The development of such an architecture, however, presents two key challenges: (i) the determination of appropriate sensors and (ii) the selection of suitable AI approaches to recognise individual activities. While existing studies often only focus on addressing one challenge at a time, in this paper, we present the design and implementation of a real-time human activity recognition system called HARNIC, which uses not only non-intrusive sensors but also utilises continual learning to classify individual activities in a simulated environment. We conducted a thorough analysis of current non-intrusive sensors and subsequently selected appropriate sensors for real-time activity monitoring by considering several features such as adjustable sensitivity, detection range, trigger modes, processing power and accuracy. Using the sensors, we designed and simulated a smart aged care environment in a laboratory setting and collected ADL data. This data is categorised into three levels i.e., low, medium, and high, based on the type of activity. We then worked on generating a benchmark data set used to build machine learning models and performed testing of our models. To address the second challenge, we considered incremental and non-incremental methods and evaluated their effectiveness in recognising individual activities in real-time. Our initial experiment results indicate a clear superiority of our HARNIC over the existing state-of-the-art methods used in this study.
Awards & Achievements (9)
🏆 Early Career Fellowship
Description
🏆 Charles Sturt Excellence Awards
Description
🏆 The Cambridge Commonwealth, European & International Trust award
Description
🏆 Travel award
Description
🏆 Best student paper award
Description
🏆 Travel award
Description
🏆 The Ridley Ken Davies Award ($50,000)
Description
🏆 Certara-Monash Fellowship Awarded
Description
🏆 Best Impact Award
Description
Publications (183)
Paddy cultivation is a significant global economic sector, with rice production playing a crucial role in influencing worldwide economies. However, insects in paddy farms predominantly impact the grow...
Infectious fungi have been an increasing global concern in the present era. A promising approach to tackle this pressing concern involves utilizing Antifungal peptides (AFP) to develop an antifungal d...
Modern healthcare should include artificial intelligence (AI) technologies for disease identification and monitoring, particularly for chronic conditions, including heart, diabetes, kidney, liver, and...
The worldwide prevalence of thyroid disease is on the rise, representing a chronic condition that significantly impacts global mortality rates. Machine learning (ML) approaches have demonstrated poten...
Background
Upper respiratory infections (URIs) are the leading cause of acute disease incidence worldwide and contribute to a substantial health-care burden. Although acute otitis media is a common c...
dd