Niharika Tewari
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Niharika Tewari has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Feng Xia
School of Computing Technologies, RMIT University
2 shared publications - Mujie Liu
Institute of Innovation, Science and Sustainability, Federation University Australia, Ballarat, VIC, Australia
2 shared publications - Nguyen Linh Dan Le
RMIT University, Australia
2 shared publications - Chenze Wang
Zhejiang Gongshang University
1 shared publication Imran Hossain Showrov
Institute of Computer Science,Bangladesh Atomic Energy Commission,Dhaka,Bangladesh
1 shared publication- Jiangang Ma
Institute of Innovation, Science and Sustainability Federation University Australia 3353 Ballarat Australia
1 shared publication
Latest Publications
- Open Access
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
Explainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia
Dementia is a progressive neurodegenerative disorder with multiple etiologies, including Alzheimer's disease, Parkinson's disease, frontotemporal dementia, and vascular dementia. Its clinical and biological heterogeneity makes diagnosis and subtype differentiation highly challenging. Graph Neural Networks (GNNs) have recently shown strong potential in modeling brain connectivity, but their limited robustness, data scarcity, and lack of interpretability constrain clinical adoption. Explainable Graph Neural Networks (XGNNs) have emerged to address these barriers by combining graph-based learning with interpretability, enabling the identification of disease-relevant biomarkers, analysis of brain network disruptions, and provision of transparent insights for clinicians. This paper presents the first comprehensive review dedicated to XGNNs in dementia research. We examine their applications across Alzheimer's disease, Parkinson's disease, mild cognitive impairment, and multi-disease diagnosis. A taxonomy of explainability methods tailored for dementia-related tasks is introduced, alongside comparisons of existing models in clinical scenarios. We also highlight challenges such as limited generalizability, underexplored domains, and the integration of Large Language Models (LLMs) for early detection. By outlining both progress and open problems, this review aims to guide future work toward trustworthy, clinically meaningful, and scalable use of XGNNs in dementia research.
- 21 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Computing for Healthcare
Open AccessExplainable Graph Neural Networks: Understanding Brain Connectivity and Biomarkers in Dementia
Dementia is a progressive neurodegenerative disorder with multiple etiologies, including Alzheimer's disease, Parkinson's disease, frontotemporal dementia, and vascular dementia. Its clinical and biological heterogeneity makes diagnosis and subtype differentiation highly challenging. Graph Neural Networks (GNNs) have recently shown strong potential in modeling brain connectivity, but their limited robustness, data scarcity, and lack of interpretability constrain clinical adoption. Explainable Graph Neural Networks (XGNNs) have emerged to address these barriers by combining graph-based learning with interpretability, enabling the identification of disease-relevant biomarkers, analysis of brain network disruptions, and provision of transparent insights for clinicians. This paper presents the first comprehensive review dedicated to XGNNs in dementia research. We examine their applications across Alzheimer's disease, Parkinson's disease, mild cognitive impairment, and multi-disease diagnosis. A taxonomy of explainability methods tailored for dementia-related tasks is introduced, alongside comparisons of existing models in clinical scenarios. We also highlight challenges such as limited generalizability, underexplored domains, and the integration of Large Language Models (LLMs) for early detection. By outlining both progress and open problems, this review aims to guide future work toward trustworthy, clinically meaningful, and scalable use of XGNNs in dementia research.
- 27 November 2025
- Published by Springer Nature
- p. 359-372
Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-Efficient Psychiatric Diagnosis
- 27 November 2025
- Published by Springer Nature
- p. 359-372
Structure Matters: Brain Graph Augmentation via Learnable Edge Masking for Data-Efficient Psychiatric Diagnosis
- 3 July 2023
- Published by San International Scientific Publications
Artificial Intelligence in Finance and Industry: Opportunities and Challenges
Author: Niharika Tewari, Assistant Professor, School of Data Science, Asian Academy of Film and Television, Sector16A, Film City, Noida, UP, India Editors: Dr. Divya Mahajan, Dr. Saumya Vatsayan, Dr. Santosh Kumar, Dr. Priyanka Dadhich ISBN: 978-81-963849-1-3 DOI: https://doi.org/10.59646/edbookc5/009 Abstract Access to and management of financial resources are being transformed by artificial intelligence (AI). Everything from chatbot assistants to […]
- 3 July 2023
- Published by San International Scientific Publications
Artificial Intelligence in Finance and Industry: Opportunities and Challenges
Author: Niharika Tewari, Assistant Professor, School of Data Science, Asian Academy of Film and Television, Sector16A, Film City, Noida, UP, India Editors: Dr. Divya Mahajan, Dr. Saumya Vatsayan, Dr. Santosh Kumar, Dr. Priyanka Dadhich ISBN: 978-81-963849-1-3 DOI: https://doi.org/10.59646/edbookc5/009 Abstract Access to and management of financial resources are being transformed by artificial intelligence (AI). Everything from chatbot assistants to […]
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A Review of Omega Based Portfolio Optimization
Portfolio optimization aims to pick risky assets to meet the goal of maximizing the return and minimizing the risk. One should model the best combination of assets by striving the optimal relationship between risk and return for an appropriate investor even when the constraints are present. This paper aims to study the risk measure Conditional Value At Risk with constraints, that are added in a portfolio and are analyzed in the optimization problem. It also focuses on how will the portfolio work when a threshold value $L(\alpha)$:- CVaR is fixed. The dataset was taken from YAHOO Finance consisting of weekly historical prices were implemented.
- 1 November 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
A Review of Omega Based Portfolio Optimization
Portfolio optimization aims to pick risky assets to meet the goal of maximizing the return and minimizing the risk. One should model the best combination of assets by striving the optimal relationship between risk and return for an appropriate investor even when the constraints are present. This paper aims to study the risk measure Conditional Value At Risk with constraints, that are added in a portfolio and are analyzed in the optimization problem. It also focuses on how will the portfolio work when a threshold value $L(\alpha)$:- CVaR is fixed. The dataset was taken from YAHOO Finance consisting of weekly historical prices were implemented.