Dr. Anurag Sharma, PhD (Can., Aus.), IEEE Senior Member is a Senior Lecturer at the University of the South Pacific. With extensive experience in artificial intelligence, his research spans machine learning, computer vision, and natural language processing, focusing on developing innovative deep learning models, including Generative Adversarial Networks (GANs) and Large Language Models (LLMs), for healthcare and social media applications. He has published widely in reputed journals and regularly reviews leading international journals in these fields. Currently, he is working on methods to make AI models smarter and more adaptable in solving real-world problems.

Research Interest

AI, machine learning, optimization, and their applications in healthcare, education, and data processing

Undergraduate Courses:

• CS112
• CS214

Postgraduate Course:

• CS412

IEEE Senior member

Some selected publications are shown below:

Journals:

[1]          Chaudhry, S., Sharma, A., “Data Distribution-Based Curriculum Learning,” IEEE Access, vol. 12, pp. 138429–138440, 2024.

[2]          Sharma, A., “Guided Stochastic Gradient Descent Algorithm for inconsistent datasets,” Applied Soft Computing, vol. 73, pp. 1068–1080, Dec. 2018.

[3]          Sharma, A., “Guided parallelized stochastic gradient descent for delay compensation,” Applied Soft Computing, vol. 102, p. 107084, Apr. 2021.

[4]          Sharma, A. et al., “SMOTified-GAN for Class Imbalanced Pattern Classification Problems,” IEEE Access, vol. 10, pp. 30655–30665, 2022.

[5]          Sharma, A., Kumar, D., “Classification with 2-D convolutional neural networks for breast cancer diagnosis,” Scientific Reports, vol. 12, no. 1, p. 21857, Dec. 2022.

Conferences:

[1]          Hussein, S. et al., “Multi-step-ahead chaotic time series prediction using coevolutionary recurrent neural networks,” in 2016 IEEE Congress on Evolutionary Computation (CEC), 2016, pp. 3084–3091.

[2]          Nand, R., Sharma, A., “Meta-heuristic approaches to tackle Skill Based Group allocation of Students in Project Based Learning Courses,” in 2019 IEEE Congress on Evolutionary Computation (CEC), 2019, pp. 1782–1789.

[3]          Raj, A. et al., “Depression Detection Using BERT on Social Media Platforms,” in 2024 IEEE International Conference on Artificial Intelligence in Engineering and Technology (IICAIET), 2024, pp. 228–233.

[4]          Sharma, A.K. et al., “Analysis on the Occurrence of Tropical Cyclone in the South Pacific Region Using Recurrent Neural Network with LSTM,” in Neural Information Processing, 2018, pp. 476–486.

[5]          Sharma, P. et al., “A Strategic Weight Refinement Maneuver for Convolutional Neural Networks,” in 2021 International Joint Conference on Neural Networks (IJCNN), 2021, pp. 1–7.

Books:
Chapters:

[1]          Onwubolu, G.C., Sharma, A., “Particle Swarm Optimization for the assignment of facilities to locations,” in New Optimization Techniques in Engineering, Springer-Verlag, 2004.

[2]          Sharma, A., Onwubolu, G., “Hybrid Particle Swarm Optimization and GMDH System,” in Hybrid Self-Organizing Modeling Systems, G. C. Onwubolu, Ed. Berlin, Heidelberg: Springer, 2009, pp. 193–231.

I am actively engaged in projects at the intersection of Artificial Intelligence (AI), machine learning, and optimization, with applications spanning education, healthcare, and data processing. My recent work includes:

1. Advancing Learning Systems through Curriculum and Guided Learning:
   • Developing innovative techniques such as Dynamic Data Distribution-based Curriculum Learning (DDCL) and Guided Stochastic Gradient Descent (GSGD) to improve the efficiency and adaptability of learning algorithms.
   • Exploring novel approaches to optimize learning pathways, enabling AI systems to learn more effectively and robustly across diverse datasets.
2. Data Transformation for Deep Learning Applications:
   • Creating methodologies to transform non-image numerical datasets into formats compatible with 2D Convolutional Neural Networks (CNNs).
   • Investigating the potential of these transformations in improving model performance for tasks such as medical diagnostics and disease classification.
3. AI in Healthcare:
   • Applying advanced deep learning methods to address critical medical challenges, such as detecting depression through analysis of social media posts by transforming textual data into image-based representations.
   • Enhancing diagnostic tools for medical applications by leveraging the capabilities of CNNs and other state-of-the-art algorithms.
4. Addressing Imbalanced Data Challenges:
   • Developing methods to tackle imbalanced datasets using techniques like SOMTified-GAN, which combines  Synthetic Minority Over-sampling Technique (SMOTE) and Generative Adversarial Networks (GANs) to generate synthetic data and balance distributions effectively.
   • Applying these methods to enhance the performance of classifiers in tasks such as medical diagnostics where data imbalance is a significant challenge.
5. Optimization Techniques for Complex Systems:
   • Working on constraint optimization problems, with a focus on multi-objective and bilevel optimization frameworks.
   • Extending the Intelligent Constraint Handling Evolutionary Algorithm (ICHEA) to solve real-world challenges, including applications in industrial and medical domains.

I welcome highly motivated PhD and MSc students to join my research group and contribute to these exciting and impactful projects. Prospective students will have the opportunity to work on cutting-edge topics in AI and optimization, with applications that span healthcare, education, and complex systems. If you are passionate about innovation and research in these areas, I encourage you to reach out to discuss potential collaboration opportunities.