publications

Publications

• Mishra, P. and Roudot, P., (2024). Comparative study of transformer robustness for multiple particle tracking without clutter. In EUSIPCO.
  This paper offers a proof-of-concept study of the benefit of the transformer architecture in tracking scenarios where the prediction challenge does not come from the complexity of the sequence, but from the number of hypothetical paths the sequence can take. We show that while the transformer requires very little training to significantly outperform conventional tracking approaches on long sequences, it cannot match the theoretically optimal performances of MHT on short sequences even with extensive training. Hence, our work motivates the broader application of transformers in sequences and opens the way to the development of frugal methods thanks to the combination of both statistical and neural network frameworks for particle tracking.

• Dutta P., Mishra P., Saha S. (2020). Incomplete multi-view gene clustering with data regeneration using Shape Boltzmann Machine. Computers in Biology and Medicine, Elsevier.
  We addressed the problem of clustering gene data when different types of data (views) are missing. Our proposed approach used Shape Boltzmann Machines to regenerate missing data and subsequently perform clustering. This method aims to enhance the accuracy and reliability of gene clustering by leveraging information from multiple data sources, even in the presence of incomplete data. We evaluated our method on several real-world gene datasets and demonstrated its superior performance compared to existing approaches.

Complete List of Published and Archived Work

• 2024
  • Mishra, P. and Roudot, P., (2024). Comparative study of transformer robustness for multiple particle tracking without clutter. In EUSIPCO. PDF
• 2023
  • Mishra, P., (2023). Comparative study of stochastic filtering and attention-based approaches for intracellular dynamics estimation, Institut de Mathématiques de Marseille. PDF
• 2022
  • Mishra, P., (2022). Understanding the Human Genome Language with Natural Language Models, Stony Brook University & Aix-Marseille Université. PDF
• 2021
  • Mishra, P., Mohapatra, P., Patra, T. K., & Subham, P. (2021, December). Disease Diagnosis in Grapevines–A Hybrid Resnet-Jaya Approach. In International Advanced Computing Conference (pp. 39-56). Cham: Springer International Publishing.
• 2020
  • Mishra, P., Sahoo, D., Khandelwal, H., Amman, N., & Sobhanayak, S. (2020, October). Minimised jaya algorithm-based structure optimisation for heterogeneous wireless sensor networks. In 2020 5th International Conference on Computing, Communication and Security (ICCCS) (pp. 1-8). IEEE.
  • Dutta P., Mishra P., Saha S. (2020). Incomplete multi-view gene clustering with data regeneration using Shape Boltzmann Machine. Computers in Biology and Medicine, Elsevier.
• 2019
  • Mishra, P., Dey, S., Ghosh, S. S., Seal, D. B., & Goswami, S. (2019, September). Human activity recognition using deep neural network. In 2019 International conference on data science and engineering (ICDSE) (pp. 77-83). IEEE.

Google Scholar