Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal International Journal of Engineering, Science and Information Technology
Swarna, B
Unknown Affiliation
Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Education Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Social Sciences Transportation

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Transformer-Based Tabular Foundation Models: Outperforming Traditional Methods with TabPFN Babu, R Anand; Priya V, Vishwa; Kumar Mishra, Manoj; Ramesh Raja, Inakoti; Kiran Chebrolu, Surya; Swarna, B
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1146

Abstract

Scientific research and commercial applications rely heavily on tabular data, yet efficiently modelling this data has constantly been a problem. For over twenty years, the standard method for machine learning has been based on traditional models, with gradient-boosted decision trees (GBDTs). Despite recent advancements in deep learning, neural networks often fail to provide satisfactory results on compact tabular datasets due to factors such as overfitting, insufficient data intricate feature relationships. The study offers a Tabular Prior data Fitted Network, a foundation model developed by meta-learning on more than one million synthetic datasets generated sequentially, which is constructed on transformers to tackle these limitations. Without retraining or hyperparameter optimization, TabPFN learns to anticipate the best solutions for tabular problems, gaining inspiration from the achievements of GPT-like models in natural language processing. When applied to small to medium-sized datasets, its cutting-edge performance in inference speed accuracy outperforms that of traditional methods. TabPFN redefines efficient and scalable tabular data modelling, including generative capabilities, few-shot learning, rapid adaptation.
A Novel Hybrid Method for DAP: Differential Evolution with Variable Neighborhood Search Thakur, Mamta; Sushma, Talluri; Vellanki, Nagaraju; Shareef, R. M. Mastan; Anusha, Peruri Venkata; Swarna, B; Peter, Geno
International Journal of Engineering, Science and Information Technology Vol 5, No 3 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i3.1296

Abstract

This research investigates MOPFSP-SDST, an advanced and highly computational scheduling difficulty in real-world manufacturing systems. It examines how it correlates with multi-objective permutation flow shops. LS-MOVNS stands for "Learning and Swarm-based Multi-objective Variable neighbourhood Search." It is a better metaheuristic method that combines evolutionary swarm search and adaptive local search techniques to address this Problem. The two main improvements have been discussed: a partial neighbourhood assessment framework that reduces the computational expenses by analysing only a particular portion of the neighbourhood, and an adaptable neighbourhood series selection procedure that rapidly chooses the most beneficial neighbourhood order depending on past performance rates. These improvements aim to make searches more effective and productive by finding a better balance between exploration and exploitation. Particularly in medium to large problem sizes, experimental tests in benchmark instances show that LS-MOVNS frequently outperforms current modern algorithms in convergence and diversity. The results verify the long-term reliability, scalability, and practical applicability of LS-MOVNS for resolving challenging multi-objective scheduling issues.
Co-Authors Anusha, Peruri Venkata Babu, R Anand Kiran Chebrolu, Surya Kumar Mishra, Manoj Peter, Geno Priya V, Vishwa Ramesh Raja, Inakoti Shareef, R. M. Mastan Sushma, Talluri Thakur, Mamta Vellanki, Nagaraju