Personal information

Machine Learning, Deep Learning, NLP, MLOPS, Generative AI, LLM
India

Biography

I'm a B.Tech Computer Science and Engineering student, driven by a passion for utilizing technology to create positive change. I dedicate substantial time to mastering new technologies and crafting projects aimed at benefiting others.

💻 Proficient in programming languages such as C, C++, and Python, I also have experience in a range of cutting-edge technologies including machine learning, deep learning, natural language processing, MLOPS, Generative AI and LLM.

Activities

Education and qualifications (1)

Dr B. C. Roy Engineering College: Durgapur, West Bengal, IN

2021 to 2025 | BTech (Computer Science and Engineering)
Education
Source: Self-asserted source
Subhayu Dutta

Works (10)

MusicalBSI - musical genres responses to fMRI signals analysis with prototypical model agnostic meta-learning for brain state identification in data scarce environment

Computers in Biology and Medicine
2025-04 | Journal article
Contributors: Subhayu Dutta; Saptiva Goswami; Sonali Debnath; Subhrangshu Adhikary; Anandaprova Majumder
Source: check_circle
Crossref

FedTinyWolf—A Memory Efficient Federated Embedded Learning Mechanism

IEEE Embedded Systems Letters
2024-12 | Journal article
Contributors: Subhrangshu Adhikary; Subhayu Dutta
Source: check_circle
Crossref

TinyWolf — Efficient on-device TinyML training for IoT using enhanced Grey Wolf Optimization

Internet of Things
2024-12 | Journal article
Contributors: Subhrangshu Adhikary; Subhayu Dutta; Ashutosh Dhar Dwivedi
Source: check_circle
Crossref

VisFormers—Combining Vision and Transformers for Enhanced Complex Document Classification

Machine Learning and Knowledge Extraction
2024-02-16 | Journal article
Contributors: Subhayu Dutta; Subhrangshu Adhikary; Ashutosh Dhar Dwivedi
Source: check_circle
Crossref
grade
Preferred source (of 3)‎

Diabetes Prediction Using Machine Learning: A Detailed Insight

Computational Sciences and Sustainable Technologies
2024-02-03 | Conference paper
Part of ISBN: 9783031509926
Part of ISBN: 9783031509933
Part of ISSN: 1865-0929
Part of ISSN: 1865-0937
Contributors: Gour Sundar Mitra Thakur; Subhayu Dutta; Bratajit Das
Source: Self-asserted source
Subhayu Dutta
grade
Preferred source (of 2)‎

Secret learning for lung cancer diagnosis—a study with homomorphic encryption, texture analysis and deep learning

Biomedical Physics & Engineering Express
2024-01-01 | Journal article
Contributors: Subhrangshu Adhikary; Subhayu Dutta; Ashutosh Dhar Dwivedi
Source: check_circle
Crossref
grade
Preferred source (of 2)‎

Enhancing Memory Utilization For On-Device Training of TinyML Models Utilizing Enhanced Grey Wolf Optimization Pushing State-of-the-Art Limits - TinyWolf

SSRN Electronic Journal
2023 | Journal article
Part of ISSN: 1556-5068
Contributors: Subhrangshu Adhikary; Subhayu Dutta
Source: Self-asserted source
Subhayu Dutta

If Human Can Learn from Few Samples, Why Can’t AI? An Attempt On Similar Object Recognition With Few Training Data Using Meta-Learning

2023 IEEE North Karnataka Subsection Flagship International Conference (NKCon)
2023-11-19 | Conference paper
Contributors: Subhayu Dutta; Saptiva Goswami; Sonali Debnath; Subhrangshu Adhikary; Anandaprova Majumder
Source: Self-asserted source
Subhayu Dutta
grade
Preferred source (of 2)‎

Price Prediction of Digital Currencies using Machine Learning

2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA)
2023-11-06 | Conference paper
Contributors: Ashutosh Dhar Dwivedi; Subhayu Dutta; Subhrangshu Adhikary; Jens Myrup Pedersen
Source: Self-asserted source
Subhayu Dutta
grade
Preferred source (of 2)‎

Evolutionary Swarming Particles To Speedup Neural Network Parametric Weights Updates

2023 9th International Conference on Smart Computing and Communications (ICSCC)
2023-08-17 | Conference poster
Contributors: Subhayu Dutta; Subhrangshu Adhikary
Source: Self-asserted source
Subhayu Dutta
grade
Preferred source (of 2)‎

Peer review (1 review for 1 publication/grant)

Review activity for Information sciences. (1)