Imran Chowdhury Dipto
Doctoral Candidate 6
Politecnico di Torino
Short Bio: Imran received a Bachelor’s Degree in Information Technology from the University of Derby, where his thesis focused on comparing Machine Learning models for predicting Coronary Artery Disease. He later moved to Manchester, UK, to pursue a Master’s in Data Science with an optional placement year. His master’s thesis proposed an image dataset and a proof-of-concept Deep Learning model for predicting Diabetic Foot Ulcers. His research interests include Machine Learning, Computer Vision, and Deep Learning, with a focus on real-world applications.
Research Topic: AI-based power saving and distributed sensing/failure prevention from optical telemetry
Project Summary: Implement Large Language models for the design and deployment of Network Resources and Quality of Transmission Estimation. Investigation of various prompting techniques and evaluation of different ML-based models for such tasks. Deployment of such ML-based software applications for the Optical Network-as-a-Service for the Next Generation Metro Access Convergence.
| Host Institution: | Politecnico di Torino (POLITO) Physical Layer Aware NETworking (PLANET) https://planet.polito.it/home/ |
| Supervisors: | Prof Vittorio Curri |
| Secondments planned: | Nokia Germany (Munich) Nokia Portugal (Lisbon) |
| PhD Enrolment Institution: | Politecnico di Torino (POLITO) |
| Industrial Mentor: | Dr Antonio Napoli, Dr Joao Pedro |
- Dipto, I. C. (2025, June 16). Network Data Based Transfer Learning Failure Prediction Agent Pre-Trained Using Digital Twin. ONDM 2025, https://doi.org/10.23919/ONDM65745.2025.11029222, Zenodo OA: https://zenodo.org/records/17273029
- G. Malik, I.Dipto, et al., "Intelligent Detection of Overlapping Fiber Anomalies in Optical Networks Using Machine Learning," 2025 IEEE Photonics Society Summer Topicals Meeting Series (SUM), Berlin, Germany, 2025, pp. 1-2, doi: 10.1109/SUM65312.2025.11121809. Zenodo OA: https://zenodo.org/records/17272991
- G. Malik, I.Dipto et al., "Demonstration of Real-Time AI-Enabled Smart Fault Detection using State-of-Polarization Monitoring," 2025 25th Anniversary International Conference on Transparent Optical Networks (ICTON), Barcelona, Spain, 2025, pp. 1-4, doi: 10.1109/ICTON67126.2025.11125473. Zenodo OA: https://zenodo.org/records/17272965
- Dipto, I. C. (2025). SOP-Based Anomaly Detection Leveraging Machine Learning for Proactive Optical Restoration. Zenodo. https://doi.org/10.5281/zenodo.17272922
- Dipto, I. C. (2025). AI-based power saving and distributed sensing/failure prevention from Optical Telemetry. Zenodo. https://doi.org/10.5281/zenodo.17252550
- Malik, G.; Dipto, I.C.; Masood, M.U.; Cheruvakkadu Mohamed, M.; Straullu, S.; Bhyri, S.K.; Galimberti, G.M.; Napoli, A.; Pedro, J.; Wakim, W.; Curri, V. Resilient Anomaly Detection in Fiber-Optic Networks: A Machine Learning Framework for Multi-Threat Identification Using State-of-Polarization Monitoring. AI 2025, 6(7), 131. https://doi.org/10.3390/ai6070131
Imran's secondment programme includes two visits, each lasting 5 months, to the Nokia Germany (Munich) and Nokia Portugal (Lisbon) teams in 2026. Further details on the objectives, progress, and outcomes of the secondments will be made available in due course.