Speaker: Dr.Celia Shahnaz, Professor, EEE, BUET

Title of the Talk: Deep Learning , Generative AI and Federated Learning for Advanced Multimedia, Human Computer Interface and Biomedical Applications

Date: 28 April 2025

Time: 3 PM

Venue: Room number 634, ECE building, West Palashi, BUET, Dhaka-1000 The dept. of EEE, BUET is conducting regular research seminar for fostering knowledge sharing environment and encouraging collaborative research effort. This will be a platform for EEE, BUET faculty member, members of academia from home and abroad as well as experts in the field of electrical engineering to share their experience in research and innovation.

Abstract of the talk:

This talk explores the intersection of Deep Learning, Generative AI, and Federated Learning in advancing solutions for Multimedia Processing, Human-Computer Interaction (HCI), and Medical Healthcare Applications. The session aims to present a set of intelligent frameworks that address real-world challenges through scalable, privacy-aware, and high-performance learning systems. Beginning with biomedical signal analysis, the talk introduces LAACNN, a hybrid architecture combining convolutional, recurrent, and attention mechanisms for classifying neuromuscular diseases using raw EMG signals. This approach enhances early diagnostic potential through non-invasive, data-driven insights. In the realm of advanced multimedia, speech enhancement is tackled through two novel Generative AI models. CAR-UNet employs ConvNeXT blocks and gated attention to jointly enhance magnitude and phase information, ensuring clarity under extreme noise conditions. N2N2N, a clean-data-independent approach using a modified cGAN, refines noisy speech where clean references are unavailable, making it suitable for realistic deployment. For Human-Computer Interaction, the session features CAPRes50-GAN, a real-time, GAN-based classifier for word-level sign language recognition. It leverages multi-head attention alongside ResNet-based architectures to efficiently interpret gestures and support inclusive communication systems. The discussion continues with BreastDCGAN, an end-to-end framework for breast cancer detection using mammography and ultrasound. It combines generative segmentation and attention-based classification to assist in accurate and early medical analysis. Concluding the talk, pFLOCT is introduced—a Personalized Federated Learning framework for optical imaging that accommodates heterogeneous client data while preserving privacy, advancing collaborative learning in medical domains.

Bio of the speaker: Celia Shahnaz, SMIEEE, Fellow IEB, received Ph.D. degree from Concordia University, Canada and is currently a professor at, Department of EEE, BUET, Bangladesh since 2015. She was the winner of Canadian Common Scholarship for pursuing her Ph.D study in Canada and recipient of Bangladesh Academy of Science Gold Medal for her contributions in science and technology. The World Academy of Science (TWAS) members have elected her as a Fellow of TWAS for the advancement of science in developing countries, effective 1 January 2023. Recently, her nomination has been approved and she has been inducted into IEEE-Eta Kappa Nu as a Professional Member into the Eta Chapter of the Board of Governors. She has been selected as 2025 IEEE Computer society Distinguished Visitor. She has been appointed as 2025-26 Chair, IEEE WIE Nominations and Appoints. She has been elected as 2022 IEEE WIE Committee Chair-Elect and she has served as the 2023-2024 IEEE WIE Committee Chair. She has been appointed as 2024-25, Division V Representative, IEEE TAB Award and Recognition Committee , 2024-25 Member, IEEE Fourier Award for Signal Processing Committee , 2024-25 IEEE Computer society Awards Chair, 2025 Member, IEEE CS Diversity and Inclusion Committee, 2024 Member, IEEE CS Election Committee, 2020, 2022-23 Member, IEEE New Initiative Committee, 2021-24 Member, IEEE History Committee, Liaison between IEEE History Committee and IEEE WIE, 2023 Corresponding member, IEEE BOD Ad-Hoc: Coordinating IEEE’s Response to Multimedia-Based Digital Reality Technologies, 2023 Member, the future of the IEEE WIE ILC Adhoc. She has served as 2021-22 Chair, IEEE SPS Women in Signal Processing, 2021-22 Liaison between IEEE SPS and IEEE WIE, 2021-22 Member, IEEE Educational Activities Board Faculty Resource Committee, 2022 Member, IEEE WIE Strategic planning Committee, 2021 Chair, IEEE WIE History Subcommittee, 2020-21 Member, IEEE WIE Senior Member Elevation Drive and 2019-2022 Member, IEEE WIE WePower Subcommittee. She has served as an Editorial board member, IET Signal Processing From 2018 to date. She is the immediate past Chair, IEEE Bangladesh Section, Co-founder & Chair, IEEE EMBS, IAS, RAS, SSIT Bangladesh Chapters, Co-founder & Vice-Chair, IEEE SPS Bangladesh Chapter, Founder and Advisor, WIE AG, and founder and Chair of SIGHT group FLASH, IEEE Bangladesh Section. She is the recipient of the 2021 IEEE MGA Achievement Award, 2021 Inspiring Women in Academia Award from Bangladesh brand forum, 2019 R10 Humanitarian Activities Outstanding Volunteer Award, 2016 MGA Leadership Award 2015 WIE Inspiring Member Award, 2013 R10 WIE Professional Volunteer Award. She has more than 24 years of experience (24 years as an IEEE volunteer) in leading impactful Technical, Professional, Educational, Industrial, Women Empowerment, Humanitarian Technology, Power and Energy-related Projects at national/international levels.