Emon Dey

Ph.D. Candidate at University of Maryland, Baltimore County (UMBC)
1000 Hilltop Circle, Baltimore, MD21250

edey1 [at] umbc [dot] edu
Google Scholar GitHub Resume LinkedIn

About

I am a Ph.D. Candidate at the Department of Information Systems at the University of Maryland, Baltimore County (UMBC). I am working as a Research Assistant at the Center for Real-time Distributed Sensing and Autonomy (CARDS). I am also affiliated with Mobile, Pervasive, and Sensor Computing (MPSC) Lab and advised by Dr. Nirmalya Roy. My research interests mainly focus on the area of Artifical Intelligence and Robotics, particularly on developing deep model compression algorithm, robust communication protocol for Federated Learning, and build packages on Robot Operating Systems (ROS).

I received my M.S. degree in Information Systems from UMBC in 2022. Before that, I received my Bachelor's degree in Electrical and Electronic Engineering from Chittagong University of Engineering & Technology. My thesis Supervisor was Sharmin Majumder and I have worked on developing a novel Image Watermarking algorithm.

News

2023/08: Demonstrated remote robotics experimentation on Class Incremental Federated Learning at Graces Quarters under ArtiAMAS project. Check out the details here.
2023/04: Paper accepted at IEEE MASS'23 on addressing asymmetry in Collaborative Autonomous Systems.
2023/04: Paper accepted at ICCCN'23 on developing a novel ROS2 QoS policy.
2023/04: Paper accepted at Smartcomp'23 on domain adaptibility of a mmWave radar.
2023/03: Paper accepted at FedVision'23, in conjunction with CVPR'2023.
2023/02: Our research got featured on CBS News, Baltimore.
2023/02: Presented my work and sucessfully demonstrated the Remote Robotics Experimentation at ArtIAMAS Winter Meeting.
2022/12: I have successfully defended my Ph.D. proposal.
2022/08: Successfully demonstrated a search and rescue based remote experimentation using ARL Distributed Virtual Probing Ground (DVPG).
2022/06: “RhythmEdge” won best paper award at SMARTCOMP 2022. Happy to be a part of this work.
2022/06: Paper on Multi-modal Federated Learning won best paper award at SPIE 2022. A contented collaborator, indeed.
2022/05: “SynchroSim” accepted at IEEE DCOSS 2022.
2022/04: Received audience choice award at the Work-in-progress track of IS Research Symposium.

Current Research

I am currently working on developing a viable algorithm to make the data communication protocol robust for a Federated Learning (FL) scenario under contested environment. To be specific, I am interested in reducing the packet loss due to the higher velocity difference among agents participated in building the FL model.

Education

Doctor of Philosophy (Ph.D.) in Information Systems, UMBC, August 2019 - May 2024 (expected)
Master of Science (M.S.) in Information Systems, UMBC, August 2019 - May 2022
Bachelor of Science (B.Sc.) in Electrical and Electronic Engineering, Chittagong University of Engineering and Technology, July 2013 - October 2017

Publications

Under Review

Empirically Driven Adaptive Transmission for Enhanced Communication in Adversarial Environment
Emon Dey, Anuradha Ravi, Vinay Krishna Kumar, Jared Lewis, Nirmalya Roy
MobHeteroCAS : Mobility-Aware DNN Task Scheduling in Heterogeneous Collaborative Autonomous System
Mohammad Saeid Anwar, Anuradha Ravi, Emon Dey, Indrajeet Ghosh, Masud Ahmed, Nirmalya Roy

Under Preparation

Adaptive Quantization Technique to Tackle Class Imbalance in Compression-aware Federated Learning
Emon Dey, Anuradha Ravi, Gaurav Shinde, Garvit Chugh, Vinay Krishna Kumar, Serena Lin, Nirmalya Roy
FedRhythmEdge: Federated Learning based Contactless Heart Rate Estimation on the Edge
Emon Dey, Zahid Hasan, Sukriti Roy, Nirmalya Roy

Published Works

HeteroEdge: Addressing Asymmetry in Heterogeneous Collaborative Autonomous Systems [Paper]
Mohammad Saeid Anwar, Emon Dey, Maloy Kumar Devnath, Indrajeet Ghosh, Naima Khan, Jade Freeman,
Timothy Gregory, Niranjan Suri, Kasthuri Jayarajah, Sreenivasan Ramasamy Ramamurthy, Nirmalya Roy
The 20^th IEEE International Conference on Mobile Ad-Hoc and Smart Systems (MASS 2023).
A Novel ROS2 QoS Policy-enabled Synchronizing Middleware for Co-simulation of Heterogeneous Multi-Robot Systems [Paper]
Emon Dey, Mikolaj Walczak, Mohammad Saeid Anwar, Nirmalya Roy,
Jade Freeman, Timothy Gregory, Niranjan Suri, Carl Busart
The 32^nd International Conference on Computer Communications and Networks (ICCCN 2023).
A Systematic Study on Object Recognition Using Millimeter-wave Radar [Paper]
Maloy Kumar Devnath, Avijoy Chakma, Mohammad Saeid Anwar,
Emon Dey, Zahid Hasan, Marc Conn, Biplab Pal, Nirmalya Roy
9^th International Conference on Smart Computing (SMARTCOMP)'2023.
Mixed Quantization Enabled Federated Learning to Tackle Gradient Inversion Attacks [Paper]
Pretom Roy Ovi, Emon Dey, Nirmalya Roy, and Aryya Gangopadhyay
2^nd Workshop on Federated Learning for Computer Vision, in conjunction with CVPR'2023.
OMAD: On-device Mental Anomaly Detection for Substance and Non-Substance Users [Paper]
Emon Dey and Nirmalya Roy
2020 IEEE 20^th International Conference on Bioinformatics and Bioengineering (BIBE).
A new approach to color image watermarking based on joint DWT-SVD domain in YIQ color space [Paper] [Code]
Emon Dey, Sharmin Majumder, and Arnab Neelim Mazumder
2017 3^rd International Conference on Electrical Information and Communication Technology (EICT).
SynchroSim: An Integrated Co-simulation Middleware for Heterogeneous Multi-robot System [Paper]
Emon Dey, Jumman Hossain, Nirmalya Roy, and Carl Busart
2022 18^th International Conference on Distributed Computing in Sensor Systems (DCOSS).
ARIS: A Real Time Edge Computed Accident Risk Inference System [Paper] [Code]
Pretom Roy Ovi*, Emon Dey*, Nirmalya Roy, and Aryya Gangopadhyay (* Equal Contribution)
2021 IEEE International Conference on Smart Computing (SMARTCOMP).
A Color Image Watermarking Scheme Employing the Features of Directive Contrast in the DWT-SVD Domain [Paper] [Code]
Arnab Neelim Mazumder, Emon Dey, and Sharmin Majumder
2019 IEEE 5^th International Conference for Convergence in Technology (I2CT).
RhythmEdge: Enabling Contactless Heart Rate Estimation on the Edge [Paper]
Zahid Hasan, Emon Dey, Sreenivasan Ramasamy Ramamurthy, Nirmalya Roy, and Archan Misra
2022 IEEE International Conference on Smart Computing (SMARTCOMP).
Towards developing a data security aware federated training framework in multi-modal contested environments [Paper] [Code]
Pretom Roy Ovi, Emon Dey, Nirmalya Roy, Aryya Gangopadhyay, and Robert F. Erbacher
Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications IV.
Demo: RhythmEdge: Enabling Contactless Heart Rate Estimation on the Edge [Paper] [Code]
Zahid Hasan, Emon Dey, Sreenivasan Ramasamy Ramamurthy, Nirmalya Roy, and Archan Misra
2022 IEEE International Conference on Smart Computing (SMARTCOMP).

Skills

Programming Languages: C, MATLAB, Python, R
Simulation Software: Gazebo, Unity, NS-3, WinterSim, WEKA, Tableau, AutoCAD, Candence
Deep Learning Framework: Keras, Pytorch, TensorFlow
Specialized Tools: TFF, PySyft, TF-Lite, ONNX, Q-Keras, Robot Operating Systems (ROS)
Hardware Proficiency: Raspberry Pi, Jetson Nano, Google Coral Dev Board, Intel NCS2, Arduino
Others: Shell Scripting, Git, Ubuntu, Docker, Raspbian, MikroC

Research Experience

Graduate Research Assistant, Center for Real-time Distributed Sensing and Autonomy (CARDS), UMBC, August 2021 - Present
Graduate Research Assistant, Mobile Pervasive and Sensor Computing (MPSC) Lab, UMBC, August 2019 - July 2020

Teaching Experience

Lecturer, Port City International University, September 2018 - July 2019
- EEE 463: High Voltage Engineering
- EEE 316: Machine Design
- EEE 320: Electrical Services Design
- EEE 465: Power System II
- BUS 217: Professional Ethics
- EEE 325: Digital Signal Processing I
Teaching Assistant, UMBC, August 2020 - May 2021
- IS425 : Decision Support Systems (Fall 2020)
- IS320 : Advanced Business Applications (Spring 2021)
Student Mentor, NSF-REU in Smart Computing and Communications, UMBC
- Project 1: Addressing Statistical Heterogeneity in Federated Learning For Sea Ship Datasets (Summer 2023)
- Project 2: Synchronizing Middleware for a Heterogeneous Multi-Robot System with Low Latency Co-Simulation (Summer 2022)
- Project 3: A Federated Learning Approach for Camera-based Contact-less Heart Rate Monitoring (Summer 2022)
- Project 4: A Resource Efficient Quantized Federated Learning Model for Brain Tumor Segmentation (Summer 2021)

Awards

Best paper awards at IEEE SMARTCOMP'22 and SPIE'22 conferences.
Audience choice award at UMBC IS Research Symposium.
Achieved student travel grant for IEEE ICCCN'23, SPIE'22, DCOSS'22, and IEEE BIBE'20 conferences ($7125).

Media Coverage

Research on Remote Robotics Experimentation using ARL facility named DVPG got featured on CBS News, Baltimore. Check out the news here.

Professional Activities

Registered Peer Reviewer
- Pervasive and Mobile Computing (PMC) journal
- ACM International Conference On Distributed Computing And Networking (ICDCN)
- IEEE Intelligent Environments (IE)
- International Conference on Big Data Computing, Applications and Technologies (BDCAT)
- Also reviewed papers from IEEE SMARTCOMP 2021, 2022, IEEE Chase 2021, 2022, IEEE PerCom, TIST Journal, REU Symposium, and WristSense workshop.
Student member of the Society of Photo-Optical Instrumentation Engineers (SPIE).
Presented my papers at multiple venues i.e., IEEE BIBE'20, IEEE SMARTCOMP'22, SPIE'22, IEEE ICCCN'23.