My research focuses broadly on developing algorithms for efficient and scalable machine learning systems. I am particularly interested in hardware-friendly deep learning algorithms and its applications in biometrics, vision, language, and speech using the edge computing paradigm. I am passionate about applying my research to accelerate progress in science and engineering. My research is supported by CITeR, Verizon and Badger Technologies. Before joining UW-Green Bay as a tenure-track assistant professor, I was a research assistant at Clarkson University, where I earned my Ph.D. in the ECE department. Additionally, I had the privilege of working on several exciting industrial projects throughout my career. Notably, I spent nearly five years at Samsung R&D, where I had the opportunity to work on IoT, SHealth and Tizen project.

Year: 2024

• 'Journal Paper Accepted!!' Our paper, "Deep Age-Invariant Fingerprint Segmentation System" has been accepted for publication in IEEE Transactions on Biometrics, Behavior, and Identity Science (T-BIOM), October 2024.
• 'Big News!' Received a research grant as the lead Principal Investigator (PI) from WiSys.
• Webinar: Presented my research on contactless fingerprint segmentation in a webinar hosted by CITeR.
• Developed a contactless fingerprint segmentation system and shared it with the Canadian government.

Year: 2023

• 'Conference paper accepted!!' Our paper, titled " The Utility of Feature Reuse: Transfer Learning in Data-Starved Regimes" has been accepted for publication at the IEEE International Conference on Computational Science and Computational Intelligence 2023.
• Webinar: Presented my research on fingerprint segmentation in a webinar hosted by CITeR.
• Collaborated with the Department of homeland security to share, deploy and improve the slap fingerprint segmentation system.
• Started a new position as an Assistant Professor (tenure-track) of Computer Science at the University of Wisconsin - Green Bay.
• Complete my P.hD. Dissertation title: ''Efficient and Resource-Aware Deep Learning for Improved Object Detection''.
• Collaborated with the UK government's biometric security department to share a fingerprint segmentation system.
• Presented the final report for the 'Robust Contactless Fingerprint Processing Tool' project at the CITeR conference in Martigny, Switzerland, showcasing our innovative solution for contactless fingerprint processing.
• Attended EAB and CITeR Biometrics Workshop, hosted by the Idiap Research Institute in Martigny, Switzerland, the European Association for Biometrics (EAB) and the Center for Identification Technology Research (CITeR) on the topics of Bias Mitigation, Template Security, Presentation Attack Detection and Deepfakes.
• Showcased our project on the 'Detection of Over-Rotated Biometric Images and Incorrect Labeling of Fingerprints.' at the EAB and CITeR Biometrics Workshop.
• Showcased progress report for the 'Explainable Face and Fingerprint Matching via Improved Localization' project at CITeR Biometrics Workshop in Martigny, Switzerland.

Year: 2022

• 'Book Chapter accepted!' Our (M. G. Sarwar Murshed, James J. Carroll, Nazar Khan, Faraz Hussain) chapter entitled " Efficient Deployment of Deep Learning Models on Autonomous Robots in the ROS Environment" has been accepted and published at Deep Learning Applications, Volume 3, Pages 215-243, Springer Singapore.
• Awarded a research grant from CITeR for our new project, 'Explainable Face and Fingerprint Matching via Improved Localization,' which aims to improve the accuracy and transparency of biometric identification systems.
• Awarded a research grant from CITeR for our new project, 'Robust Contactless Fingerprint Processing Tool,' which aims to improve the accuracy and performance of contactless biometric identification systems.
• Presented our novel age-invariant contact-based fingerprint segmentation system for the 'Detection of Over-Rotated Biometric Images and Incorrect Labeling of Fingerprints' project at the CITeR conference at MSU, Michigan, sharing our final report and engaging with industry experts to gather valuable feedback on our innovative solution for biometric identification.
• Showcased progress report for the 'Robust Contactless Fingerprint Processing Tool' project at the CITeR conference - MSU, Michigan.
• Presented our novel age-invariant contact-based fingerprint segmentation system for the 'Detection of Over-Rotated Biometric Images and Incorrect Labeling of Fingerprints' project at the CITeR conference at the University at Buffalo, Buffalo. sharing our final report and engaging with industry experts to gather valuable feedback on our innovative solution for biometric identification.

Year: 2021

• I attended and presented our conference paper at IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), 2021. Check out the paper [Paper_Link]
• 'Conference paper accepted!!' Our (MG Sarwar Murshed, Robert Kline, Keivan Bahmani, Faraz Hussain, Stephanie Schuckers) paper entitled " Deep Slap Fingerprint Segmentation for Juveniles and Adults" has been accepted at IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), 2021.
• 'Big News!!' 'Journal paper accepted at ACM Computing Survey ((Impact Factor = 14.324. Ranked #10 in Engineering & Computer Science (general) by Google Scholar) in 2021)!!' Our (MG Sarwar Murshed, Christopher Murphy, Daqing Hou, Nazar Khan, Ganesh Ananthanarayanan, Faraz Hussain) paper entitled "Machine learning at the network edge: A survey" has been accepted at ACM Computing Surveys (CSUR), 2021.
• 'Book Chapter accepted!' Our (Edward Verenich, MG Sarwar Murshed, Nazar Khan, Alvaro Velasquez, Faraz Hussain) chapter entitled " Mitigating the Class Overlap Problem in Discriminative Localization: COVID-19 and Pneumonia Case Study" has been accepted and published at Explainable AI Within the Digital Transformation and Cyber Physical Systems: XAI Methods and Applications, Pages 125-151, Springer International Publishing.
• Awarded a research grant (extension of the previous work) from Verizon Wireless for our new project, 'Fingerprint Template Security,' which aims to enable Cloud-Based Biometric Solutions through High Performance, Secure Matching.
• Awarded a research grant from CITeR for our new project, 'Robust Contactless Fingerprint Processing Tool,' which aims to improve the accuracy and performance of contactless biometric identification systems.
• Presented our novel age-invariant contact-based fingerprint segmentation system for the 'Fingerprint Segmentation for Juveniles and Adults' project at the CITeR conference. sharing our final report and engaging with industry experts to gather valuable feedback on our innovative solution for biometric identification.
• Showcased progress report for the 'Detection of Over-Rotated Biometric Images and Incorrect Labeling of Fingerprints' project at the CITeR conference - MSU, Michigan.

Year: 2020

• Completed my M.Sc. in Computer Science.
• Awarded a research grant from Verizon Wireless for our new project, 'Fingerprint Template Security,' which aims to enable Cloud-Based Biometric Solutions through High Performance, Secure Matching.
• Presented our paper at 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA).
• Awarded a research grant from Badger Technologies, which aims to develop the framework to deploy deep learning on ROS OS.
• Presented our paper at HotEdge Conference.
• 'Conference paper accepted!!' Our (MG Sarwar Murshed, James J Carroll, Nazar Khan, Faraz Hussain) paper entitled " Resource-aware on-device deep learning for supermarket hazard detection" has been accepted at 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA).
• Presented our paper at at 2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI).
• 'Conference poster accepted!!' Our (Edward Verenich, Alvaro Velasquez, MG Sarwar Murshed, Faraz Hussain) paper entitled " FlexServe: Deployment of PyTorch Models as Flexible REST Endpoints." has been accepted at USENIX, OpML, 2020.
• 'Conference paper accepted!!' Our (Baogang Zhang, MG Sarwar Murshed, Faraz Hussain, Rickard Ewetz) paper entitled " Fast Resilient-Aware Data Layout Organization for Resistive Computing Systems." has been accepted at 2020 IEEE Computer Society Annual Symposium on VLSI (ISVLSI), 2020.
• 'Conference poster accepted!!' Our (MG Sarwar Murshed, Edward Verenich, Conrad Gende, James J Carroll, Nazar Khan, Faraz Hussain) paper entitled " Hazard Detection in Supermarkets using Deep Learning on the Edge." has been accepted at USENIX, HotEdge, 2020.