Computer Science Seminar, Wed, Jan 31, 11:30-12:30



3D? -

Virtual Reality? -

Artificial Intelligence/Machine Learning? -

PIZZA? -


Are you interested in cool😎 medical applications of computer engineering and computer science? Then this is a talk not to be missed. 


Computer Science Department Seminar

Wednesday, January 31, 2018

Adams Hall 208

11:30-12:30 pm

Pizza will be served

All Students and Faculty are invited to attend

 

 

 

Title: Digital/Biomedical Embedded Software

and Hardware Co-Designs

Miad Faezipour, Ph.D., Associate Professor

Department of Computer Science and Engineering

Department of Biomedical Engineering

University of Bridgeport, Connecticut

 

Abstract: Recent trends in clinical and telemedicine applications highly demand automation in signal processing and bio-signal classification. This talk addresses various biomedical applications and briefly discusses the signal/image processing, machine learning, embedded software/hardware co-designs and techniques used for classification. The first application is based on repetition-detection cardiac behavior profiling to classify/identify irregular heart beats from normal ones. Second, bed posture classification is discussed for pressure ulcer prevention. The patient's posture is identified/classified through a whole-body pressure distribution map using principle component analysis of pressure images, and an efficient turning schedule is proposed for bed-bound patients. Then, a few on-going D-BEST (digital/biomedical embedded systems & technology) lab research efforts on embedded hardware/software co-designs for biomedical applications are also discussed. A study on the use of virtual reality to assist patients with breathing disorders is introduced. This work makes use of 3-D computer animations and human-computer interactions from respiratory sounds aiding patients to regulate their breath in a virtual environment. Human-computer interactions are classified for highest performance. The above approaches achieved classification accuracies greater than 97%, making them highly efficient for deployment in conjunction with traditional medical training, diagnosis and treatment.

 

Biography: Miad Faezipour is currently an Associate Professor in the computer science & engineering and biomedical engineering departments at the University of Bridgeport (UB) and the director of the digital/biomedical embedded systems & technology (D-BEST) Lab. She joined UB as an assistant professor in July 2011. Prior to joining UB, she has been a post-doctoral research associate at the University of Texas at Dallas collaborating with the Center for Integrated Circuits and Systems and the Quality of Life Technology laboratories. She received the B.Sc. in electrical engineering from the University of Tehran, Tehran, Iran and the M.Sc. and Ph.D. in electrical engineering from the University of Texas at Dallas in 2010. Her research interests lie in the broad area of biomedical signal processing, machine learning and classification, assistive technology and human-machine-interfaces, high-speed packet processing architectures, and digital/biomedical embedded systems. Dr. Faezipour is a member of IEEE, EMBS, and IEEE Women in Engineering.