ASMS_CSC Archives

MS Student

ASMS_CSC@LISTSERV.GSU.EDU

Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Tammie Dudley <[log in to unmask]>
Reply To:
MS Student <[log in to unmask]>
Date:
Wed, 16 Mar 2011 15:31:52 -0400
Content-Type:
text/plain
Parts/Attachments:
text/plain (23 lines)
Departmental Colloquium
> Cognitive and Secure Tele-Healthcare Networking and Signal Processing
>
> Start: 03/17/2011 2:00 pm
> End: 03/17/2011 3:00 pm
> Department Conference Room
>
> Dr. Fei Hu
> Associate Professor
> Department of Electrical and Computer Engineering
> University of Alabama
>
> This talk focuses on how to establish an intelligent, secure tele-healthcare system called c-THIRA (Cognitive Tele-Healthcare with Distilled Sampling, Reasoning and Actuation) that can handle high-dimensional medical signals and complex disease states in large-scale medical decision sub-spaces. Especially we propose a new concept called distilled computing (DC), which has a strategy analogous to water distillation, which uses a refined procedure to improve water purification. First, just like the water "heat-up" process that performs water molecule decomposition, we perform signal projection to map medical signals to discrete basis functions. Then, in the “cool-down” step we obtain purified reminiscent – refined disease symptoms extracted from signal projection space. Eventually we can convert complex medical data to low-dimensional, symptom-reserved signals or medical decision states.
>
> c-THIRA aims to solve three challenging issues (listed below) that are centered on the concept of Symptom-of-Interest (SoI). Here SoI is defined as an interpretable medical signal wave with an easily-recognized disease anomaly pattern.
>
>     * (Distilled Sampling) Multi-condition Patient Monitoring via SoI-based, Compressive Bayesian Sampling: Conventional medical sensing schemes consume significant sensor energy due to the use of Nyquist sampling rate. They also cannot adapt to flexible disease diagnosis requirements due to their ignorance of real-time medical context information such as new coming symptoms.
>     * (Distilled Reasoning) Disease Pattern Capture from Complex Medical Signals via Manifold Learning: Conventional pattern recognition schemes cannot efficiently extract SoIs from high-dimensional medical signals because they ignore disease prior knowledge. We thus propose to extract SoIs from complex medical signals through a new approach called distilled reasoning.
>     * (Distilled Actuation) Intelligent Medical Treatment Models via Compressed Decision Subspace Finding: The final purpose of SoI reasoning is to achieve an accurate patient treatment, i.e., using a Decision-Making Model (DMM) to control medical treatment devices such as an insulin pump, pacemaker, etc. Traditional DMMs have difficulties handling partially observable sensor inputs and uncertainties among (patient) states/(treatment) actions.
>
> About the Speaker: Dr. Fei Hu is currently an associate professor in the Department of Electrical and Computer Engineering at the University of Alabama, Tuscaloosa, AL, USA. His research interests are wireless networks, wireless security, and their applications in bio-medicine. His research has been supported by NSF, Cisco, Sprint, and other sources. He obtained his first Ph.D. degree at Shanghai Tongji University, China, in Signal Processing (in 1999), and second Ph.D. degree at Clarkson University (New York State) in the field of Electrical and Computer Engineering (in 2002).
> --------------------------------

ATOM RSS1 RSS2