東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Design and development of an adaptiv...

University of Medicine and Dentistry of New Jersey.

FindBook

Google Book

Amazon

博客來

Design and development of an adaptive neuro-fuzzy based early detection system.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Design and development of an adaptive neuro-fuzzy based early detection system./
作者:	Majagah, Koushby.
面頁冊數:	132 p.
附註:	Adviser: Syed Haque.
Contained By:	Dissertation Abstracts International69-07B.
標題:	Biology, Bioinformatics. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3323029
ISBN:	9780549746904

Design and development of an adaptive neuro-fuzzy based early detection system.
Majagah, Koushby.

Design and development of an adaptive neuro-fuzzy based early detection system. - 132 p.

Adviser: Syed Haque.

Thesis (Ph.D.)--University of Medicine and Dentistry of New Jersey, 2008.

Emergency Medical Services (EMS) are the first healthcare providers on the scene in any medical emergency or disaster situation. Providing this front line defense with tools and applications to alert key medical personal and medical and health organizations of the potential damage in a timely manor is extremely important. The process of developing a scalable and flexible Integrated Disaster Response Information Surveillance (IDRIS) system consists of two complimentary models: the architectural model and the computational model. The architectural model is required for recording, displaying, and storing victim's information at the disaster sites and linking this information with any outside systems while maintaining security policy and compliance with HL7 and HIPAA standards. Many EMS works still use paper and pen solutions for recording information occurring in a medical emergency. To identify early outbreaks these paper based systems need to be converted in to an electronic form so that various algorithms can be applied on this data. Rather than converting this data the approached described in this paper is to change the gathering of this data by training the EMS workers into using electronic devices that mimic their paper based solutions. To reduce the learning curve of using a new system, the paper based forms are converted to electronic based forms. Before applying the computational model, the infrastructure for handling this information is crucial. The computational model can detection anomalies as they occur in the real world and in real time using neural networks and fuzzy logic algorithms combined. The combination of these two key algorithms provides the ability to find patterns in the data gathered and can categorizes these outcomes into new or existing syndromes for addressing syndromic surveillance. Providing the infrastructure for gathering data to key personal and then building various components that can analyze this data in real-time offers the medical and health community features that can adapt to suit different conditions has the potential to be a key component for syndromic surveillance and disaster management strategies.

ISBN: 9780549746904Subjects--Topical Terms:

1018415
Biology, Bioinformatics.

Design and development of an adaptive neuro-fuzzy based early detection system.
LDR:03078nmm 2200277 a 45 001 867112
005 20100802
008 100802s2008 ||||||||||||||||| ||eng d
020 $a 9780549746904
035 $a (UMI)AAI3323029
035 $a AAI3323029
040 $a UMI $c UMI
100 1 $a Majagah, Koushby. $3 1035817
245 1 0 $a Design and development of an adaptive neuro-fuzzy based early detection system.
300 $a 132 p.
500 $a Adviser: Syed Haque.
500 $a Source: Dissertation Abstracts International, Volume: 69-07, Section: B, page: 4265.
502 $a Thesis (Ph.D.)--University of Medicine and Dentistry of New Jersey, 2008.
520 $a Emergency Medical Services (EMS) are the first healthcare providers on the scene in any medical emergency or disaster situation. Providing this front line defense with tools and applications to alert key medical personal and medical and health organizations of the potential damage in a timely manor is extremely important. The process of developing a scalable and flexible Integrated Disaster Response Information Surveillance (IDRIS) system consists of two complimentary models: the architectural model and the computational model. The architectural model is required for recording, displaying, and storing victim's information at the disaster sites and linking this information with any outside systems while maintaining security policy and compliance with HL7 and HIPAA standards. Many EMS works still use paper and pen solutions for recording information occurring in a medical emergency. To identify early outbreaks these paper based systems need to be converted in to an electronic form so that various algorithms can be applied on this data. Rather than converting this data the approached described in this paper is to change the gathering of this data by training the EMS workers into using electronic devices that mimic their paper based solutions. To reduce the learning curve of using a new system, the paper based forms are converted to electronic based forms. Before applying the computational model, the infrastructure for handling this information is crucial. The computational model can detection anomalies as they occur in the real world and in real time using neural networks and fuzzy logic algorithms combined. The combination of these two key algorithms provides the ability to find patterns in the data gathered and can categorizes these outcomes into new or existing syndromes for addressing syndromic surveillance. Providing the infrastructure for gathering data to key personal and then building various components that can analyze this data in real-time offers the medical and health community features that can adapt to suit different conditions has the potential to be a key component for syndromic surveillance and disaster management strategies.
590 $a School code: 0301.
650 4 $a Biology, Bioinformatics. $3 1018415
650 4 $a Computer Science. $3 626642
690 $a 0715
690 $a 0984
710 2 $a University of Medicine and Dentistry of New Jersey. $3 1026090
773 0 $t Dissertation Abstracts International $g 69-07B.
790 $a 0301
790 1 0 $a Haque, Syed, $e advisor
791 $a Ph.D.
792 $a 2008
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=3323029