Wednesday, 7 July 2010

Wseas Transactions

New Subscription to Wseas Transactions

The following information was submitted:

Transactions: WSEAS TRANSACTIONS ON CIRCUITS AND SYSTEMS
Transactions ID Number: 52-232
Full Name: Wan Fazlida Hanim Abdullah
Position: Ph.D. Candidate
Age: ON
Sex: Female
Address: No 14 Jalan Jasper 7/15, Seksyen 7, Shah Alam, Selangor
Country: MALAYSIA
Tel: +6019-2217347
Tel prefix:
Fax:
E-mail address: wanfaz@pc.jaring.my
Other E-mails:
Title of the Paper: Improving Ion-Sensitive Field-Effect Transistor Selectivity with Backpropagation Neural Network
Authors as they appear in the Paper: Wan Fazlida Hanim Abdullah, Masuri Othman, Mohd Alaudin Mohd Ali, Md Shabiul Islam
Email addresses of all the authors: wanfaz@pc.jaring.my, masuri.othman@mimos.my, mama@eng.ukm.my, mdshabiul@ukm.my
Number of paper pages: 10
Abstract: The ion-sensitive field-effect transistor (ISFET) is an electrochemical sensor based on the metal-oxide field-effect transistor structure. When immersed in ionic solution with mixed ions of similar chemical characteristics, ISFETs respond with deceptive voltage signals due to the interfering ion contribution over the main ion of interest. The objective of this work is to improve the selectivity of ion concentration estimation by applying neural network backpropagation as post-processing stage. In this paper, data was acquired from a readout-interface circuit biased with ISFET array immersed in titration solution of potassium and ammonium ion. Primary data from measured observations that included device fabrication variation and background ion was fed to a feedforward multilayer perceptron trained with back-propagation algorithm. Comparison of output-target regression factor and mean-square error were done using variations of backpropagation algorithm and multiple c!
lassifier system consisting of backpropagation trained networks achieved by bagging. Results show that neural network is able to improve concentration estimation by 15% improvement with 4 sensor array compared to direct estimation without post-processing. Additionally, averaging from multiple classifiers is shown to give a further 5% improvement on the output-target regression factor with consistently stable ion concentration estimations.
Keywords: Microsensors; Electrochemical devices; MOSFET; Sensor array; Supervised learning, Selectivity
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: Adlina Abdullah, adlin@salam.uitm.edu.my
IP ADDRESS: 110.159.139.117