Title :
E-nose herbs recognition system based on Artificial Neural Network technique
Author :
Kit, Chow Kar ; Soh, Azura Che ; Yusof, Umi Kalsom Mohamad ; Ishak, A.J. ; Hassan, Mohammad Kamrul ; Khamis, Shamsul
Author_Institution :
Dept. of Electr. & Electron. Eng., Univ. Putra Malaysia, Serdang, Malaysia
fDate :
Nov. 29 2013-Dec. 1 2013
Abstract :
Electronic sensing technology intervention was intended to overcome human´s physical limitation. It has developed and greatly advanced over the decade. This project emphasizes on characterizing herbs species based on unique of herbs odor. E-nose system in this project consist an array of commercial gas sensor which detects gas through an increase in electrical conductivity when reducing gases are absorbed on the sensor´s surface. Data obtained from sensors array are classified using Artificial Neural Network (ANN) technique. The E-nose system with five sensors has the highest capability in classifying herbs sample. Accuracy in classifying the correct herbs increases with number of the sensors used. Results show that sensitivity of E-nose towards herbs classification increases with higher number of sensors.
Keywords :
agrochemicals; chemical products; computerised instrumentation; electrical conductivity; electronic noses; neural nets; pattern classification; sensor arrays; E-nose herbs recognition system; artificial neural network technique; data classification; electrical conductivity; electronic sensing technology; gas detection; gas sensor array; herbs odor detection; herbs sample classification; herbs species characterisation; human physical limitation; Artificial neural networks; Chemical sensors; Sensor arrays; Sensor systems; Training; array of sensor; artificial neural network; classification; electronic nose;
Conference_Titel :
Control System, Computing and Engineering (ICCSCE), 2013 IEEE International Conference on
Conference_Location :
Mindeb
Print_ISBN :
978-1-4799-1506-4
DOI :
10.1109/ICCSCE.2013.6719932