Development Of Neural Network-Based Electronic Nose For Herbs Recognition

The ability to classify distinctive odor pattern for aromatic plants species provides significant impact in food industry especially for herbs. Each herbs species has a unique physicochemical and a distinctive odors. This project emphasizes on the techniques of artificial intelligence (AI) to distinguish distinctive odor pattern for herbs. Neural Network method has been exploited for the classification and optimization of various odor patterns. Based on AI techniques, Neural Network-based electronic nose system for herbs recognition has been developed. The system consist multi-sensor gas array which detects gas through an increase in electrical conductivity when reducing gases are absorbed on the sensor's surface. The output from individual sensors are collectively assembled and integrated to produce a distinct digital response pattern. A selected sensor array shows its relationship with the aroma of the herbs through the GC-MS test. By using five samples of herbs, the E-nose system has been tested with five different types of sensor. From the results, E-nose system with five sensors has the highest capability in classifying herbs sample. Accuracy in classifying the correct herbs increases with the number of sensors used. This investigation demonstrates that the neural network-based electronic nose technique promises a successful technique in the ability to classify distinctive odor pattern for aromatic herbs species.

[1]  Yixin Chen,et al.  Image Feature Selection Based on Ant Colony Optimization , 2011, Australasian Conference on Artificial Intelligence.

[2]  Pedro Larrañaga,et al.  A review of feature selection techniques in bioinformatics , 2007, Bioinform..

[3]  Abdul Hamid Adom,et al.  Classification of Agarwood Oil Using an Electronic Nose , 2010, Sensors.

[4]  John S. Payne,et al.  Sensor array techniques for mimicking the mammalian olfactory system , 1996 .

[5]  Puteh Saad,et al.  Plant leaf identification using moment invariants & General Regression Neural Network , 2011, 2011 11th International Conference on Hybrid Intelligent Systems (HIS).

[6]  Khalil Arshak,et al.  A review of gas sensors employed in electronic nose applications , 2004 .

[7]  Vincent O. S. Olunloyo,et al.  Neural network-based electronic nose for cocoa beans quality assessment , 2012 .

[8]  Alphus D. Wilson,et al.  Applications and Advances in Electronic-Nose Technologies , 2009, Sensors.

[9]  Kea-Tiong Tang,et al.  Development of a Portable Electronic Nose System for the Detection and Classification of Fruity Odors , 2010, Sensors.

[10]  Nidal F. Shilbayeh,et al.  Quality Control of Coffee Using an Electronic Nose System , 2004 .

[11]  Xiaofeng Wang,et al.  Recognition of Plant Leaves Using Support Vector Machine , 2008, ICIC.

[12]  H. T. Nagle,et al.  Handbook of Machine Olfaction , 2002 .

[13]  K. Persaud,et al.  Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose , 1982, Nature.

[14]  Jun Kong,et al.  Plant Species Identification Based on Neural Network , 2008, 2008 Fourth International Conference on Natural Computation.

[15]  F. Hogewind,et al.  On Spray-Electricity and Waterfall-Electricity , 1919 .

[16]  Salina Abdul Samad,et al.  An Electronic Nose for Reliable Measurement and Correct Classification of Beverages , 2011, Sensors.

[17]  Julian W. Gardner,et al.  A brief history of electronic noses , 1994 .

[18]  Jun Fu,et al.  Pattern Classification Using an Olfactory Model with PCA Feature Selection in Electronic Noses: Study and Application , 2012, Sensors.

[19]  Asnor Juraiza Ishak,et al.  Original paper: Weed image classification using Gabor wavelet and gradient field distribution , 2009 .

[20]  Bipan Tudu,et al.  Normalization techniques for gas sensor array as applied to classification for black tea , 2009 .

[21]  J. Vincent,et al.  Information processing in the mammalian olfactory system. , 2005, Physiological reviews.