Classification of tea specimens using novel hybrid artificial intelligence methods

Abstract Two innovative systems based on feed-forward and recurrent neural network used for qualitative analysis has been applied to specimens of different fruit tea. Their performance was compared against the conventional methods of artificial intelligence. The proposed systems are a combination of data preprocessing methods, genetic algorithms and Levenberg–Marquardt (LM) algorithm used for learning feed forward and recurrent neural networks. The initial weights and biases of neural networks chosen by the use of genetic algorithms were then tuned with a LM algorithm. The evaluation was made on the basis of accuracy and complexity criteria. The main advantage of the proposed systems is the elimination of the random selection of the network weights and biases resulting in the increased efficiency of the systems.

[1]  Panos M. Pardalos,et al.  hGA: Hybrid genetic algorithm in fuzzy rule-based classification systems for high-dimensional problems , 2012, Appl. Soft Comput..

[2]  B. Snopok,et al.  Multisensor systems for chemical analysis: state-of-the-art in Electronic Nose technology and new trends in machine olfaction , 2002 .

[3]  César Hervás-Martínez,et al.  A two-stage algorithm in evolutionary product unit neural networks for classification , 2011, Expert Syst. Appl..

[4]  Tohru Nomura,et al.  BATTERY OPERATED SEMICONDUCTOR CO SENSOR USING PULSE HEATING METHOD , 1998 .

[5]  Anne-Claude Romain,et al.  Use of a simple tin oxide sensor array to identify five malodours collected in the field , 2000 .

[6]  Amadou Dicko,et al.  Aging fingerprint characterization of beer using electronic nose , 2011 .

[7]  Min-Yuan Cheng,et al.  Evolutionary fuzzy hybrid neural network for project cash flow control , 2010, Eng. Appl. Artif. Intell..

[8]  C Cevoli,et al.  Classification of Pecorino cheeses using electronic nose combined with artificial neural network and comparison with GC-MS analysis of volatile compounds. , 2011, Food chemistry.

[9]  Leszek Rutkowski,et al.  Computational intelligence - methods and techniques , 2008 .

[10]  Wojciech Maziarz,et al.  Dynamic response of a semiconductor gas sensor analysed with the help of fuzzy logic , 2003 .

[11]  Cheng-Hung Chen,et al.  Nonlinear system control using self-evolving neural fuzzy inference networks with reinforcement evolutionary learning , 2011, Appl. Soft Comput..

[12]  John H. Lilly,et al.  Fuzzy Control and Identification , 2010 .

[13]  José María Font,et al.  Evolutionary construction and adaptation of intelligent systems , 2010, Expert Syst. Appl..

[14]  Ryszard Tadeusiewicz,et al.  Place and role of intelligent systems in computer science , 2010 .

[15]  Satoshi Nakata,et al.  Non-linear dynamic responses of a semiconductor gas sensor — Competition effect on the sensor responses to gaseous mixtures , 2001 .

[16]  Ryszard Tadeusiewicz,et al.  New trends in neurocybernetics , 2010 .

[17]  Amine Bermak,et al.  FPGA implementation of a neural network classifier for gas sensor array applications , 2009, 2009 6th International Multi-Conference on Systems, Signals and Devices.

[18]  Shih-Hung Yang,et al.  An evolutionary constructive and pruning algorithm for artificial neural networks and its prediction applications , 2012, Neurocomputing.

[19]  Lei Zhang,et al.  Gases concentration estimation using heuristics and bio-inspired optimization models for experimental chemical electronic nose , 2011 .

[20]  S. M. Yang,et al.  A two-stage algorithm integrating genetic algorithm and modified Newton method for neural network training in engineering systems , 2011, Expert Syst. Appl..

[21]  W. Maziarz,et al.  Gas sensors in a dynamic operation mode , 2008 .

[22]  Afshin Fassihi,et al.  Application of an expert system based on Genetic Algorithm-Adaptive Neuro-Fuzzy Inference System (GA-ANFIS) in QSAR of cathepsin K inhibitors , 2012, Expert Syst. Appl..

[23]  Jun Wang,et al.  Quality grade identification of green tea using the eigenvalues of PCA based on the E-nose signals , 2009 .

[24]  Abdelhakim Artiba,et al.  Artificial Intelligence Methods , 1998 .

[25]  Habibollah Haron,et al.  Accumulated risk of body postures in assembly line balancing problem and modeling through a multi-criteria fuzzy-genetic algorithm , 2012, Comput. Ind. Eng..

[26]  Ryszard Tadeusiewicz,et al.  Introduction to Intelligent Systems , 2011, Intelligent Systems.

[27]  Dong-Ling Tong,et al.  Hybrid genetic algorithm-neural network: Feature extraction for unpreprocessed microarray data , 2011, Artif. Intell. Medicine.

[28]  Beatrice Lazzerini,et al.  Learning concurrently partition granularities and rule bases of Mamdani fuzzy systems in a multi-objective evolutionary framework , 2009, Int. J. Approx. Reason..

[29]  Mengjie Zhang,et al.  Encoding subcomponents in cooperative co-evolutionary recurrent neural networks , 2011, Neurocomputing.

[30]  K. Ihokura,et al.  The Stannic Oxide Gas SensorPrinciples and Applications , 1994 .

[31]  Donna L. Hudson,et al.  Neural networks and artificial intelligence for biomedical engineering , 1999 .