Font Size: a A A

The Research Of Quality Evaluation Of Fish Freshness By Electronic Nose

Posted on:2009-08-04Degree:MasterType:Thesis
Country:ChinaCandidate:C W ShenFull Text:PDF
GTID:2121360242991829Subject:Signal and Information Processing
Abstract/Summary:PDF Full Text Request
As the economy of our country getting better and better and the daily life of our people being improved day by day these years, the yield and consumption of fish are increasing. Thus, the government and consumers are paying more and more attention to detection of fish freshness and sanitation quality. As the routine examination such as physical and chemical methods for fish freshness detection are so tedious and time-consuming. So it is difficult to employ them for real-time fish freshness detection in our daily life. There is a great need to establish a method which is simpler, faster, more scientific and objective. Electronic nose (E-nose) is a new burgeoning non-destructive technique of detection. With the computer science and sensor technology become more and more mature, Electronic nose developed very fast these years. Nowadays, Electronic nose synchronizes many technologies, such as sensor, electronics, signal processing and computer et al, which can overcome faults in traditional single sensor and recognize mixed gas qualitatively and quantitatively. Electronic nose has been widely applied in food industry, medicine, quality control and deleterious gas detecting.This research work takes good advantage of the electronic nose to evaluate the quality of fish freshness. Based on the research, the correlation between the inner characteristic and response of sensors has been analyzed, and prediction models of fish freshness have been established. It provides a new method of nondestructive evaluation of meat for further research.This research work takes good advantage of the electronic nose to evaluate the quality of fish freshness. Based on the research, the correlation between the inner characteristic and response of sensors has been analyzed, and prediction models of fish freshness have been established. It provides a new method of nondestructive evaluation of meat for further research.The electronic nose (Cyranose320) produced by Cyrano science corporation was used. This system is provided with objectivity, reliability and repetition. In the same time, the electronic nose responses to the fish, so it is a non-destructive method to evaluate quality of fish freshness. It has a convenience operation and celerity inspection, which is one of the most popular and advanced electronic nose. The hairtail was chose in this experiment. We frozen the hairtail and obtained the odor data by Cyranose320 from the hairtail in the first day, the third day, the fifth day, the seven day and the ninth day in the same situation. First, chose the best headspace situation by PCA analsis. Then, chose the reasonable sensors from the sensor array. Finally, the data in different days were analyzed by the PCA and the PLS . The results indicated that the signals of the sensors changed corresponding to the freshness of the sample which was detected. In the score plots of PCA and PLS figures, the samples can be discriminated clearly according to their freshness. The results showed that there was a related mathematics relation between the score plots of PCA and the fish freshness.In the algorithm of the recognition technology of the electronic nose, a Gabor atom neural network (GANN) was firstly proposed. The GANN was used to classify the odor signal, and the main principle and the designed method were introduced in detail. The algorithm takes good advantage of the Gabor atom transformation's validity in signal expression and the BP network's advantage in signal classification. Compared with the standard back propagation network, the result shows that the Gabor atom network is feasible and has a higher recognition probability. And it has great application meaning in recognition technology of the electronic nose.
Keywords/Search Tags:Electronic nose, Gas sensor array, Gabor atom, Back propagation neural network, Fish freshness
PDF Full Text Request
Related items