A honey detection method based on parameter selection of support vector machine classifier based on particle swarm optimization

Abstract

A honey detection method based on particle swarm optimization and support vector machine classifier parameter selection, which is characterized in that random individuals are initialized, and individual changes are performed by calculating the gap between the current individual fitness function value and the optimal fitness value of the group. Compared with genetic Algorithm, the particle swarm optimization algorithm converges faster, and reaches the optimal point in about 6 generations. The optimization result is: the highest accuracy rate of the training set is 91.25%, c=32.3362, r=0.0100. Under this condition, the prediction accuracy rate is 88.61%, Among them, rapeseed honey is 21 / 23, linden honey is 14 / 17, and acacia honey is 36 / 39.

Description

A honey detection method based on particle swarm optimization algorithm and support vector machine classifier parameter selection technical field The present application relates to a honey detection method based on particle swarm algorithm support vector machine classifier parameter selection. Background technique my country's honey production ranks first in the world. In recent years, the output has maintained a rapid growth trend, from 252,000 tons in 2001 to 402,000 tons in 2009, accounting for more than 30% of the world's total output from nearly 20%. However, due to the drive of economic interests, the current honey market is seriously adulterated, resulting in adulterated honey accounting for 20% to 30% of the honey market. In some areas, adulterated and fake bee products account for about 50%, seriously damaging the interests of consumers and affecting The healthy development of the honey industry and the fight against foreign exchange earnings from export trade. ...

AI Technical Summary

Problems solved by technology

However, it is still weak in differential information mining, which is also a bottleneck restricting the development of electronic noses.

Images