Pattern Discovery from Big Data of Food Sampling Inspections Based on Extreme Learning Machine

Food sampling programs are implemented from time to time in local areas or throughout the country in order to guarantee food safety and to improve food quality. The hidden patterns in the accumulated huge amount of data and their potential values are worthy to research. In this paper, Extreme learning machine (ELM) is employed on real data sets collected from the food safety inspections of China in recent two years, in order to mine the relationship between food quality and food category, manufacturing site and season, inspection site and season, and many other attributes. Experimental results indicate that the ELM approach has better prediction precision and generalization ability than Logistic regression that was adopted in preceding work. The patterns obtained are helpful for making more effective food sampling plans and for more targeted food safety tracing.

[1]  Leonardo Ramos Rodrigues,et al.  Pruning Extreme Learning Machines Using the Successive Projections Algorithm , 2015, IEEE Latin America Transactions.

[2]  Shuai Li,et al.  Inverse-Free Extreme Learning Machine With Optimal Information Updating , 2016, IEEE Transactions on Cybernetics.

[3]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[4]  Dennis K. J. Lin,et al.  Model Selection for Poisson Regression via Association Rules Analysis , 2015 .

[5]  Chee Kheong Siew,et al.  Universal Approximation using Incremental Constructive Feedforward Networks with Random Hidden Nodes , 2006, IEEE Transactions on Neural Networks.

[6]  Yimin Yang,et al.  Multilayer Extreme Learning Machine With Subnetwork Nodes for Representation Learning , 2016, IEEE Transactions on Cybernetics.

[7]  Yongjun Ma,et al.  Research of food safety risk assessment methods based on big data , 2016, 2016 IEEE International Conference on Big Data Analysis (ICBDA).

[8]  Shichao Zhang,et al.  Shell-neighbor method and its application in missing data imputation , 2011, Applied Intelligence.

[9]  S. Sonka,et al.  Big Data and the Ag Sector: More than Lots of Numbers , 2014 .

[10]  Yimin Yang,et al.  Extreme Learning Machine With Subnetwork Hidden Nodes for Regression and Classification , 2016, IEEE Transactions on Cybernetics.

[11]  Qunxiong Zhu,et al.  Research of Food Safety Event Detection Based on Multiple Data Sources , 2015, 2015 International Conference on Cloud Computing and Big Data (CCBD).

[12]  Cristiano Cervellera,et al.  Low-Discrepancy Points for Deterministic Assignment of Hidden Weights in Extreme Learning Machines , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[13]  Guoqiang Li,et al.  An enhanced extreme learning machine based on ridge regression for regression , 2011, Neural Computing and Applications.

[14]  Eros Pasero,et al.  Defect detection in food ingredients using Multilayer Perceptron Neural Network , 2014, 2014 World Symposium on Computer Applications & Research (WSCAR).

[15]  Yue Liu,et al.  Prediction of soil moisture based on Extreme Learning Machine for an apple orchard , 2014, 2014 IEEE 3rd International Conference on Cloud Computing and Intelligence Systems.

[16]  Dilpreet Singh,et al.  A survey on platforms for big data analytics , 2014, Journal of Big Data.

[17]  Yibin Ying,et al.  Spectroscopy-based food classification with extreme learning machine , 2014 .

[18]  Tihomir Florijančić,et al.  Background to the preparation of the Croatian Food Safety Strategy , 2008 .

[19]  Pei-Sheng Lin,et al.  An optimal k-nearest neighbor for density estimation , 2012 .

[20]  Eros Pasero,et al.  Artificial neural network classifier for quality inspection of nuts , 2014, 2014 International Conference on Robotics and Emerging Allied Technologies in Engineering (iCREATE).