Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/10/2018
Publication Date: 4/25/2018
Citation: Guo, M., Xuehua, S., Zichen, Z., Miao, M., Wu, X., Mankin, R.W. 2018. Identification and classification of damaged corn kernels with impact acoustics multi-domain patterns. Computers and Electronics in Agriculture. 150:152-161. https://doi.org/10.1016/j.compag.2018.04.008.
DOI: https://doi.org/10.1016/j.compag.2018.04.008

Interpretive Summary: Insect- and mildew-damaged corn kernels cause significant nutritional and quality damage to stored corn. Researchers in the School of Computer Science at Shaanxi Normal University, China, the School of Automation and Information Engineering at the Xi'an University of Technology, China, and the USDA, Agricultural Research Service, Center for Medical, Agricultural, and Veterinary Entomology, Gainesville, Florida, collaborated to automated methods that distinguish undamaged corn kernels from insect- or mildew-damaged kernels. Sounds produced by kernels dropped onto a steel plate using an inexpensive impact acoustic signal processing system were analyzed to develop a mutifactoral machine that considerably improved the accuracy of detecting insect- or mildew-damaged kernels. This system establishes the potential for automated grain inspection to assist warehouse managers in improving the quality of stored corn.

Technical Abstract: An impact acoustic signal device was tested with undamaged, insect-damaged, and mildew-damaged corn kernels, and the different signals were compared using ensemble empirical mode decomposition methods. These methods were adopted based on their known superiority in processing of non-stationary signals and in suppressing of mode mixing. Time domain, frequency domain, and Hilbert domain features were extracted from an ensemble empirical mode decomposition of the impact acoustic signals. Four features were extracted from the time domain: the average amplitude change, Wilson amplitude, average absolute value, and peak-to-peak value. Three features were extracted from the frequency domain: the mean square frequency, the root mean square of the power spectrum, and the frequency band variance. The energy of the high- and low-frequency bands and the average values of the envelopes were extracted from the Hilbert domain. Subsequently, these features were used as inputs to a support vector machine which was optimized by particle swarm optimization. The use of hybrid features enabled higher classification accuracy than usage of features in each domain separately. In this study, the optimal classification accuracies were 99.2%, 99.8%, and 98.6% for undamaged kernels, insect-damaged kernels and mildew-damaged kernels, respectively. These results, based on ensemble empirical mode decomposition and integration of multi-domain features, are encouraging for the potential of an automated inspection system.