Location: Insect Behavior and Biocontrol ResearchTitle: Detection of damaged wheat kernels using an impact acoustic signal processing technique based on Gaussian modelling and an improved extreme learning machine algorithm
|GAUO, MIN - SHAANXI NORMAL UNIVERSITY|
|MA, YUTING - SHAANXI NORMAL UNIVERSITY|
|YANG, XIAOJING - SHAANXI NORMAL UNIVERSITY|
Submitted to: Biosystems Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 4/30/2019
Publication Date: 5/1/2019
Citation: Gauo, M., Ma, Y., Yang, X., Mankin, R.W. 2019. Detection of damaged wheat kernels using an impact acoustic signal processing technique based on Gaussian modelling and an improved extreme learning machine algorithm. Biosystems Engineering. 184:37-44. https://doi.org/10.1016/j.biosystemseng.2019.04.022.
Interpretive Summary: Insect damage results in significant nutritional and quality damage to stored wheat. Researchers in the Key Laboratory of Modern Teaching Technology, Shaanxi University, Xian, China, in collaboration with a scientist at USDA-ARS, Center for Medical, Agricultural and Veterinary Entomology, Gainesville, Florida, developed automated methods to distinguish sounds made by undamaged wheat kernels from insect-damaged ones. Wheat grain samples that were dropped onto a steel plate for inspection resonated with different sounds as identified by employing an Extreme Learning Machine. The Extreme Learning Machine enhanced listening system was able to correctly identify undamaged-, insect-damaged, and sprout-damaged kernels with greater that 92% accuracy. This Extreme Learning Machine enhanced acoustic system provides a rapid, automated means to assist warehouse managers and grain inspectors in inspecting and establishing the quality of wheat samples.
Technical Abstract: Wheat kernel damage is a major source of food quality degradation, and long-term feeding on products from damaged wheat kernels will result in malnutrition or even induce dis- eases. Therefore, detection of damaged wheat kernels is of significant interest. An impact acoustic signal processing technique based on Gaussian modelling and an improved extreme learning machine approach was proposed for detection of insect and sprout- damaged wheat kernels. Discriminant features extracted from Gaussian-model-estimated parameters were fed to an extreme learning machine based on a C-matrix embedded optimization approximation solution. The best results, 92.0% of undamaged, 96.0% of insect-damaged, and 95.0% of sprout-damaged wheat kernels were correctly classified by using the proposed method. Furthermore, the detection system had good processing speed. Therefore, it could be effective to detect damaged wheat kernels in real time.