Nondestructive evaluation of fish meat using ultrasound signals and machine learning methods |
| |
| Institution: | 1. National Fisheries University, 2-7-1 Nagata-Honmachi, Shimonoseki, Yamaguchi 759-6595, Japan;2. Nippon Kaiji Kentei Kyokai, 1-9-7 Hatchobori, Chuo-ku, Tokyo 104-0032, Japan;1. Universidad de Sonora, Departamento de Investigaciones Científicas y Tecnológicas, Av. Luis D. Colosio s/n, Hermosillo, Sonora, 83000, Mexico;2. Centro de Investigaciones Biológicas del Noroeste (CIBNOR), Unidad Sonora, Apdo. Postal 349, Guaymas, Sonora, 85454, Mexico;1. Federal Institute of Education, Science and Technology of Mato Grosso do Sul, Mato Grosso do Sul, Campo Grande, Brazil;2. Federal Institute of Education, Science and Technology of Mato Grosso do Sul, Mato Grosso do Sul, Aquidauana, Brazil;3. National University of Brasilia, Via L3, Brasilia-DF 70910-900, Brazil;4. University of Nebraska – Lincoln, 1101 T St. Schorr Center 223, Lincoln, NE 68588-0038, United States;5. Dom Bosco Catholic University, Av. Tamandaré, 6000, Campo Grande, MS 79117-010, Brazil;6. Federal University of Mato Grosso do Sul, Av. Costa e Silva, s/no, Campo Grande, MS 79070-900, Brazil;1. Amity School of Engineering and Technology, Amity University, Noida, India;2. Centre for Advanced Studies, Lucknow, India;1. Graduate School of Agricultural & Life Sciences, The University of Tokyo, Japan;2. Department of Food Technology and Rural Industries, Faculty of Agricultural Engineering & Technology, Bangladesh Agricultural University, Mymensingh, 2202, Bangladesh |
| |
| Abstract: | In this study, we propose a new method for the nondestructive measurement of the fat content and texture of fish meat using machine learning and the bag of features approach. We employed two machine learning methods, that is, a self-organizing map (SOM) and radial basis function (RBF) network. The SOM was applied to symbolize the pattern of the frequency spectrum extracted from ultrasound signals and to generate key features for the bag of features technique. The RBF network was applied to estimate the fat content and texture of fish meat from the bag of features histogram. We verified the accuracy of the fat content and texture estimations given by the proposed method through a series of experiments. The results showed that the fat content and texture of fish meat was estimated more accurately using the proposed method than by the conventional approach. |
| |
| Keywords: | Ultrasound Nondestructive evaluation Self-organizing map Bag of features Radial basis function |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
