Supervised machine learning approach for pork meat freshness identification

CFD Lumogdang, MG Wata, SJS Loyola… - Proceedings of the 6th …, 2019 - dl.acm.org
CFD Lumogdang, MG Wata, SJS Loyola, RE Angelia, HLP Angelia
Proceedings of the 6th International Conference on Bioinformatics Research …, 2019dl.acm.org
As the number of pork consumer increases in the meat industry, the demand for meat
supplies also rises. Determining pork meat freshness, therefore, is the primary consideration
of the pork meat customers. This smart study is mainly designed to assess and classify pork
meat quality. Loin parts weighing 100 grams from various pigs in the wet market, were
examined and became the data sets of the study, provided that a city veterinarian has
inspected and approved it. Photos of pork meat are captured to undergo image processing …
As the number of pork consumer increases in the meat industry, the demand for meat supplies also rises. Determining pork meat freshness, therefore, is the primary consideration of the pork meat customers. This smart study is mainly designed to assess and classify pork meat quality. Loin parts weighing 100 grams from various pigs in the wet market, were examined and became the data sets of the study, provided that a city veterinarian has inspected and approved it. Photos of pork meat are captured to undergo image processing. Simultaneously, electronic noses, specifically MQ-135 and MQ-136, evaluated Ammonia and Hydrogen Sulfide components of the pork meat, respectively. These parameters are then classified using the k-Nearest Neighbor Algorithm. Pork meat is distinguished from being fresh, half-fresh, and adulterated. By using the confusion matrix principle, functionality test and statistical analysis revealed that the system has a high accuracy rate of 93.33%.
ACM Digital Library
以上显示的是最相近的搜索结果。 查看全部搜索结果