Search

This study introduces the global research and technological trends related to various kinds of Information and Communications Technologies (ICTs) used and applied in the livestock industry by improving productivity via breeding, disease and optimal environment control, and smart business management. Prior research data was collected using “ICT,” “IoT,” “information technology (IT),” “ubiquitous technology,” “smart livestock,” and “big data” as main keywords. Most livestock farms in Korea adopt smart livestock technology that are mostly used in the 1st or 1.5th generations, while continuous developments are being carried out for technologies of the 2nd and 3rd generations. In the livestock house, camera vision, radio-frequency identification (RFID), beacon sensors, and environmental sensors are used in livestock farms and houses to collect information compiled into a database to introduce an automated system for livestock management. The data collected from each individual and farm can enable precise breeding and ultimately improve the productivity and efficiency of smart livestock systems. It is necessary to prepare a systematic system at the national level for data collection, ownership, and sharing to improve the productivity and efficiency of the smart livestock system.

Food safety and foodborne diseases are significant global public health concerns. Meat and poultry carcasses can be contaminated by pathogens like E. coli and salmonella, by contact with animal fecal matter and ingesta during slaughter and processing. Since fecal matter and ingesta can host these pathogens, detection, and excision of contaminated regions on meat surfaces is crucial. Fluorescence imaging has proven its potential for the detection of fecal residue but requires expertise to interpret. In order to be used by meat cutters without special training, automated detection is needed. This study used fluorescence imaging and deep learning algorithms to automatically detect and segment areas of fecal matter in carcass images using EfficientNet-B0 to determine which meat surface images showed fecal contamination and then U-Net to precisely segment the areas of contamination. The EfficientNet-B0 model achieved a 97.32% accuracy (precision 97.66%, recall 97.06%, specificity 97.59%, F-score 97.35%) for discriminating clean and contaminated areas on carcasses. U-Net segmented areas with fecal residue with an intersection over union (IoU) score of 89.34% (precision 92.95%, recall 95.84%, specificity 99.79%, F-score 94.37%, and AUC 99.54%). These results demonstrate that the combination of deep learning and fluorescence imaging techniques can improve food safety assurance by allowing the industry to use CSI-D fluorescence imaging to train employees in trimming carcasses as part of their Hazard Analysis Critical Control Point zero-tolerance plan.