Scholarlink

<p><i>Listeria monocytogenes</i> is an important pathogen responsible for major outbreaks worldwide, necessitating its early detection to prevent listeriosis. Hence, this study prioritized the early detection of <i>L. monocytogenes</i> using YOLOv5 deep-learning algorithms. An ultraviolet lamp was attached to the detection system to maintain a sterile environment. Images of <i>L. monocytogenes</i> grown on PALCAM agar were given as input for the bacterial predictions. Further, it was classified and regression layers for the identification of <i>L. monocytogenes</i> were constructed. A powerful LED light (optical-source) enhanced the performance of the detection. The effectiveness of the developed detection system was achieved with an average accuracy of ~ 94%. Perceptibly, the proposed system offers high accuracy, precision with cost-affordability and user-friendliness. The early detection of bacteria would improve food safety. In addition, exploitation of the developed system in healthcare industries may drastically reduce the endurance of resistant strains (misuse/overuse of inappropriate antibiotics), thus ensuring public health.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Detection of foodborne Listeria monocytogenes using deep learning models to ensure food safety and health

  • 期刊论文

  • 发表日期：

    2025年9月1日

查看全文
  • Ramya Ravindhiran,
  • Kavitha Dhandapani

摘要

Listeria monocytogenes is an important pathogen responsible for major outbreaks worldwide, necessitating its early detection to prevent listeriosis. Hence, this study prioritized the early detection of L. monocytogenes using YOLOv5 deep-learning algorithms. An ultraviolet lamp was attached to the detection system to maintain a sterile environment. Images of L. monocytogenes grown on PALCAM agar were given as input for the bacterial predictions. Further, it was classified and regression layers for the identification of L. monocytogenes were constructed. A powerful LED light (optical-source) enhanced the performance of the detection. The effectiveness of the developed detection system was achieved with an average accuracy of ~ 94%. Perceptibly, the proposed system offers high accuracy, precision with cost-affordability and user-friendliness. The early detection of bacteria would improve food safety. In addition, exploitation of the developed system in healthcare industries may drastically reduce the endurance of resistant strains (misuse/overuse of inappropriate antibiotics), thus ensuring public health.