Deep Learning-based Water Pathogen Detection using YOLOv11m
Utkarsh Dubey
, Pratham Dubey , Amit Kumar Pandey , Santosh Kumar Singh
Waterborne disease, Pathogen Detection, Computer Vision, Image Processing, Roboflow, YOLOv11m.
Waterborne disease are caused by various bacteria, viruses, and protozoa these pathogens together are what we call waterborne pathogens. These diseases are a major health issue as it affects millions of people all over the world. the regions with limited access to clean water are affected the most. This paper brings a solution based on Computer Vision for the detection of water pathogens and make use of the YOLOv11m model for detection. the dataset consists of five classes which are “Astrovirus,” “Cryptosporidium,” “Giardia,” “Norovirus,” and “Rotavirus,” The dataset has total of 1507 images. These images were then split into Training Set (70%), Validation Set(20%), and Testing Set (10%) sets. The YOLOv11m model was used for detection and classification this model is pre-trained so it makes it easier to use, the model yielded following results. The model achieved a mAP of 97.8%, with precision and recall scores of 93.4% and 94.9%, respectively, on the validation set. The images were taken from “Mendeley Data” and from “Kaggle”. The images were manually labelled(Annotated) on “Roboflow” and using python library called“digitalsreeni-image-annotator 0.8.12”. This model aims to rapid detection of waterborne pathogens with high accuracy and efficiency.
"Deep Learning-based Water Pathogen Detection using YOLOv11m", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.10, Issue 3, page no.b466-b477, March-2025, Available :https://ijsdr.org/papers/IJSDR2503158.pdf
Volume 10
Issue 3,
March-2025
Pages : b466-b477
Paper Reg. ID: IJSDR_301129
Published Paper Id: IJSDR2503158
Downloads: 000173
Research Area: Science All
Country: Mumbai, Maharashtra, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave