We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Rapid Classification of Microplastics by Using the Application of a Convolutional Neural Network
Summary
Researchers used convolutional neural networks (deep learning) to automatically classify microplastic particles in microscopy images into four categories: fragments, pellets, films, and fibers. The models achieved high classification accuracy, reducing the time and labor needed for manual identification. Automated AI classification could greatly accelerate large-scale microplastic monitoring programs.
The Convolutional Neural Network (CNN), a Deep Learning method, was used for the categorization of microplastics with the goal of automatically classifying the particles into four categories: fragments, pellets, film, and fiber. This has been done by using image dataset taken with a mobile phone after microplastic analyses by density separation, wet digestion and extracting. After the microplastic particles have been isolated, the three models included efficientnet_b7, inception_v3, and mobilenet_v3_large_100_224 are used to classify microplastics. The dataset consists of 1600 images that 70% of the image input are used for training, 20% for validation and 10% for testing. The findings demonstrated that the mobilenet_v3_large_100_224 is capable of classifying microplastic particles with an accuracy of 92.5%, and the network performs well when classifying fiber class. The automatic classification of microplastic particles based on the models provides a powerful tool in for environmental protection to control microplastic particles pollution.