We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
A Benchmarking on Optofluidic Microplastic Pattern Recognition: A Systematic Comparison Between Statistical Detection Models and ML-Based Algorithms
AI summary Read the abstract
This benchmarking study compared statistical detection models with machine learning classifiers from multiple supervised learning paradigms for detecting microplastics using optofluidic pattern recognition data. Results assessed performance robustness when parameters deviated from optimal conditions, providing a reference for selecting detection approaches for practical microplastic monitoring applications.
Microplastics, small particles of plastic found in the environment, have become an increasingly worrying topic in recent years. This paper compares a statistical detection model to classifiers from various supervised learning paradigms in order to detect microplastics. The objective of this paper is to present a benchmark for detecting microplastics using statistical and machine learning models. The main goal is to assess and compare their performance when the defined parameters deviate from the optimal solution of the respective model. Results are presented in terms of probability error, comparing the performance of the machine learning techniques to the statistical model. The study considers a range of signal-to-noise ratios and a priori event probabilities, focusing on the classifiers’ ability to handle amplitude variability and threshold variation. Results show that as the number of analyzed particles in the flow increases, the detection performance improves, with Support Vector Machine, Linear Discriminant Analysis and Naive Bayes standing out from the other methods.
More Papers Like This
Algorithm Comparison for Microplastic Classification: Evaluating Ensemble Models on Density and Measurement Features
AI summary Read the abstract
Researchers compared machine learning algorithms for classifying microplastic types based on density and measurement features, evaluating ensemble models against standard classifiers. The ensemble approaches outperformed individual models, suggesting that combining multiple algorithms improves automated MP identification from physical measurement data.
Online detection of floating microplastics in liquids
AI summary Read the abstract
This paper presents a novel optical detection model for identifying floating microplastic particles in liquids, using binary signal discrimination to distinguish particle signals from noise. The approach offers a new method for online real-time monitoring of microplastic contamination in water.
From microplastics to pixels: testing the robustness of two machine learning approaches for automated, Nile red-based marine microplastic identification
AI summary Read the abstract
Two machine learning approaches using Nile red fluorescence staining and automated image analysis were tested for robustness on marine microplastics of multiple polymer types and weathering states, finding performance varied with particle heterogeneity and environmental aging.
Replacing human judgment in fluorescence-based microplastic detection with machine learning: toward harmonization with spectroscopic methods
AI summary Read the abstract
Researchers developed a machine learning application called NRmachine to replace subjective human judgment in fluorescence-based microplastic detection. The study found that the optimal ML model achieved detection probability of 50% for 40-micrometer particles and 90% for 100-micrometer particles, with accuracy comparable to established FTIR spectroscopy methods.
Approaches to Detect Microplastics in Water Using Electrical Impedance Measurements and Support Vector Machines
AI summary Read the abstract
Researchers developed an electrical impedance spectroscopy method enhanced with machine learning to detect microplastics in water, achieving over 98% classification accuracy for stationary samples and over 85% for dynamic flow measurements across different plastic materials and particle sizes.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.