Model evaluation for automated scoring of electropenetrography waveform data from mosquitoes
5 affiliations
- 1Auburn University
- 2Swarthmore College
- 3Harvey Mudd College
- 4San Joaquin Valley Agricultural Science Center
- 5National Bio and Agro-Defense Facility
Abstract
Electropenetrography (EPG) is a powerful tool for quantifying how arthropods interact with their hosts, but manually labeling EPG feeding behavior waveforms is subjective, labor-intensive, and time-consuming. Machine-learning models for supervised classification have achieved widespread success in pattern recognition in scientific contexts and have the potential to automate and standardize waveform labeling. Here, the performance of various common machine learning methods for EPG waveform labeling was compared using a representative dataset of Culex tarsalis EPG waveforms; the top five models are presented. A neural network based on the UNet architecture with attention layers was the top-performing model, achieving an overall accuracy of 86% and a Macro F1 score of 0.78. To the authors’ knowledge, this is the first attempt to apply machine learning to identify waveforms from a blood-feeding arthropod, rather than a plant-feeding hemipteran. Experiments indicate that previously proposed machine learning approaches for classifying hemipteran waveforms do not apply well to waveforms from blood-feeding arthropods. This suggests that analyzing species with distinct waveform patterns may require differing machine learning approaches. The findings of this study will facilitate the development of an automated waveform identification tool that researchers can use to score waveforms from mosquitoes and other blood-feeding arthropods.
Related
- Automated segmentation and quantification of histological liver features for MASH/MASLD scoring
- Technical Performance and Automated-manual Scoring Agreement in Type III Home Sleep Apnea Testing: A Single-center Study from Saudi Arabia.
- The value of ultrasound semi-quantitative scoring in the clinical evaluation of acute gouty arthritis with normal and elevated serum uric acid
- Comparative Evaluation of Prognostic Scoring Systems for Metastatic Spinal Tumors: Utility of the New Katagiri and Skeletal Oncology Research Group Models
- Evaluation of the Obstetric Quality of Recovery-10 scoring tool up to 30 days postpartum: a secondary cross-sectional psychometric analysis (SOCRATES cohort)
BibTeX
@article{cooper2026model,
title = {{Model evaluation for automated scoring of electropenetrography waveform data from mosquitoes}},
author = {Anastasia M. W. Cooper and Gabriel Hope and Mehrezat Abbas and Milo Knell and Devanshi Guglani and Lillian Vernooy and Zachary Traul and Elaine A. Backus and Dana N. Mitzel and Kathryn E. Reif},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-57373-w},
url = {https://doi.org/10.1038/s41598-026-57373-w},
note = {CC BY},
}
RIS
TY - JOUR
TI - Model evaluation for automated scoring of electropenetrography waveform data from mosquitoes
AU - Anastasia M. W. Cooper
AU - Gabriel Hope
AU - Mehrezat Abbas
AU - Milo Knell
AU - Devanshi Guglani
AU - Lillian Vernooy
AU - Zachary Traul
AU - Elaine A. Backus
AU - Dana N. Mitzel
AU - Kathryn E. Reif
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-57373-w
UR - https://doi.org/10.1038/s41598-026-57373-w
AB - Electropenetrography (EPG) is a powerful tool for quantifying how arthropods interact with their hosts, but manually labeling EPG feeding behavior waveforms is subjective, labor-intensive, and time-consuming. Machine-learning models for supervised classification have achieved widespread success in pattern recognition in scientific contexts and have the potential to automate and standardize waveform labeling. Here, the performance of various common machine learning methods for EPG waveform labeling was compared using a representative dataset of Culex tarsalis EPG waveforms; the top five models are presented. A neural network based on the UNet architecture with attention layers was the top-performing model, achieving an overall accuracy of 86% and a Macro F1 score of 0.78. To the authors’ knowledge, this is the first attempt to apply machine learning to identify waveforms from a blood-feeding arthropod, rather than a plant-feeding hemipteran. Experiments indicate that previously proposed machine learning approaches for classifying hemipteran waveforms do not apply well to waveforms from blood-feeding arthropods. This suggests that analyzing species with distinct waveform patterns may require differing machine learning approaches. The findings of this study will facilitate the development of an automated waveform identification tool that researchers can use to score waveforms from mosquitoes and other blood-feeding arthropods.
SN - 2045-2322
ER -