project-highlight-image

Larval Mosquito Detection Device

This project focused on the design and evaluation of a low-cost mosquito larvae detection device using optical sensing and machine learning–based image analysis. Images collected from standing water samples were used to train and evaluate a supervised machine learning model to distinguish mosquito larvae from background features such as debris and surface reflections. The work combined hardware integration, data collection, model training, and performance evaluation, highlighting both the potential and practical limitations of machine learning–based environmental monitoring in real-world conditions.
Home
Questions?
hero-image

Drew Geiser

Project Timeline

Jan 2023 - May-2023

HighlightS

  • Trained and validated a machine learning model to detect the presence and absence of mosquito larvae
  • Assessed detection performance under varying lighting and background conditions to identify failure modes
  • Collected ~ 100 labeled images under varying conditions and larval densities to support supervised model training and evaluation
  • Designed and fabricated a low-cost, field-deployable prototype using a Raspberry Pi, camera module, PVC pipe, and waterproof enclosure.

SKILLS

Machine learning
Solidworks
Raspberry Pi system integration
Prototype fabrication & assembly

External Links

Model Limitations and Observations

Testing showed that detection performance was sensitive to lighting variation, surface glare, and background clutter. Thin debris and water reflections were the most common sources of false positives, particularly in low-contrast conditions. These results highlighted challenges in using raw image data for aquatic monitoring and motivated recommendations for improved lighting control, preprocessing, and expanded training data in future iterations.

Engineering Tradeoffs and Design Context

The system was designed around low-cost, readily available components to support affordability and ease of deployment. Design decisions favored portability, durability, and simplicity over image quality optimization, reflecting realistic constraints for field-deployable environmental monitoring devices. The project demonstrates the tradeoffs involved in integrating machine learning with embedded hardware in uncontrolled environments.

| lowinertia |
Engineering Portfolio in 15 minutes
Create Your Portfolio