You are here

Sensors Protect Crops from Insect Damage

What do you get when you combine Legos, a 99¢ laser pointer, and a piece from a television remote? If you ask Eamonn Keogh, a computer science professor at University of California (UC) Riverside’s Bourns College of Engineering, the answer is a sensor to help farmers protect their crops from insect damage and to limit the spread of insect-borne diseases such as malaria and dengue fever.

For more than five decades, research to classify insects has been limited by a number of factors, including relying too much on acoustic sensing devices, focusing heavily on wingbeat frequency, and having limited data.

Researchers included Keogh; Yanping Chen, a computer science graduate student at UC Riverside; Adena Why, an entomology graduate student at UC Riverside; Gustavo Batista, University of São Paulo in Brazil; and Agenor Mafra-Neto, ISCA Technologies in Riverside.

They conquered those barriers by building an inexpensive wireless bug sensor. The device can track many insect flight-behavior patterns and generate much larger amounts of data. The information can then be incorporated into classification algorithms.

By having dozens of sensors running in parallel 24 hours a day, the researchers collected tens of millions of data points in about three years, which is more than all previous work in this field combined.

“We set out not knowing what was possible,” says Keogh. “Now, the problem is essentially solved. We have created insect-classification tools that can outperform the world’s top entomologists in a fraction of the time.”

The sensor, which consists of a phototransistor array, is connected to an electronic board and a laser pointing at the phototransistor array.

When an insect passes across the laser beam, its wings partially block the light, causing a small light fluctuation. The fluctuations are captured by the phototransistor array as changes in current. Then the signal is filtered and amplified by the custom-designed electronic board.

The output of the electronic board is fed into a digital sound recorder, recorded as an MP3 and downloaded to a computer.

The goal is to make this automated classification method as simple and inexpensive as sticky traps and interception traps – only with digital advantages such as higher accuracy, real-time monitoring, and the ability to collect additional flight-behavior patterns.

Testing theories
In their experiments, the researchers worked with six species of insects. As they added additional insect flight-behavior patterns to their classification algorithm, they were able to increase their success in classifying the different species.

For instance, when the researchers used only wingbeat sounds, there was an 88% success rate. The success rate rose to 95% when time of day was added. After adding location, the success rate increased two more percentage points.

Researchers believe the success rate can be improved even more by adding other variables like the flying height of insects and environmental factors such as temperature and humidity.

In a separate experiment, the researchers tested classification accuracy by adding an increasing number of species. With two species, they had 99% accuracy.

However, that percentage declined as they added more species. For example, with five species, they had a 96% accuracy rate; with 10 species, it was 79%.

Next steps
For centuries, humans have made an effort to eliminate unwanted insects. While some mass methods have accomplished that goal, they can be costly and create environmental problems.

The bug sensors aim to change that by counting and classifying the insects so that the substance used to eradicate the harmful insects can be applied on a precisely targeted level. Keogh believes such sensors can be built for less than $10 each, and they can be powered by solar power or a battery that lasts one year.

In the next year, he plans to focus on deploying the sensors around the world. Currently, Brazil and Hawaii are using them on a small scale.

Keogh is also working with entomologist Tovi Lehmann with the Laboratory of Malaria and Vector Research at the National Institute of Allergy and Infectious Diseases (niaid.nih.gov) in Rockville, Maryland, to implement the sensors in Mali.

Learn more
Eamonn Keogh
951/827-2032
eamonn@cs.ucr.edu

Read more about

Talk in Marketing

Most Recent Poll

Will you plant more corn or soybeans next year?