Job offersmore »
- Experienced International Buyer/Seller Germany
- Project and Sales Manager - Russia/Caucasian Region
- Quality Coordinator EU in Supply Chain Management Dep.
- Regional Sales Director - United States
- Territory Sales Position - US
- International Tomato Grower - Worldwide
- Grower Manager - US
- Application Scientist Salesperson - US
- Technical & Operations Manager - Australia
- Eco Brewing & Growing Technician - UK
Top 5 - yesterday
- No news was published yesterday.
Top 5 - last week
Top 5 - last month
Exchange ratesmore »
Spain: Artificial intelligence to Identify diseases in citrusThe fight of producers in the region against diseases in citrus is intense. The attention is mainly focused in three diseases that the European Union considers to be cases worthy of quarantine: scabies, cancrosis and Dark Spot. A single fruit infected and exported can cause a whole shipment to be refused. And the ones able to identify those diseases are few.
But the story is about to end, since new advances in artificial intelligence are reaching the citrus sector. Soon a photo will be enough, when sent to a system that can detected if the fruit is infected or not. This is the result of work carried out by experts at the Investigation Group for Signs and Computational Intelligence from the School of Engineering and Hydric Science in the National University of the Coast and CONICET.
According to Diego Milone, investigator in the team, the project is about the use of strong neural networks to process the spots in oranges or mandarines and determine if they belong to one of more than 20 quarantine worthy diseases that exist. For now, the idea is that producers can send an sms with the spots characteristics to a server so the neural network can say to which disease they belong. That way, they can determine what to do with the shipment.
The Experimental Station for Agro-Livestock Concordia - INTA has a lot of experience in the study of the three quarantine diseases affecting citrus: scabies, cancrosis and Dark Spot.
Observations of several characteristics in the sympthoms, like color, deepness, relief, among others, provides the information required to introduce to the intelligent system designed by the Milone team.
"With that data we feed a super visioned neural system, where we have elements to know which is the best way. The information from INTA gives us many examples that tell us to what kind of characteristics correspond to what disease. That way we can train the neural network. We tell it that when it sees that kind of color or relief, or texture, the way out must be "Dark Spot", for example. Then all the synapses are adjusted, so when that information gets in again, the neural network knows the correct way out", he said, adding that despite the training there will be cases of spots quite hard to interpret and they will need the opinion of an expert: "Although, this can be two of a hundred cases", he stated.
Publication date: 5/4/2012
Receive the daily newsletter in your email for free | Click here
Other news in this sector: