- Publication . Article . 2021Closed AccessAuthors:Makoto Ikeda; Natwadee Ruedeeniraman; Leonard Barolli;Makoto Ikeda; Natwadee Ruedeeniraman; Leonard Barolli;Publisher: Elsevier BV
Abstract In the field of agriculture, there are many individual micro businesses with low investment capacity and awareness of IT utilization, and it is difficult to obtain a return on investment . In recent years, edge computing and Artificial Intelligence (AI) technologies have attracted a lot of attention in the agricultural industry to cover the labor shortage. Also, safer vegetables are required by peoples due to COVID-19 epidemic and radioactive pollution. In this paper, we propose an agricultural support system called VegeCareAI for agricultural workers. The proposed system supports vegetable classification , plant disease classification and insect pest classification to improve the crops’ productively. The support system can show the growth condition of vegetables. When there are some problems, the VegeCareAI presents information on how to deal with diseases and insect pests. From the results, we found that our proposed VegeCareAI tool has advantage for supporting several crops. For vegetable classification, our training data for 300 epochs predicted six kinds of vegetables correctly. For plant disease classification, for 400 epochs the accuracy is more than 96% accuracy for both potato and corn leaves. For insect pest classification, the accuracy of corn insect pests is more than 73%, but the results of different life cycles showed low classification accuracy , which present a future challenge.
Average popularityAverage popularity In bottom 99%Average influencePopularity: Citation-based measure reflecting the current impact.Average influence In bottom 99%Influence: Citation-based measure reflecting the total impact.add Add to ORCIDPlease grant OpenAIRE to access and update your ORCID works.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.
1 Research products, page 1 of 1
Loading
- Publication . Article . 2021Closed AccessAuthors:Makoto Ikeda; Natwadee Ruedeeniraman; Leonard Barolli;Makoto Ikeda; Natwadee Ruedeeniraman; Leonard Barolli;Publisher: Elsevier BV
Abstract In the field of agriculture, there are many individual micro businesses with low investment capacity and awareness of IT utilization, and it is difficult to obtain a return on investment . In recent years, edge computing and Artificial Intelligence (AI) technologies have attracted a lot of attention in the agricultural industry to cover the labor shortage. Also, safer vegetables are required by peoples due to COVID-19 epidemic and radioactive pollution. In this paper, we propose an agricultural support system called VegeCareAI for agricultural workers. The proposed system supports vegetable classification , plant disease classification and insect pest classification to improve the crops’ productively. The support system can show the growth condition of vegetables. When there are some problems, the VegeCareAI presents information on how to deal with diseases and insect pests. From the results, we found that our proposed VegeCareAI tool has advantage for supporting several crops. For vegetable classification, our training data for 300 epochs predicted six kinds of vegetables correctly. For plant disease classification, for 400 epochs the accuracy is more than 96% accuracy for both potato and corn leaves. For insect pest classification, the accuracy of corn insect pests is more than 73%, but the results of different life cycles showed low classification accuracy , which present a future challenge.
Average popularityAverage popularity In bottom 99%Average influencePopularity: Citation-based measure reflecting the current impact.Average influence In bottom 99%Influence: Citation-based measure reflecting the total impact.add Add to ORCIDPlease grant OpenAIRE to access and update your ORCID works.This Research product is the result of merged Research products in OpenAIRE.
You have already added works in your ORCID record related to the merged Research product.