If you prefer to download a single file with all the LARCC bibliography, you can find it here. One can also follow new publications by RSS.
In addition, you can also check the publications in the LARCC profile on Google Scholar .
2019 |
Scheer, Claudio; Guder, Larissa Deep Learning in Agriculture: A Systematic Literature Review Undergraduate Thesis Forthcoming Undergraduate Thesis, Forthcoming. Abstract | BibTeX | Tags: Agriculture, Deep learning, Literature review @misc{larcc:claudio_larissa:TCC:19, title = {Deep Learning in Agriculture: A Systematic Literature Review}, author = {Claudio Scheer and Larissa Guder}, year = {2019}, date = {2019-06-01}, address = {Três de Maio, RS, Brazil}, school = {Sociedade Educacional Três de Maio (SETREM)}, abstract = {With the growth of computational power, the deep learning algorithms have achieved remarkable results in several areas. Agriculture is one of the areas that are using these algorithms for the most varied domains. Therefore, this work presents a systematic literature review to consolidate the state-of-the-art about the use of deep learning applied to agricultural challenges. Papers published between January 2012 and April 2019 were considered. From the 819 papers found, 230 papers were classified. We evaluated the deep learning techniques used, crops covered, data sets used, deep learning and agriculture challenges, and among other important insights. The results have shown that deep learning is successfully used for several crops in agriculture. In the livestock branch, for example, most of the works achieved an accuracy above 95%. In total, 47.2% of the papers achieved an accuracy above 95%. Consequently, there is a lot of work to be done in the area of deep learning for agriculture. Our analysis are very important to support new research that seeks to apply deep learning in agriculture and highlight the research gaps.}, howpublished = {Undergraduate Thesis}, keywords = {Agriculture, Deep learning, Literature review}, pubstate = {forthcoming}, tppubtype = {misc} } With the growth of computational power, the deep learning algorithms have achieved remarkable results in several areas. Agriculture is one of the areas that are using these algorithms for the most varied domains. Therefore, this work presents a systematic literature review to consolidate the state-of-the-art about the use of deep learning applied to agricultural challenges. Papers published between January 2012 and April 2019 were considered. From the 819 papers found, 230 papers were classified. We evaluated the deep learning techniques used, crops covered, data sets used, deep learning and agriculture challenges, and among other important insights. The results have shown that deep learning is successfully used for several crops in agriculture. In the livestock branch, for example, most of the works achieved an accuracy above 95%. In total, 47.2% of the papers achieved an accuracy above 95%. Consequently, there is a lot of work to be done in the area of deep learning for agriculture. Our analysis are very important to support new research that seeks to apply deep learning in agriculture and highlight the research gaps. |
Allebrandt, Alisson; Schimidt, Diego Henrique Simplificando a Interpretação de Análise de Solo com Inteligência Artificial Undergraduate Thesis Undergraduate Thesis, 2019. Abstract | Links | BibTeX | Tags: Agriculture, Deep learning @misc{larcc:alisson_diego:TCC:19, title = {Simplificando a Interpretação de Análise de Solo com Inteligência Artificial}, author = {Alisson Allebrandt and Diego Henrique Schimidt}, url = {https://larcc.setrem.com.br/wp-content/uploads/2020/08/TCC_SETREM__Alisson_e_Diego_.pdf}, year = {2019}, date = {2019-06-01}, address = {Três de Maio, RS, Brazil}, school = {Sociedade Educacional Três de Maio (SETREM)}, abstract = {One of the aspects that interferes in a good production and agricultural crop is the soil. Its conservation through the correct application of nutrients and fertilization is of paramount importance. Based on this scenario and with the accelerated growth of agricultural technology, an application capable of interpreting the soil analyzes that are generated by soil laboratories resulting from a sample of land collected by the rural producer is proposed. After the analysis, the idea is to suggest the appropriate amount of fertilizers and agricultural nutrients that the producer should apply in his crop. Currently this recommendation process is still manually done by agronomists or desktop software that uses liming and fertilization manuals as the basis for recommendation calculations. This work aims to use machine learning technology, in which more than 30,000 soil analysis records were extracted from the SETREM soil laboratory. Based on the study and analysis of these data, a solution was proposed aimed at creating a training model and a generic way to receive soil analyzes, normalize them, interpret, generate recommendations, and save to a single database so that this data can be used for BI and mining in the future. Therefore, it was developed a mobile application capable of interpreting a photo taken from the soil analysis and then transform the values of the chemical elements present in the image into digital information, which can be consulted and shared in a faster way among the interested people, in addition to starting with the process of feeding a database with information on soil analysis. We obtained results regarding the current need to still use manuals of liming and fertilization as well as the application of artificial intelligence in front of this area. Also, we studied tools of image processing and interpretation of characters with the use of Machine Learning, such as Tesseract OCR and Google Vision, which resulted in a comparison of the two interpretation tools tested.}, howpublished = {Undergraduate Thesis}, keywords = {Agriculture, Deep learning}, pubstate = {published}, tppubtype = {misc} } One of the aspects that interferes in a good production and agricultural crop is the soil. Its conservation through the correct application of nutrients and fertilization is of paramount importance. Based on this scenario and with the accelerated growth of agricultural technology, an application capable of interpreting the soil analyzes that are generated by soil laboratories resulting from a sample of land collected by the rural producer is proposed. After the analysis, the idea is to suggest the appropriate amount of fertilizers and agricultural nutrients that the producer should apply in his crop. Currently this recommendation process is still manually done by agronomists or desktop software that uses liming and fertilization manuals as the basis for recommendation calculations. This work aims to use machine learning technology, in which more than 30,000 soil analysis records were extracted from the SETREM soil laboratory. Based on the study and analysis of these data, a solution was proposed aimed at creating a training model and a generic way to receive soil analyzes, normalize them, interpret, generate recommendations, and save to a single database so that this data can be used for BI and mining in the future. Therefore, it was developed a mobile application capable of interpreting a photo taken from the soil analysis and then transform the values of the chemical elements present in the image into digital information, which can be consulted and shared in a faster way among the interested people, in addition to starting with the process of feeding a database with information on soil analysis. We obtained results regarding the current need to still use manuals of liming and fertilization as well as the application of artificial intelligence in front of this area. Also, we studied tools of image processing and interpretation of characters with the use of Machine Learning, such as Tesseract OCR and Google Vision, which resulted in a comparison of the two interpretation tools tested. |