000136050 001__ 136050
000136050 005__ 20240711103551.0
000136050 0247_ $$2doi$$a10.1016/j.compag.2018.05.007
000136050 0248_ $$2sideral$$a106404
000136050 037__ $$aART-2018-106404
000136050 041__ $$aeng
000136050 100__ $$0(orcid)0000-0003-2733-680X$$aEspejo-Garcia, Borja$$uUniversidad de Zaragoza
000136050 245__ $$aMachine learning for automatic rule classification of agricultural regulations: A case study in Spain
000136050 260__ $$c2018
000136050 5060_ $$aAccess copy available to the general public$$fUnrestricted
000136050 5203_ $$aCurrently, pest management practices require modern equipment and the use of complex information, such as regulations and guidelines. The complexity of regulations is the root cause of the emergence of automated solutions for compliance assessment by translating regulations into sets of machine-processable rules that can be run by specialized modules of farm management information systems (FMIS). However, the manual translation of rules is prohibitively costly, and therefore, this translation should be carried out with the support of artificial intelligence techniques. In this paper, we use the official Spanish phytosanitary products registry to empirically evaluate the performance of four popular machine learning algorithms in the task of correctly classifying pesticide regulations as prohibitions or obligations. Moreover, we also evaluate how to improve the performance of the algorithms in the preprocessing of the texts with natural language processing techniques. Finally, due to the specific characteristics of the texts found in pesticide regulations, resampling techniques are also evaluated. Experiments show that the combination of the machine learning algorithm Logic regression, the natural language technique part-of-speech tagging and the resampling technique Tomek links is the best performing approach, with an F1 score of 68.8%, a precision of 84.46% and a recall of 60%. The experimental results are promising, and they show that this approach can be applied to develop a computer-aided tool for transforming textual pesticide regulations into machine-processable rules. To the best of our knowledge, this is the first study that evaluates the use of artificial intelligence methods for the automatic translation of agricultural regulations into machine-processable representations.
000136050 536__ $$9info:eu-repo/grantAgreement/ES/MINECO/RTC-2016-4790-2$$9info:eu-repo/grantAgreement/ES/MINECO/TIN2017-88002-R
000136050 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
000136050 590__ $$a3.171$$b2018
000136050 591__ $$aAGRICULTURE, MULTIDISCIPLINARY$$b5 / 56 = 0.089$$c2018$$dQ1$$eT1
000136050 591__ $$aCOMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS$$b31 / 106 = 0.292$$c2018$$dQ2$$eT1
000136050 592__ $$a0.95$$b2018
000136050 593__ $$aAgronomy and Crop Science$$c2018$$dQ1
000136050 593__ $$aAnimal Science and Zoology$$c2018$$dQ1
000136050 593__ $$aHorticulture$$c2018$$dQ1
000136050 593__ $$aForestry$$c2018$$dQ1
000136050 593__ $$aComputer Science Applications$$c2018$$dQ1
000136050 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000136050 700__ $$aMartinez-Guanter, Jorge
000136050 700__ $$aPérez-Ruiz, Manuel
000136050 700__ $$0(orcid)0000-0001-6491-7430$$aLopez-Pellicer, Francisco J.$$uUniversidad de Zaragoza
000136050 700__ $$0(orcid)0000-0002-6557-2494$$aZarazaga-Soria, F. Javier$$uUniversidad de Zaragoza
000136050 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000136050 773__ $$g150 (2018), 343-352$$pComput. electron. agric.$$tComputers and Electronics in Agriculture$$x0168-1699
000136050 8564_ $$s4169335$$uhttps://zaguan.unizar.es/record/136050/files/texto_completo.pdf$$yPostprint
000136050 8564_ $$s1663392$$uhttps://zaguan.unizar.es/record/136050/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint
000136050 909CO $$ooai:zaguan.unizar.es:136050$$particulos$$pdriver
000136050 951__ $$a2024-07-11-08:36:50
000136050 980__ $$aARTICLE