Skip to main content
2015 23rd Telecommunications Forum, TELFOR 20158 January 2016, Article number 7377613, Pages 910-91323rd Telecommunications Forum, TELFOR 2015; Sava CenterBelgrade; Serbia; 24 November 2015 through 26 November 2015; Category numberCFP1598P-CDR; Code 118995

Data mining model for early fruit diseases detection(Conference Paper)

  Save all to author list
  • aFaculty of Technical Science Kosovska Mitrovica, University of Pristina, Kneza Miloša 7, Kosovska Mitrovica, 38220, Serbia
  • bFaculty of Informatics and Computing, Singidunum University, Danijelova 32, Belgrade, 11000, Serbia

Abstract

Automatic methods for an early detection of plant diseases could be vital for precise fruit protection. Traditionally the agriculture expert's knowledge is descriptive and experiment based, therefore it is difficult to describe it mathematically and subsequently build decision system which can replace it. Key parameters of decision based fruit protection system could differ for classes of plants and diseases. However, such systems are very rare and very complex, and in many cases designed just for one plant class. For effective diseases protection of fruit, meteorological data and data about the disease appearance are the most important. In this paper authors propose one idea for data mining based system for detection of possible fruit infection. For this purpose, different types of data mining techniques were evaluated on unique data sets. © 2015 IEEE.

Author keywords

Artificial neural networksClassificationData miningDiseases predictionK-Means

Indexed keywords

Engineering controlled terms:Classification (of information)FruitsMeteorologyNeural networks
Engineering uncontrolled termsAutomatic methodData mining modelsDecision systemsDecision-basedK-meansMeteorological dataPlant diseaseProtection systems
Engineering main heading:Data mining
  • ISBN: 978-150900054-8
  • Source Type: Conference Proceeding
  • Original language: English
  • DOI: 10.1109/TELFOR.2015.7377613
  • Document Type: Conference Paper
  • Sponsors: Ericsson,et al.,Huawei Technologies doo,Telekom SRBIJA,University of Belgrade, School of Electrical Engineering (ETF),VLATACOM d.o.o.
  • Publisher: Institute of Electrical and Electronics Engineers Inc.

  Ilic, M.; Faculty of Technical Science Kosovska Mitrovica, University of Pristina, Kneza Miloša 7, Kosovska Mitrovica, Serbia;
© Copyright 2019 Elsevier B.V., All rights reserved.

Cited by 11 documents

Niaz, A.A. , Ashraf, R. , Mahmood, T.
An efficient smart phone application for wheat crop diseases detection using advanced machine learning
(2025) PLoS ONE
Asif Jamal, G.A. , Kalaiselvi, K. , Sathiyavathi, V.
Crop Disease Prediction Using Classification Techniques
(2023) Proceedings of the 2nd IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCAI 2023
Qassir, S.A.
PFDINN: Comparison between three back-propagation algorithms for pear fruit disease identification
(2021) Iraqi Journal of Science
View details of all 11 citations
Inform me when this document is cited in Scopus:
Set citation alert Set citation feed
{"topic":{"name":"Neural Network; Support Vector Machine; Machine Learning","id":11136,"uri":"Topic/11136","prominencePercentile":98.299126,"prominencePercentileString":"98.299","overallScholarlyOutput":0},"dig":"65e1c2767a01bd19b460c7fee748462e9f9333311c154e9982dd80152c21b683"}

SciVal Topic Prominence

Topic:
Prominence percentile: