IoT monitoring system for early detection of agricultural pests and diseases

Ntihemuka Materne, Masahiro Inoue

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Technological revolution in farming has been led by advances in sensing technologies. Nowadays the ability of applying the state of the art related to Internet of Things (IoT) is intensely increasing however, the development of daily long-distance agricultural systems is still in its early stage. As agricultural sector continues to be suffering with climate changes, the current challenges of the less favorable climatic conditions thrives the greater risks of transboundary plant pests and diseases; which affect crops production, as well as threatening food security and some significant losses to the farmers. In this research we have combined the sensors devices using wireless sensors networks(WSN), to build a farmland environmental monitoring platform that can simultaneously monitor eight important environmental parameters identified as high correlation to boom pests and diseases in plantation. The overall structure of the system enabled real-time monitoring and acquisition of the huge amount of data on daily basis. Due to this reason, we have researched insight of these collected data using machine learning technique through the algorithms like KNN, Random Forest, Logistic Regression and Linear Regression. The objective of this paper is to do an experiment on benefit of using IoT system in farmland for data collection and analysis for identifying a prediction model which can be used for predicting outbreaks of plantation diseases with better accuracy.

Original languageEnglish
Title of host publicationProceedings - 12th SEATUC Symposium, SEATUC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538650943
DOIs
Publication statusPublished - 2018 Mar 1
Event12th South East Asian Technical University Consortium Sysmposium, SEATUC 2018 - Yogyakarta, Indonesia
Duration: 2018 Mar 122018 Mar 13

Publication series

NameProceedings - 12th SEATUC Symposium, SEATUC 2018

Conference

Conference12th South East Asian Technical University Consortium Sysmposium, SEATUC 2018
CountryIndonesia
CityYogyakarta
Period18/3/1218/3/13

Fingerprint

Monitoring
Real time systems
Linear regression
Climate change
Crops
Learning systems
Logistics
Wireless sensor networks
Sensors
Internet of things
Experiments

Keywords

  • Environment paramters
  • IoT
  • Machine learning
  • Pests and diseases

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Energy Engineering and Power Technology
  • Industrial and Manufacturing Engineering
  • Control and Optimization

Cite this

Materne, N., & Inoue, M. (2018). IoT monitoring system for early detection of agricultural pests and diseases. In Proceedings - 12th SEATUC Symposium, SEATUC 2018 [8788860] (Proceedings - 12th SEATUC Symposium, SEATUC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SEATUC.2018.8788860

IoT monitoring system for early detection of agricultural pests and diseases. / Materne, Ntihemuka; Inoue, Masahiro.

Proceedings - 12th SEATUC Symposium, SEATUC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. 8788860 (Proceedings - 12th SEATUC Symposium, SEATUC 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Materne, N & Inoue, M 2018, IoT monitoring system for early detection of agricultural pests and diseases. in Proceedings - 12th SEATUC Symposium, SEATUC 2018., 8788860, Proceedings - 12th SEATUC Symposium, SEATUC 2018, Institute of Electrical and Electronics Engineers Inc., 12th South East Asian Technical University Consortium Sysmposium, SEATUC 2018, Yogyakarta, Indonesia, 18/3/12. https://doi.org/10.1109/SEATUC.2018.8788860
Materne N, Inoue M. IoT monitoring system for early detection of agricultural pests and diseases. In Proceedings - 12th SEATUC Symposium, SEATUC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8788860. (Proceedings - 12th SEATUC Symposium, SEATUC 2018). https://doi.org/10.1109/SEATUC.2018.8788860
Materne, Ntihemuka ; Inoue, Masahiro. / IoT monitoring system for early detection of agricultural pests and diseases. Proceedings - 12th SEATUC Symposium, SEATUC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. (Proceedings - 12th SEATUC Symposium, SEATUC 2018).
@inproceedings{426345719b5246ae8b1bcc84e5b4a2e5,
title = "IoT monitoring system for early detection of agricultural pests and diseases",
abstract = "Technological revolution in farming has been led by advances in sensing technologies. Nowadays the ability of applying the state of the art related to Internet of Things (IoT) is intensely increasing however, the development of daily long-distance agricultural systems is still in its early stage. As agricultural sector continues to be suffering with climate changes, the current challenges of the less favorable climatic conditions thrives the greater risks of transboundary plant pests and diseases; which affect crops production, as well as threatening food security and some significant losses to the farmers. In this research we have combined the sensors devices using wireless sensors networks(WSN), to build a farmland environmental monitoring platform that can simultaneously monitor eight important environmental parameters identified as high correlation to boom pests and diseases in plantation. The overall structure of the system enabled real-time monitoring and acquisition of the huge amount of data on daily basis. Due to this reason, we have researched insight of these collected data using machine learning technique through the algorithms like KNN, Random Forest, Logistic Regression and Linear Regression. The objective of this paper is to do an experiment on benefit of using IoT system in farmland for data collection and analysis for identifying a prediction model which can be used for predicting outbreaks of plantation diseases with better accuracy.",
keywords = "Environment paramters, IoT, Machine learning, Pests and diseases",
author = "Ntihemuka Materne and Masahiro Inoue",
year = "2018",
month = "3",
day = "1",
doi = "10.1109/SEATUC.2018.8788860",
language = "English",
series = "Proceedings - 12th SEATUC Symposium, SEATUC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings - 12th SEATUC Symposium, SEATUC 2018",

}

TY - GEN

T1 - IoT monitoring system for early detection of agricultural pests and diseases

AU - Materne, Ntihemuka

AU - Inoue, Masahiro

PY - 2018/3/1

Y1 - 2018/3/1

N2 - Technological revolution in farming has been led by advances in sensing technologies. Nowadays the ability of applying the state of the art related to Internet of Things (IoT) is intensely increasing however, the development of daily long-distance agricultural systems is still in its early stage. As agricultural sector continues to be suffering with climate changes, the current challenges of the less favorable climatic conditions thrives the greater risks of transboundary plant pests and diseases; which affect crops production, as well as threatening food security and some significant losses to the farmers. In this research we have combined the sensors devices using wireless sensors networks(WSN), to build a farmland environmental monitoring platform that can simultaneously monitor eight important environmental parameters identified as high correlation to boom pests and diseases in plantation. The overall structure of the system enabled real-time monitoring and acquisition of the huge amount of data on daily basis. Due to this reason, we have researched insight of these collected data using machine learning technique through the algorithms like KNN, Random Forest, Logistic Regression and Linear Regression. The objective of this paper is to do an experiment on benefit of using IoT system in farmland for data collection and analysis for identifying a prediction model which can be used for predicting outbreaks of plantation diseases with better accuracy.

AB - Technological revolution in farming has been led by advances in sensing technologies. Nowadays the ability of applying the state of the art related to Internet of Things (IoT) is intensely increasing however, the development of daily long-distance agricultural systems is still in its early stage. As agricultural sector continues to be suffering with climate changes, the current challenges of the less favorable climatic conditions thrives the greater risks of transboundary plant pests and diseases; which affect crops production, as well as threatening food security and some significant losses to the farmers. In this research we have combined the sensors devices using wireless sensors networks(WSN), to build a farmland environmental monitoring platform that can simultaneously monitor eight important environmental parameters identified as high correlation to boom pests and diseases in plantation. The overall structure of the system enabled real-time monitoring and acquisition of the huge amount of data on daily basis. Due to this reason, we have researched insight of these collected data using machine learning technique through the algorithms like KNN, Random Forest, Logistic Regression and Linear Regression. The objective of this paper is to do an experiment on benefit of using IoT system in farmland for data collection and analysis for identifying a prediction model which can be used for predicting outbreaks of plantation diseases with better accuracy.

KW - Environment paramters

KW - IoT

KW - Machine learning

KW - Pests and diseases

UR - http://www.scopus.com/inward/record.url?scp=85071576264&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85071576264&partnerID=8YFLogxK

U2 - 10.1109/SEATUC.2018.8788860

DO - 10.1109/SEATUC.2018.8788860

M3 - Conference contribution

AN - SCOPUS:85071576264

T3 - Proceedings - 12th SEATUC Symposium, SEATUC 2018

BT - Proceedings - 12th SEATUC Symposium, SEATUC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -