About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Industrial Networks and Intelligent Systems. 9th EAI International Conference, INISCOM 2023, Ho Chi Minh City, Vietnam, August 2-3, 2023, Proceedings

Research Article

A Smart Agriculture Solution Includes Intelligent Irrigation and Security

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-47359-3_1,
        author={Tang Nguyen-Tan and Chien Dang-Ngoc and Quan Le-Trung},
        title={A Smart Agriculture Solution Includes Intelligent Irrigation and Security},
        proceedings={Industrial Networks and Intelligent Systems. 9th EAI International Conference, INISCOM 2023, Ho Chi Minh City, Vietnam, August 2-3, 2023, Proceedings},
        proceedings_a={INISCOM},
        year={2023},
        month={10},
        keywords={Smart Agricultural Time-series Forecasting Transformer IoT Security},
        doi={10.1007/978-3-031-47359-3_1}
    }
    
  • Tang Nguyen-Tan
    Chien Dang-Ngoc
    Quan Le-Trung
    Year: 2023
    A Smart Agriculture Solution Includes Intelligent Irrigation and Security
    INISCOM
    Springer
    DOI: 10.1007/978-3-031-47359-3_1
Tang Nguyen-Tan1, Chien Dang-Ngoc1, Quan Le-Trung1,*
  • 1: Faculty of Computer Networks and Communications
*Contact email: quanlt@uit.edu.vn

Abstract

One of the key roles of a smart agricultural system is irrigation, which is carried out automatically, optimally, and at each stage of the growth of each crop. The optimal soil moisture data for each plant at each stage of growth that have been stored in the database, along with two forecasts of the weather and the soil moisture level for the next hour, are incorporated to propose an autonomous irrigation solution in this paper. Two Transformer deep-learning models were used to train forecasts of the weather and soil moisture. The test results demonstrate that the Transformer model is able with the same accuracy of 91.41% on the weather forecast test set and 82.06% on the soil moisture forecast test set despite having 40.62% fewer training variables than the LSTM model. As an Internet of Things system, the smart agriculture system must be safeguarded against eavesdropping, attacks that spoof control commands, and machine learning models that are poisoned with false data. In this research, we have also proposed an end-to-end encryption and authentication solution using AES 256-bit, HMAC, along with a safe CRYSTALS-Kyber key exchange technique in the quantum age. The evaluation results show that the proposed solution can be deployed on IoT devices similar to Arduino, STM32, and Raspberry Pi 4.

Keywords
Smart Agricultural Time-series Forecasting Transformer IoT Security
Published
2023-10-31
Appears in
SpringerLink
http://dx.doi.org/10.1007/978-3-031-47359-3_1
Copyright © 2023–2025 ICST
EBSCOProQuestDBLPDOAJPortico
EAI Logo

About EAI

  • Who We Are
  • Leadership
  • Research Areas
  • Partners
  • Media Center

Community

  • Membership
  • Conference
  • Recognition
  • Sponsor Us

Publish with EAI

  • Publishing
  • Journals
  • Proceedings
  • Books
  • EUDL