• E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2024

    6.713

    Impact Factor 2023

    6.464

  • E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2024

    6.713

    Impact Factor 2023

    6.464

  • E-ISSN:

    2454-9584

    P-ISSN

    2454-8111

    Impact Factor 2024

    6.713

    Impact Factor 2023

    6.464

INTERNATIONAL JOURNAL OF INVENTIONS IN ENGINEERING & SCIENCE TECHNOLOGY

International Peer Reviewed (Refereed), Open Access Research Journal
(By Aryavart International University, India)

Paper Details

Developing a Smart integrated Model for an Autonomous Irrigation System Design Based on K-Nearest Neighbour (KNN) by Leveraging the Tools and Techniques of Machine Learning (ML) and Internet of Things (IoT)

Ishant Sangwan

Class X student, Venkateshwar Global School

58 - 65 Vol. 9, Issue 1, Jan-Dec, 2023
Receiving Date: 2023-02-04;    Acceptance Date: 2023-02-21;    Publication Date: 2023-04-22
Download PDF

Abstract

Efficient irrigation is pivotal for water conservation and agricultural sustainability. This paper describes the design, implementation, and evaluation of a low-cost, real-time smart irrigation system combining Internet of Things (IoT) hardware with a K-Nearest Neighbors (KNN) machine learning model. Soil moisture and environmental data are collected via capacitive sensors, DHT22 modules, and ESP8266 nodes. Collected data are processed locally to decide irrigation actions every 10 minutes. Field trials conducted over four weeks on a 100 m² vegetable plot compared KNN’s performance with Random Forest (RF) and Support Vector Machine (SVM). KNN achieved 78 % accuracy, moderate precision (0.75) and recall (0.80), outperforming some literature reports, while RF scored 82 % and SVM 76 %. Comparative analysis highlights KNN’s low computational overhead, simplicity, and adequate performance for small-scale applications. Cost and energy analysis suggest the KNN-ESP8266 system is affordable (~USD 50) and energy-efficient, making it well-suited for resource-constrained environments. Limitations include sensitivity to noisy sensor data and absence of weather forecasting integration. Future work will focus on adaptive K selection, cloud-edge orchestration, and integration of dynamic weather inputs to improve precision and scalability.

    References

  1. Arora, P., & Sharma, V. (2021). Smart irrigation using Arduino and GSM. IEEE SmartTech. https://doi.org/10.1109/SmartTech52427
  2. Food and Agriculture Organization (FAO). (2019). Water use in agriculture. https://energypedia.info/wiki/Water_Use_in_Agriculture
  3. International Conference on Contemporary Computing and Informatics (IC3I). (2022). IoT- and ML-based irrigation system using KNN algorithm. Proceedings of the 5th IC3I. https://doi.org/10.1109/IC3I56241.2022.10072613
  4. Rahman, Z., [et al.]. (2020). LoRaWAN enabled IoT irrigation system. Sensors, *20*(4), 1058. https://doi.org/10.3390/s20041058
Back

Disclaimer: Indexing of published papers is subject to the evaluation and acceptance criteria of the respective indexing agencies. While we strive to maintain high academic and editorial standards, International Journal of Inventions in Engineering & Science Technology does not guarantee the indexing of any published paper. Acceptance and inclusion in indexing databases are determined by the quality, originality, and relevance of the paper, and are at the sole discretion of the indexing bodies.