A synthesis of machine learning and internet of things in developing autonomous fleets of heterogeneous unmanned aerial vehicles for enhancing the regenerative farming cycle

The use of Unmanned Aerial Vehicles (UAVs) for agricultural monitoring and management offers additional advantages over traditional methods, ranging from cost reduction to environmental protection, especially when they utilize Machine Learning (ML) methods, and Internet of Things (IoT). This article...

Full description

Saved in:
Bibliographic Details
Published in:Computing Vol. 106; no. 12; pp. 4167 - 4192
Main Authors: Almalki, Faris A., Angelides, Marios C.
Format: Journal Article
Language:English
Published: Vienna Springer Vienna 01.12.2024
Springer Nature B.V
Subjects:
Ant colony optimization
Antennas
Artificial Intelligence
Bit error rate
Computer Appl. in Administrative Data Processing
Computer Communication Networks
Computer Science
Deep learning
Density ratio
Distribution functions
Environmental management
Environmental protection
Farming
Information Systems Applications (incl.Internet)
Internet of Things
Machine learning
Mean square errors
MIMO communication
Normalized difference vegetative index
Power spectral density
Reflectance
Regular Paper
Signal strength
Software Engineering
Synchronism
Synthesis
Task scheduling
Unmanned aerial vehicles
Autonomous UAV fleet
Wireless communications
Regenerative farming
Machine learning
IoT
ISSN:0010-485X, 1436-5057
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The use of Unmanned Aerial Vehicles (UAVs) for agricultural monitoring and management offers additional advantages over traditional methods, ranging from cost reduction to environmental protection, especially when they utilize Machine Learning (ML) methods, and Internet of Things (IoT). This article presents an autonomous fleet of heterogeneous UAVs for use in regenerative farming the result of a synthesis of Deep Reinforcement Learning (DRL), Ant Colony Optimization (ACO) and IoT. The resulting aerial framework uses DRL for fleet autonomy and ACO for fleet synchronization and task scheduling inflight. A 5G Multiple Input Multiple Output-Long Range (MIMO-LoRa) antenna enhances data rate transmission and link reliability. The aerial framework, which has been originally prototyped as a simulation to test the concept, is now developed into a functional proof-of-concept of autonomous fleets of heterogeneous UAVs. For assessing performance, the paper uses Normalized Difference Vegetation Index (NDVI), Mean Squared Error (MSE) and Received Signal Strength Index (RSSI). The 5G MIMO-LoRa antenna produces improved results with four key performance indicators: Reflection Coefficient (S11), Cumulative Distribution Functions (CDF), Power Spectral Density Ratio (Eb/No), and Bit Error Rate (BER).
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0010-485X
1436-5057
DOI:10.1007/s00607-024-01347-1