Applying an Adaptive Neuro-Fuzzy Inference System to Path Loss Prediction in a Ruby Mango Plantation
Issued Date
2023-10-01
Resource Type
eISSN
22242708
Scopus ID
2-s2.0-85175300719
Journal Title
Journal of Sensor and Actuator Networks
Volume
12
Issue
5
Rights Holder(s)
SCOPUS
Bibliographic Citation
Journal of Sensor and Actuator Networks Vol.12 No.5 (2023)
Suggested Citation
Phaiboon S., Phokharatkul P. Applying an Adaptive Neuro-Fuzzy Inference System to Path Loss Prediction in a Ruby Mango Plantation. Journal of Sensor and Actuator Networks Vol.12 No.5 (2023). doi:10.3390/jsan12050071 Retrieved from: https://repository.li.mahidol.ac.th/handle/20.500.14594/90959
Title
Applying an Adaptive Neuro-Fuzzy Inference System to Path Loss Prediction in a Ruby Mango Plantation
Author(s)
Author's Affiliation
Other Contributor(s)
Abstract
The application of wireless sensor networks (WSNs) in smart agriculture requires accurate path loss prediction to determine the coverage area and system capacity. However, fast fading from environment changes, such as leaf movement, unsymmetrical tree structures and near-ground effects, makes the path loss prediction inaccurate. Artificial intelligence (AI) technologies can be used to facilitate this task for training the real environments. In this study, we performed path loss measurements in a Ruby mango plantation at a frequency of 433 MHz. Then, an adaptive neuro-fuzzy inference system (ANFIS) was applied to path loss prediction. The ANFIS required two inputs for the path loss prediction: the distance and antenna height corresponding to the tree level (i.e., trunk and bottom, middle, and top canopies). We evaluated the performance of the ANFIS by comparing it with empirical path loss models widely used in the literature. The ANFIS demonstrated a superior prediction accuracy with high sensitivity compared to the empirical models, although the performance was affected by the tree level.