An adaptive neuro-fuzzy propagation model for LoRaWAN

Salaheddin Hosseinzadeh, Hadi Larijani, Krystyna Curtis, Andrew Wixted

Research output: Contribution to journalArticle

4 Downloads (Pure)

Abstract

This article proposes an adaptive-network-based fuzzy inference system (ANFIS) model for accurate estimation of signal propagation using LoRaWAN. By using ANFIS, the basic knowledge of propagation is embedded into the proposed model. This reduces the training complexity of artificial neural network (ANN)-based models. Therefore, the size of the training dataset is reduced by 70%
compared to an ANN model. The proposed model consists of an efficient clustering method to identify the optimum number of the fuzzy nodes to avoid overfitting, and a hybrid training algorithm to train and optimize the ANFIS parameters. Finally, the proposed model is benchmarked with extensive
practical data, where superior accuracy is achieved compared to deterministic models, and better generalization is attained compared to ANN models. The proposed model outperforms the nondeterministic models in terms of accuracy, has the flexibility to account for new modeling parameters, is easier to use as it does not require a model for propagation environment, is resistant to data collection inaccuracies and uncertain environmental information, has excellent
generalization capability, and features a knowledge-based implementation that alleviates the training process.
This work will facilitate network planning and propagation prediction in complex scenarios.
Original languageEnglish
Number of pages11
JournalApplied System Innovation
Volume2
Issue number1
DOIs
Publication statusPublished - 18 Mar 2019

Fingerprint

Fuzzy inference
Neural networks
Planning

Keywords

  • propagation modeling
  • adaptive-network-based fuzzy system
  • LoRa & LoRaWAN
  • radio wave propagation
  • artificial neural networks
  • subtracting clustering

Cite this

Hosseinzadeh, Salaheddin ; Larijani, Hadi ; Curtis, Krystyna ; Wixted, Andrew. / An adaptive neuro-fuzzy propagation model for LoRaWAN. In: Applied System Innovation . 2019 ; Vol. 2, No. 1.
@article{e03e6dd3807a48b7aacc770aedaed080,
title = "An adaptive neuro-fuzzy propagation model for LoRaWAN",
abstract = "This article proposes an adaptive-network-based fuzzy inference system (ANFIS) model for accurate estimation of signal propagation using LoRaWAN. By using ANFIS, the basic knowledge of propagation is embedded into the proposed model. This reduces the training complexity of artificial neural network (ANN)-based models. Therefore, the size of the training dataset is reduced by 70{\%} compared to an ANN model. The proposed model consists of an efficient clustering method to identify the optimum number of the fuzzy nodes to avoid overfitting, and a hybrid training algorithm to train and optimize the ANFIS parameters. Finally, the proposed model is benchmarked with extensive practical data, where superior accuracy is achieved compared to deterministic models, and better generalization is attained compared to ANN models. The proposed model outperforms the nondeterministic models in terms of accuracy, has the flexibility to account for new modeling parameters, is easier to use as it does not require a model for propagation environment, is resistant to data collection inaccuracies and uncertain environmental information, has excellent generalization capability, and features a knowledge-based implementation that alleviates the training process.This work will facilitate network planning and propagation prediction in complex scenarios.",
keywords = "propagation modeling, adaptive-network-based fuzzy system, LoRa & LoRaWAN, radio wave propagation, artificial neural networks, subtracting clustering",
author = "Salaheddin Hosseinzadeh and Hadi Larijani and Krystyna Curtis and Andrew Wixted",
note = "Acceptance from webpage",
year = "2019",
month = "3",
day = "18",
doi = "10.3390/asi2010010",
language = "English",
volume = "2",
number = "1",

}

Hosseinzadeh, S, Larijani, H, Curtis, K & Wixted, A 2019, 'An adaptive neuro-fuzzy propagation model for LoRaWAN', Applied System Innovation , vol. 2, no. 1. https://doi.org/10.3390/asi2010010

An adaptive neuro-fuzzy propagation model for LoRaWAN. / Hosseinzadeh, Salaheddin; Larijani, Hadi; Curtis, Krystyna; Wixted, Andrew.

In: Applied System Innovation , Vol. 2, No. 1, 18.03.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - An adaptive neuro-fuzzy propagation model for LoRaWAN

AU - Hosseinzadeh, Salaheddin

AU - Larijani, Hadi

AU - Curtis, Krystyna

AU - Wixted, Andrew

N1 - Acceptance from webpage

PY - 2019/3/18

Y1 - 2019/3/18

N2 - This article proposes an adaptive-network-based fuzzy inference system (ANFIS) model for accurate estimation of signal propagation using LoRaWAN. By using ANFIS, the basic knowledge of propagation is embedded into the proposed model. This reduces the training complexity of artificial neural network (ANN)-based models. Therefore, the size of the training dataset is reduced by 70% compared to an ANN model. The proposed model consists of an efficient clustering method to identify the optimum number of the fuzzy nodes to avoid overfitting, and a hybrid training algorithm to train and optimize the ANFIS parameters. Finally, the proposed model is benchmarked with extensive practical data, where superior accuracy is achieved compared to deterministic models, and better generalization is attained compared to ANN models. The proposed model outperforms the nondeterministic models in terms of accuracy, has the flexibility to account for new modeling parameters, is easier to use as it does not require a model for propagation environment, is resistant to data collection inaccuracies and uncertain environmental information, has excellent generalization capability, and features a knowledge-based implementation that alleviates the training process.This work will facilitate network planning and propagation prediction in complex scenarios.

AB - This article proposes an adaptive-network-based fuzzy inference system (ANFIS) model for accurate estimation of signal propagation using LoRaWAN. By using ANFIS, the basic knowledge of propagation is embedded into the proposed model. This reduces the training complexity of artificial neural network (ANN)-based models. Therefore, the size of the training dataset is reduced by 70% compared to an ANN model. The proposed model consists of an efficient clustering method to identify the optimum number of the fuzzy nodes to avoid overfitting, and a hybrid training algorithm to train and optimize the ANFIS parameters. Finally, the proposed model is benchmarked with extensive practical data, where superior accuracy is achieved compared to deterministic models, and better generalization is attained compared to ANN models. The proposed model outperforms the nondeterministic models in terms of accuracy, has the flexibility to account for new modeling parameters, is easier to use as it does not require a model for propagation environment, is resistant to data collection inaccuracies and uncertain environmental information, has excellent generalization capability, and features a knowledge-based implementation that alleviates the training process.This work will facilitate network planning and propagation prediction in complex scenarios.

KW - propagation modeling

KW - adaptive-network-based fuzzy system

KW - LoRa & LoRaWAN

KW - radio wave propagation

KW - artificial neural networks

KW - subtracting clustering

U2 - 10.3390/asi2010010

DO - 10.3390/asi2010010

M3 - Article

VL - 2

IS - 1

ER -

Hosseinzadeh S, Larijani H, Curtis K, Wixted A. An adaptive neuro-fuzzy propagation model for LoRaWAN. Applied System Innovation . 2019 Mar 18;2(1). https://doi.org/10.3390/asi2010010