Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

RSSI Estimation for Constrained Indoor Wireless Networks using ANN

Samrah Arif, M. Arif Khan, Sabih Ur Rehman

TL;DR

This paper tackles RSSI-based channel estimation for low-power IoT in indoor settings by introducing two ANN-based approaches: a Feature-based ANN that learns from environmental features and a Sequence-based ANN that uses selected RSSI sequences. Both models are trained and evaluated on a real indoor dataset collected with Waspmote devices under LoS/NLoS conditions, showing substantial accuracy gains over traditional methods and other DL models. The Feature-based model achieves an $MSE$ reduction of up to 88% and the Sequence-based model up to 97% relative to prior work, with the Sequence-based approach also offering lower computational overhead. The work demonstrates the practical potential of ANN-based RSSI estimation for LP-IoT deployments and outlines avenues for real-time, multi-environment applicability and scalability.

Abstract

In the expanding field of the Internet of Things (IoT), wireless channel estimation is a significant challenge. This is specifically true for low-power IoT (LP-IoT) communication, where efficiency and accuracy are extremely important. This research establishes two distinct LP-IoT wireless channel estimation models using Artificial Neural Networks (ANN): a Feature-based ANN model and a Sequence-based ANN model. Both models have been constructed to enhance LP-IoT communication by lowering the estimation error in the LP-IoT wireless channel. The Feature-based model aims to capture complex patterns of measured Received Signal Strength Indicator (RSSI) data using environmental characteristics. The Sequence-based approach utilises predetermined categorisation techniques to estimate the RSSI sequence of specifically selected environment characteristics. The findings demonstrate that our suggested approaches attain remarkable precision in channel estimation, with an improvement in MSE of $88.29\%$ of the Feature-based model and $97.46\%$ of the Sequence-based model over existing research. Additionally, the comparative analysis of these techniques with traditional and other Deep Learning (DL)-based techniques also highlights the superior performance of our developed models and their potential in real-world IoT applications.

RSSI Estimation for Constrained Indoor Wireless Networks using ANN

TL;DR

This paper tackles RSSI-based channel estimation for low-power IoT in indoor settings by introducing two ANN-based approaches: a Feature-based ANN that learns from environmental features and a Sequence-based ANN that uses selected RSSI sequences. Both models are trained and evaluated on a real indoor dataset collected with Waspmote devices under LoS/NLoS conditions, showing substantial accuracy gains over traditional methods and other DL models. The Feature-based model achieves an reduction of up to 88% and the Sequence-based model up to 97% relative to prior work, with the Sequence-based approach also offering lower computational overhead. The work demonstrates the practical potential of ANN-based RSSI estimation for LP-IoT deployments and outlines avenues for real-time, multi-environment applicability and scalability.

Abstract

In the expanding field of the Internet of Things (IoT), wireless channel estimation is a significant challenge. This is specifically true for low-power IoT (LP-IoT) communication, where efficiency and accuracy are extremely important. This research establishes two distinct LP-IoT wireless channel estimation models using Artificial Neural Networks (ANN): a Feature-based ANN model and a Sequence-based ANN model. Both models have been constructed to enhance LP-IoT communication by lowering the estimation error in the LP-IoT wireless channel. The Feature-based model aims to capture complex patterns of measured Received Signal Strength Indicator (RSSI) data using environmental characteristics. The Sequence-based approach utilises predetermined categorisation techniques to estimate the RSSI sequence of specifically selected environment characteristics. The findings demonstrate that our suggested approaches attain remarkable precision in channel estimation, with an improvement in MSE of of the Feature-based model and of the Sequence-based model over existing research. Additionally, the comparative analysis of these techniques with traditional and other Deep Learning (DL)-based techniques also highlights the superior performance of our developed models and their potential in real-world IoT applications.
Paper Structure (16 sections, 6 equations, 4 figures, 3 tables)

This paper contains 16 sections, 6 equations, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. System Model
  4. Problem Formulation
  5. ANN Model Development
  6. Feature-based ANN Model
  7. Phase I - Data Preparation
  8. Phase II - Model's Construction
  9. Phase III - Model Training
  10. Sequence-based ANN Model
  11. Phase I - Data Preparation
  12. Phase II - Model's Construction
  13. Phase III - Model Training
  14. Experimental Data Collection
  15. Performance Evaluation and Discussion
  16. ...and 1 more sections

Figures (4)

  • Figure 1: A block-based representation of the ANN-Based estimation process in LP-IoT systems.
  • Figure 2: Visual representation of ANN-based LP-IoT estimation models.
  • Figure 3: Visual representation of the results of Feature-based ANN model for LP-IoT wireless channel estimation.
  • Figure 4: Visual representation of the results of Sequence-based ANN model for LP-IoT wireless channel estimation.