Decision-Tree Based Transceiver Selection for Medium Access Control in Wireless Sensor Networks

TY - GEN

T1 - Decision-Tree Based Transceiver Selection for Medium Access Control in Wireless Sensor Networks

AU - Chau, Arnold

AU - Dawson, John

AU - Mitchell, Paul D

N1 - © IEEE 2021. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy. Further copying may not be permitted; contact the publisher for details

PY - 2021/10/20

Y1 - 2021/10/20

N2 - The primary contribution of this paper lies in evaluating the potential benefits of using decision tree based transceiver selection algorithms for multi-hub wireless sensor networks (WSNs) to improve network performance andstability. The classification algorithm helps improve network throughput and reduce unnecessary transceiver handovers by considering multiple decision factors, without any additional hardware complexity at the sensor nodes. The algorithms allow the nodes to use information included in the reference messages from the transceivers, and the Receiver Signal Strength Indicator (RSSI) as decision factors. This paper demonstrates the effectiveness of decision tree based algorithms (Decision Tree and Random Forest) through simulation, and the resultsshow that this approach can enhance throughput and provideextra stability to the WSN in the scenarios considered,compared to traditional approach using distance or RSSI.

AB - The primary contribution of this paper lies in evaluating the potential benefits of using decision tree based transceiver selection algorithms for multi-hub wireless sensor networks (WSNs) to improve network performance andstability. The classification algorithm helps improve network throughput and reduce unnecessary transceiver handovers by considering multiple decision factors, without any additional hardware complexity at the sensor nodes. The algorithms allow the nodes to use information included in the reference messages from the transceivers, and the Receiver Signal Strength Indicator (RSSI) as decision factors. This paper demonstrates the effectiveness of decision tree based algorithms (Decision Tree and Random Forest) through simulation, and the resultsshow that this approach can enhance throughput and provideextra stability to the WSN in the scenarios considered,compared to traditional approach using distance or RSSI.

M3 - Conference contribution

BT - The 12th International Conference on ICT Convergence

CY - Ramada Plaza Hotel, Jeju Island, Korea

T2 - The 12th International Conference on ICT Convergence

Y2 - 20 October 2021 through 22 October 2021

ER -