Predicting types of failures in wireless sensor networks using an adaptive neuro-fuzzy inference system

Cheng Leong Lim, Cindy Goh, Asiya Khan, Aly Syed, Yun Li

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

In this paper, Adaptive Neuro-Fuzzy Interference System (ANFIS) technique is used to develop models to predict two conditions commonly found in a Wireless Sensor Network's deployment; these conditions are failure due to (i) poorly deployed environment and (ii) human movements. ANFIS models are trained using parameters obtained from actual ZigBee PRO nodes' Neighbour Table experimented under the influence of associated network challenges. These parameters are Mean RSSI, Standard Deviation RSSI, Average Coefficient of Variation RSSI and Neighbour Table Connectivity. The individual and combined effects of parameters are investigated in-depth. Results showed the mean RSSI is a critical parameter and the combination of mean RSSI, ACV RSSI and NTC produced the best prediction results (∼92%) for all ANFIS models.

LanguageEnglish
Title of host publication2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016
Number of pages7
DOIs
Publication statusPublished - 30 Nov 2016
Event12th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016 - New York, United States
Duration: 17 Oct 201619 Oct 2016

Conference

Conference12th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016
CountryUnited States
CityNew York
Period17/10/1619/10/16

Fingerprint

Fuzzy inference
Wireless sensor networks
Zigbee

Keywords

  • ANFIS
  • human movements
  • poor deployment
  • wireless sensor network
  • ZigBee PRO

Cite this

Lim, C. L., Goh, C., Khan, A., Syed, A., & Li, Y. (2016). Predicting types of failures in wireless sensor networks using an adaptive neuro-fuzzy inference system. In 2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016 [7763207] https://doi.org/10.1109/WiMOB.2016.7763207
Lim, Cheng Leong ; Goh, Cindy ; Khan, Asiya ; Syed, Aly ; Li, Yun. / Predicting types of failures in wireless sensor networks using an adaptive neuro-fuzzy inference system. 2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016. 2016.
@inproceedings{34ad867e89144334800b735f0d9fed22,
title = "Predicting types of failures in wireless sensor networks using an adaptive neuro-fuzzy inference system",
abstract = "In this paper, Adaptive Neuro-Fuzzy Interference System (ANFIS) technique is used to develop models to predict two conditions commonly found in a Wireless Sensor Network's deployment; these conditions are failure due to (i) poorly deployed environment and (ii) human movements. ANFIS models are trained using parameters obtained from actual ZigBee PRO nodes' Neighbour Table experimented under the influence of associated network challenges. These parameters are Mean RSSI, Standard Deviation RSSI, Average Coefficient of Variation RSSI and Neighbour Table Connectivity. The individual and combined effects of parameters are investigated in-depth. Results showed the mean RSSI is a critical parameter and the combination of mean RSSI, ACV RSSI and NTC produced the best prediction results (∼92{\%}) for all ANFIS models.",
keywords = "ANFIS, human movements, poor deployment, wireless sensor network, ZigBee PRO",
author = "Lim, {Cheng Leong} and Cindy Goh and Asiya Khan and Aly Syed and Yun Li",
year = "2016",
month = "11",
day = "30",
doi = "10.1109/WiMOB.2016.7763207",
language = "English",
booktitle = "2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016",

}

Lim, CL, Goh, C, Khan, A, Syed, A & Li, Y 2016, Predicting types of failures in wireless sensor networks using an adaptive neuro-fuzzy inference system. in 2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016., 7763207, 12th IEEE International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016, New York, United States, 17/10/16. https://doi.org/10.1109/WiMOB.2016.7763207

Predicting types of failures in wireless sensor networks using an adaptive neuro-fuzzy inference system. / Lim, Cheng Leong; Goh, Cindy; Khan, Asiya; Syed, Aly; Li, Yun.

2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016. 2016. 7763207.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Predicting types of failures in wireless sensor networks using an adaptive neuro-fuzzy inference system

AU - Lim, Cheng Leong

AU - Goh, Cindy

AU - Khan, Asiya

AU - Syed, Aly

AU - Li, Yun

PY - 2016/11/30

Y1 - 2016/11/30

N2 - In this paper, Adaptive Neuro-Fuzzy Interference System (ANFIS) technique is used to develop models to predict two conditions commonly found in a Wireless Sensor Network's deployment; these conditions are failure due to (i) poorly deployed environment and (ii) human movements. ANFIS models are trained using parameters obtained from actual ZigBee PRO nodes' Neighbour Table experimented under the influence of associated network challenges. These parameters are Mean RSSI, Standard Deviation RSSI, Average Coefficient of Variation RSSI and Neighbour Table Connectivity. The individual and combined effects of parameters are investigated in-depth. Results showed the mean RSSI is a critical parameter and the combination of mean RSSI, ACV RSSI and NTC produced the best prediction results (∼92%) for all ANFIS models.

AB - In this paper, Adaptive Neuro-Fuzzy Interference System (ANFIS) technique is used to develop models to predict two conditions commonly found in a Wireless Sensor Network's deployment; these conditions are failure due to (i) poorly deployed environment and (ii) human movements. ANFIS models are trained using parameters obtained from actual ZigBee PRO nodes' Neighbour Table experimented under the influence of associated network challenges. These parameters are Mean RSSI, Standard Deviation RSSI, Average Coefficient of Variation RSSI and Neighbour Table Connectivity. The individual and combined effects of parameters are investigated in-depth. Results showed the mean RSSI is a critical parameter and the combination of mean RSSI, ACV RSSI and NTC produced the best prediction results (∼92%) for all ANFIS models.

KW - ANFIS

KW - human movements

KW - poor deployment

KW - wireless sensor network

KW - ZigBee PRO

UR - http://www.scopus.com/inward/record.url?scp=85014150541&partnerID=8YFLogxK

U2 - 10.1109/WiMOB.2016.7763207

DO - 10.1109/WiMOB.2016.7763207

M3 - Conference contribution book

BT - 2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016

ER -

Lim CL, Goh C, Khan A, Syed A, Li Y. Predicting types of failures in wireless sensor networks using an adaptive neuro-fuzzy inference system. In 2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications, WiMob 2016. 2016. 7763207 https://doi.org/10.1109/WiMOB.2016.7763207