Towards a Smart Fault Tolerant Indoor Localization System through Recurrent Neural Networks

Eduardo C. Carvalho; Bruno V. Ferreira; Geraldo P. R. Filho; Pedro H. Gomes; Gustavo M. Freitas; Patricia A. Vargas; Jó Ueyama; Gustavo Pessin

doi:10.1109/IJCNN.2019.8852007

Towards a Smart Fault Tolerant Indoor Localization System through Recurrent Neural Networks

Eduardo C. Carvalho
, Bruno V. Ferreira
, Geraldo P. R. Filho
, Pedro H. Gomes
, Gustavo M. Freitas
, Patricia A. Vargas
, Jó Ueyama
, Gustavo Pessin

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

11 Citations (Scopus)

152 Downloads (Pure)

Abstract

This paper proposes a fault-tolerant indoor localization system that employs Recurrent Neural Networks (RNNs) for the localization task. A decision module is designed to detect failures and this is responsible for the allocation of RNNs that are suitable for each situation. As well as the fault-tolerant system, several architectures and models for RNNs are exploited in the system: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM) and Simple RNN. The system uses as inputs a collection of Wi-Fi Received Signal Strength Indication (RSSI) signals, and the RNN classifies the position of an agent on the basis of this collection. A fault-tolerant mechanism has been designed to handle two types of failures: (i) momentary failure, and (ii) permanent failure. The results show that the RNNs are suitable for tackling the problem and that the whole system is reliable when employed for a series of failures.

Original language	English
Title of host publication	2019 International Joint Conference on Neural Networks (IJCNN)
Publisher	IEEE
ISBN (Electronic)	9781728119854
DOIs	https://doi.org/10.1109/IJCNN.2019.8852007
Publication status	Published - 30 Sept 2019
Event	2019 International Joint Conference on Neural Network - Budapest, Hungary Duration: 14 Jul 2019 → 19 Jul 2019

Publication series

Name	International Joint Conference on Neural Networks
Publisher	IEEE
ISSN (Electronic)	2161-4407

Conference

Conference	2019 International Joint Conference on Neural Network
Abbreviated title	IJCNN 2019
Country/Territory	Hungary
City	Budapest
Period	14/07/19 → 19/07/19

Keywords

Fault-Tolerance
Gated Recurrent Unit
Indoor Localization
Intelligent Control
Long Short-Term Memory

ASJC Scopus subject areas

Software
Artificial Intelligence

Access to Document

10.1109/IJCNN.2019.8852007

Download pdf
© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Accepted author manuscript, 503 KB

Cite this

Carvalho, E. C., Ferreira, B. V., Filho, G. P. R., Gomes, P. H., Freitas, G. M., Vargas, P. A., Ueyama, J., & Pessin, G. (2019). Towards a Smart Fault Tolerant Indoor Localization System through Recurrent Neural Networks. In 2019 International Joint Conference on Neural Networks (IJCNN) Article 8852007 (International Joint Conference on Neural Networks). IEEE. https://doi.org/10.1109/IJCNN.2019.8852007

@inproceedings{22c04782285c4cb3ae1f9d3abf93bfc3,

title = "Towards a Smart Fault Tolerant Indoor Localization System through Recurrent Neural Networks",

abstract = "This paper proposes a fault-tolerant indoor localization system that employs Recurrent Neural Networks (RNNs) for the localization task. A decision module is designed to detect failures and this is responsible for the allocation of RNNs that are suitable for each situation. As well as the fault-tolerant system, several architectures and models for RNNs are exploited in the system: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM) and Simple RNN. The system uses as inputs a collection of Wi-Fi Received Signal Strength Indication (RSSI) signals, and the RNN classifies the position of an agent on the basis of this collection. A fault-tolerant mechanism has been designed to handle two types of failures: (i) momentary failure, and (ii) permanent failure. The results show that the RNNs are suitable for tackling the problem and that the whole system is reliable when employed for a series of failures.",

keywords = "Fault-Tolerance, Gated Recurrent Unit, Indoor Localization, Intelligent Control, Long Short-Term Memory",

author = "Carvalho, \{Eduardo C.\} and Ferreira, \{Bruno V.\} and Filho, \{Geraldo P. R.\} and Gomes, \{Pedro H.\} and Freitas, \{Gustavo M.\} and Vargas, \{Patricia A.\} and J{\'o} Ueyama and Gustavo Pessin",

year = "2019",

month = sep,

day = "30",

doi = "10.1109/IJCNN.2019.8852007",

language = "English",

series = "International Joint Conference on Neural Networks",

publisher = "IEEE",

booktitle = "2019 International Joint Conference on Neural Networks (IJCNN)",

address = "United States",

note = "2019 International Joint Conference on Neural Network, IJCNN 2019 ; Conference date: 14-07-2019 Through 19-07-2019",

}

Carvalho, EC, Ferreira, BV, Filho, GPR, Gomes, PH, Freitas, GM, Vargas, PA, Ueyama, J & Pessin, G 2019, Towards a Smart Fault Tolerant Indoor Localization System through Recurrent Neural Networks. in 2019 International Joint Conference on Neural Networks (IJCNN)., 8852007, International Joint Conference on Neural Networks, IEEE, 2019 International Joint Conference on Neural Network, Budapest, Hungary, 14/07/19. https://doi.org/10.1109/IJCNN.2019.8852007

Towards a Smart Fault Tolerant Indoor Localization System through Recurrent Neural Networks. / Carvalho, Eduardo C.; Ferreira, Bruno V.; Filho, Geraldo P. R. et al.
2019 International Joint Conference on Neural Networks (IJCNN). IEEE, 2019. 8852007 (International Joint Conference on Neural Networks).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Towards a Smart Fault Tolerant Indoor Localization System through Recurrent Neural Networks

AU - Carvalho, Eduardo C.

AU - Ferreira, Bruno V.

AU - Filho, Geraldo P. R.

AU - Gomes, Pedro H.

AU - Freitas, Gustavo M.

AU - Vargas, Patricia A.

AU - Ueyama, Jó

AU - Pessin, Gustavo

PY - 2019/9/30

Y1 - 2019/9/30

N2 - This paper proposes a fault-tolerant indoor localization system that employs Recurrent Neural Networks (RNNs) for the localization task. A decision module is designed to detect failures and this is responsible for the allocation of RNNs that are suitable for each situation. As well as the fault-tolerant system, several architectures and models for RNNs are exploited in the system: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM) and Simple RNN. The system uses as inputs a collection of Wi-Fi Received Signal Strength Indication (RSSI) signals, and the RNN classifies the position of an agent on the basis of this collection. A fault-tolerant mechanism has been designed to handle two types of failures: (i) momentary failure, and (ii) permanent failure. The results show that the RNNs are suitable for tackling the problem and that the whole system is reliable when employed for a series of failures.

AB - This paper proposes a fault-tolerant indoor localization system that employs Recurrent Neural Networks (RNNs) for the localization task. A decision module is designed to detect failures and this is responsible for the allocation of RNNs that are suitable for each situation. As well as the fault-tolerant system, several architectures and models for RNNs are exploited in the system: Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM) and Simple RNN. The system uses as inputs a collection of Wi-Fi Received Signal Strength Indication (RSSI) signals, and the RNN classifies the position of an agent on the basis of this collection. A fault-tolerant mechanism has been designed to handle two types of failures: (i) momentary failure, and (ii) permanent failure. The results show that the RNNs are suitable for tackling the problem and that the whole system is reliable when employed for a series of failures.

KW - Fault-Tolerance

KW - Gated Recurrent Unit

KW - Indoor Localization

KW - Intelligent Control

KW - Long Short-Term Memory

UR - https://www.scopus.com/pages/publications/85073211732

U2 - 10.1109/IJCNN.2019.8852007

DO - 10.1109/IJCNN.2019.8852007

M3 - Conference contribution

AN - SCOPUS:85073211732

T3 - International Joint Conference on Neural Networks

BT - 2019 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

T2 - 2019 International Joint Conference on Neural Network

Y2 - 14 July 2019 through 19 July 2019

ER -

Towards a Smart Fault Tolerant Indoor Localization System through Recurrent Neural Networks

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this