Abstract
Individuals, with mental or physical disabilities, need that others know their localization within an indoor environment in order to receive adequate healthcare. This paper presents an indoor positioning system based on a received signal strength indicator (RSSI) sensor network, where positions are determined by an artificial neural network (ANN) from the received signals. This work investigates the effect of using the past and present data from the other sensors to estimate one missing signal, using a second ANN, and using it as a virtual sensor in the main ANN. For the study, a database was built in a typical residential environment with one transmitter and four receivers. The research studies the effect on the performance caused by the failure of one sensor showing the gains of using virtual signals, as well as a comparison of this virtual data with the measured data. The ANNs are trained with the cross-validation method to avoid overfitting. The selected number of neurons in the inner layer, for each case, was the complexity capable of presenting at least the same performance of an oversized ANN, which was also trained without overfitting. The system developed achieved a considerable efficiency, being able to reproduce the position of the individual with less than 0.36 m of average error when all four receivers were working properly. However, this average error can increase to 0.52–0.91 m when a receiver is at failure, depending on which one fails. Nevertheless, the use of the proposed virtual sensor can diminish about 0.2 m of average error in case of failure. Therefore, the use of virtual data proved to be a feature capable of improving positioning when a sensor fails, in relation to the alternative of performing this positioning without this sensor nor its corresponding virtual signal.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Wyffels J, Goemaere JP, Verhoeve P et al (2012) A novel indoor localization system for healthcare environments. In: 25th IEEE international symposium on computer-based medical systems (CBMS), Rome, Italy, pp 1–6
Chaiwongven A, Kovavisaruch L, Sanpechuda T et al (2018) An analyze movement path of employees in fire drill by indoor location system using Bluetooth. iSAI-NLP, Pattaya, Thailand, pp 1–6
Dickinson P, Cielniak G, Szymanezyk O et al (2016) Indoor positioning of shoppers using a network of Bluetooth low energy beacons. IPIN, Alcala de Henares, Spain, pp 1–8
Mahfouz S, Mourad-Chehade F, Honeine P et al (2015) Kernel-based machine learning using radio-fingerprints for localization in WSNS. IEEE Trans Aerosp Electron Syst 51:1324–1336
Yan H, Xu Y, Gidlund M (2009) Experimental e-health applications in wireless sensor networks. CMC 2009, Kunming, China, pp 563–567
Giovanelli D, Farella E, Fontanelli D et al (2018) Bluetooth-based indoor positioning through TOF and RSSI data fusion. IPIN, Nantes, France, pp 1-8
Leung C, Sum J, Cheung H et al (2014) Lagrange programming neural networks for time-of-arrival-based source localization. Neural Comput Appl 24:109–116
Ouyang R, Wong A, Lea C et al (2012) Indoor location estimation with reduced calibration exploiting unlabeled data via hybrid generative/discriminative learning. IEEE Trans Mob Comput 11(11):1613–1626
Herrera J, Plöger P, Hinkenjann A et al (2014) Pedestrian indoor positioning using smartphone multi-sensing, radio beacons, user positions probability map and indoor OSM floor plan representation. IPIN 2014, Busan, South Korea, pp 636–645
Van Haute T, De Poorter E, Crombez P et al (2016) Performance analysis of multiple indoor positioning systems in a healthcare environment. Int J Health Geograph 15:1–7
Henningsson M, Tunestal P, Johansson R et al (2012) A virtual sensor for predicting diesel engine emissions from cylinder pressure data. IFAC Proc Vol 45(30):424–431
McCulloch W, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4):115–133
Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65(6):386
Widrow B, Hoff M (1960) Adaptive switching circuits. IRE WESCON Conv Rec 1960:96–104
Rumelhart D, Geoffrey E, Hinton G, Williams R (1986) Learning representations by back-propagating errors. Nature 323(1): 533–536
Hecht-Nielsen R (1987) Kolmogorov’s mapping neural network existence theorem. Neural Netw 3: 11–14
Hornik K, Stinchcombe M, Halbert WH (1989) Multilayer feedforward networks are universal approximators. Neural Networks 2(5):359–366
Hecht-Nielsen R (1989) Theory of the backpropagation neural network. IJCNN, Washington, USA, pp 593–605
Adell M, Gonzalez J (2013) Smart indoor-outdoor positioning handover for smartphones. IPIN, Montbeliard-Belfort, France, pp 1–7
Yan H, Xu Y, Gidlund M (2009) Experimental e-health applications in wireless sensor networks. CMC, Yunnan, China, pp 5630–5670
Huang H, Hsieh C, Liu K et al (2019) Multi-sensor fusion approach for improving map-based indoor pedestrian localization. Sensors 19(17):3786
Cabrera-Goyes E, Ordóñez-Camacho D (2017) Towards a bluetooth indoor positioning system with android consumer devices. INCISCOS, Quito, Ecuador, pp 56–59
Liu M, Chen R, Li D, Chen Y, Guo G et al (2017) Scene recognition for indoor localization using a multi-sensor fusion approach. Sensors 17(12):2847
Sarbadhikari S, Basak J, Pal S et al (1998) Noisy fingerprints classification with directional fft based features using mlp. Neural Comput Appl 7(2):180–191
Qinghua Luo Q, Xiaozhen Yan X, Junbao Li J et al (2016) Dedf: lightweight wsn distance estimation using RSSI data distribution-based fingerprinting. Neural Comput Appl 27(6):1567–1575
Jianyong Z, Haiyong L, Zili C et al (2014) RSSI based bluetooth low energy indoor positioning. IPIN, Busan, South Korea, pp 526–533
Hao Zhang H, Kai Liu K, Feiyu Jin F et al (2020) A scalable indoor localization algorithm based on distance fitting and fingerprint mapping in wi-fi environments. Neural Comput Appl 32:5131–5145
Jiang X, Liu J, Chen Y et al (2016) Feature adaptive online sequential extreme learning machine for lifelong indoor localization. Neural Comput Appl 27(1):215–225
Vandersmissen B, Knudde N, Jalalvand A et al (2019) Indoor human activity recognition using high-dimensional sensors and deep neural networks. Neural Comput Appl
Acknowledgements
We are thankful to Coordination of Improvement of Higher Education Personnel (CAPES) for the financial support.
Conflict of Interest
The authors declare that they have no conflict of interest.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Pedrollo, G.R., Balbinot, A. (2022). Dual Neural Network Approach for Virtual Sensor at Indoor Positioning System. In: Bastos-Filho, T.F., de Oliveira Caldeira, E.M., Frizera-Neto, A. (eds) XXVII Brazilian Congress on Biomedical Engineering. CBEB 2020. IFMBE Proceedings, vol 83. Springer, Cham. https://doi.org/10.1007/978-3-030-70601-2_210
Download citation
DOI: https://doi.org/10.1007/978-3-030-70601-2_210
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70600-5
Online ISBN: 978-3-030-70601-2
eBook Packages: EngineeringEngineering (R0)