Performance evaluation of RSS fingerprinting method to track ZigBee devices location using artificial neural networks

Pradityo, Hening Pram; Rosyidi, Lukman; Misbahuddin, Misbahuddin; Sari, Riri Fitri

doi:10.1109/ictc.2017.8190984

Cited by 5 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Zigbee (IEEE 802.15.4 standard) based localization techniques [59] [60] share the primary drawback of Wi-Fibased techniques. But the use of Zigbee networks (mainly used for wireless sensor networks) is not as widespread in indoor environments as Wi-Fi networks, and require an additional deployment that increases the cost of the localization system.…”

Section: B Zigbeementioning

confidence: 99%

Room-Level Localization System Based on LoRa Backscatters

2021

View full text Add to dashboard Cite

The aim of this paper is to propose a novel room-level localization approach to locate LoRa backscatter devices, which can be easily embedded into wearable devices or smartphones. The advantages of this system lie in its series of low-cost, low-power, low-complexity and long-range features. LoRa backscattering operates by alternatively connecting an antenna, through a switch, to two loads with high reflection coefficients and opposite phase. The result is a frequency shift of the LoRa incident signal equal to the backscatter switching frequency. The localization system comprises several LoRa receivers distributed among the rooms, a LoRa transmitter located at a central point and the backscatter device, which is carried or worn by a subject. The position of the LoRa backscatter device can be determined by comparing the received signal strength between all receivers. In order to improve the accuracy of the system, different machine learning classifiers were compared. System performance was tested in a real-life scenario, achieving an accuracy up to 89.7% using linear discriminant analysis (LDA). INDEX TERMS Backscatter communications, LoRa, localization, wireless sensor networks, RFID, zeropower sensor, internet of things (IoT).

show abstract

Section: B Zigbeementioning

confidence: 99%

Room-Level Localization System Based on LoRa Backscatters

2021

View full text Add to dashboard Cite

show abstract

“…Perangkat pengirim/penerima dapat menggunakan perangkat berjarak jangkau pendek (short range), seperti RFID/NFC [3], BLE 802.15.1 [4], dan WiFi 802.11x [5]. Perangkat lainnya adalah yang berjarak jangkau [6], [7]. Perangkat yang berjarak jangkau jauh (long range) yang digunakan di antaranya adalah SigFox [8], [9], LoRa [10], dan NB-IoT [11].…”

Section: Pendahuluanunclassified

“…Semua penelitian tentang penentuan posisi yang menggunakan metode fingerprint sebagaimana disebutkan sebelumnya hanya menggunakan salah satu metode yang ada saat ini. Metode yang digunakan untuk fingerprint adalah di antaranya kNN [8], [9], jaringan saraf tiruan [7], dan radial basis function (RBF) [10]. Sampai saat ini belum ada kajian yang melakukan evaluasi kinerja beberapa algoritme untuk menguji tingkat akurasi yang terbaik.…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Neural network performance based on backpropagation and LVQ as the LoRa RSS fingerprint algorithms for positioning in an open space

Misbahuddin

Iqbal

Wiriasto

et al. 2020

Jurnal Teknologi dan Sistem Komputer

View full text Add to dashboard Cite

Outdoor positioning is one of the important applications in the Internet of things (IoT). The usage of GPS is unsuitable for low-power IoT devices. Alternatively, it can use the LoRa devices. This research aims to find a better method as the fingerprint algorithm for determining the outdoor position using RSS LoRa. The methods used as the fingerprint algorithm were two artificial neural network models, i.e. backpropagation (BP) with four types of training methods and learning vector quantization (LVQ) with two types of training methods. The experiment results show the performance of LVQ1 better than those of LVQ2. Besides, the LVQ1 was also better than the BP method. However, both BP and LVQ2 have a performance that is almost similar to about 70 %. Both of the artificial neural network models, BP and LVQ, can be used as a fingerprint algorithm to determine quite accurate the outdoor object position.

show abstract

“…Fingerprint can be divided into two types of technologies. One is node-based localization, which is based on indoor wireless communication technologies such as Wi-Fi [ 1 , 2 , 3 ], Bluetooth Low-Energy (BLE) [ 4 , 5 , 6 ], and Zigbee [ 7 , 8 ]. It uses the RSS indicator (RSSI) to show the wireless signal strength according to the presence of a node.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Recursive Fingerprint Radio Map Creation Algorithm Combining Wi-Fi and Geomagnetism

Seong

Seo

2018

Sensors

View full text Add to dashboard Cite

Fingerprint is a typical indoor-positioning algorithm, which measures the strength of wireless signals and creates a radio map. Using this radio map, the position is estimated through comparisons with the received signal strength measured in real-time. The radio map has a direct effect on the positioning performance; therefore, it should be designed accurately and managed efficiently, according to the type of wireless signal, amount of space, and wireless-signal density. This paper proposes a real-time recursive radio map creation algorithm that combines Wi-Fi and geomagnetism. The proposed method automatically recreates the radio map using geomagnetic radio-map dual processing (GRDP), which reduces the time required to create it. It also reduces the size of the radio map by actively optimizing its dimensions using an entropy-based minimum description length principle (MDLP) method. Experimental results in an actual building show that the proposed system exhibits similar map creation time as a system using a Wi-Fi–based radio map. Geomagnetic radio maps exhibiting over 80% positioning accuracy were created, and the dimensions of the radio map that combined the two signals were found to be reduced by 23.81%, compared to the initially prepared radio map. The dimensions vary according to the wireless signal state, and are automatically reduced in different environments.

show abstract

Performance evaluation of RSS fingerprinting method to track ZigBee devices location using artificial neural networks

Cited by 5 publications

References 8 publications

Room-Level Localization System Based on LoRa Backscatters

Room-Level Localization System Based on LoRa Backscatters

Neural network performance based on backpropagation and LVQ as the LoRa RSS fingerprint algorithms for positioning in an open space

Real-Time Recursive Fingerprint Radio Map Creation Algorithm Combining Wi-Fi and Geomagnetism

Contact Info

Product

Resources

About