Hybrid Wireless Fingerprint Indoor Localization Method Based on a Convolutional Neural Network

Abstract

In the indoor location field, the quality of received-signal-strength-indicator (RSSI) fingerprints plays a key role in the performance of indoor location services. However, changes in an indoor environment may lead to the decline of location accuracy. This paper presents a localization method employing a Hybrid Wireless fingerprint (HW-fingerprint) based on a convolutional neural network (CNN). In the proposed scheme, the Ratio fingerprint was constructed by calculating the ratio of different RSSIs from important contribution access points (APs). The HW-fingerprint combined the Ratio fingerprint and the RSSI to enhance the expression of indoor environment characteristics. Moreover, a CNN architecture was constructed to learn important features from the complex HW-fingerprint for indoor locations. In the experiment, the HW-fingerprint was tested in an actual indoor scene for 15 days. Results showed that the average daily location accuracy of the K-Nearest Neighbor (KNN), Support Vector Machines (SVMs), and CNN was improved by 3.39%, 8.03% and 9.03%, respectively, when using the HW-fingerprint. In addition, the deep-learning method was 4.19% and 16.37% higher than SVM and KNN in average daily location accuracy, respectively.

Sensors and Sensing Technologies for Indoor Positioning and Indoor Navigation

“…In these experiments, the system proposed achieved an optimal tracking performance in most cases. Machine Learning (ML) is also used to implement fingerprinting methods, as seen in [ 7 ]. The paper proposed a way to overcome the problem of changes in indoor environments when using Received Signal Strength Indicator (RSSI) fingerprints that can lead to low performance using a a Hybrid Wireless fingerprint (HW-fingerprint) based on a Convolutional Neural Network (CNN).…”

RSSI Sinyalleri Kullanarak İç Ortamda Parmak İzi Tabanlı YSA ile Konum Tespitinin Gerçekleştirilmesi

“…Ayrıca, bu sistem normalde benzer parmak izi, eksik değer ve gürültülü RSSI değeri gibi sorunlardan muzdarip olduğu için düzgün bir yer tahmini sağlayamaz. Wu = √( − ) 2 + ( − ) 2 (1) = ∑ =1…”

Preparation of polymer gold nanoparticle composites with tunable plasmon coupling and their application as SERS substrates

“…6,7 Gold nanoparticles (AuNPs) are particularly well studied and applications include plasmon enhanced catalysis, 8 electrocatalytic activity, 9 sensing, 10 payload delivery, 11 and radiosensitisation. 12 In order to preserve the optical properties of AuNPs, it is important to ensure the sample stability and resistance to aggregation 13 One approach to achieve this is to use AuNP composite materials, 14 which can be prepared through in-situ growth 15 or the immobilisation of pre-formed AuNPs on a supporting material. 16 In the latter case a variety of supports have been used including polymer beads, 17 silica, 13,18,19 nanotubes 20 and graphene oxide.…”

“…12 In order to preserve the optical properties of AuNPs, it is important to ensure the sample stability and resistance to aggregation 13 One approach to achieve this is to use AuNP composite materials, 14 which can be prepared through in-situ growth 15 or the immobilisation of pre-formed AuNPs on a supporting material. 16 In the latter case a variety of supports have been used including polymer beads, 17 silica, 13,18,19 nanotubes 20 and graphene oxide. 21 These materials have been shown to display improved stability to biological medium 14 and improved performance compared to discrete AuNPs, particularly in surface enhanced Raman spectroscopy (SERS).…”