scholarly journals Feature Learning for Fingerprint-Based Positioning in Indoor Environment

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Zengwei Zheng ◽  
Yuanyi Chen ◽  
Tao He ◽  
Lin Sun ◽  
Dan Chen
Keyword(s):  
Indoor Environment ◽  
Dynamic Environment ◽  
Feature Learning ◽  
Signal Strength ◽  
Access Point ◽  
Received Signal Strength ◽  
Heterogeneous Devices ◽  
Positioning Algorithm ◽  
Positioning Time ◽  
Fingerprint Feature

Recent years have witnessed a growing interest in using Wi-Fi received signal strength for indoor fingerprint-based positioning. However, previous study about this problem has primarily faced two main challenges. One is that positioning fingerprint feature using received signal strength is unstable due to heterogeneous devices and dynamic environment status, which will greatly degrade the positioning accuracy. Another is that some improved positioning fingerprint features will suffer the curse of dimensionality in online positioning. In this paper, we designed a novel positioning fingerprint feature using the segment similarity of Wi-Fi access points, considering both the received signal strength value and the Wi-Fi access point. Based on this designed fingerprint feature, we proposed a two-stage positioning algorithm for indoor fingerprint-based positioning. Experiment results indicate that our proposed positioning methodology can not only achieve better positioning performance but also consume less positioning time compared to three baseline methods.

scholarly journals Indoor localization system based on virtual access points with filtering schemes

2019 ◽  
Vol 15 (7) ◽  
pp. 155014771986613 ◽  
Author(s):  
Dong Myung Lee ◽  
Boney Labinghisa
Keyword(s):  
Kalman Filter ◽  
Indoor Environment ◽  
Performance Testing ◽  
Signal Strength ◽  
Access Point ◽  
Received Signal Strength ◽  
Indoor Environments ◽  
Received Signal Strength Indicator ◽  
Access Points ◽  
Error Distance

In indoor positioning techniques, Wi-Fi is one of the most used technology because of its availability and cost-effectiveness. Access points are usually the main source of Wi-Fi signals in an indoor environment. If access points are optimized to cover the indoor area, this could improve Wi-Fi signal distribution. This article proposed an alternative to optimizing access point placement and distribution by introducing virtual access points that can be virtually placed in any part of the indoor environment without installation of actual access points. Virtual access points will be created heuristically by correlating received signal strength indicator of already existing access points and through linear regression. After introducing virtual access points in the indoor environment, next will be the addition of filters to improve signal fluctuation and reduce noise interference. Kalman filter has been previously used together with virtual access point and showed improvement by decreasing error distance of Wi-Fi fingerprinting results. This article also aims to include particle filter in the system to further improve localization and test its effectiveness when paired with Kalman filter. The performance testing of the algorithm in different indoor environments resulted in 3.18 and 3.59 m error distances. An improvement was added on the system by using relative distances instead of received signal strength indicator values in distance estimation and gave an error distance average of 1.85 m.

scholarly journals Side-Information-Aided Preprocessing Scheme for Deep-Learning Classifier in Fingerprint-Based Indoor Positioning

Electronics ◽  
2020 ◽  
Vol 9 (6) ◽  
pp. 982 ◽  
Author(s):  
Yue Liu ◽  
Rashmi Sharan Sinha ◽  
Shu-Zhi Liu ◽  
Seung-Hoon Hwang
Keyword(s):  
Deep Learning ◽  
Side Information ◽  
Success Probability ◽  
Dynamic Environment ◽  
Signal Strength ◽  
Access Point ◽  
Indoor Positioning ◽  
Received Signal Strength ◽  
Learning Classifier ◽  
Learning Classifiers

Deep-learning classifiers can effectively improve the accuracy of fingerprint-based indoor positioning. During fingerprint database construction, all received signal strength indicators from each access point are combined without any distinction. Therefore, the database is created and utilised for deep-learning models. Meanwhile, side information regarding specific conditions may help characterise the data features for the deep-learning classifier and improve the accuracy of indoor positioning. Herein, a side-information-aided preprocessing scheme for deep-learning classifiers is proposed in a dynamic environment, where several groups of different databases are constructed for training multiple classifiers. Therefore, appropriate databases can be employed to effectively improve positioning accuracies. Specifically, two kinds of side information, namely time (morning/afternoon) and direction (forward/backward), are considered when collecting the received signal strength indicator. Simulations and experiments are performed with the deep-learning classifier trained on four different databases. Moreover, these are compared with conventional results from the combined database. The results show that the side-information-aided preprocessing scheme allows better success probability than the conventional method. With two margins, the proposed scheme has 6.55% and 5.8% improved performances for simulations and experiments compared to the conventional scheme. Additionally, the proposed scheme, with time as the side information, obtains a higher success probability when the positioning accuracy requirement is loose with larger margin. With direction as the side information, the proposed scheme shows better performance for high positioning precision requirements. Thus, side information such as time or direction is advantageous for preprocessing data in deep-learning classifiers for fingerprint-based indoor positioning.

scholarly journals A Generative Method for Indoor Localization Using Wi-Fi Fingerprinting

Sensors ◽  
2021 ◽  
Vol 21 (7) ◽  
pp. 2392
Author(s):  
Óscar Belmonte-Fernández ◽  
Emilio Sansano-Sansano ◽  
Antonio Caballer-Miedes ◽  
Raúl Montoliu ◽  
Rubén García-Vidal ◽  
...  
Keyword(s):  
Markov Model ◽  
Hidden Markov Model ◽  
Indoor Localization ◽  
Hidden Markov ◽  
Signal Strength ◽  
Access Point ◽  
Received Signal Strength ◽  
Machine Learning Algorithms ◽  
Forward Algorithm ◽  
Generative Method

Indoor localization is an enabling technology for pervasive and mobile computing applications. Although different technologies have been proposed for indoor localization, Wi-Fi fingerprinting is one of the most used techniques due to the pervasiveness of Wi-Fi technology. Most Wi-Fi fingerprinting localization methods presented in the literature are discriminative methods. We present a generative method for indoor localization based on Wi-Fi fingerprinting. The Received Signal Strength Indicator received from a Wireless Access Point is modeled by a hidden Markov model. Unlike other algorithms, the use of a hidden Markov model allows ours to take advantage of the temporal autocorrelation present in the Wi-Fi signal. The algorithm estimates the user’s location based on the hidden Markov model, which models the signal and the forward algorithm to determine the likelihood of a given time series of Received Signal Strength Indicators. The proposed method was compared with four other well-known Machine Learning algorithms through extensive experimentation with data collected in real scenarios. The proposed method obtained competitive results in most scenarios tested and was the best method in 17 of 60 experiments performed.

scholarly journals A Research Cluster based Scheme for Node Positioning in Indoor Environment

2019 ◽  
Vol 8 (6S) ◽  
pp. 79-83
Keyword(s):  
Wireless Sensor Network ◽  
Sensor Network ◽  
Indoor Environment ◽  
Cluster Head ◽  
Signal Strength ◽  
Received Signal Strength ◽  
Location Estimation ◽  
Wireless Sensor ◽  
Localization Error ◽  
Network Efficiency

Location estimation in Wireless Sensor Network (WSN) is mandatory to achieve high network efficiency. Identifying the positions of sensors is an uphill task as monitoring nodes are involved in estimation and localization. Clustered Positioning for Indoor Environment (CPIE) is proposed for estimating the position of the sensors using a Cluster Head (CH) based mechanism. The CH estimates the number of neighbor nodes in each floor of the indoor environment. It sends the requests to the cluster members and the positions are estimated based on the Received Signal Strength Indicators (RSSIs) from the members of the cluster. The performance of the proposed scheme is analyzed for both stable and mobile conditions by varying the number of floors. Experimental results show that the propounded scheme offers better network efficiency and reduces delay and localization error

Improved Algorithm on Wide Range Positioning for Partial Discharge in Substation

2013 ◽  
Vol 860-863 ◽  
pp. 2177-2181
Author(s):  
Xi Ran Wang ◽  
Huai Dong Liu ◽  
Yi Fan He ◽  
Qi Ming Zhao ◽  
He Wu
Keyword(s):  
Electrical Discharge ◽  
Partial Discharge ◽  
Signal Strength ◽  
Received Signal Strength ◽  
Experimental Result ◽  
Wide Range ◽  
Positioning Algorithm ◽  
Received Signal Strength Indication ◽  
Improved Algorithm

This paper proposes a Improved positioning algorithm of electrical partial discharge applied for substations. This algorithm is based on received signal strength indication, and taken practical condition of sensors into consideration by replenishing beacon nodes. Compared with traditional trilateral weighting positioning algorithm, this paper introduces indefinite amount of localization perpendicular lines and combined them with trilateral districts to calculate the weighting result, which can reduce error. This model meets the requirement of reality that the height of electrical discharge spots differentiate from the height of the plane formed by beacon nodes (signal sensors). The experimental result indicates that the revised position model proposed by this paper can effectively fit the condition of monitoring hardware. Error of this algorithm is less than that of traditional trilateral localization.

scholarly journals A Novel Enhanced Positioning Trilateration Algorithm Implemented for Medical Implant In-Body Localization

2013 ◽  
Vol 2013 ◽  
pp. 1-10 ◽  
Author(s):  
Peter Brida ◽  
Juraj Machaj
Keyword(s):  
Signal Strength ◽  
Received Signal Strength ◽  
Position Estimation ◽  
Time Of Arrival ◽  
Medical Implant ◽  
Exact Position ◽  
Two Phases ◽  
Positioning Algorithm ◽  
Selection Of

Medical implants based on wireless communication will play crucial role in healthcare systems. Some applications need to know the exact position of each implant. RF positioning seems to be an effective approach for implant localization. The two most common positioning data typically used for RF positioning are received signal strength and time of flight of a radio signal between transmitter and receivers (medical implant and network of reference devices with known position). This leads to positioning methods: received signal strength (RSS) and time of arrival (ToA). Both methods are based on trilateration. Used positioning data are very important, but the positioning algorithm which estimates the implant position is important as well. In this paper, the proposal of novel algorithm for trilateration is presented. The proposed algorithm improves the quality of basic trilateration algorithms with the same quality of measured positioning data. It is called Enhanced Positioning Trilateration Algorithm (EPTA). The proposed algorithm can be divided into two phases. The first phase is focused on the selection of the most suitable sensors for position estimation. The goal of the second one lies in the positioning accuracy improving by adaptive algorithm. Finally, we provide performance analysis of the proposed algorithm by computer simulations.

Sign in / Sign up

Export Citation Format

Share Document