Location Fixing and Fingerprint Matching Fingerprint Map Construction for Indoor Localization (original) (raw)
Related papers
Map-aided fingerprint-based indoor positioning
2013 IEEE 24th Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), 2013
The objective of this work is to investigate potential accuracy improvements in the fingerprint-based indoor positioning processes, by imposing map-constraints into the positioning algorithms in the form of a-priori knowledge. In our approach, we propose the introduction of a Route Probability Factor (RPF), which reflects the possibility of a user, to be located on one position instead of all others. The RPF does not only affect the probabilities of the points along the pre-defined frequent routes, but also influences all the neighbouring points that lie at the proximity of each frequent route. The outcome of the evaluation process, indicates the validity of the RPF approach, demonstrated by the significant reduction of the positioning error.
Multi Fingerprint Map for Indoor Localisation
2015
Fingerprinting is one of the location estimation technique used in indoor applications. It maps information about wireless signals (e.g. the RSS value) into spatial coordinates. Because WiFi is an ubiquitous communication technology, supported by smartphones, Fingerprinting-based localisation algorithms that use WiFi signals are suitable for LBS applications. Although good results can be achieved using Fingerprinting, this is not an error free localisation technique. The end-user of the LBS application can interfere with these algorithms. If a user that was facing an Access Point rotates 180, the received RSS from that Access Point will decrease (and vice-versa). Although the user did not move, this RSS variation might be interpreted as ”the user moved”. A possible solution to cope with this problem is to acquire data at different directions, at each spatial point, during the off-line phase. Multiple Fingerprint Maps, that also include direction information, can therefore be built. ...
Scalable and Efficient Clustering for Fingerprint-Based Positioning
IEEE Internet of Things Journal
Indoor positioning based on IEEE 802.11 wireless LAN (Wi-Fi) fingerprinting needs a reference data set, also known as a radio map, in order to match the incoming fingerprint in the operational phase with the most similar fingerprint in the data set and then estimate the device position indoors. Scalability problems may arise when the radio map is large, e.g., providing positioning in large geographical areas or involving crowdsourced data collection. Some researchers divide the radio map into smaller independent clusters, such that the search area is reduced to less dense groups than the initial database with similar features. Thus, the computational load in the operational stage is reduced both at the user devices and on servers. Nevertheless, the clustering models are machine-learning algorithms without specific domain knowledge on indoor positioning or signal propagation. This work proposes several clustering variants to optimize the coarse and fine-grained search and evaluates them over different clustering models and data sets. Moreover, we provide guidelines to obtain efficient and accurate positioning depending on the data set features. Finally, we show that the proposed new clustering variants reduce the execution time by half and the positioning error by ≈ 7% with respect to fingerprinting with the traditional clustering models.
Indoor Localization Accuracy Estimation from Fingerprint Data
2017 18th IEEE International Conference on Mobile Data Management (MDM), 2017
The demand for indoor localization services has led to the development of techniques that create a Fingerprint Map (FM) of sensor signals (e.g., magnetic, Wi-Fi, bluetooth) at designated positions in an indoor space and then use FM as a reference for subsequent localization tasks. With such an approach, it is crucial to assess the quality of the FM before deployment, in a manner disregarding data origin and at any location of interest, so as to provide deployment staff with the information on the quality of localization. Even though FM-based localization algorithms usually provide accuracy estimates during system operation (e.g., visualized as uncertainty circle or ellipse around the user location), they do not provide any information about the expected accuracy before the actual deployment of the localization service. In this paper, we develop a novel framework for quality assessment on arbitrary FMs coined ACCES. Our framework comprises a generic interpolation method using Gaussian Processes (GP), upon which a navigability score at any location is derived using the Cramer-Rao Lower Bound (CRLB). Our approach does not rely on the underlying physical model of the fingerprint data. Our extensive experimental study with magnetic FMs, comparing empirical localization accuracy against derived bounds, demonstrates that the navigability score closely matches the accuracy variations users experience.
Using unlocated fingerprints in generation of WLAN maps for indoor positioning
Record - IEEE PLANS, Position Location and Navigation Symposium, 2012
This paper presents five methods for generation of WLAN maps for indoor positioning using crowdsourced fingerprints. A fingerprint is assumed to contain identifiers of WLAN access points, received signal strength values and, if the fingerprint is collected outdoors, a GPS position. The proposed methods use the fingerprints' information to generate a WLAN map that contains estimated access point locations. Two of the proposed methods use RSS values in access point location estimation. In our evaluation with simulations and with real data, the Access Point Least Squares method, which does not use RSS information, is the fastest and its accuracy is as good as more complex methods that use RSS information.
Fingerprints and Floor Plans Construction for Indoor Localisation Based on Crowdsourcing
Sensors
The demand for easily deployable indoor localisation solutions has been growing. Although several systems have been proposed, their limitations regarding the high implementation costs hinder most of them to be widely used. Fingerprinting-based IPS (Indoor Positioning Systems) depend on characteristics pervasively available in buildings. However, such systems require indoor floor plans, which might not be available, as well as environmental fingerprints, that need to be collected through human resources intensive processes. To overcome these limitations, this paper proposes an algorithm for the automatic construction of indoor maps and fingerprints, solely depending on non-annotated crowdsourced data from smartphones. Our system relies on multiple gait-model based filtering techniques for accurate movement quantification in combination with opportunistic sensing observations. After the reconstruction of users’ movement with PDR (Pedestrian Dead Reckoning) techniques, Wi-Fi measuremen...
2018
The conventional way of finding the closest pair of points is the use of brute force method that simply computes the distances of all pair of points in the plane and finds the points with the minimum distance. An improved version of this method was the use of divide and conquer algorithm. However, the expedition for improving the computational cost of this problem continues to grow because of potential applications in location estimation and sequence matching. This paper attempted to develop and analyze a new method called closest coordinate scheme to determine the estimated position for indoor positioning system. The enhanced fingerprint localization technique was linked with the closest coordinate scheme to test its value in terms of accuracy and efficiency. Results showed that the closest coordinate scheme is efficient and accurate. Future endeavor may focus on the time and space complexities of closest coordinate scheme and find out similar applications.
New Reconstructed Database for Cost Reduction in Indoor Fingerprinting Localization
IEEE Access, 2019
Location fingerprinting is a technique widely suggested for challenging indoor positioning. Despite the significant benefits of this technique, it needs a considerable amount of time and energy to measure the Received Signal Strength (RSS) at Reference Points (RPs) and build a fingerprinting database to achieve an appropriate localization accuracy. Reducing the number of RPs can reduce this cost, but it noticeably degrades the accuracy of positioning. In order to alleviate this problem, this paper takes the interior architecture of the indoor area and signal propagation effects into account and proposes two novel recovery methods for creating the reconstructed database instead of the measured one. They only need a few numbers of RPs to reconstruct the database and even are able to produce a denser database. The first method is a new zone-based path-loss propagation model which employs fingerprints of different zones separately and the second one is a new interpolation method, zone-based Weighted Ring-based (WRB). The proposed methods are compared with the conventional path-loss model and six interpolation functions. Two different test environments along with a benchmarking testbed, and various RPs configurations are also utilized to verify the proposed recovery methods, based on the reconstruction errors and the localization accuracies they provide. The results indicate that by taking only 11% of the initial RPs, the new zone-based pathloss model decreases the localization error up to 26% compared to the conventional path-loss model and the proposed zone-based WRB method outperforms all the other interpolation methods and improves the accuracy by 40%.
Performance analysis of clustering-based fingerprinting localization systems
Wireless Networks, 2018
Localization is highly required to develop the smart-phone based pervasive computing applications. Because of very poor signal strength of global positioning system in indoor areas, various indoor localization systems have been proposed in literature. Among these, received signal strength (RSS) based fingerprinting localization systems are very popular. However, these localization systems at first, need to construct a fingerprint database by collecting RSS patterns at a set of known training locations and then determine the location of an object by comparing the currently observed RSS pattern with all the RSS patterns stored in the fingerprint database. Thus, such localization systems can provide better positioning accuracy by including large number of training data, which in turn, increase the searching overhead. To resolve this issue, several clustering strategies, which restrict the search within a smaller subset of the whole fingerprint database for such localization systems, have been proposed in the literature over the past decade. This paper presents an extensive comparative performance analysis of various clustering-based fingerprinting localization systems to demonstrate their effectiveness on the large-scale positioning system in the presence of radio irregularities and wall attenuation in the wireless environment.