Leveraging Logical Anchor into Topology Optimization for Indoor Wireless Fingerprinting

The rapid growth of mobile communication and the proliferation of smart phones have drawn significant attention to location-based services (LBS). The Wi-Fi positioning system (WPS) is a newly attractive method as a widely applicable positioning technique in LBS. In WPS, the received signal strength indication (RSSI) data of all Wi-Fi access points (APs) are measured, and stored in a huge database, as a form of radio fingerprint map. Because of the millions of APs in urban areas, radio fingerprint data are seriously contaminated. Therefore, we present a coherent filtering method for radio fingerprint data. All fingerprints used in the developed test bed are harvested from actual radio fingerprint measurements taken throughout Seoul, Korea. This demonstrates the practical usefulness of the proposed methodology.

Indoor positioning methods using location-sensitive features of available wireless signals can achieve high accuracy. In particular, many state-of-the-art methods exploit quite unique sets of location-dependent received signal strength (RSS) measurements from multiple wireless local area network (WLAN) access points (APs), also called as wireless fingerprints. However, reception of signals from WLAN APs is not often stable, and RSS measurements tend to be unavailable due to WLAN card or AP transient effects, limited sensitivity of WLAN cards, and fluctuating attenuation and reflection of signals due to a multipath environment, structural changes and moving objects. In certain hostile scenarios, bogus APs may be installed to disorient WLAN localisation algorithms. In this study, two approaches are proposed to mitigate the impact of faulty signal strength measurements. Performance figures are provided for both simulated and empirical environments in order to support conclusions.

Fingerprint-based localization systems mainly utilize the received signal strength (RSS) to estimate the location of a receiver, and the localization accuracy depends largely on the number and placement of access points (APs). In this paper, we propose a novel method for placing the APs, which aims to minimize the total number of similar fingerprints (SFs) over the entire array of training locations. Minimizing SFs will increase the diversity of RSS array and hence improve localization accuracy. To solve the problem using a simple brute force search would be highly computationally expensive and inefficient. Instead, we propose a heuristic optimization algorithm based on Simulated Annealing (SA). Numerical results are obtained for both the brute force search and the SA based approach. Finally, the proposed algorithm's outputs, i.e., the APs' locations, are used with a K-Nearest Neighbors based localization algorithm, and the resulting localization errors are analyzed.

The paper answers a fundamental question: can the accuracy of Wi-Fi based localization be significantly increased by fusing information from alternate sources like LTE signals and magnetometers, collected through software defined radios and smart-devices? Further, it aims to eliminate dependency of well established localization techniques on only Wi-Fi access point (AP) positions, and instead, proposes a diversity-leveraging architecture called as the Wireless Locator (Wi-LO) framework. Wi-LO is a client-server paradigm for indoor localization that achieves precision by pattern-matching the collected signal samples with a priori references for each transmitter type, thus giving a stand-alone decision for these diverse sensing modes. The novelty of the paper is fusing these decision outcomes and resolving mis-matches (for e.g., Wi-Fi and LTE suggest different locations) in a seamless manner, and also identifying the best source to use at each location based on its spatial resolution. Wi-Lo is rigorously evaluated on a test-bed, with the proposed scheme of combining Wi-Fi, LTE and magnetometer performing better localization than the classical Wi-Fi-only approach in both urban (+8%) and rural (+25%) scenarios.

Due to the advent and pervasive deployment of wireless local area networks, WiFi-based indoor localization systems have received increasing attention in the last few years. However, their localization accuracy has always been a challenging issue. In addition, because of diverse interference such as multipath effects, the block of signals, an unstable or weak signal in itself, etc., not all the access points (APs) are informative for the localization. Faced with these problems, we propose a WiFi-based localization model by modifying the large localization errors and enhancing the Gaussian process regression (MEGPR). 1) To select the AP subsets that contribute more to the localization and further reduce the computational load, the AP discrimination criterion (APDC) is introduced to quantify the discernibility of the APs detected in the workspace and filter out the APs with low discrimination. 2) Second, to enhance the localization model, the localization residual is fed and learnt by the model. 3) Furthermore, the large localization errors are mitigated by the location modification method (LMM). Experiments were conducted in a real environment with an area of more than 1200 m <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> and the results show that compared with other existing localization models, the average localization error of the proposed MEGPR model is minimum, which further verifies the effectiveness of the proposed MEGPR localization model.

Simultaneous localization and mapping (SLAM) has been extensively researched in past years particularly with regard to range-based or visual-based sensors. Instead of deploying dedicated devices that use visual features, it is more pragmatic to exploit the radio features to achieve this task, due to their ubiquitous nature and the widespread deployment of the Wi-Fi wireless network. This article presents a novel approach for collaborative simultaneous localization and radio fingerprint mapping (C-SLAM-RF) in large unknown indoor environments. The proposed system uses received signal strengths (RSS) from Wi-Fi access points (APs) in the existing infrastructure and pedestrian dead reckoning (PDR) from a smartphone, without a prior knowledge about map or distribution of AP in the environment. We claim a loop closure based on the similarity of the two radio fingerprints. To further improve the performance, we incorporate the turning motion and assign a small uncertainty value to a loop closure if a matched turning is identified. The experiment was done in an area of 130 m by 70 m and the results show that our proposed system is capable of estimating the tracks of four users with an accuracy of 0.6 m with Tango-based PDR and 4.76 m with a step counter-based PDR.

The cutting-edge wireless technologies offer huge array of services, from ultra-high-speed data communications to internet of things. But the current existing infrastructure cannot handle these use cases. Consequently, it is becoming a trend to apply computational intelligence algorithms such as machine learning (ML), deep learning (DL), reinforcement learning (RL) and artificial intelligence (AI) to wireless network infrastructures. And one of these applications is on wireless indoor localization. Wireless indoor localization takes advantage of wireless access points (WAPs) received signal strength indicators (RSSI) values to pinpoint the location of a user, similar to concept of GPS but indoors. The goal of this paper is to develop predictive models that can be used to predict the location of a user using RSSI readings that his smartphone receives. In this study, four ML algorithms are used which are support vector machines, random forest, Naïve-Bayes classifier and neural networks. The accuracy of each model are 97.83%, 97.67%, 98.50% and 97.33% respectively. Also, a recursive feature elimination algorithm is also used to determine the predictor that has the least impact amongst all other features and it is found out in the study that WAP2 is contributes the least influence when the predictive models are developed.

ABSTRACTThis paper presents the design, implementation and evaluation of the FreeMobility localization system—a distributed system that allows access points (APs) or cellular towers to dynamically determine the location of a mobile user using only received signal strength (SS) and mobility information (direction and traveled distance) from the mobile. FreeMobility does not require special infrastructure or installation, and it is readily applicable to commodity devices like laptops, PDAs and cell phones using existing Wi‐Fi and/or cellular networks. This paper introduces mathematical methodology that dynamically predicts the location of the mobile; the paper also presents detailed analysis and experimental results that explore practical issues in implementing the system. FreeMobility was evaluated using: (1) measurements from IEEE 802.11 networks at both the University of South Carolina, Beaufort (USC Beaufort) and a residential neighborhood in Columbia, SC; and (2) online data resources from war‐driving community and other research communities. The results demonstrate that FreeMobility provides reliable location estimates, and the localization error is comparable with other existing systems. With the assistance of the geographic information system (GIS), FreeMobility does not require dense tower deployment, and it is able to provide location attributes in addition to pure coordinates from most other systems. Copyright © 2009 John Wiley &amp; Sons, Ltd.

The access point (AP) deployment is a fundamental task for constructing an accurate localization system. Existing literature mainly deals with the AP placement problem using optimal geometry analysis since the target-AP geometry will affect the localization performance. However, some non-ideal phenomena in practical scenario, e.g., the existence of obstacles, array orientation and path loss, will degrade the accuracy of angle-of-arrival (AoA) estimation as well as the localization accuracy. In this article, we reformulate the AP planning incorporating these factors. We decompose the problem into two subproblems, namely AP selection problem and error minimization problem. The AP selection problem selects the minimum number of APs to satisfy a desired localization accuracy, aided by a refined orientation updating procedure. We design a centralized and a distributed error minimization algorithm to further decrease the localization error. The centralized algorithm shows superiority in time efficiency. Nevertheless, the case with large number of APs may lead to excessive computational cost. Accordingly, we further devise the distributed algorithm which is adaptive to large-scale deployment. Numerical studies in indoor environments with barriers are conducted to verify our proposed approach.

In indoor positioning environment, the existence of mobile Access Points (APs) has a potential risk in localization effectiveness. To address this problem, we first analogize the process of localization into the process of information propagation in a communication system to obtain the analytical result of localization error bound under the interference of both environment noise and mobile APs. Second, we propose a joint judgment criterion which consists of two judgment sub-criteria to judge the state of each hearable AP. Finally, the extensive experimental results demonstrate that the proposed approach can precisely detect mobile APs and preserve a satisfactory localization performance.

In recent years, indoor fingerprint-based localization algorithm has been widely used by applications on smart phone. In these localization algorithms, it’s very popular to use WiFi signal characteristics to represent the location fingerprint. With the fast popularization of WiFi, the WiFi access points (APs) could be seen everywhere. However, as the number of APs increases, the dimension of the fingerprint and the complexity of fingerprint-based localization algorithm subsequently increase. Responding to the above challenges, this paper proposes a novel indoor localization algorithm MAPS (indoor localization algorithm based on multiple access point selection). MAPS could effectively reduce the complexity of localization computation, and improve the performance of localization through AP selection method. With the first round AP selection, MAPS can obtain a stable subset of AP, thus reducing the dimension of fingerprint, and obtaining better discrimination. And with the second round of AP selection, AP subset could be further condensed to construct a decision tree in each location cluster. This step can further improve the localization performance. The experimental results shown, as compared with classical indoor localization algorithm, MAPS has better positioning accuracy, and could achieve the accuracy of over 90% within 2m location error.

Aiming at the urgent demands on constructing WiFi communication networks under emergency environments such as rescue and relief work, FC-WiFi, a WiFi network based on OpenFlow was proposed. FC-WiFi employs name-based routing algorithm, and has the characteristics as follows: (i) supporting free configuration access for mobile hosts, (ii) sharing information among mobile hosts and servers, (iii) maintaining the ongoing connection during mobile hosts handover between access points. A prototype system is implemented and experiments show that, hosts can communicate with each other when they associate to FC-WiFi with free configuration. The mobile host can keep TCP connections uninterrupted while passing through multiple access points and the handover delay is under the influence of the original configuration.

This research focused on distance measurement using Received Signal Strength Indicator (RSSl) that utilizing Pythagoras theory to get the position of a smartphone with the help of 4 Access Point (AP) in indoor environment. There were many research have been done in this area, but the issue is about the accuracy. From studies that have been done before, there are differences between the results of calculation using RSSl with the actual distance with the average of 1.6 meters. Our result indicate that when calculating the distance using optimization RSSl method, we can reduce the distance difference average value between Access Point (AP) and smartphone is 0.6 meters with an accuracy of 86.1%. Coordinate measurement using Pythagoras Theory also produce average of localization error valued of 0.6 meters.

Recent rapid rise of indoor location based services for smartphones has further increased the importance of precise localization of Wi-Fi Access Point (AP). However, most existing AP localization algorithms either exhibit high errors or need specialized hardware in practical scenarios. In this paper, we propose a novel RSSI gradient-based AP localization algorithm. It consists of the following three major steps: firstly, it uses the local received signal strength variations to estimate the direction (minus gradient) of AP, then employs a direction clustering method to identify and filter measurement outliers, and finally adopts triangulation method to localize AP with the selected gradient directions. Experimental results demonstrate that the average localization error of our proposed algorithm is less than 2 meters, far outperforming that of the weighted centroid approach.

A wireless electromagnetic localization method for tracking a medical micro-device in the gastrointestinal tract has been proposed and a prototype for the localization system has been developed. In the electromagnetic localization system, several excitation coils were mounted above the abdomen of human body to generate a varying electromagnetic field one by one. Then a wireless magnetic sensor was used to measure the magnetic field strength at the location of the micro-device. Thus the position and orientation of the micro-device could be obtained by solving the inverse problem of magnetic fields. In order to improve the localization precision, a global error correction technique based on the Hardy's Multi-Quadric scattered data interpolation method was investigated to correct the static errors. In the calibration experiment, dependencies between true locations of the micro-device and the corresponding tracked locations within the operational space were established. Based on these data sets, the Hardy's Multi-Quadric correction function was derived. The experimental results show that the localization error can be greatly reduced by using the Hardy's Multi-Quadric correction method. The advantage of the approach is that it allows for smooth continuous mapping from the tracked space to the true space within the entire tracked space.