RSS-eye: Human-assisted indoor localization without radio maps

Location-based service is one of the most popular buzzwords in the field of U-city. Positioning a user is an essential ingredient of a location-based system on a U-city. For the outdoor positioning, GPS based practical solutions have been introduced. However, GPS measurement error is too big to be used for U-campus services because the size of a campus is relatively smaller than a city. We propose Relative-Interpolation Method in order to improve the correctness of outdoor positioning. Besides, indoor positioning is necessary for U-campus while GPS signal is not available inside buildings. For the indoor positioning, Cricket, Active Badge, and so on have been introduced. These methods require special equipments dedicated for positioning. Our method does not require such equipments because it determines the user’s position based on the receiver signal strength indicators (RSSI) from access points (AP) which are already installed for WLAN. The algorithm we are using for indoor positioning is a kind of finger prints method. However our algorithm builds a decision tree instead of a look-up table in the off-line phase. Therefore, our method is faster than existing indoor positioning methods in the real-time phase. We have integrated our indoor and outdoor positioning methods and implemented a prototype of our indoor-outdoor positioning method on a laptop. Our experimental results are discussed in this paper.

A robust radio map is essential in implementing a fingerprint-based indoor positioning system (IPS). However, the offline site survey to manually construct the radio map is time-consuming and labour-intensive. Various interpolation techniques have been proposed to infer the virtual fingerprints to reduce the time and effort required for offline site surveys. This paper presents a novel fingerprint interpolator using a multi-path loss model (M-PLM) to create the virtual fingerprints from the collected sample data based on different signal paths from different access points (APs). Based on the historical signal data, the poor signal paths are identified using their standard deviations. The proposed method reduces the positioning errors by smoothing out the wireless signal fluctuations and stabilizing the signals for those poor signal paths. By considering multipath signal propagations from different APs, the inherent noise from these signal paths can be alleviated. Firstly, locations of the signal data with standard deviations higher than the threshold are identified. The new fingerprints are then generated at these locations based on the proposed M-PLM interpolation function to replace the old fingerprints. The proposed technique interpolates virtual fingerprints based on good signal paths with more stable signals to improve the positioning performance. Experimental results show that the proposed scheme enhances the positioning accuracy by up to 44% compared to the conventional interpolation techniques such as the Inverse Distance Weighting, Kriging, and single Path Loss Model. As a result, we can overcome the site survey problems for IPS by building an accurate radio map with more reliable signals to improve indoor positioning performance.

The increasing demand of indoor Location Based Services (LBS) has made Indoor Positioning System (IPS) a hot research topic. Recently, various machine learning techniques have been developed to tackle the problems of IPS. The WLAN fingerprinting technique is one of the most cost effective choices for IPS due to the use of existing Wi-Fi networks in commercial and public buildings. However, the variation of Received Signal Strength (RSS) at any specific location due to the indoor fading issue leads to serious challenges in the accuracy of the distance estimates. In this paper, we propose a new technique by using Probabilistic Neural Network (PNN) multi-classifier based on Multiple Service Set Identifiers (MSSIDs) that are configured on the same access point. A spatial voting scenario for three PNN-classifiers is proposed as a tool to determine the location of the user. Using a spatial voting based technique is specifically designed to tackle the negative impact of the multi-path propagation on the performance of IPS. The proposed system is performed inside the College of Engineering and Applied Sciences (CEAS) at Western Michigan University. The performance of the proposed system compared with some of the common methods such as K-Nearest Neighbors (K-NN) and multi-class support vector machine (SVM). According to the experimental results, the spatial voting of the three PNN-dassifiers can significantly mitigate the adverse effects of RSS variation. The performance of the multi-classifier exhibits superior performance to that of the other single classifiers in all Area of Interest (AOI). Over 3000 m2 AOI, the proposed system achieves localization accuracy < 0.73m and with precision 90 % of the distance error less than 2m.

With the development of mobile internet, requirements of positioning accuracy for the LBS (Location Based Service) are becoming more and more higher. The LBS is based on the position of each mobile device. So, it requires a proper acquisition of accurate user's indoor position. Thus indoor positioning technology and its accuracy is crucial for various LBS. In general, RSSI (Received Signal Strength Indicator) measurements are used to obtain the position information of mobile unit under WLAN environment. However, indoor positioning error increases as multiple AP's configurations are becoming more complex. To overcome this problem, an enhanced indoor localization method by AP (Access Point) selection criteria adopting DOP (Dilution of Precision) is proposed.

With growing technology, Location Based Services (LBSs) are becoming a vital part of life. The rapid development of mobile internet has offered an opportunity for Wi-Fi indoor positioning to come under the spotlight due to its low cost. Here, indoor positioning is performed using Wi-Fi. The earlier solutions like GPS does not provide efficient positioning in indoor environment due to weak signal reception which makes Wi-Fi more reliable. However, nowadays the accuracy of the traditional indoor positioning algorithms like trilateration cannot meet the practical requirement. This paper proposes the performance analysis of indoor positioning algorithms using Wi-Fi technology based on Received Signal Strength (RSS) from the access points in the network. The positioning algorithms are based on location fingerprinting consisting of two stages: The offline database creation and the online positioning. The RSS values obtained by the mobile device at reference points are sent to the server where all the location fingerprints of all reference points are stored in a database. Coordinates of user position are calculated using positioning algorithms and the position is displayed in terms of 2Dcoordinates of the room and indoor map. Basic Fingerprint algorithm, RSS Fingerprint with minimum Euclidean Distance algorithm and RSS Fingerprint with Euclidean Distance and k-nearest neighbors' algorithm were implemented. Moreover comparison of their performance was carried out in terms of accuracy of position. From the result, it is found that an average accuracy of 0.4962 meters was achieved by RSS Fingerprint with minimum Euclidean distance algorithm.

Towards a better indoor positioning system: A location estimation process using artificial neural networks based on a semi-interpolated database

Indoor localization has been a challenging problem for over a decennium. Wi-Fi Fingerprinting based solutions stand out in comparison with Angle-Of-Arrival (AOA), Time-Of-Arrival (TOA), Time-Difference-Of-Arrival (TDOA) approaches as they inherently incorporate radio propagation models in fingerprints (FP) which provide more realistic information than radio signal propagation models as well as do not need extra hardware. Diverse Location Based Services (LBS) heavily rely on the performance of localization algorithms used for pattern matching with the collected FP database. This work investigates the performance of several machine learning algorithms as a multiclass classifier for room-level indoor localization including K*, k-NN, Random Forest, FURIA, Multi-Layer Perceptron, and J48. We report results of top five algorithms along with five algorithms selected from various algorithmic categories obtaining an accuracy greater than 95%. Data was generated by collecting 14,080 fingerprints from 20 Access Points at 180 reference points in 1209 m2 area of Software Engineering Center, University of Engineering and Technology (UET), Lahore to construct real-world FP dataset. The results obtained indicate that the best performance is achieved by K* followed by k-NN, Random Forest, FURIA, Multilayer Perceptron, J48 with accuracies 99.52, 99.06, 98.76, 97.26, 97.05, and 95.91% respectively.

The Global Positioning System (GPS) is one of the core technologies for the Location Based Service (LBS), and has various applications from the leisure business to the military. LBS requires accurate location information of an object, which GPS estimates using at least four satellites. In order to enhance the GPS signal quality, angle-of-arrival (AOA) information is required, but these are difficult to estimate because the system operates with a low signal-to-noise ratio (SNR) and in the presence of high-power interference. In this paper, we explore an extension of a recently proposed GPS AOA estimation technique based on a modified despreader for multiple GPS signals. Since the extended estimator does not require a singular value decomposition (SVD), unlike conventional AOA estimation algorithms such as Multiple Signal Classification (MUSIC), it has a relatively low computational complexity. Also, this technique does not need to choose the GPS AOAs from all estimated AOAs because those of the interference signals are not estimated. We demonstrate the performance of the GPS AOA estimation algorithm for multiple satellites via a computer simulation example.

Traditional Angle of Arrival (AoA)-based WiFi array indoor localization algorithms do not fuse Channel State Information (CSI) inter-packet data for estimation, which makes WiFi arrays less effective for localization in complex indoor environments. Most algorithms are overburdened leading to inefficient localization. To address these issues, in this article, an indoor positioning algorithm based on Higher-Order Singular Value Decomposition (HOSVD) is proposed. First, the CSI data are reconstructed as a new measurement matrix by borrowing subcarriers, and a third-order tensor is constructed. Next, tensor compression techniques are used to reduce computational complexity and the signal subspace is obtained by HOSVD. Then, the AoA is obtained by the Reduced Dimension Multiple Signal Classification (RD-MUSIC) method. Finally, the coordinates of the target can be obtained by triangulating the AoAs of the three Access Points (APs). According to the simulation experiments, the AoA can be estimated accurately at a low SNR and with low snapshots. In practical experiments, we can successfully estimate the AoA in complex indoor environments with shorter timelines using HOSVD without modifications to commercial hardware and produce a lower AoA error and localization error rates compared to other algorithms. The effectiveness of our proposed algorithm is proven by simulations and practical experiments.

With the development of the Internet of Things, location-based services are becoming ubiquitous. Rapid and accurate deployment of access points (AP) in indoor environments is an effective way to improve the positioning accuracy. In this paper, a method is proposed for optimal deployment of indoor positioning access points based on Deep Deterministic Policy Gradient Algorithms (DDPG). With this method, the APs, in their initial states, are randomly placed in the target area under the premise of ensuring full network coverage. Each AP is regarded as an agent, and the optimal objective of AP deployment is defined as achieving the maximum Euclidean distance of the reference signal. The priority experience replay mechanism is introduced in this process, which guides the behavior by performing a series of actions and interacting with the environment to obtain the maximum reward for the agent. Simulation experiments are carried out to evaluate the performance of the proposed method. The results show that the proposed deployment method can converge quickly. Compared with the random deployment method and the maximization-minimization method, the proposed deployment method can effectively improve the positioning accuracy.

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.

Radio channel state information (CSI) measured with many receivers is a good resource for localizing a transmitter device with machine learning with a discriminative model. However, CSI localization is nontrivial when the radio map is complicated, such as in building corridors. This article introduces a view-selective deep learning (VSDL) system for indoor localization using CSI of WiFi. The multiview training with CSI obtained from multiple groups of access points (APs) generates latent features on a supervised variational deep network. This information is then applied to an additional network for dominant view classification to minimize the regression loss of localization. As noninformative latent features from multiple views are rejected, we can achieve a localization accuracy of 1.28 m, which outperforms by 30% the best known accuracy in practical applications in a complex building environment. To the best of our knowledge, this is the first approach to apply variational inference and to construct a practical system for radio localization. Furthermore, our work investigates a methodology for supervised learning with multiview data where informative and noninformative views coexist.

At present, most mature localization technologies are based on the line-of-sight (LoS) environment. However, many human activities occur in the indoor non-line-of-sight (NLoS) environment, and thus localization in this challenging environment is also indispensable. In addition, the localization using a single access point (AP) is more suitable for limited space, such as shopping malls and teaching buildings. Therefore, it is of great significance to study the localization technology of single AP in indoor NLoS environments. This paper proposes a localization algorithm to solve this difficult problem based on the natural reflection path, which can associate the locations of the target, scatterer, and AP. Firstly, the localization model is constructed based on the angle-of-departure ( <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$A$</tex> oD), angle-of-arrival (AoA), and relative-time-of-flight (rToF) of the natural reflection path. Unlike absolute time-of-flight (ToF), rToF can eliminate synchronization errors. Then, we derive the closed form solution of the target location, and the least square (LS) algorithm is used to solve the target location. Finally, we use the commercial-grade ray-tracing simulation software to conduct the experiments. Simulation results show that the algorithm can achieve high localization accuracy with only a few natural reflection paths.

An indoor positioning optimization method based on dimensionality reduction and clustering fusion

In this paper, we introduce two indoor Wireless Local Area Network (WLAN) positioning methods using augmented sparse recovery algorithms. These schemes render a sparse user's position vector, and in parallel, minimize the distance between the online measurement and radio map. The overall localization scheme for both methods consists of three steps: 1) coarse localization, obtained from comparing the online measurements with clustered radio map. A novel graph-based method is proposed to cluster the offline fingerprints. In the online phase, a Region Of Interest (ROI) is selected within which we search for the user's location; 2) Access Point (AP) selection; and 3) fine localization through the novel sparse recovery algorithms. Since the online measurements are subject to inordinate measurement readings, called outliers, the sparse recovery methods are modified in order to jointly estimate the outliers and user's position vector. The outlier detection procedure identifies the APs whose readings are either not available or erroneous. The proposed localization methods have been tested with Received Signal Strength (RSS) measurements in a typical office environment and the results show that they can localize the user with significantly high accuracy and resolution which is superior to the results from competing WLAN fingerprinting localization methods.