RSS-Fingerprint Dimensionality Reduction for Multiple Service Set Identifier-Based Indoor Positioning Systems

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.

An RSS transform–based weighted k-nearest neighbor (WKNN) indoor positioning algorithm, Q-WKNN, is proposed to improve the positioning accuracy and real-time performance of Wi-Fi fingerprint–based indoor positioning. To smooth the RSS fluctuation difference caused by acquisition equipment, time, and environment changes, base Q is introduced in Q-WKNN to transform RSS to Q-based RSS, based on the relationship between the received signal strength (RSS) and physical distance. Analysis of the effective range of base Q indicates that Q-WKNN is more suitable for regions with noticeable environmental changes and fixed access points (APs). To reduce the positioning time, APs are selected to form a Q-WKNN similarity matrix. Adaptive K is applied to estimate the test point (TP) position. Commonly used indoor positioning algorithms are compared to Q-WKNN on Zenodo and underground parking databases. Results show that Q-WKNN has better positioning accuracy and real-time performance than WKNN, modified-WKNN (M-WKNN), Gaussian kernel (GK), and least squares-support vector machine (LS-SVM) algorithms.

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.

Indoor localization using fingerprinting techniques became more attracting to researchers in recent years because of their high accuracy. However, unpredictable Received Signal Strength (RSS) is one of the challenges. In our proposed system, it can be reduced by using strong Access Points (APs) selection method to select a subset of reliable APs and decrease the input of feature dimension. In addition, the computational cost due to a large fingerprint database was addressed by using Affinity Propagation clustering algorithm. The efficient indoor localization system relies on Support Vector Regression (SVR) due to its advantage of high generalization ability. The detailed results of real experiments indicate that the proposed system using SVR achieved a high accuracy compared to the conventional indoor algorithm.

Selective AP probing for indoor positioning in a large and AP-dense environment

A novel indoor localization method for Wi-Fi devices such as smart phones is presented. With an indoor path loss model, the distance between a mobile device (MD) and an access point (AP) can be estimated form the received signal strength (RSS). Then, least-squared-error (LSE) triangulation yields the position of the MD. Though indoor channel characteristics are highly fluctuating with perturbations, a reference point (RP) can be used to compensate for channel instability. We present two contributions: cross monitoring AP and weighted triangulation. Cross monitoring AP removes the need of deploying RPs since it can play the dual role of a regular AP and a RP. Weighted triangulation yields improvement in the accuracy of LSE estimation of the MD position. Experimental results show weighted triangulation with cross monitoring AP provides indoor localization with an error less than 2 meters.

This paper focuses on the implementation problems for indoor positioning system, whose main process includes building fingerprint database, ranging and matching online. During the construction of a fingerprint map, signal characteristics are collected at known positions or reference points in a building. While in the ranging and online phase, mobile device application scans access points around and selects two access points from which received signal strengths are stronger, then we convert the signal strengths into a rectangular region where the user is surely inside it. Meanwhile, the current fingerprint probability distributions are compared with the offline radio fingerprint map. The user's location is estimated by calculating the smallest Bhattacharyya distance in the above-mentioned rectangular region. Experiments show that our method by means of parameter optimizing reaches a median error of 2.82m, which is superior to the median error of 3.4m by traditional Wi-Fi fingerprint.

Optical Camera Communication (OCC) is an emerging technology that has attracted research interest in recent decades. Unlike previous communication technologies, OCC uses visible light as the medium to transmit data from receivers and cameras to receive the data. OCC has several advantages that can be capitalized in several implementations. However, the Internet of Things (IoT) has emerged as a technology with immense potential. Numerous research endeavors support the IoT’s prospective technology that can be implemented in various sectors, including the healthcare system. This study introduces a novel implementation of the Internet of Medical Things (IoMT) system, using OCC for real-time health monitoring and indoor location tracking. The innovative system uses standard closed-circuit television CCTV setups, integrating deep learning-based OCC to monitor multiple patients simultaneously, each represented by an LED matrix. The effectiveness of the system was demonstrated through two scenarios: the first involves dual transmitters and a single camera, highlighting real-time monitoring of vital health data; the second features a transmitter with dual cameras, focusing patient movement tracking across different camera fields of view. To accurately locate and track the position of LED arrays in the camera, the system used YOLO (You Only Look Once). Data are securely transmitted to an edge server and stored using the REST API, with a web interface providing real-time patient updates. This study highlights the potential of OCC in IoMT for advanced patient care and proposes future exploration in larger healthcare systems and other IoT domains.

Currently, an indoor positioning system based on a fingerprint technique for wireless networks under IEEE 802.11 standard uses a method to collect a received signal strengths (RSS) to create a radio map in an offline phase. Then, it detects the RSS in an online phase to compare and find the position. However, while detecting and gathering the RSS, there are some variations of the RSS that affect the accuracy of position estimation. Therefore, there are several methods used to estimate the position in order to improve the accuracy, but the one focused in this paper is a decision tree based classification. The decision tree based classification method is found that it can provide better improvement in accuracy than the others, e.g., K-Nearest Neighbor (K-NN), Bayesian, and Neural networks. However, the techniques used to construct the decision tree are varied depending on the algorithm used to implement. Therefore, this paper is a comparison of decision tree based techniques using typical decision tree (DT) and Gradient boosted tree algorithms for estimating the position indoor. In the study, the RSSs collected from access points in the experimental area are used as the training and testing data. The decision tree models are created by using typical DT and Gradient boosted algorithms based on the training data obtained. There are two factors to consider in the comparative study, i.e., the number of training data and the number of reference radio signals. The testing results from the experiment showed that the decision tree based on Gradient boosted algorithm yielded more accurate results than typical DT, where the amount of 19 reference radio signals and 50 samples of training data gave the best result.

The most viable strategy to establish a dependable indoor positioning system is by employing the received signal strength (RSS) based fingerprinting technique, which encompasses both the offline and online phases. The offline phase involves constructing a radio map, which can be arduous in vast indoor environments. To tackle this, radio map interpolation is often used to interpolate RSS by utilizing the RSS recorded at a coarser level of known reference points (RPs). This paper proposes a novel RSS-based radio map interpolation to enhance the existing inverse distance weighting (IDW) interpolation technique. The method divides the deployment area into zones and optimizes the density of known RPs in each zone based on the number of access points (APs) with average RSS exceeding the threshold. It allocates higher RP density for the zones with poor AP coverage and reduces it for well-covered zones. Results demonstrates that the proposed method achieves substantial improvements over the baseline IDW scheme in average positioning error of up to 6.58% at the floor level and 3.77% overall.

Indoor localization systems have already wide applications for providing localized information and directions. They can also be very useful in medical applications, as an individual’s indoor movements can be indicative of his/her clinical status. Research for indoor localization systems is ongoing and there are numerous solutions with different hardware or algorithmic approaches, for different use cases. Ease of setup and cost are significant factors when using indoor localization systems for medical applications. This paper proposes an indoor localization system with room-level accuracy, focusing on an easy installation procedure that can be easily followed from non-technical staff, as well as on low cost, so that it can be widely adopted. The proposed system has been mainly designed for behavioural monitoring of adults in an indoor environment. The system operates by tracking a carried device based on the processing of RSS (Received Signal Strength) measurements from Bluetooth Low Energy beacons placed in the area. The proposed system has been evaluated in realistic settings and and achieves an accuracy of 95.31% in room estimation.

In indoor location environment, shadowing, multipath and reflection phenomena make the position estimation inaccurate. Large number of Access Points (APs) equipped with single antenna could obtain enough Receive Signal Strength (RSS) information to describe signal characteristics of the target space. However, it results in a large investment costs. This paper provides a novel indoor positioning solution using the multi-antennas architecture to increase the accuracy of location estimation. The system obtains enough RSS to compute the user location and provides a reasonable cost of deployments in indoor location environment. Experimental and numerical results show that the proposed indoor location estimation demonstrates a high accuracy of positioning and outstanding performance when RSS is collected by smart antenna technique. More specifically, the accuracy is increased from 1.34% to 92.4% and the error variance is reduced by 96% as compared to the traditional location fingerprint method.

It is usually possible to associate with more than one Access Point (AP) in IEEE 802.11 Wireless LANs. AP selection is a crucial issue because the performance achieved by a user heavily depends on the AP selected. A received signal strength (RSS)-based association mechanism is specified by the IEEE 802.11 standard. However, this does not consider the channel conditions and AP load, which leads to a low throughput and a low user transmission rate. An alternative to using the RSS is to exploit the airtime metric, which provides users with information on how busy the channel is, but the results of our simulations show that the airtime metric cannot indicate the exact status of the channel. In this paper, we present a new association framework using channel occupancy in order to provide users with exact channel status information of APs. Via the proposed scheme, users can compare the achievable throughput provided by each AP and select the best AP. We validate our proposed association method via simulation results, which show that the throughput improvement of the method is worthy of notice.

With the proliferation of the Internet of Things (IoT), employing Received Signal Strength (RSS) as a metric to determine the location of a target (e.g., person or mobile device) is of great interest in terms of cost and ease of implementation. Indeed, RSS measurements can be easily obtained for most off-the-shelf devices, such as WiFi- or ZigBee compatible devices or sensors. This paper deals with the indoor localization problem in wireless sensor networks (WSNs) and proposes a new approach for radio signal propagation modelling and localization estimation, that accounts for the imperfection of RSS measurements and the reliability of RSS sources by using the Dempster-Shafer Theory (DST). In the signal propagation modelling, key information regarding the geometry of indoor environment that is divided into zones separated by walls (zoning), are considered. Based on the number of walls, the RSS irregularities are estimated using different distance intervals, which are weighted by a probability density determined experimentally. To estimate the location of a target node, the PCR6 rule is used to combine the belief masses of the positions obtained from the probability density. In order to evaluate the performance of the proposed approach, an experimental WSN has been deployed in a living apartment. The obtained results demonstrate that the proposed approach improves the localization accuracy compared to the case without zoning. Moreover, the obtained localization mean error proves the feasibility of a precise localization of humans in indoor environments in the case of Ambient Assisted Living and Social Robotics applications.

In this paper, a real WiFi fingerprint based indoor localization system is considered for experiments, including three primary components: the APP in the smart phone, the server system and the embedded localization algorithm. As we all know, one of the main drawbacks in fingerprint based localization is the labor intensity and time consumption of data collection. This paper proposes an improved graph-based semi-supervised learning (I-GSSL) to better overcome this problem. Apart from taking advantage of the indoor propagation model, the I-GSSL algorithm is proposed to handle the existing out-of-sample problem where an elastic regularization is considered as an extra constraint. Meanwhile, due to unequal amount of location information in the received signal strength (RSS) from different access points (APs) and the redundancy of RSS at APs, a double weighted K nearest neighbor (DWKNN) algorithm is proposed for localization. Experimental results show the proposed scheme achieves a better label propagation and localization accuracy.