WI-LO: Wireless indoor localization through multi-source radio fingerprinting

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.

Wireless indoor localization has attracted extensive research recently due to its potential for large-scale deployment. However, the performances of different systems vary and it is difficult to compare these systems systematically in different indoor scenarios. In this work, we propose \(E^3\), a Gaussian process based error estimation approach for fingerprint-based wireless indoor localization systems. With an efficient error estimation algorithm, \(E^3\) is able to efficiently estimate the localization errors of the localization systems without requiring the expensive site evaluations. Our evaluation results show that the proposed approach efficiently estimates the performance of fingerprint-based indoor localization systems and can be used as an efficient tool to tune system parameters.

As a result of the drastic increase in the number of mobile device users, there is considerable public debate about possible health hazards especially due to base stations and Wi-Fi access points. For this reason, in this study the effects of the number of users in a base station and wireless fidelity (Wi-Fi) access point on electric field strength (E) levels were investigated using real-time measurements. Two-stage E measurements were performed on Ondokuz Mayıs University's (OMU) Kurupelit Campus with a PMM-8053 and SRM-3006 electromagnetic field (EMF) meter. In the first stage, 24-h measurements were performed with PMM-8053 at the location where the maximum E was measured and from which the busiest times of the day were then determined. The relationship among band selective E values was assessed using the number of users per minute provided by three cellular system operators for the location. Upper and lower bounds of E according to the number of users were calculated, and then an empirical model that helps calculate the E of medium with 86% accuracy was proposed. In the second stage, the effect of the number of users in a Wi-Fi access point on E level was investigated. For this purpose, the measurement environment was set as including one Wi-Fi access point with needed measurement devices. The number of users was increased as per user per minute. The number of users was validated with the data obtained from OMU IT Department. Using the measurement result, a model with a 96% accuracy between the E value in the environment and the number of users accessing the Wi-Fi system is proposed. With the use of these models, E level in the medium can be determined without using any EMF meters, thus precautions can be taken to stay within regulatory limits.

Bluetooth Low Energy (BLE) based Wireless Indoor Localization System (WILS) with high localization accuracy and high localization precision is a key requirement in enabling the Internet of Things (IoT) in today’s applications. In this paper, we investigated the effect of BLE signal variations on indoor localization caused by the change in BLE transmission power levels. This issue is not often discussed as most of the works on localization algorithms use the highest power levels but has important practical implications for energy efficiency, e.g., if a designer would like to trade-off localization performance and node lifetime. To analyze the impact, we used the established trilateration based localization model with two methods i.e., Centroid Approximation (CA) and Minimum Mean Square Error (MMSE). We observed that trilateration based localization with MMSE method outperforms the CA method. We further investigated the use of two filters i.e., Low Pass Filter (LPF) and Kalman Filter (KF) and evaluated their effects in terms of mitigating the random variations from BLE signal. In comparison to non-filter based approach, we observed a great improvement in localization accuracy and localization precision with a filter-based approach. Furthermore, in comparison to LPF based trilateration localization with CA, the performance of a KF based trilateration localization with MMSE is far better. An average of 1 m improvement in localization accuracy and approximately 50% improvement in localization precision is observed by using KF in trilateration based localization model with the MMSE method. In conclusion, with KF in trilateration based localization model with MMSE method effectively eliminates random variations in BLE RSS with multiple transmission power levels and thus results in a BLE based WILS with high accuracy and high precision.

Wireless Indoor Localization Using Passive RFID Tags

The car navigation service has opened through the global positioning system (GPS). People's lives have changed through car navigation services, and this service is indispensable nowadays. GPS provides reliable location accuracy in open space, but its location accuracy is degraded where multipath and other error factors are present. In particular, since GPS signals must be received in order to calculate the position, the navigation system cannot calculate the position in an indoor space such as underground parking lot, subway or tunnel where GPS signals are cut off. When car navigation is performed in an indoor parking lot where GPS signals are not transmitted, the user cannot calculate the current location, so the user has to go out by relying on the traffic sign because he does not know the current location. Also, when the user leave the parking lot, the car navigation system has problems. In an urban canyon, it is difficult to calculate accurate current position due to multipath. Because the route is calculated through the current location and route, the car navigation system provides the wrong route to the user. In addition, when entering a tunnel while using car navigation, the car navigation system calculates the position using the initial tunnel entry velocity estimated by the GPS. As the speed of the user increases or decreases, the position error also increases. Then the position suddenly changes when passing through the tunnel. And it is difficult to provide a proper guidance at the branch road or exit in the tunnel because of the positioning error. People are demanding a complete car navigation service, but the current navigation service provides the wrong route and position information to the user where the GPS signal quality is poor. In order to solve the above problem, in this paper, we have studied to improve the user's position accuracy by using LTE signal and mobile phone internal sensor. In general, observed time difference of arrival (OTDOA) technique is applied for the LTE based positioning. Because this method gives tens of meters of error, it is difficult to be used for the car navigation service. In our research, we estimate the position using the LTE signal strength. The difference from conventional fingerprinting method is that instead of using only current signal strength, the signal strength pattern accumulated while moving is utilized to estimate the user position. The signal strength increases as the user approach the access point (AP), and decreases as the user move away from the AP. Therefore, when a user moves and stores signal strength with respect to a specific AP, a pattern that could occur only in the corresponding region is saved. There are many similar candidates in the database when using only the current signal strength. However, when using a pattern, similar candidates exist only around the true position. And, when using several LTE signals, the positioning accuracy could be increased. Since the user receives multiple LTE signals, the pattern becomes surface. The surface is compared with the database, and the position with the highest correlation value is estimated as the current position. We call this method surface correlation (SC). In order to verify the performance of the proposed method, experiments were conducted in the Gangnam beltway tunnel in Seoul. The testbed consisted of three tunnel and total distance is almost 11.8 Km. In the tunnel, repeater and several antennas are installed to widen the area of the LTE signal. When an LTE signal is received by the vehicle, the largest signal strength is received every time when the vehicle passes the nearest antenna. As a result, for a specific LTE signal, when the vehicle has passed through the LTE signal region, a unique pattern with multiple peaks is generated. In order to estimate the position, we first estimate the position with the SC technique. Then, the estimated position is corrected by comparing the peak of the currently received pattern with the peak of the database. Through this method, the position was estimated with an error of less than 50meter in the tunnel. Conclusion In this research, the LTE signal strength based positioning technology is presented. Especially, this technology, SC, provides the positioning performance that could be used for the car navigation in the tunnel where GPS signal is blocked. We expected that user would be use the accurate car navigation service through this technology in the GPS challenging environment.

The indoor subarea localization is of great significance in the application of dynamic hot-zone identification, indoor layout optimization, store dynamic pricing and crowd flow trend prediction. The ubiquitous mobile devices provide the opportunity for wireless fingerprinting-based indoor localization services. However, there are two places where the existing methods have been criticized. One is a tagging approach that requires a large number of professional surveys, with too much overhead wireless fingerprint construction and the weakened system scalability. The other is the crowdsourcing fingerprint-based methods meet the cold start problem in the initial stage of the operation. To attack these problems, the paper proposes a topology optimization approach with dynamic logical anchor selection for a subarea localization system. First of all, taking advantage of the feedback selection of logic anchor, a new annular-based radio map construction strategy is presented. The implementation of this strategy harnesses the characteristics of the indoor building structure and inter-subarea overlapping recognition, without depending on the topology and distribution of physical anchor (e.g., Access points or POIs). Secondly, exploiting the probabilistic support vector machine algorithm, the target is localized in the corresponding subarea in real-time pattern. Furthermore, the localization error is used to calibrate the localization result with an error recognition algorithm. Finally, massive experiments and simulations are implemented on a prototype system. The results show that the proposed method can decrease the human effort and computing cost and achieve higher localization accuracy compared with the existing approaches.

Wireless indoor localization is a significant challenge because of the noise generated by building structures, electromagnetic fields, and distances between connected nodes inside a building. This study compares two main localization methods: fingerprints (real and synthetic) and ranging schemes based on the Received Signal Strength Indicator (RSSI) of the ZigBee network. We followed four steps for the fingerprinting scheme. First, we obtained real data from the transceivers. Second, we computed the path-loss exponent for each device. Third, we produced a synthetic fingerprint dataset. Finally, we used three localization methods: k-nearest neighbor (KNN), multilayer perceptron (MLP), and long short-term memory recurrent neural network (LSTM-RNN). We assessed the performance of the localization methods by measuring their accuracy, precision, error-to-active area ratio, and installation difficulties. The results show that the real fingerprint scheme has the best performance, but it requires more installation time. While the synthetic fingerprint generation is based on the path-loss method that mixes the advantage of both fingerprint and path-loss. Furthermore, we compared the proposed estimated path-loss with that of a state-of-the-art method and demonstrated that the proposed method exhibits superior performance. These results suggest that the proposed method is more precise and suitable for real datasets.

Optimizing AP and Beacon Placement in WiFi and BLE hybrid localization

Precise localization of Wi-Fi Access Point (AP) is becoming increasingly important with the rise of diverse location-based services based on smartphone. In this article, we propose a new method for precise Wi-Fi AP localization using GPS information of smartphone. The idea is that the possible area of Wi-Fi AP location, called AP_Area, is first determined by measuring GPS information and the Received Signal Strength (RSS) of smartphones from Wi-Fi AP. As the number of measurement points from users' smartphones increases, the AP_Area can be successively narrowed down to the actual AP location. Simulation results show that the proposed algorithm can detect the Wi-Fi AP localization within 5 m (probability over than 80%).

While wireless local area network-based indoor localization is attractive, the problems concerning how to capture the signal-propagating character in the complex dynamic environment and how to accommodate the receiver gain difference of different mobile devices are challenging. In this article, we solve these problems by modeling them as common mode noise and develop a localization algorithm based on a novel differential radio map approach. We propose a differential operation to improve the performance of the radio map module, where the location is estimated according to the difference of received signal strength (RSS) instead of RSS itself. The particle filter algorithm is adopted to realize the target localization and tracking task. Furthermore, to calculate the particle weight at arbitrary locations, we propose a local linearization technique to realize continuous interpolation of the radio map. The indoor experiment results demonstrate the effectiveness and robustness of our approach.

Indoor positioning technologies are of great use in GPS-denied areas. They can be partitioned into two types of systems—infrastructure-free based and infrastructure-dependent based. WiFi based indoor positioning system is somewhere between the infrastructure-free and infrastructure-dependent systems. The reason is that in WiFi based systems, Access Points (APs) as pre-installed infrastructures are necessary. However, the APs do not need to be specially installed, because WiFi APs are already widely deployed in many indoor areas, for example, offices, malls and airports. This feature makes WiFi based indoor positioning suitable for many practical applications. In this paper, a seq2seq model based, deep learning method is proposed for WiFi based fingerprinting. The model can learn from different length of training sequences, and thus can exploit the context information for positioning. The context information denotes the information contained in the sequence, which can help finding the correspondences between RSS fingerprints and the coordinate positions. A simple example piece of context information is human walking routine (such as no sharp turns). The proposed method shows an improvement with an open source dataset, when compared against deep learning based counterpart methods.

Map information and sensor information is considered to be an effective way to assist indoor wireless location. Wireless location combined with map information and Sensor information can solve many problem such as positioning point cross the wall, falling into the wrong room. In this paper, a new indoor map matching algorithm was proposed based on particle filter. The indoor positioning system could be considered as non-linear system, so Non-parametric Monte Carlo (Monte Carlo) simulation method could achieve recursive Bayesian filtering, at the same time, the indoor GIS data, and sensor information, wireless location information was incorporated into the weight value of the particles to revise the observations constantly. Many experiments show that the indoor positioning accuracy is improved.

More and more applications of location-based services lead to the development of indoor positioning technology. Wi-Fi-based indoor localization has been attractive due to its extensive distribution and low cost properties. IEEE 802.11-2016 now includes a Wi-Fi Fine Time Measurement (FTM) protocol which provides a more robust approach for Wi-Fi ranging between the mobile terminal and Wi-Fi access point (AP). To improve the positioning accuracy, in this paper, we propose a robust dead reckoning algorithm combining the results of Wi-Fi FTM and multiple sensors (DRWMs). A real-time Wi-Fi ranging model is built which can effectively reduce the Wi-Fi ranging errors, and then a multisensor multi-pattern-based dead reckoning is presented. In addition, the Unscented Kalman filter (UKF) is applied to fuse the results of Wi-Fi ranging model and multiple sensors. The experiment results show that the proposed DRWMs algorithm can achieve accurate localization performance in line-of-sight/non-line-of-sight (LOS)/(NLOS) mixed indoor environment. Compared with the traditional Wi-Fi positioning method and the traditional dead reckoning method, the proposed algorithm is more stable and has better real-time performance for indoor positioning.

In this paper, we present Wi-Cache, an SDN (Software Defined Networking) based distributed content caching system in a wireless local area network (WLAN). One way to effectively reduce congestion in the backhaul links of today's IP network is caching videos and non-voice traffic closer to mobile and wireless devices. Cellular base stations and WiFi access points (APs) are the major serving points and the closest network nodes to mobile and wireless devices. WiFi APs are becoming a part of heterogeneous cellular networks (HCNs), and are also present abundantly at homes and workplaces. Therefore, one viable solution to reduce the bandwidth consumption of backhaul links is caching contents in these WiFi APs so that user requests can be served locally. Wi-Cache caches contents on low-cost wireless APs, and delivers them to mobile clients when they are requested. It minimizes the need to fetch contents from remote content servers. It also addresses two major WLAN challenges during content delivery-client mobility and load balancing on WiFi APs. Wi-Cache prototype implementation, and the evaluation of its feasibility and performance is based on Odin, an open source SDN framework for enterprise WLANs.