Synthetic Trajectory Sharing Indoors under Privacy Constraints

A quickly growing location-based services area has led to increased demand for indoor positioning and localization. Undoubtedly, Wi-Fi fingerprint-based localization is one of the promising indoor localization techniques, yet the variation of received signal strength is a major problem for accurate localization. Magnetic field-based localization has emerged as a new player and proved a potential indoor localization technology. However, one of its major limitations is degradation in localization accuracy when various smartphones are used. The localization performance is different from various smartphones even with the same localization technique. This research leverages the use of a deep neural network-based ensemble classifier to perform indoor localization with heterogeneous devices. The chief aim is to devise an approach that can achieve a similar localization accuracy using various smartphones. Features extracted from magnetic data of Galaxy S8 are fed into neural networks (NNs) for training. The experiments are performed with Galaxy S8, LG G6, LG G7, and Galaxy A8 smartphones to investigate the impact of device dependence on localization accuracy. Results demonstrate that NNs can play a significant role in mitigating the impact of device heterogeneity and increasing indoor localization accuracy. The proposed approach is able to achieve a localization accuracy of 2.64 m at 50% on four different devices. The mean error is 2.23 m, 2.52 m, 2.59 m, and 2.78 m for Galaxy S8, LG G6, LG G7, and Galaxy A8, respectively. Experiments on a publicly available magnetic dataset of Sony Xperia M2 using the proposed approach show a mean error of 2.84 m with a standard deviation of 2.24 m, while the error at 50% is 2.33 m. Furthermore, the impact of devices on various attitudes on the localization accuracy is investigated.

Novel weighted ensemble classifier for smartphone based indoor localization

Where am I in the dark: Exploring active transfer learning on the use of indoor localization based on thermal imaging

Although a number of indoor navigation approaches have been proposed, most either require prior knowledge on floor plans, or relying on extra sensors or images, to provide accurate indoor localization and navigation. This paper presents FreeNavi, a landmark-based indoor navigation algorithm that leverages only WiFi signals to direct users in sophisticated indoor environments without prior device deployment or floor plans. FreeNavi takes advantage of human intelligence as an important input to locate and navigate users based on landmarks. With WiFi fingerprints collected at landmarks and walking traces collected in a crowdsourced manner, FreeNavi is able to create a virtual map connecting landmarks with each other. During navigation, FreeNavi produces human understandable directions based on landmarks in the virtual map. Evaluation result shows that FreeNavi can build mostly correct maps and provide efficient directions to users despite relying only on WiFi signals.

Local Differential Privacy (LDP) mechanisms consist of (locally) adding controlled noise to data in order to protect the privacy of their owner. In this paper, we introduce a new cryptographic primitive called LDP commitment. Usually, a commitment ensures that the committed value cannot be modified before it is revealed. In the case of an LDP commitment, however, the value is revealed after being perturbed by an LDP mechanism. Opening an LDP commitment therefore requires a proof that the mechanism has been correctly applied to the value, to ensure that the value is still usable for statistical purposes. We also present a security model for this primitive, in which we define the hiding and binding properties. Finally, we present a concrete scheme for an LDP staircase mechanism (generalizing the randomized response technique), based on classical cryptographic tools and standard assumptions. We provide an implementation in Rust that demonstrates its practical efficiency (the generation of a commitment requires just a few milliseconds).On the application side, we show how our primitive can be used to ensure simultaneously privacy, usability and traceability of medical data when it is used for statistical studies in an open science context. We consider a scenario where a hospital provides sensitive patients data signed by doctors to a research center after it has been anonymized, so that the research center can verify both the provenance of the data (i.e. verify the doctors’ signatures even though the data has been noised) and that the data has been correctly anonymized (i.e. is usable even though it has been anonymized).

In local differential privacy (LDP), each user perturbs her data locally before sending the noisy data to a data collector. The latter then analyzes the data to obtain useful statistics. Unlike the setting of centralized differential privacy, in LDP the data collector never gains access to the exact values of sensitive data, which protects not only the privacy of data contributors but also the collector itself against the risk of potential data leakage. Existing LDP solutions in the literature are mostly limited to the case that each user possesses a tuple of numeric or categorical values, and the data collector computes basic statistics such as counts or mean values. To the best of our knowledge, no existing work tackles more complex data mining tasks such as heavy hitter discovery over set-valued data. In this paper, we present a systematic study of heavy hitter mining under LDP. We first review existing solutions, extend them to the heavy hitter estimation, and explain why their effectiveness is limited. We then propose LDPMiner, a two-phase mechanism for obtaining accurate heavy hitters with LDP. The main idea is to first gather a candidate set of heavy hitters using a portion of the privacy budget, and focus the remaining budget on refining the candidate set in a second phase, which is much more efficient budget-wise than obtaining the heavy hitters directly from the whole dataset. We provide both in-depth theoretical analysis and extensive experiments to compare LDPMiner against adaptations of previous solutions. The results show that LDPMiner significantly improves over existing methods. More importantly, LDPMiner successfully identifies the majority true heavy hitters in practical settings.

An indoor localization system in wireless sensor networks has become a hot development area. Received signal strength indicator (RSSI)-based localization is a promising technique since it requires a relatively low configuration, battery power and easy control. However, the received signal strength is influenced by channel interference and propagation environments. This characteristic affects channel stability and location accuracy in RSSI-based localization. As a result, we propose a novel indoor localization system consisting of a preprocessing method and a post-processing method. To improve channel stability, the pre-processing method selects an optimal channel in terms of the smallest distance error. The optimal channel is less affected to IEEE 802.11. To develop location accuracy, the post-processing method performs maximum likelihood estimation-based location tracking scheme considering the reliability of the RSSI value measurement. We apply three methods to the existing MLE to improve the reliability of the RSSI value. By using this indoor localization system with preprocessing and post-processing, the location error can be reduced. We also proved the performance of the indoor localization system by conducting experiments in a real indoor environment.

As smartphones are increasingly popular, location-based services (LBSs) have become one of the crucial applications in daily lives. While outdoor localization is relatively easy leveraging GPS signals, localization in indoor environments is difficult due to the lack of GPS. Thus, due to the pervasive deployment of WiFi access points, there have been numerous studies on WiFi based indoor positioning. However, the multi-path fading of WiFi signals causes time-varying received signal strengths of WiFi signals, which leads to poor accuracy of WiFi localization. Moreover, WiFi scanning period, about 3∼4 seconds in general smartphone, may provide poor quality of services in the context of refreshment interval. Motivated by these limitations, we study the usability of tw o other sources that are currently available in smartphones: magnetic field strength and cellular signal strength, for indoor positioning purposes. Our preliminary measurements show that these two sources satisfy three properties needed for localization: time-in-variance, location representativeness and universality. Because these three sensors have their own characteristics, some problems in single sensory data based localization could be complementarily overcome. We will show how to combine the three smartphone sensory data for indoor positioning based on each module's characteristics, and how much accuracy is achieved by the hybrid localization.

Sensors-based and radio frequency (RF)-based indoor localization technology is one of the keys in location-based services. The IEEE 802.11-2016 introduced the Wi-Fi fine timing measurement (FTM) protocol, which provides a new approach for Wi-Fi-based indoor localization. However, Wi-Fi signals are susceptible to complex indoor environments. To improve the positioning accuracy and stability, an enhanced particle filter (PF) with two different state update strategies, a new criterion for divergence monitoring and rapid re-initialization is proposed to integrate the advantages of pedestrian dead reckoning (PDR) and Wi-Fi FTM. In addition, an adaptive tilt compensation is proposed to improve real-time heading estimation of conventional PDR, and the Wi-Fi FTM outliers are detected by displacement estimation of the PDR. The experimental results show that the proposed PF has better localization performance than the single source positioning methods in a typical indoor scenario. The accuracy of final localization is within 1 m in 86.7% of the dynamic cases and the average calculation time is less than 0.5 s when the number of particles is 2000.

WiFi signals based applications, such as indoor localization, human activity recognition and trace tracking, have been increasing attention in the past decade. WiFi signals are sensitive to the change of indoor environment, so the above mentioned applications encounter challenges which contain dynamic indoor environment, device diversity and motion influence. We mainly survey techniques of motion detecting and estimate changes of WiFi signals reflected by motion behaviors. Moreover, we analyze the impact of motion behaviors on applications based on WiFi signals, and deeply research developmental trend of WiFi signals. Finally, we pay closed attention to opportunities and future research directions in this new and large open area.

Distributed K-Means clustering guaranteeing local differential privacy

With the rapid development of the mobile Internet, applications based on indoor localization have received increasing attention. In recent years, WiFi received signal strength (RSS) is widely used in indoor localization for the universally available WiFi infrastructure. However, the WiFi signal could easily be affected by non-line-of-sight and multipath propagation, which reduces the localization accuracy. In this paper, we propose an enhanced indoor localization system using multi-source measurements including WiFi RSS, ultra wideband (UWB) ranging, and inertial sensors to improve the performance. The multi-source measurements collected by users' smartphones are used for site survey in our system. To recover users' trajectories, we propose a crowdsourcing method to construct radio map. Moreover, a reference point clustering approach is used to improve system efficiency. A two-step localization method is proposed to locate a user. Experimental results show that the proposed system achieves better performance than only WiFi-based or UWB-based method.

As a widely established and accessible infrastructure, wireless local area networks (WLANs) have emerged as a viable option for indoor localization for both mobile and stationary users. However, WLANs present several challenges that must be fulfilled to achieve localization based on Wi-Fi signals and to obtain proper coverage prediction maps. This paper presents a study based on the application of extra-trees regression (ETR) for indoor localization using coverage prediction maps. The aim of the proposed method is to accurately estimate a user’s position within a radio environment map (REM) area using collected signal strength indicator (RSSI) values collected by a mobile robot. Our methodology consists of utilizing the RSSI collected values to construct the REM, which is then leveraged to create a dataset for indoor localization. This process involves tracking a user’s movements within a specific area of interest while considering a single access point. The proposed scheme explores various machine learning (ML) regression algorithms, with hyperparameter tuning carried out to optimize their performance through 10-fold cross-validation. To assess the REM, we employed metrics, such as the root mean square error, absolute error, and R-squared error. Additionally, we evaluated the indoor localization accuracy using location error metrics. Among the ML techniques assessed, our proposed ETR-based approach demonstrates the highest performance based on these error metrics. The combination of generating coverage maps and utilizing regression techniques for localization presents a potent approach for analyzing the radio frequency environment in indoor spaces.

This work designs and develops indoor and outdoor navigation architecture for accurate positioning in small areas. It combines sophisticated technologies, including GPS, Google Maps API, and spatial and descriptive data, to create a precise and user-friendly navigation solution. In addition, maintaining an updated database and integrating interactive features facilitates the adoption of future advanced technologies such as Bluetooth Low Energy (BLE) and Wi-Fi networks for improved accuracy in indoor navigation. This architecture is applied at the University of Mosul to guide students and visitors aboard the large university with many campus facilities. The application allows users to find specific colleges and facilities, look for destinations, and find the shortest way to reach their desired location. The testing results show that the application is efficient regarding location accuracy and response speed, with a 95% user satisfaction rate.

Local Differential Privacy (LDP) provides a formal guarantee of privacy that enables the collection and analysis of sensitive data without revealing any individual's data. While LDP methods have been extensively studied, there is a lack of a systematic and empirical comparison of LDP methods for descriptive statistics. In this paper, we first provide a systematization of LDP methods for descriptive statistics, comparing their properties and requirements. We demonstrate that several mean estimation methods based on sampling from a Bernoulli distribution are equivalent in the one-dimensional case and introduce methods for variance estimation. We then empirically compare methods for mean, variance, and frequency estimation. Finally, we provide recommendations for the use of LDP methods for descriptive statistics and discuss their limitations and open questions.