scispace - formally typeset
Search or ask a question
Proceedings ArticleDOI

Mining channel state information from bluetooth low energy RSSI for robust object-to-object ranging

TL;DR: This work proposes a truly unsupervised approach for channel-annotation of RSSI data received by a stationary receiver object and proposes a sliding-window based algorithm which utilizes two well-established Likelihood-Ratio algorithms - KLIEP and uLSIF - for extracting Channel State Information of retrospective RSSI observation data.
Abstract: In the world of smart objects, device-ranging and localization using Bluetooth Low Energy (BLE) is becoming popular due to its attractive energy performance, wide platform support and low costs. There has been sufficient motivation on statistical analysis of Channel State Information of Received Signal Strength Indicator (RSSI) data for more effective ranging-based models. However, there has been no ubiquitous solution which is both receiver-agnostic and does not require alteration in the advertisement protocol or packet structure of BLE. In this paper, we propose a truly unsupervised approach for channel-annotation of RSSI data received by a stationary receiver object. Given a sequence of RSSI observations and a discoverable receiver channel-switching policy, we determine the period and hence the time spent by the receiver in an individual channel. Then, we propose a sliding-window based algorithm which utilizes two well-established Likelihood-Ratio algorithms - KLIEP and uLSIF - for extracting Channel State Information of retrospective RSSI observation data. We believe this work lays the foundation of motivating future work in completely unsupervised methods for object-to-object ranging and localization.
Citations
More filters
Proceedings ArticleDOI
22 Feb 2019
TL;DR: AIDE offers a streamlined on-boarding process by automatically associating devices at different locations with their corresponding Received Signal Strength (RSS) profiles, which can be applied to a wide range of wireless technologies such as WiFi, BLE and Zigbee.
Abstract: In order to use and manage IoT devices, a prerequisite is to onboard them so that they can be initialized and connected to the infrastructure. This requires mapping each physical device with its digital identity. Doing so manually is tedious, error-prone and not scalable. In this paper, we propose AIDE, a mechanism that provides Augmented onboarding of IoT Devices at Ease. AIDE offers a streamlined on-boarding process by automatically associating devices at different locations with their corresponding Received Signal Strength (RSS) profiles, which can be applied to a wide range of wireless technologies such as WiFi, BLE and Zigbee. AIDE does not require additional infrastructure or hardware support, and can work by simply using a COTS smartphone as receiver. The mechanism employs a carefully designed measurement approach and a post-processing algorithm to mitigate multi-path effect and improve measurement accuracy. Preliminary experiments in different indoor environments show that AIDE achieves about 90% on-boarding accuracy when devices are 6 feet away from the measurement point, and 100% accuracy when devices are directly approachable.

2 citations


Cites methods from "Mining channel state information fr..."

  • ..., hopping) and each channel has its own characteristics, we want to explore techniques such as channel separation [12] and leverage different channels separately to improve the accuracy....

    [...]

Journal ArticleDOI
01 Aug 2022
TL;DR: The positioning accuracy of the positioning model in complex situations is increased, the anti-interference of the data is improved, and the accurate positioning of the motion trajectory is realized.
Abstract: At present, there have been many researches on indoor location, but due to the weak signal penetration ability in distance-based measurement, it is very easy to be blocked by obstacles, so the accuracy of location will be greatly affected in complex environments. In this paper, the problem of ultra wideband indoor precise positioning under signal interference is studied in order to improve the indoor positioning accuracy of the model under complex conditions and ensure its anti-interference. Firstly, data cleaning is performed, the missing data group is filled or deleted by using the traditional data preprocessing method, and the filtering technology is used to identify and delete outliers. Secondly, the positioning model is established, the distance between the target and the anchor is calculated by using the ranging principle based on the time of flight(TOF), and the genetic algorithm is used for optimization operation to find the target coordinates that meet the minimum absolute value difference between the distance from the target to each anchor and the actual value, so as to continuously train the positioning model. In addition, since UWB(ultra-wideband) technology is unknown whether there is signal interference in the collected data, the classification model is established by the method of amplifying the influence of outliers by means of average, which improves the accuracy of the model in judging whether there is signal interference. Thus, the positioning accuracy of the positioning model in complex situations is increased, the anti-interference of the data is improved, and the accurate positioning of the motion trajectory is realized.
Proceedings ArticleDOI
08 Oct 2018
TL;DR: My research interests lie in developing systems for event detection and pattern recognition using smartphone sensor data, and leveraging micro-events for deep context mining including human-human interactions and behavior.
Abstract: I am a fifth year Ph.D. Student (enrolled January '14) working in Data Science (Department of Mathematics) at Shiv Nadar University, India. I have an undergraduate major in Computer Science, and my research interests lie in two primary areas - (i) developing systems for event detection and pattern recognition using smartphone sensor data, and (ii) leveraging micro-events for deep context mining including human-human interactions and behavior. Having been an active part of the ubiquitous computing research community during my undergraduate as well as during my Ph.D. (expected completion Summer '19), my future aspirations are to join as a post-doctoral researcher in the same field, and continue to build upon my skills and contribute both as an active researcher as well as a mentor for budding undergraduate students.

Cites background from "Mining channel state information fr..."

  • ...My recent work towards the goal above - to model systems for human-human interaction analysis [1] - deals with RSSI based ranging models for heterogeneous Bluetooth Low Energy (BLE) devices, particularly smartphones and BLE Beacons....

    [...]

Proceedings ArticleDOI
01 Aug 2022
TL;DR: In this paper , the problem of ultra wideband indoor precise positioning under signal interference is studied in order to improve the indoor positioning accuracy of the model under complex conditions and ensure its anti-interference.
Abstract: At present, there have been many researches on indoor location, but due to the weak signal penetration ability in distance-based measurement, it is very easy to be blocked by obstacles, so the accuracy of location will be greatly affected in complex environments. In this paper, the problem of ultra wideband indoor precise positioning under signal interference is studied in order to improve the indoor positioning accuracy of the model under complex conditions and ensure its anti-interference. Firstly, data cleaning is performed, the missing data group is filled or deleted by using the traditional data preprocessing method, and the filtering technology is used to identify and delete outliers. Secondly, the positioning model is established, the distance between the target and the anchor is calculated by using the ranging principle based on the time of flight(TOF), and the genetic algorithm is used for optimization operation to find the target coordinates that meet the minimum absolute value difference between the distance from the target to each anchor and the actual value, so as to continuously train the positioning model. In addition, since UWB(ultra-wideband) technology is unknown whether there is signal interference in the collected data, the classification model is established by the method of amplifying the influence of outliers by means of average, which improves the accuracy of the model in judging whether there is signal interference. Thus, the positioning accuracy of the positioning model in complex situations is increased, the anti-interference of the data is improved, and the accurate positioning of the motion trajectory is realized.
Proceedings ArticleDOI
12 Apr 2021
TL;DR: This paper assesses the robustness of an IPS system built that uses BLE and ML by executing a distance fraud attack, and shows a significant difference between the calculated positions of the system operating under benign conditions and operating under attack.
Abstract: Determining position within an indoor environment can be difficult when GPS signals become too weak. For this reason, alternatives are desired for indoor positioning systems (IPSes). The Bluetooth Low Energy (BLE) protocol is one alternative solution for IPSes. BLE is a low power wireless technology used for connecting devices with each other. There are two different methods for using BLE for localization: deterministic, and machine learning (ML) models. Each method uses a measured received signal strength indicator (RSSI) to determine distances from fixed, known locations. Deterministic models rely on empirical equations relating signal strength to distance, while ML uses collected signal strengths, or fingerprints, to learn positions. This paper assesses the robustness of an IPS system we built that uses BLE and ML by executing a distance fraud attack. A distance fraud attack causes intentional miscalculations of positions. The attack executed on the system assumes the attacker has network access and has compromised some small fraction of the receiving nodes. The results show a significant difference between the calculated positions of the system operating under benign conditions and operating under attack. We explore one possible defense against this attack by training an ML system for attack identification.

Cites background from "Mining channel state information fr..."

  • ...In [12], it is stated that RCPI overcomes these limitations by providing a quantized, comparative measure of power level for all channels/rates and among all PHYs and STAs....

    [...]

References
More filters
Journal ArticleDOI
TL;DR: This survey article enumerates, categorizes, and compares many of the methods that have been proposed to detect change points in time series, and presents some grand challenges for the community to consider.
Abstract: Change points are abrupt variations in time series data. Such abrupt changes may represent transitions that occur between states. Detection of change points is useful in modelling and prediction of time series and is found in application areas such as medical condition monitoring, climate change detection, speech and image analysis, and human activity analysis. This survey article enumerates, categorizes, and compares many of the methods that have been proposed to detect change points in time series. The methods examined include both supervised and unsupervised algorithms that have been introduced and evaluated. We introduce several criteria to compare the algorithms. Finally, we present some grand challenges for the community to consider.

788 citations


"Mining channel state information fr..." refers methods in this paper

  • ...For Unsupervised CSI accuracy, we use a similar variant of the Mean Root Mean Square (MRMS) period difference (known period = 15s or 150 observations) - as given in [1]....

    [...]

  • ...Unsupervised segmentation algorithms [1] have been used to segment time series data, thus finding change points based on data features, and are essentially attractive because they may handle a variety of different situations without requiring prior training for each situation....

    [...]

Proceedings Article
03 Dec 2007
TL;DR: This paper proposes a direct importance estimation method that does not involve density estimation and is equipped with a natural cross validation procedure and hence tuning parameters such as the kernel width can be objectively optimized.
Abstract: A situation where training and test samples follow different input distributions is called covariate shift. Under covariate shift, standard learning methods such as maximum likelihood estimation are no longer consistent—weighted variants according to the ratio of test and training input densities are consistent. Therefore, accurately estimating the density ratio, called the importance, is one of the key issues in covariate shift adaptation. A naive approach to this task is to first estimate training and test input densities separately and then estimate the importance by taking the ratio of the estimated densities. However, this naive approach tends to perform poorly since density estimation is a hard task particularly in high dimensional cases. In this paper, we propose a direct importance estimation method that does not involve density estimation. Our method is equipped with a natural cross validation procedure and hence tuning parameters such as the kernel width can be objectively optimized. Simulations illustrate the usefulness of our approach.

785 citations


"Mining channel state information fr..." refers methods in this paper

  • ...It is similar to KLIEP in terms of the objective, i.e., to estimate the density ratio directly, albeit with different loss functions. uLSIF utilizes the same density-ratio model as KLIEP (refer eq....

    [...]

  • ...The Kullback-Leibler Importance Estimation Procedure (KLIEP)[9] algorithm directly estimates the density ratio ŵ such that the Kullback-Leibler divergence from the true test window density pt(o) to its estimate, i.e. ŵ(oti;α)pr(oti), is minimized....

    [...]

  • ...The error in the trivial KLIEP algorithm can be countered by setting a tolerance on the samples actually used for computing mK , which can be set at 80-90% of nc (i.e. ≈ 40-50 observations)....

    [...]

  • ...KLIEP utilizes log loss while uLSIF utilizes the squared loss....

    [...]

  • ...We employ direct-density ratio estimators using KLIEP and uLSIF to detect and annotate CSI....

    [...]

Journal ArticleDOI
TL;DR: This work provides a detailed study of BLE fingerprinting using 19 beacons distributed around a ~600 m2 testbed to position a consumer device, and investigates the choice of key parameters in a BLE positioning system, including beacon density, transmit power, and transmit frequency.
Abstract: The complexity of indoor radio propagation has resulted in location-awareness being derived from empirical fingerprinting techniques, where positioning is performed via a previously-constructed radio map, usually of WiFi signals. The recent introduction of the Bluetooth Low Energy (BLE) radio protocol provides new opportunities for indoor location. It supports portable battery-powered beacons that can be easily distributed at low cost, giving it distinct advantages over WiFi. However, its differing use of the radio band brings new challenges too. In this work, we provide a detailed study of BLE fingerprinting using 19 beacons distributed around a $\sim\! 600\ \mbox{m}^2$ testbed to position a consumer device. We demonstrate the high susceptibility of BLE to fast fading, show how to mitigate this, and quantify the true power cost of continuous BLE scanning. We further investigate the choice of key parameters in a BLE positioning system, including beacon density, transmit power, and transmit frequency. We also provide quantitative comparison with WiFi fingerprinting. Our results show advantages to the use of BLE beacons for positioning. For one-shot (push-to-fix) positioning we achieve $30\ \mbox{m}^2$ ), compared to $100\ \mbox{m}^2$ ) and < 8.5 m for an established WiFi network in the same area.

736 citations


"Mining channel state information fr..." refers background in this paper

  • ...al in [3] report the mean levels of the three separated signals to be varied : (C37: -63....

    [...]

  • ...Several studies [3, 8] have explored BLE localization using device-ranging....

    [...]

Journal Article
TL;DR: This paper proposes a new importance estimation method that has a closed-form solution; the leave-one-out cross-validation score can also be computed analytically and is computationally highly efficient and simple to implement.
Abstract: We address the problem of estimating the ratio of two probability density functions, which is often referred to as the importance. The importance values can be used for various succeeding tasks such as covariate shift adaptation or outlier detection. In this paper, we propose a new importance estimation method that has a closed-form solution; the leave-one-out cross-validation score can also be computed analytically. Therefore, the proposed method is computationally highly efficient and simple to implement. We also elucidate theoretical properties of the proposed method such as the convergence rate and approximation error bounds. Numerical experiments show that the proposed method is comparable to the best existing method in accuracy, while it is computationally more efficient than competing approaches.

492 citations


"Mining channel state information fr..." refers background or methods in this paper

  • ...6 in [7], where λ > 0 is the regularization parameter, which is chosen by cross-validation....

    [...]

  • ...The uLSIF (Unconstrained Least-Squares Importance Fitting) [7] algorithm uses Pearson (PE) divergence as a dissimilarity measure....

    [...]

Journal ArticleDOI
TL;DR: The BLE beacon’s cutting-edge applications, the interoperability between packet profiles, the reliability of its signal detection and distance estimation methods, the sustainability of its low energy, and its deployment constraints are discussed to identify research opportunities and directions.
Abstract: While the Internet of Things (IoT) is driving a transformation of current society toward a smarter one, new challenges and opportunities have arisen to accommodate the demands of IoT development. Low power wireless devices are, undoubtedly, the most viable solution for diverse IoT use cases. Among such devices, Bluetooth low energy (BLE) beacons have emerged as one of the most promising due to the ubiquity of Bluetooth-compatible devices, such as iPhones and Android smartphones. However, for BLE beacons to continue penetrating the IoT ecosystem in a holistic manner, interdisciplinary research is needed to ensure seamless integration. This paper consolidates the information on the state-of-the-art BLE beacon, from its application and deployment cases, hardware requirements, and casing design to its software and protocol design, and it delivers a timely review of the related research challenges. In particular, the BLE beacon’s cutting-edge applications, the interoperability between packet profiles, the reliability of its signal detection and distance estimation methods, the sustainability of its low energy, and its deployment constraints are discussed to identify research opportunities and directions.

277 citations