Radio frequency (RF)-based indoor positioning systems (IPSs) use wireless technologies (including Wi-Fi, Zigbee, Bluetooth, and ultra-wide band (UWB)) to estimate the location of persons in areas where no Global Positioning System (GPS) reception is available, for example in indoor stadiums or sports halls. Of the above-mentioned forms of radio frequency (RF) technology, UWB is considered one of the most accurate approaches because it can provide positioning estimates with centimeter-level accuracy. However, it is not yet known whether UWB can also offer such accurate position estimates during strenuous dynamic activities in which moves are characterized by fast changes in direction and velocity. To answer this question, this paper investigates the capabilities of UWB indoor localization systems for tracking athletes during their complex (and most of the time unpredictable) movements. To this end, we analyze the impact of on-body tag placement locations and human movement patterns on localization accuracy and communication reliability. Moreover, two localization algorithms (particle filter and Kalman filter) with different optimizations (bias removal, non-line-of-sight (NLoS) detection, and path determination) are implemented. It is shown that although the optimal choice of optimization depends on the type of movement patterns, some of the improvements can reduce the localization error by up to 31%. Overall, depending on the selected optimization and on-body tag placement, our algorithms show good results in terms of positioning accuracy, with average errors in position estimates of 20 cm. This makes UWB a suitable approach for tracking dynamic athletic activities.

In this article, we consider indoor positioning of a shopping cart in a store with a hybrid approach combining ultra wideband (UWB) and a people dead reckoning (PDR) system. While UWB can provide a very accurate positioning estimate in ideal circumstances, its accuracy reduces in non-line-of-sight situations and the update rate decreases when the number of users increases. To solve these issues, each shopping cart is not only equipped with a UWB tag, but also with an inertial measurement unit (IMU) sensor to determine the step length and heading of the user moving the shopping cart, in order to track the shopping cart in between two UWB measurements. As the IMU is not attached to the body, the measured acceleration will be different than in other works considering PDR systems. In this article, we therefore first extract a model for the acceleration, and use the resulting model in the PDR system, where we look for the best acceleration component to track the cart. To combine the PDR and UWB information, we consider two approaches, i.e. Kalman and particle filtering, and compare both approaches. Moreover, we investigate the effect of the presence of map information of the store on the trajectory information. Our experiments show that the average positioning error using UWB only equals 62.6 cm, while the Kalman and particle filter result in an accuracy of respectively 34.1 cm and 41.3 cm, and when using map information in combination with particle filtering, the accuracy improves to 28.0 cm.

A popular approach to track the position of a user is to use an inertial measurement unit (IMU), which allows to track a user with a pedestrian dead reckoning (PDR) system by estimating the length and heading of each step a user takes. Furthermore, a user’s steps together with their length can be used to detect anomalies in the gait due to e.g. a gait disorder. To determine the length and/or heading of a step, we first need an algorithm that estimates the boundaries of a step, i.e. the start and end, in the IMU signals. In this paper, we propose a deep-learning-based step detection algorithm that detects the start and end of a step using only data from a handheld accelerometer. In this algorithm, also the relationship between the start and end of a step is used to improve performance. To evaluate the performance of the detector, in contrast to most previous works that only look at the total number of detected steps, we determine if the start and end of each step are detected at the correct instant. This resulted in a step detector with an f-score of 99.2% and 99.0% for respectively detecting the start and end of a step. After detecting the start and end of the steps, we use a LSTM/CNN-based step length estimator, which resulted in in a mean absolute error on the step length of 3.21 cm. Finally, we also determine the combined performance of the step detector and step length estimator, i.e. where the proposed step detector is used to extract the accelerometer fragments of a step instead of assuming that the boundaries are known. This resulted in a mean absolute error of 6.56 cm using the deep-learning-based step length estimator.

Although ultra wideband (UWB) positioning is considered as one of the most promising solutions for indoor positioning due to its high positioning accuracy, the accuracy in situations with a large number of users will be reduced because the time between two UWB position updates can be very high. To obtain a position estimate in between these updates, we can combine the UWB positioning with a different technology, e.g., an inertial measurement unit (IMU) that captures data from an accelerometer, gyroscope, and magnetometer. Previous research using the IMU outputs for location-based services employs the periodic behaviour of the accelerometer signal to count steps. However, most of these algorithms require extensive manual tuning of multiple parameters to obtain satisfactory accuracy. To overcome these practical issues, step counting algorithms using machine learning (ML) principles can be developed. In this paper, we consider accelerometer-based step counters using ML. As the performance and complexity of such algorithms depend on the features used in the training and inference phase, proper selection of the employed features is important. Therefore, in this paper, we propose a novel feature selection algorithm, where we first rank the features based on their Bhattacharyya coefficients and then systematically construct a subset of these ranked features. In this paper, we compare three ranking approaches and apply our algorithm to different ML algorithms employing an experimental set. Although the performance of the evaluated combinations slightly varies for different ML algorithms, their performance is comparable to state-of-the-art step counters, without the need to tune parameters manually.

An accurate step length estimation can provide valuable information to different applications such as indoor positioning systems or it can be helpful when analyzing the gait of a user, which can then be used to detect various gait impairments that lead to a reduced step length (caused by e.g., Parkinson’s disease or multiple sclerosis). In this paper, we focus on the estimation of the step length using machine learning techniques that could be used in an indoor positioning system. Previous step length algorithms tried to model the length of a step based on measurements from the accelerometer and some tuneable (user-specific) parameters. Machine-learning-based step length estimation algorithms eliminate these parameters to be tuned. Instead, to adapt these algorithms to different users, it suffices to provide examples of the length of multiple steps for different persons to the machine learning algorithm, so that in the training phase the algorithm can learn to predict the step length for different users. Until now, these machine learning algorithms were trained with features that were chosen intuitively. In this paper, we consider a systematic feature selection algorithm to be able to determine the features from a large collection of features, resulting in the best performance. This resulted in a step length estimator with a mean absolute error of $3.48$ cm for a known test person and $4.19$ cm for an unknown test person, while current state-of-the-art machine-learning-based step length estimators resulted in a mean absolute error of $4.94$ cm and $6.27$ cm for respectively a known and unknown test person.