Radio frequency (RF)-based localization yields centimeter-accurate positions under mild propagation conditions. However, propagation conditions predominant in indoor environments (e.g. industrial production) are often challenging as signal blockage, diffraction and dense multipath lead to errors in the time of flight (TOF) estimation and hence to a degraded localization accuracy. A major topic in high-precision RF-based localization is the identification of such anomalous signals that negatively affect the localization performance, and to mitigate the errors introduced by them. As such signal and error characteristics depend on the environment, data-driven approaches have shown to be promising. However, there is a trade-off to a bad generalization and a need for an extensive and time-consuming recording of training data associated with it. We propose to use generative deep learning models for out-of-distribution detection based on channel impulse responses (CIRs). We use a Variational Autoencoder (VAE) to predict an anomaly score for the channel of a TOF-based Ultra-wideband (UWB) system. Our experiments show that a VAE trained only on line-of-sight (LOS) training data generalizes well to new environments and detects non-line-of-sight CIRs with an accuracy of 85%. We also show that integrating our anomaly score into a TOF-based extended Kalman filter (EKF) improves tracking performance by over 25%.

The performance of a machine learning model degrades when it is applied to data from a similar but different domain than the data it has initially been trained on. To mitigate this domain shift problem, domain adaptation (DA) techniques search for an optimal transformation that converts the (current) input data from a source domain to a target domain to learn a domain-invariant representation that reduces domain discrepancy. This paper proposes a novel supervised DA based on two steps. First, we search for an optimal class-dependent transformation from the source to the target domain from a few samples. We consider optimal transport methods such as the earth mover's distance, Sinkhorn transport and correlation alignment. Second, we use embedding similarity techniques to select the corresponding transformation at inference. We use correlation metrics and higher-order moment matching techniques. We conduct an extensive evaluation on time-series datasets with domain shift including simulated and various online handwriting datasets to demonstrate the performance.

This paper presents a handwriting recognition (HWR) system that deals with online character recognition in real-time. Our sensor-enhanced ballpoint pen delivers sensor data streams from triaxial acceleration, gyroscope, magnetometer and force signals at 100 Hz. As most existing datasets do not meet the requirements of online handwriting recognition and as they have been collected using specific equipment under constrained conditions, we propose a novel online handwriting dataset acquired from 119 writers consisting of 31,275 uppercase and lowercase English alphabet character recordings (52 classes) as part of the UbiComp 2020 Time Series Classification Challenge. Our novel OnHW-chars dataset allows for the evaluations of uppercase, lowercase and combined classification tasks, on both writer-dependent (WD) and writer-independent (WI) classes and we show that properly tuned machine learning pipelines as well as deep learning classifiers (such as CNNs, LSTMs, and BiLSTMs) yield accuracies up to 90 % for the WD task and 83 % for the WI task for uppercase characters. Our baseline implementations together with the rich and publicly available OnHW dataset serve as a baseline for future research in that area.

Interference signals cause position errors and outages to global navigation satellite system (GNSS) receivers. However, to solve these problems, the interference source must be detected, classified, its purpose determined, and localized to eliminate it. Several interference monitoring solutions exist, but these are expensive, resulting in fewer nodes that may miss spatially sparse interference signals. This article introduces a low-cost commercial-off-the-shelf (COTS) GNSS interference monitoring, detection, and classification receiver. It employs machine learning (ML) on tailored signal pre-processing of the raw signal samples and GNSS measurements to facilitate a generalized, high-performance architecture that does not require human-in-the-loop (HIL) calibration. Therefore, the low-cost receivers with high performance can justify significantly more receivers being deployed, resulting in a significantly higher probability of intercept (POI). The architecture of the monitoring system is described in detail in this article, including an analysis of the energy consumption and optimization. Controlled interference scenarios demonstrate detection and classification capabilities exceeding conventional approaches. The ML results show that accurate and reliable detection and classification are possible with COTS hardware.

Handwriting is one of the most frequently occurring patterns in everyday life and with it comes challenging applications such as handwriting recognition, writer identification and signature verification. In contrast to offline HWR that only uses spatial information (i.e., images), online HWR uses richer spatio-temporal information (i.e., trajectory data or inertial data). While there exist many offline HWR datasets, there are only little data available for the development of OnHWR methods on paper as it requires hardware-integrated pens. This paper presents data and benchmark models for real-time sequence-to-sequence learning and single character-based recognition. Our data are recorded by a sensor-enhanced ballpoint pen, yielding sensor data streams from triaxial accelerometers, a gyroscope, a magnetometer and a force sensor at 100 Hz. We propose a variety of datasets including equations and words for both the writer-dependent and writer-independent tasks. Our datasets allow a comparison between classical OnHWR on tablets and on paper with sensor-enhanced pens. We provide an evaluation benchmark for seq2seq and single character-based HWR using recurrent and temporal convolutional networks and transformers combined with a connectionist temporal classification (CTC) loss and cross-entropy (CE) losses. Our convolutional network combined with BiLSTMs outperforms transformer-based architectures, is on par with InceptionTime for sequence-based classification tasks and yields better results compared to 28 state-of-the-art techniques. Time-series augmentation methods improve the sequence-based task, and we show that CE variants can improve the single classification task. Our implementations together with the large benchmark of state-of-the-art techniques of novel OnHWR datasets serve as a baseline for future research in the area of OnHWR on paper.

Multivariate Time Series (MTS) classification is important in various applications such as signature verification, person identification, and motion recognition. In deep learning these classification tasks are usually learned using the cross-entropy loss. A related yet different task is predicting trajectories observed as MTS. Important use cases include handwriting reconstruction, shape analysis, and human pose estimation. The goal is to align an arbitrary dimensional time series with its ground truth as accurately as possible while reducing the error in the prediction with a distance loss and the variance with a similarity loss. Although learning both losses with Multi-Task Learning (MTL) helps to improve trajectory alignment, learning often remains difficult as both tasks are contradictory. We propose a novel neural network architecture for MTL that notably improves the MTS classification and trajectory regression performance in online handwriting (OnHW) recognition. We achieve this by jointly learning the cross-entropy loss in combination with distance and similarity losses. On an OnHW task of handwritten characters with multivariate inertial and visual data inputs we are able to achieve crucial improvements (lower error with less variance) of trajectory prediction while still improving the character classification accuracy in comparison to models trained on the individual tasks.