In critical domains such as healthcare and law, accurately modelling the uncertainty of automatic computational models is essential. For instance, healthcare models must produce reliable estimates to guide human decision-making. However, modelling uncertainty remains challenging, particularly for models handling low-resource datasets and complex, domain-specific vocabulary. Most existing predictive models model point estimates rather than probability distributions, limiting our ability to quantify model uncertainty. This paper introduces a novel model, BAKER, designed to address these limitations. BAKER combines the strengths of Bayesian inference, known for its effectiveness in modelling uncertainty, and kernel methods, which excel at capturing complex data relationships. Incorporating kernel functions enhances model performance, particularly by reducing overfitting in data-limited scenarios. Our experimental analysis shows that BAKER significantly improves uncertainty reasoning compared to existing models.

Passive radar imaging has been extensively studied and is based on an illuminator-of-opportunity, such as a wireless access point, providing a signal that scatters from targets and is incident on a receiving node(s) in order to infer information on the range and velocity of the target scene. Such systems universally require reference signal regeneration, from a dedicated channel, that is cross-correlated with the received signal in order to extract the range/Doppler information of the target. This paper presents one of several techniques developed by the authors to achieve passive radar (or RF) imaging without any requirement for extraction of the reference signal. The concept is analogous to optical systems in which various source(s) provide general illumination of a target scene, the scattered signals of which are gathered and processed at an optical sensor in order to reconstruct the image, but without any requirement to extract the illumination (reference) source itself. Such an approach offers numerous practical advantages in achieving imaging from a single passive sensor without the additional requirement of precise, or indeed any, regeneration of the illuminating source: a reference-free approach. This paper presents one such technique based on sampling of the complex signal distribution over an antenna aperture and near-field processing to form a two/three-dimensional reconstruction of the target scene. The fundamental principles of the technique are described along with analysis of basic performance limits. Modelling is presented to illustrate the capability of the technique, which is validated by experimental measurement with a WiFi access point-based prototype system.

This paper introduces the “RF-Pointer,” an innovative radio-frequency-based interaction framework designed for real-time tracking and projection of hand movements in virtual spaces. The system can provide a hands-free and distinctive interaction experience suitable for emerging domains like virtual reality and augmented reality. In this study, we delve into the architectural and operational dynamics of the RF-Pointer, utilizing a prototype equipped with a 77 GHz radar sensor. Initial tests reveal an average tracking error of 2.5 cm in estimating the pointer's location. To further illustrate the efficacy of the proposed architecture, we conduct a qualitative comparison, presenting the results in the form of tracked trajectories corresponding to both ground truth and the RF-Pointer estimated trajectories. The tracking results demonstrate that RF-Pointer trajectories closely align with ground truth trajectories.

Motion tracking systems based on optical sensors typically often suffer from issues, such as poor lighting conditions, occlusion, limited coverage, and may raise privacy concerns. More recently, radio frequency (RF)-based approaches using commercial WiFi devices have emerged which offer low-cost ubiquitous sensing whilst preserving privacy. However, the output of an RF sensing system, such as Range-Doppler spectrograms, cannot represent human motion intuitively and usually requires further processing. In this study, MDPose, a novel framework for human skeletal motion reconstruction based on WiFi micro-Doppler signatures, is proposed. It provides an effective solution to track human activities by reconstructing a skeleton model with 17 key points, which can assist with the interpretation of conventional RF sensing outputs in a more understandable way. Specifically, MDPose has various incremental stages to gradually address a series of challenges: First, a denoising algorithm is implemented to remove any unwanted noise that may affect the feature extraction and enhance weak Doppler signatures. Secondly, the convolutional neural network (CNN)-recurrent neural network (RNN) architecture is applied to learn temporal-spatial dependency from clean micro-Doppler signatures and restore key points' velocity information. Finally, a pose optimising mechanism is employed to estimate the initial state of the skeleton and to limit the increase of error. We have conducted comprehensive tests in a variety of environments using numerous subjects with a single receiver radar system to demonstrate the performance of MDPose, and report 29.4mm mean absolute error over all key points positions, which outperforms state-of-the-art RF-based pose estimation systems.

Abstract Voice identification is being increasingly adopted in various domains, including security infrastructures, intelligent home systems, and personalised digital assistants. Notably, it harbours significant promise in transforming healthcare, especially in electronic health record detecting and speech impairment monitoring such as aphasia. Current strategies such as acoustic models based on deep learning, voice bio‐metrics, and spectrogram analysis, have been identified with several drawbacks including vulnerability to altered voices, susceptibility to ambient noise, and the necessity for significant computational power. In response to these issues, the authors introduce a ground‐breaking method of voice identification using Ultra‐Wideband (UWB) technology. This method capitalises on the micro‐Doppler shifts associated with movements of the laryngeal prominence. The distinctive nature of these bio‐metric traits related to speech production provides superior resistance against common pitfalls of voice identification. The proposed model leverages the high‐resolution characteristics of UWB to register tiny variations in laryngeal movements produced during speech, thus forming a distinct voice profile for each speaker. Through rigorous testing, the proposed system demonstrated significant progress in voice identification, achieving close to 90% accuracy in controlled experimental settings. This breakthrough indicates that UWB‐enabled voice identification could have a profound effect on medical applications, providing potential improvements in diagnosing, monitoring, possibly treating speech disorders, and thereby shaping a future of enhanced and secured healthcare services.

The growing capabilities of AI raise questions about their trustworthiness in healthcare, particularly due to opaque decision-making and limited data availability. This paper proposes a novel approach to address these challenges, introducing a Bayesian Monte Carlo Dropout model with kernel modelling. Our model is designed to enhance reliability on small medical datasets, a crucial barrier to the wider adoption of AI in healthcare. This model leverages existing language models for improved effectiveness and seamlessly integrates with current workflows. We demonstrate significant improvements in reliability, even with limited data, offering a promising step towards building trust in AI-driven medical predictions and unlocking its potential to improve patient care.

This study investigates radar technology for non-invasive brain imaging and tumor detection, offering an alternative to MRI and CT scans. Using Ansys HFSS to simulate electromagnetic interactions in brain tissues, we evaluate the penetration, signal strength, and safety of Patch and Vivaldi antennas. Results show Patch antennas are optimal for tumor localization, while Vivaldi antennas suit broader scanning applications. Although promising for safer, more accessible imaging, especially in resource-limited environments, further research with diverse models and actual patient data is essential to advance this technology in non-invasive medical diagnostics.

Predicting legal judgments with reliable confidence is paramount for responsible legal AI applications. While transformer-based deep neural networks (DNNs) like BERT have demonstrated promise in legal tasks, accurately assessing their prediction confidence remains crucial. We present a novel Bayesian approach called BayesJudge that harnesses the synergy between deep learning and deep Gaussian Processes to quantify uncertainty through Bayesian kernel Monte Carlo dropout. Our method leverages informative priors and flexible data modelling via kernels, surpassing existing methods in both predictive accuracy and confidence estimation as indicated through brier score. Extensive evaluations of public legal datasets showcase our model's superior performance across diverse tasks. We also introduce an optimal solution to automate the scrutiny of unreliable predictions, resulting in a significant increase in the accuracy of the model's predictions by up to 27\%. By empowering judges and legal professionals with more reliable information, our work paves the way for trustworthy and transparent legal AI applications that facilitate informed decisions grounded in both knowledge and quantified uncertainty.

Abstract This work introduces an attention mechanism that can be integrated into any standard convolution neural network to improve model sensitivity and prediction accuracy with minimal computational overhead. The attention mechanism is introduced in a lightweight network – Alexnet and its classification performance for human micro‐Doppler signatures is evaluated. The Alexnet model trained with an attention module can implicitly highlight the salient regions in the radar signatures while suppressing the irrelevant background regions and consistently improving network predictions. Network visualizations are provided through class activation mapping, providing better insights into how the predictions are made. The visualizations demonstrate how the attention mechanism focusses on the region of interest in the radar signatures.

Radio-frequency-based noncooperative monitoring of humans has numerous applications ranging from law enforcement to ubiquitous sensing applications such as ambient assisted living and biomedical applications for nonintrusively monitoring patients. Large training datasets, almost unlimited memory capacity, and ever-increasing processing speeds of computers could drive forward the data-driven deep-learning-focused research in the abovementioned applications. However, generating and labeling large volumes of high-quality, diverse radar datasets is an onerous task. Furthermore, unlike the fields of vision and image processing, the radar community has limited access to databases that contain large volumes of experimental data. Therefore, in this article, we present an open-source motion capture data-driven simulation tool, SimHumalator, that can generate large volumes of human micro-Doppler radar data in passive WiFi scenarios. The simulator integrates IEEE 802.11 WiFi Standards (IEEE 802.11 g, n, and ad) compliant transmissions with the human animation data to generate the micro-Doppler features that incorporate the diversity of human motion characteristics and the sensor parameters. The simulated signatures have been validated with experimental data gathered using an in-house-built hardware prototype. This article describes simulation methodology in detail and provides case studies on the feasibility of using simulated micro-Doppler spectrograms for data augmentation tasks.

This paper presents a comprehensive dataset intended to evaluate passive Human Activity Recognition (HAR) and localization techniques with measurements obtained from synchronized Radio-Frequency (RF) devices and vision-based sensors. The dataset consists of RF data including Channel State Information (CSI) extracted from a WiFi Network Interface Card (NIC), Passive WiFi Radar (PWR) built upon a Software Defined Radio (SDR) platform, and Ultra-Wideband (UWB) signals acquired via commercial off-the-shelf hardware. It also consists of vision/Infra-red based data acquired from Kinect sensors. Approximately 8 hours of annotated measurements are provided, which are collected across two rooms from 6 participants performing 6 daily activities. This dataset can be exploited to advance WiFi and vision-based HAR, for example, using pattern recognition, skeletal representation, deep learning algorithms or other novel approaches to accurately recognize human activities. Furthermore, it can potentially be used to passively track a human in an indoor environment. Such datasets are key tools required for the development of new algorithms and methods in the context of smart homes, elderly care, and surveillance applications.

This paper presents an indoor joint communication and sensing system that consists of synchronized off-the-shelf wireless network interface cards (NIC) and Raspberry Pis. There exists a significant body of research that uses the channel state information (CSI) reported by wireless network interface cards for sensing, but only the amplitude and phase difference of the CSI between receiver antennas are processed. The raw phase of the CSI is contaminated by the carrier frequency offset, packet detection delay and other hardware imperfections, so it is too noisy to use. Our work introduces the raw phase of CSI into sensing by synchronizing the transmitter and receiver clocks to remove carrier frequency offset and using a new method to remove packet detection delay. We validate our design in a real-world scenario to detect breathing and walking and demonstrate that the raw phase of the CSI offers an evident improvement in Wi-Fi CSI-based sensing. Additionally, we are the first to use the Raspberry Pi and ATH9k wireless network interface card together for CSI data collection, which is cheap, portable and versatile.

Micro-Doppler signatures contain considerable information about target dynamics. However, the radar sensing systems are easily affected by noisy surroundings, resulting in uninterpretable motion patterns on the micro-Doppler spectrogram ( $\mu $ -DS). Meanwhile, radar returns often suffer from multipath, clutter, and interference. These issues lead to difficulty in, for example, motion feature extraction and activity classification using micro-Doppler signatures. In this article, we propose a latent feature-wise mapping strategy, called feature mapping network (FMNet), to transform measured spectrograms so that they more closely resemble the output from a simulation under the same conditions. Based on measured spectrogram and the matched simulated data, our framework contains three parts: an encoder which is used to extract latent representations/features, a decoder outputs reconstructed spectrogram according to the latent features, and a discriminator minimizes the distance of latent features of measured and simulated data. We demonstrate the FMNet with six activities data and two experimental scenarios, and final results show strong enhanced patterns and can keep actual motion information to the greatest extent. On the other hand, we also propose a novel idea which trains a classifier with only simulated data and predicts new measured samples after cleaning them up with the FMNet. From final classification results, we can see significant improvements.

Abstract Software defined radar (SDRadar) systems have become an important area for future radar development and are based on similar concepts to Software defined radio (SDR). Most of the processing like filtering, frequency conversion and signal generation are implemented in software. Currently, radar systems tend to have complex signal processing and operate at wider bandwidth, which means that limits on the available computational power must be considered when designing a SDRadar system. This paper presents a feasible solution to this potential limitation by accelerating the signal processing using a GPU to enable the development of a high speed SDRadar system. The developed system overcomes the limitation on the processing speed by CPU‐only, and has been tested on three different SDR devices. Results show that, with GPU accelerator, the processing rate can achieve up to 80 MHz compared to 20 MHz with the CPU‐only. The high speed processing makes it possible to run in real‐time and process full bandwidth across the WiFi signal acquired by multiple channels. The gains made through porting the processing to the GPU moves the technology towards real‐world application in various scenarios ranging from healthcare to IoT, and other applications that required significant computational processing.

Software Defined Radar (SDRadar) is a unique radar system, where most of its processing, like filtering, correlation, signal generation etc. is performed by software. This means SDRadar can be flexibly deployed for different purposes and with a relative short development process. In this paper, we present a generic SDRadar system that can operate in different setups for near-field monitoring applications. Practical solutions for traditional limitations in SDRadar and high sampling rates are introduced, and its performance is demonstrated using a commercial universal software radio peripheral (USRP) device with four synchronized receiving channels and a maximum sampling rate of 100MHz. Additionally, a GPU accelerator has been implemented to deal with the high sampling rate. Three different setups have been tested to demonstrate the feasibility of the propose SDRadar system with distributed nodes, vertically positioned nodes and a miniature scenario. Recorded Doppler signatures have shown the proposed SDRadar can effectively capture the body and hand gestures. Such results can be used in a range of applications such as eHealth, human-machine interaction and indoor tracking.

IoT ecosystems consist of a range of smart devices that generated a plethora of Radio Frequency (RF) transmissions. This provides an attractive opportunity to exploit already-existing signals for various sensing applications such as e-Healthcare, security and smart home. In this paper, we present Passive IoT Radar (PIoTR), a system that passively uses RF transmissions from IoT devices for human monitoring. PIoTR is designed based on passive radar technology, with a generic architecture to utilize various signal sources including the WiFi signal and wireless energy at the Industrial, Scientific and Medical (ISM) band. PIoTR calculates the phase shifts caused by human motions and generates Doppler spectrogram as the representative. To verify the proposed concepts and test in a more realistic environment, we evaluate PIoTR with four commercial IoT devices for home use. Depending on the effective signal and power strength, PIoTR performs two modes: coarse sensing and fine-grained sensing. Experimental results show that PIoTR can achieve an average of 91% in occupancy detection (coarse sensing) and 91.3% in activity recognition (fine-grained sensing).

This work investigates the degradation effects of four distinct jamming signal styles on human micro-Doppler signatures by examining the ability of a linear discriminant classifier to accurately distinguish signatures collected using a simulated frequency modulated continuous wave (FMCW) radar which have been injected with jamming. Misclassification dependence on jamming signal power for each jamming style is presented along with the nature of misclassifications.

Human micro-Doppler signatures in most passive WiFi radar (PWR) scenarios are captured through real-world measurements using various hardware platforms. However, gathering large volumes of high quality and diverse real radar datasets has always been an expensive and laborious task. This work presents an open-source motion capture data-driven simulation tool SimHumalator that is able to generate human micro-Doppler radar data in PWR scenarios. We qualitatively compare the micro-Doppler signatures generated through SimHumalator with the measured real signatures. Here, we present the use of SimHumalator to simulate a set of human actions. We demonstrate that augmenting a measurement database with simulated data, using SimHumalator, results in an 8% improvement in classification accuracy. Our results suggest that simulation data can be used to augment experimental datasets of limited volume to address the cold-start problem typically encountered in radar research.