As radars become more prevalent as a sensing solution, detecting and profiling unknown radars become crucial for privacy or interference avoidance purposes. ChirpEye [3] is a radar detection system capable of identifying the parameters and angle of arrival (AoA) of Frequency-Modulated Continuous-Wave (FMCW) radars without prior knowledge of radar configuration or location. In this paper, we provide and extended analysis on robustness of ChirpEye under varying multipath conditions or highly mobile scenarios. First, we prove that Chirpeye can preserve its accurate radar detection and characterization even under high mobility due to the unique tag structure that cancels out Doppler shifts. Furthermore, through controlled simulations, we show that multipath interference could cause chirp slope and AoA estimation errors only under low SINR conditions and within a specific multipath delay range.

As Frequency-Modulated Continuous Wave (FMCW) radar systems become increasingly prevalent across various sensing applications, detecting their presence is crucial to mitigate interference and address potential security risks. Existing methods for spectrum sensing or detecting unintended Radio Frequency (RF) transmissions rely on expensive specialized hardware because these radars typically operate in the GHz frequency range and utilize large bandwidths. To overcome these limitations, we present ChirpEye, a simple but effective tag design that is capable of identifying FMCW radar waveforms without requiring prior knowledge of radar parameters such as chirp slope, operating frequency, or bandwidth. In addition, ChirpEye can identify the direction of incident signal, hinting at the potential location of the radar. The key innovation of ChirpEye lies in its novel tag design, which uses multiple antennas and delay lines to process GHz-level radar signals with only kHz sampling rates. The tag structure generates unique baseband frequencies that are proportional to FMCW waveform parameters. We also propose a new super-resolution algorithm, called Spectra-MUSIC, which can accurately estimate these beat frequencies from noisy data. Our extensive evaluations demonstrate that ChirpEye achieves 99% accuracy in detecting FMCW radars at distances up to 15 meters with less than 5% median error in estimating the radar chirp slope and less than 15 degrees median error in estimating the direction of the radar.

This paper introduces BiScatter2 as an extension of BiScatter [3], an integrated radar backscatter communication and sensing system. BiScatter2 provides simultaneous uplink and downlink communications, and precise radar-based sensing and localization. By refining the signal processing techniques and tag architecture design, BiScatter2 extends the operational range, setting a new baseline for two-way radar backscatter systems. This functionality is enabled through the use of chirp-slope-shift-keying modulation applied to Frequency Modulated Continuous Wave (FMCW) radars. BiScatter2 incorporates passive differential circuitry on backscatter tags for efficient, low-power decoding and extends its coverage range by combining the tag decoder and retro-reflective structure. Our evaluation results show an increase of 46% maximum range under the same throughput in downlink communication, which increases the original work's capability for commercial radars.

Recent regulations on monitoring infants and children in vehicle cabins have spurred interest in using Millimeter-wave (mmWave) radars due to their reliability in various lighting conditions and privacy benefits. However, existing radar-based vital sign detection solutions fail in car settings with abundant occlusions or closely-seated multi-person scenarios. To resolve these limitations, we introduce BSENSE, a joint occupancy and vital sign monitoring system using a single radar that is robust to occlusion and varying seating arrangements and number of occupants in vehicle cabins. BSENSE incorporates synthetic wireless reflectors positioned in car corners to redirect radar signals toward blind spots, enabling Non-Line-of-Sight (NLoS) vital sign detection while maintaining sensing performance in Line-of-Sight (LoS) areas. The proposed system employs a hybrid architecture combining signal processing and a deep learning pipeline that can detect the car seating layout and jointly learn occupied seats and signatures of breathing to distinguish adults from children and infants, and monitor their vital signs over time. Our extensive evaluations with 120,000 radar data points, 400 different experimental scenarios, a mix of 10 adults, 5 children of age 1--11, and two programmable infant and child simulators demonstrate BSENSE's capability in child detection with over 97% accuracy and estimating their breathing rate within 6 BPM error, even in multi-person and NLoS scenarios, and across different car models.

The Internet of Things (IoT) boom has revolutionized almost every corner of people’s daily lives: healthcare, environment, transportation, manufacturing, supply chain, and so on. With the recent development of sensor and communication technology, IoT artifacts, including smart wearables, cameras, smartwatches, and autonomous systems can accurately measure and perceive their surrounding environment. Continuous sensing generates massive amounts of data and presents challenges for machine learning. Deep learning models (e.g., convolution neural networks and recurrent neural networks) have been extensively employed in solving IoT tasks by learning patterns from multi-modal sensory data. Graph neural networks (GNNs), an emerging and fast-growing family of neural network models, can capture complex interactions within sensor topology and have been demonstrated to achieve state-of-the-art results in numerous IoT learning tasks. In this survey, we present a comprehensive review of recent advances in the application of GNNs to the IoT field, including a deep dive analysis of GNN design in various IoT sensing environments, an overarching list of public data and source codes from the collected publications, and future research directions. To keep track of newly published works, we collect representative papers and their open-source implementations and create a Github repository at GNN4IoT.

End-Stage Kidney Disease (ESKD) patients on hemodialysis suf-fer from kidney failure, with the inability to remove excess fluid causing fluid overload. This can cause many morbidities, and is one of the most insidious and common risk factors for mortality in ESKD patients. Existing solutions for fluid intake monitoring such as self-report and weight gain monitoring are burdensome, non-continuous, and usually administered in clinics only. It is then critical to develop a ubiquitous fluid intake monitoring system to help ESKD patients better control their fluid consumption. In this study, we propose to leverage smartwatch sensor data (e.g., Photoplethysmography (PPG), Gyroscope, etc.) combined with a temporal sensor relation graph neural network (TSR-GNN) to predict fluid intake given past sensing data between two dialysis sessions. Our empirical experiments highlight promising findings about the feasibility of using ubiquitous sensing to predict fluid intake, and demonstrate that the proposed model TSR-GNN outperforms the selected baseline models in both accuracy and robustness. Additionally, an in-depth analysis of model interpretability by attention weights and GNNExplainer variant is conducted to better under-stand the inter-sensor interactions and sensor contributions to the fluid intake prediction results.

Global monitoring of novel diseases and outbreaks is crucial for pandemic prevention. To this end, movement data from cell-phones is already used to augment epidemiological models. Recent work has posed individual cell-phone metadata as a universal data source for syndromic surveillance for two key reasons: (1) these records are already collected for billing purposes in virtually every country and (2) they could allow deviations from people's routine behaviors during symptomatic illness to be detected, both in terms of mobility and social interactions. In this paper, we develop the necessary models to conduct population-level infectious disease surveillance by using cell-phone metadata individually linked with health outcomes. Specifically, we propose GraphDNA---a model that builds Graph neural networks (GNNs) into Dynamic Network Anomaly detection. Using cell-phone call records (CDR) linked with diagnostic information from Iceland during the H1N1v influenza outbreak, we show that GraphDNA outperforms state-of-the-art baselines on individual Date-of-Diagnosis (DoD) prediction, while tracking the epidemic signal in the overall population. Our results suggest that proper modeling of the universal CDR data could inform public health officials and bolster epidemic preparedness measures.

Recent advancements in deep learning techniques have shown great potential for smart Internet of Things (IoT) applications. However, the edge devices of IoT applications often collect and store only limited data, which is insufficient for training modern deep learning models. Collaborative training methods such as cloud computing and federated learning set steps to build robust models for IoT applications, yet these methods bring the concern of data privacy (e.g., untrusted central server, model inversion). On the other hand, directly applying privacy-preserving techniques such as differential privacy can dramatically degrade the performance of IoT applications. Inspired by the development of model personalization, we aim to design a federated learning framework in a personalized fashion to reduce the accuracy loss caused by privacy-preserving techniques. In this paper, we present PFed-LDP, a private and accurate federated local differential privacy (LDP) framework for IoT sensing data. We first design a dynamic layer sharing mechanism to separate the local model into global layers and personalized layers. Second, we apply LDP noise to the global layers and transmit them to the federated learning framework for aggregation. Third, each local client updates their model with local personalized layers and aggregated global layers to perform IoT tasks. Our experiments on real-world datasets show that we only sacrifice 1.6% of accuracy to achieve privacy-preserving IoT applications. We also observe that our method has the smallest accuracy range, which means we can achieve the best performance for the worst performed client.

Mental health disorders, such as generalized anxiety disorder and depression, are prevalent in modern society. Early detection of mental illness is essential to minimize the negative consequences of long-term psychological discomfort and behavioral dysfunction. As a diverse set of embedded sensors in smart mobile devices becomes commonplace, passively and continuously collected mobile sensing data are increasingly being used to develop machine learning based tools for early-stage disease diagnosis. In the training process of machine learning models, self-reported results from ecological momentary assessments (EMAs) are usually employed to provide supervisions. However, complete responses of these high-frequency surveys in the wild are impractical due to heavy user burden and low user engagement. Without the availability of EMA responses in low level of label granularity, the annotations in the high level can only provide weak supervisions. To leverage the vast majority of unannotated data in different levels of granularity, in this paper, we propose an end-to-end graph neural network algorithm called semi-supervised Graph Instance Transformer (SS-GIT) based on multiple instance learning and contrastive self-supervised learning to predict early signs of generalized anxiety disorder and depression under the weak supervisions. Using a mobile sensing dataset that we collected from around 1,300 participants in the wild, our empirical results demonstrate improved performance when compared to the existing state-of-the-art baseline graph neural networks for mental health inference. On average, our proposed model outperforms the best baseline model by 8.8% on Fl-score, 6.7% on ROC-AUC, and 7.2% on PR-AUC.