Search for: All records

The increasing prevalence of wearable devices enables low-cost, long-term collection of health relevant data such as heart rate, exercise, and sleep signals. Currently these data are used to monitor short term changes with limited interpretation of their relevance to health. These data provide an untapped resource to monitor daily and long-term activity patterns. Changes and trends identified from such data can provide insights and guidance to the management of many chronic conditions that change over time. In this study we conducted a machine learning based analysis of longitudinal heart rate data collected over multiple years from Fitbit devices. We built a multi-resolutional pipeline for time series analysis, using model-free clustering methods inspired by statistical conformal prediction framework. With this method, we were able to detect health relevant events, their interesting patterns (e.g., daily routines, seasonal differences, and anomalies), and correlations to acute and chronic changes in health conditions. We present the results, lessons, and insights learned, and how to address the challenge of lack of labels. The study confirms the value of long-term heart rate data for health monitoring and surveillance, as complementary to extensive yet intermittent examinations by health care providers.

 

Progress in hardware and algorithms for artificial intelligence (AI) has ushered in large machine learning models and various applications impacting our everyday lives. However, today's AI, mainly artificial neural networks, still cannot compete with human brains because of two major issues: the high energy consumption of the hardware running AI models and the lack of ability to generalize knowledge and self-adapt to changes. Neuromorphic systems built upon emerging devices, for instance, memristors, provide a promising path to address these issues. Although innovative memristor devices and circuit designs have been proposed for neuromorphic computing and applied to different proof-of-concept applications, there is still a long way to go to build large-scale low-power memristor-based neuromorphic systems that can bridge the gap between AI and biological brains. This Perspective summarizes the progress and challenges from memristor devices to neuromorphic systems and proposes possible directions for neuromorphic system implementation based on memristive devices. 

Radar-based solutions support practical and longi- tudinal respiration monitoring owing to their non-invasive nature. Nighttime respiration monitoring at home provides rich and high- quality data, mostly free of motion disturbances because the user is quasi-stationary during sleep, and 6-8 hours per day rather than tens of minutes, promising for longitudinal studies. However, most existing work was conducted in laboratory environments for short periods, thus the environment, user motions, and postures can differ significantly from those in real homes. To understand how to obtain quality, overnight respiration data in real homes, we conduct a thorough experimental study with 6 participants of various sleep postures over 9 nights in 4 real-home testbeds, each configured with 3–4 sensors around the bed. We first compare the performance among four typical sensor placements around the bed to understand which is the optimal location for high quality data. Then we explore methods to track range bins with high quality signals as occasional user motions change the distance thus signal qualities, and different aspects of amplitude and phase data to further improve the signal quality using metrics of the periodicity-to-noise ratio (PNR) and end-to-end (e2e) accuracy. The experiments demonstrate that the sensor placement is a vital factor, and the bedside is an optimal choice considering both accuracy and ease of deployment (2.65 bpm error at 80 percentile), also consistent among four typical sleep postures. We also observe that, a proper range bin selection method can improve the PNR by 2 dB at 75-percentile, and e2e accuracy by 0.9 bpm at 80-percentile. Both amplitude and phase data have comparable e2e accuracy, while phase is more sensitive to motions thus suitable for nighttime movement detection. Based on these discoveries, we develop a few simple practical guidelines useful for the community to achieve high quality, longitudinal home- based overnight respiration monitoring. 

Fully decentralized model training for on-road vehicles can leverage crowdsourced data while not depending on central servers, infrastructure or Internet coverage. However, under unreliable wireless communication and short contact duration, model sharing among peer vehicles may suffer severe losses thus fail frequently. To address these challenges, we propose “RoADTrain”, a route-assisted decentralized peer model training approach that carefully chooses vehicles with high chances of successful model sharing. It bounds the per round communication time yet retains model performance under vehicle mobility and unreliable communication. Based on shared route information, a connected cluster of vehicles can estimate and embed the link reliability and contact duration information into the communication topology. We decompose the topology into subgraphs supporting parallel communication, and identify a subset of them with the highest algebraic connectivity that can maximize the speed of the information flow in the cluster with high model sharing successes, thus accelerating model training in the cluster. We conduct extensive evaluation on driving decision making models using the popular CARLA simulator. RoADTrain achieves comparable driving success rates and 1.2−4.5× faster convergence than representative decentralized learning methods that always succeed in model sharing (e.g., SGP), and significantly outperforms other benchmarks that consider losses by 17−27% in the hardest driving conditions. These demonstrate that route sharing enables shrewd selection of vehicles for model sharing, thus better model performance and faster convergence against wireless losses and mobility. 

While radio frequency (RF) based respiration monitoring for at- home health screening is receiving increasing attention, robustness remains an open challenge. In recent work, deep learning (DL) methods have been demonstrated effective in dealing with non- linear issues from multi-path interference to motion disturbance, thus improving the accuracy of RF-based respiration monitoring. However, such DL methods usually require large amounts of train- ing data with intensive manual labeling efforts, and frequently not openly available. We propose RF-Q for robust RF-based respiration monitoring, using self-supervised learning with an autoencoder (AE) neural network to quantify the quality of respiratory signal based on the residual between the original and reconstructed sig- nals. We demonstrate that, by simply quantifying the signal quality with AE for weighted estimation we can boost the end-to-end (e2e) respiration monitoring accuracy by an improvement ratio of 2.75 compared to a baseline. 

Continuous monitoring of respiration provides invaluable insights about health status management (e.g., the progression or recovery of diseases). Recent advancements in radio frequency (RF) technologies show promise for continuous respiration monitoring by virtue of their non-invasive nature, and preferred over wearable solutions that require frequent charging and continuous wearing. However, RF signals are susceptible to large body movements, which are inevitable in real life, challenging the robustness of respiration monitoring. While many existing methods have been proposed to achieve robust RF-based respiration monitoring, their reliance on supervised data limits their potential for broad applicability. In this context, we propose, RF-Q, an unsupervised/self-supervised model to achieve signal quality assessment and quality-aware estimation for robust RF-based respiration monitoring. RF-Q uses the recon- struction error of an autoencoder (AE) neural network to quantify the quality of respiratory information in RF signals without the need for data labeling. With the combination of the quantified sig- nal quality and reconstructed signal in a weighted fusion, we are able to achieve improved robustness of RF respiration monitor- ing. We demonstrate that, instead of applying sophisticated models devised with respective expertise using a considerable amount of labeled data, by just quantifying the signal quality in an unsupervised manner we can significantly boost the average end-to-end (e2e) respiratory rate estimation accuracy of a baseline by an improvement ratio of 2.75, higher than the gain of 1.94 achieved by a supervised baseline method that excludes distorted data.