Search for: All records

Abstract 24/7 continuous recording of in-home daily trajectories is informative for health status assessment (e.g., monitoring Alzheimer’s, dementia based on behavior patterns). Indoor device-free localization/tracking are ideal because no user efforts on wearing devices are needed. However, prior work mainly focused on improving the localization accuracy. They relied on well-calibrated sensor placements, which require hours of intensive manual setup and respective expertise, feasible only at small scale and by mostly researchers themselves. Scaling the deployments to tens or hundreds of real homes, however, would incur prohibitive manual efforts, and become infeasible for layman users. We presentSCALING, a plug-and-play indoor trajectory monitoring system that layman users can easily set up by walking a one-minute loop trajectory after placing radar nodes on walls. It uses a self calibrating algorithm that estimates sensor locations through their distance measurements to the person walking the trajectory, a trivial effort without taxing layman users physically or cognitively. We evaluateSCALINGvia simulations and two testbeds (in lab and home configurations of sizes 3$$\times$$ $\times$6 sq m and 4.5$$\times$$ $\times$8.5 sq m). Experimental results demonstrate thatSCALINGoutperformed the baseline using the approximate multidimensional scaling (MDS, the most relevant method in the context of self calibration) by 3.5 m/1.6 m in 80-percentile error of self calibration and tracking, respectively. Notably, only 1% degradation in performance has been observed withSCALINGcompared to the classical multilateration with known sensor locations (anchors), which costs hours of intensive calibrating effort. In addition, we conduct Monte Carlo experiments to numerically analyze the impact of sensor placements and develop practical guidelines for deployment in real life scenarios. 

Abstract Over 80% of older adults want to live independently in their own homes and communities, maintaining quality of life, autonomy, and dignity as they age. We are using community engaged research methods to aid in developing in-home cost-conscious remote sensing technologies to support older adults age in place. To understand their needs, we engaged older adults in discussions on home-based sensing technologies. We used visuals and demonstrations to facilitate discussions, showing participants our sensor prototypes and a vignette describing the challenges an older adult and the family face managing a chronic condition. Participants voiced their interest in monitoring for select health conditions and situations when either they or the person(s) they care for are home alone. Discussants raised concerns about personal security/privacy, loss of independence, ethics of data collection and sharing, and being overwhelmed by collected data. Discussions have provided valuable feedback to help us develop a sensor system that is flexible enough to accommodate individuals in different life stages and comfort levels, with different home environments, levels of expendable income, and support structures. As a result, we have developed a system that uses nonvisual, non-wearable sensing that measures respiration and heart rates, and indoor location tracking to monitor the health and wellbeing of users. During this session, we will provide detailed results from our community discussions, and discuss the continuing role for community engagement as we move forward with sensor development and testing. 

Abstract As Americans live longer, a dynamic opportunity has arisen to provide enhanced resources to sustain their well-being. Cost-conscious, convenient in-home sensing will assist with chronic disease management, and become part of a long-term plan to support our aging population and shrinking healthcare workforce. The purpose of this study was to obtain input from older adults about (i) their comfort level and willingness to adopt different sensor technologies, and (ii) opinions on data sharing, security, and privacy to guide our sensor development. Over 4 different survey timeframes (2018-2022), adults aged 60 and older (N=112) completed our survey either in-person (n=77) or via a REDCap online survey (n=35) (53% female; 30% age >80; 78% college graduates; 19% living alone). Though there were significant differences (p< 0.05) in demographics based upon recruitment source, no differences in attitudes towards sensor use were found by age, gender, education, or marital status. Opinions and preferences for sensor type/number/install location, and data sharing preferences significantly differed (p< 0.05) by home living arrangements (independent, 55+ or continuous care communities). Similar to national surveys, changes in technology use were observed pre- versus post COVID. Respondents living in 55+ and continuous-care housing were more comfortable with having sensors installed in their homes than those in community dwelling independent housing. This study highlights the need to include end users throughout the lifecycle of product development and provides insights into preferences by older adults for sensor use and data sharing. 

Effective file system testing relies on coverage to detect bugs and enhance reliability. We analyzed real file system bugs and found a weak correlation between code coverage, the most commonly used metric, and test effectiveness; many bugs were in covered code but remained undetected. Our study also showed that covering diverse file system inputs and outputs—system call arguments and return values—can be key to detecting the majority of observed bugs. We present input coverage and output coverage as new metrics for evaluating and improving file system testing, and have developed the IOCov framework for computing these metrics. Unlike existing system call tracers, IOCov computes coverage using only the calls relevant to testing, excluding unrelated ones that should not be counted. To demonstrate IOCov’s utility, we used it to extend the existing testing tool CrashMonkey into CM-IOCov, which achieves broader input coverage and more thorough detection of crash consistency bugs. Our experimental evaluation shows that IOCov com- putes input and output coverage accurately with minimal overhead. IOCov is applicable to different types of file system testing and can provide insights for improvement as well as identify untested cases based on coverage results. Moreover, the bugs found exclusively by CM-IOCov are 2.1 and 12.9 times more than those found exclusively by CrashMonkey on the 6.12 and 5.6 kernels, respectively, demonstrating the effectiveness of the IOCov-based coverage approach. 

Archival systems are often tasked with storing highly valuable data that may be targeted by malicious actors. When the lifetime of the secret data is on the order of decades to centuries, the threat of improved cryptanalysis casts doubt on the long-term security of cryptographic techniques, which rely on hardness assumptions that are hard to prove over archival time scales. This threat makes the design of secure archival systems exceptionally difficult. Some archival systems turn a blind eye to this issue, hoping that current cryptographic techniques will not be broken; others often use techniques--—such as secret sharing—that are impractical at scale. This position paper sheds light on the core challenges behind building practically viable secure long-term archives; we identify promising research avenues towards this goal. 

Human activity recognition provides insights into physical and mental well-being by monitoring patterns of movement and behavior, facilitating personalized interventions and proactive health management. Radio Frequency (RF)-based human activity recognition (HAR) is gaining attention due to its less privacy exposure and non-contact characteristics. However, it suffers from data scarcity problems and is sensitive to environment changes. Collecting and labeling such data is laborintensive and time consuming. The limited training data makes generalizability challenging when the sensor is deployed in a very different relative view in the real world. Synthetic data generation from abundant videos presents a potential to address data scarcity issues, yet the domain gaps between synthetic and real data constrain its benefit. In this paper, we firstly share our investigations and insights on the intrinsic limitations of existing video-based data synthesis methods. Then we present M4X, a method using metric learning to extract effective viewindependent features from the more abundant synthetic data despite their domain gaps, thus enhancing cross-view generalizability. We explore two main design issues in different mining strategies for contrastive pairs/triplets construction, and different forms of loss functions. We find that the best choices are offline triplet mining with real data as anchors, balanced triplets, and a triplet loss function without hard negative mining for higher discriminative power. Comprehensive experiments show that M4X consistently outperform baseline methods in cross-view generalizability. In the most challenging case of the least amount of real training data, M4X outperforms three baselines by 7.9- 16.5% on all views, and 18.9-25.6% on a view with only synthetic but no real data during training. This proves its effectiveness in extracting view-independent features from synthetic data despite their domain gaps. We also observe that given limited sensor deployments, a participant-facing viewpoint and another at a large angle (e.g. 60◦) tend to produce much better performance. 

In Activities of Daily Living (ADL) research, which has gained prominence due to the burgeoning aging population, the challenge of acquiring sufficient ground truth data for model training is a significant bottleneck. This obstacle necessitates a pivot towards unsupervised representation learning methodologies, which do not require many labeled datasets. The existing research focused on the tradeoff between the fully supervised model and the unsupervised pre-trained model and found that the unsupervised version outperformed in most cases. However, their investigation did not use large enough Human Activity Recognition (HAR) datasets, both datasets resulting in 3 dimensions. This poster extends the investigation by employing a large multivariate time series HAR dataset and experimenting with the models with different combinations of critical training parameters such as batch size and learning rate to observe the performance tradeoff. Our findings reveal that the pre-trained model is comparable to the fully supervised classification with a larger multivariate time series HAR dataset. This discovery underscores the potential of unsupervised representation learning in ADL extractions and highlights the importance of model configuration in optimizing performance.