Search for: All records

Nighttime sidewalk illumination has a significant and unequal influence on where and whether pedestrians walk at night. Despite the importance of pedestrian lighting, there is currently no approach for measuring and communicating how humans experience nighttime sidewalk light levels at scale. We introduce NightLight, a new sensing approach that leverages the ubiquity of smartphones by re-appropriating the built-in light sensor—traditionally used to adapt screen brightness—to sense pedestrian nighttime lighting conditions. We validated our technique through in-lab and street-based evaluations characterizing performance across phone orientation, phone model, and varying light levels demonstrating the ability to aggregate and map pedestrian-oriented light levels with unaltered smartphones. Additionally, to examine the impact of light level data on pedestrian route choice, we conducted a qualitative user study with 13 participants using a standard map vs. one with pedestrian lighting data from NightLight. Our findings demonstrate that people changed their routes in preference of well-light routes during nighttime walking. Our work has implications for improving personalized navigation, understanding pedestrian route choice, and expanding passive urban sensing. 

Reducing the environmental footprint of electronics and computing devices requires new tools that empower designers to make informed decisions about sustainability during the design process itself. This is not possible with current tools for life cycle assessment (LCA) which require substantial domain expertise and time to evaluate the numerous chips and other components that make up a device. We observe first that informed decision-making does not require absolute metrics and can instead be done by comparing designs. Second, we can use domain-specific heuristics to perform these comparisons. We combine these insights to develop DeltaLCA, an open-source interactive design tool that addresses the dual challenges of automating life cycle inventory generation and data availability by performing comparative analyses of electronics designs. Users can upload standard design files from Electronic Design Automation (EDA) software and the tool will guide them through determining which one has greater carbon footprints. DeltaLCA leverages electronics-specific LCA datasets and heuristics and tries to automatically rank the two designs, prompting users to provide additional information only when necessary. We show through case studies DeltaLCA achieves the same result as evaluating full LCAs, and that it accelerates LCA comparisons from eight expert-hours to a single click for devices with ~30 components, and 15 minutes for more complex devices with ~100 components. 

Knowing the object grabbed by a hand can offer essential contextual information for interaction between the human and the physical world. This paper presents a novel system, ViObject, for passive object recognition that uses accelerometer and gyroscope sensor data from commodity smartwatches to identify untagged everyday objects. The system relies on the vibrations caused by grabbing objects and does not require additional hardware or human effort. ViObject's ability to recognize objects passively can have important implications for a wide range of applications, from smart home automation to healthcare and assistive technologies. In this paper, we present the design and implementation of ViObject, to address challenges such as motion interference, different object-touching positions, different grasp speeds/pressure, and model customization to new users and new objects. We evaluate the system's performance using a dataset of 20 objects from 20 participants and show that ViObject achieves an average accuracy of 86.4%. We also customize models for new users and new objects, achieving an average accuracy of 90.1%. Overall, ViObject demonstrates a novel technology concept of passive object recognition using commodity smartwatches and opens up new avenues for research and innovation in this area. 

Background Developers, designers, and researchers use rapid prototyping methods to project the adoption and acceptability of their health intervention technology (HIT) before the technology becomes mature enough to be deployed. Although these methods are useful for gathering feedback that advances the development of HITs, they rarely provide usable evidence that can contribute to our broader understanding of HITs. Objective In this research, we aim to develop and demonstrate a variation of vignette testing that supports developers and designers in evaluating early-stage HIT designs while generating usable evidence for the broader research community. Methods We proposed a method called health concept surveying for untangling the causal relationships that people develop around conceptual HITs. In health concept surveying, investigators gather reactions to design concepts through a scenario-based survey instrument. As the investigator manipulates characteristics related to their HIT, the survey instrument also measures proximal cognitive factors according to a health behavior change model to project how HIT design decisions may affect the adoption and acceptability of an HIT. Responses to the survey instrument were analyzed using path analysis to untangle the causal effects of these factors on the outcome variables. Results We demonstrated health concept surveying in 3 case studies of sensor-based health-screening apps. Our first study (N=54) showed that a wait time incentive could influence more people to go see a dermatologist after a positive test for skin cancer. Our second study (N=54), evaluating a similar application design, showed that although visual explanations of algorithmic decisions could increase participant trust in negative test results, the trust would not have been enough to affect people’s decision-making. Our third study (N=263) showed that people might prioritize test specificity or sensitivity depending on the nature of the medical condition. Conclusions Beyond the findings from our 3 case studies, our research uses the framing of the Health Belief Model to elicit and understand the intrinsic and extrinsic factors that may affect the adoption and acceptability of an HIT without having to build a working prototype. We have made our survey instrument publicly available so that others can leverage it for their own investigations. 

There is a growing body of research revealing that longitudinal passive sensing data from smartphones and wearable devices can capture daily behavior signals for human behavior modeling, such as depression detection. Most prior studies build and evaluate machine learning models using data collected from a single population. However, to ensure that a behavior model can work for a larger group of users, its generalizability needs to be verified on multiple datasets from different populations. We present the first work evaluating cross-dataset generalizability of longitudinal behavior models, using depression detection as an application. We collect multiple longitudinal passive mobile sensing datasets with over 500 users from two institutes over a two-year span, leading to four institute-year datasets. Using the datasets, we closely re-implement and evaluated nine prior depression detection algorithms. Our experiment reveals the lack of model generalizability of these methods. We also implement eight recently popular domain generalization algorithms from the machine learning community. Our results indicate that these methods also do not generalize well on our datasets, with barely any advantage over the naive baseline of guessing the majority. We then present two new algorithms with better generalizability. Our new algorithm, Reorder, significantly and consistently outperforms existing methods on most cross-dataset generalization setups. However, the overall advantage is incremental and still has great room for improvement. Our analysis reveals that the individual differences (both within and between populations) may play the most important role in the cross-dataset generalization challenge. Finally, we provide an open-source benchmark platform GLOBEM- short for Generalization of Longitudinal BEhavior Modeling - to consolidate all 19 algorithms. GLOBEM can support researchers in using, developing, and evaluating different longitudinal behavior modeling methods. We call for researchers' attention to model generalizability evaluation for future longitudinal human behavior modeling studies.