Katherine M. Steele

Megan R. Ebers, Jan P. Williams, Katherine M. Steele et al.

Sensing is one of the most fundamental tasks for the monitoring, forecasting and control of complex, spatio-temporal systems. In many applications, a limited number of sensors are mobile and move with the dynamics, with examples including wearable technology, ocean monitoring buoys, and weather balloons. In these dynamic systems (without regions of statistical-independence), the measurement time history encodes a significant amount of information that can be extracted for critical tasks. Most model-free sensing paradigms aim to map current sparse sensor measurements to the high-dimensional state space, ignoring the time-history all together. Using modern deep learning architectures, we show that a sequence-to-vector model, such as an LSTM (long, short-term memory) network, with a decoder network, dynamic trajectory information can be mapped to full state-space estimates. Indeed, we demonstrate that by leveraging mobile sensor trajectories with shallow recurrent decoder networks, we can train the network (i) to accurately reconstruct the full state space using arbitrary dynamical trajectories of the sensors, (ii) the architecture reduces the variance of the mean-square error of the reconstruction error in comparison with immobile sensors, and (iii) the architecture also allows for rapid generalization (parameterization of dynamics) for data outside the training set. Moreover, the path of the sensor can be chosen arbitrarily, provided training data for the spatial trajectory of the sensor is available. The exceptional performance of the network architecture is demonstrated on three applications: turbulent flows, global sea-surface temperature data, and human movement biomechanics.

Momona Yamagami, Kelly Mack, Jennifer Mankoff et al.

Many individuals with disabilities and/or chronic conditions (da/cc) experience symptoms that may require intermittent or on-going medical care. However, healthcare is an often-overlooked domain for accessibility work, where access needs associated with temporary and long-term disability must be addressed to increase the utility of physical and digital interactions with healthcare workers and spaces. Our work focuses on a specific domain of healthcare often used by individuals with da/cc: physical therapy (PT). Through a twelve-person interview study, we examined how people's access to PT for their da/cc is hampered by social (e.g., physically visiting a PT clinic) and physiological (e.g., chronic pain) barriers, and how technology could improve PT access. In-person PT is often inaccessible to our participants due to lack of transportation and insufficient insurance coverage. As such, many of our participants relied on at-home PT to manage their da/cc symptoms and work towards PT goals. Participants felt that PT barriers, such as having particularly bad symptoms or feeling short on time, could be addressed with well-designed technology that flexibly adapts to the person's dynamically changing needs while supporting their PT goals. We introduce core design principles (adaptability, movement tracking, community building) and tensions (insurance) to consider when developing technology to support PT access. Rethinking da/cc access to PT from a lens that includes social and physiological barriers presents opportunities to integrate accessibility and adaptability into PT technology.

Jing Wu, Benjamin R. Shuman, Bingni W. Brunton et al.

Neural correlates of movement planning onset and direction may be present in human electrocorticography in the signal dynamics of both motor and non-motor cortical regions. We use a three-stage model of jPCA reduced-rank hidden Markov model (jPCA-RR-HMM), regularized shrunken-centroid discriminant analysis (RDA), and LASSO regression to extract direction-sensitive planning information and movement onset in an upper-limb 3D isometric force task in a human subject. This mode achieves a relatively high true positive force-onset prediction rate of 60% within 250ms, and an above-chance 36% accuracy (17% chance) in predicting one of six planned 3D directions of isometric force using pre-movement signals. We also find direction-distinguishing information up to 400ms before force onset in the pre-movement signals, captured by electrodes placed over the limb-ipsilateral dorsal premotor regions. This approach can contribute to more accurate decoding of higher-level movement goals, at earlier timescales, and inform sensor placement. Our results also contribute to further understanding of the spatiotemporal features of human motor planning.