Publications

The COVID-19 pandemic placed unprecedented demands on the global public health systems for disease surveillance and contact tracing. Engineers and scientists recognized that it might be possible to augment the efforts of public health teams, if a system for automated digital contact tracing could be quickly devised and deployed to the population of smartphones. The Private Automated Contact Tracing (PACT) protocol was one of several digital contact tracing proposals offered worldwide. PACT’s mission—to preserve individuals’ privacy and anonymity while enabling them to quickly alert even nearby strangers of a likely risky exposure—was adopted by Google and Apple and realized in the Exposure Notifications (EN) service and API for mobile application development. The Exposure Notifications system, like many digital proximity tools, is based on Bluetooth signal strength estimation, and keeps much of the necessary information and computation on the smartphones themselves. It implemented a decentralized approach to contact tracing: the public health authority, and other governmental authorities, cannot access the records of an individual’s encounters with others; nor is physical location used or shared by the service. Although the service is available on most modern iOS and Android devices, it is not enabled by default; the individual must opt in to use a particular region’s implementation of the service, either by installing the regional app or by enrolling through a menu of regions in the operating system settings. Likewise, individuals must affirm their consent before the service can share anonymized infection status with the regional public health authority, and alert recent close contacts. The widespread availability of Exposure Notifications through Apple and Google’s platforms has made it a de facto world standard. Determining its accuracy and effectiveness as a public health tool has been a subject of intense interest. In July 2020, CDC’s Innovative Technologies Team designated MIT LL and the PACT team as trusted technical advisors on the deployment of private automated contact tracing systems as part of its overall public health response to COVID-19. The Innovative Technologies Team sought to answer the following key question regarding automated contact tracing: Does automated contact tracing have sufficient public health value that it is worthwhile to integrate it at scale into existing and evolving manual contact tracing systems? Rapidly rising caseloads necessitated parallel-path assessment activities of most mature systems at the time. When access to the Google and Apple Exposure Notifications system became available, MIT LL focused the assessment efforts on the systems being built and deployed. There were two immediate and significant challenges to observing and quantifying the performance of the system as a whole: first, the privacy preserving design decisions of PACT and the system implementers denied access to system-level performance metrics, and second, obtaining accurate “ground truth” data about risky encounters in the population, against which to measure the detector performance, would require an unacceptable level of effort and intrusion. Therefore, MIT LL designed a set of parallel research activities to decompose the problem into components that could be assessed quantifiably (Bluetooth sensor performance, algorithm performance, user preferences and behaviors), components that could be assessed qualitatively (potential cybersecurity risks, potential for malicious use), and components that could be modeled based on current and emergent knowledge (population-level effects). The MIT LL research team conducted early assessments of the privacy and security aspects of new EN app implementations and closely reviewed the available system code exercised by the apps, before conducting a series of phone-to-phone data collections both in the laboratory and in simulated real-world conditions. The data from these experiments fed into models and visualization tools created to predict and understand the risk score output of candidate “weights and thresholds” configurations for EN, i.e., to predict the performance of the system as-built against ground truth data for distance and duration of “exposure”. The data and performance predictions from this effort helped to inform the global and local community of practice in making configuration decisions, and can help to predict the performance of future versions of similar tools, or alternative implementations of the current system. We conducted a human factors and usability review of early app user interfaces and messaging from public health, and designed a follow-on large-scale survey to investigate questions about user trust and system adoption decisions. The results of the human factors, user trust, and adoption studies were used by U.S. public health jurisdictions to make adjustments to public-facing communications, and were shared with Apple and Google to improve the user interface. Information gathered from public health experts enabled us to better understand conventional contact tracing workflows and data streams, and we incorporated that information into an agent-based model of “hybrid” contact tracing plus Exposure Notifications. We then combined it with emerging reports on vaccination, mask effectiveness, social interaction, variant transmissibility, and our own data on the sensitivity and specificity of the Bluetooth “dose” estimator, to predict system-level effects under various conditions. Finally, we helped to establish a network of Exposure Notifications “practitioners” in public health, who surfaced desirable system-level key performance indicators (implemented during 2021 and 2022, in the Exposure Notifications Private Analytics system, or ENPA). At the conclusion of the program, many of the initial conditions of the pandemic had changed. The Exposure Notifications service was available to most of the world, but had only been deployed by 28 U.S. states and territories, and had not been adopted by much of the population in those regions. High case rates during the Omicron surge (December 2021 – January 2022) and newly available ENPA data offered the first hints at calculating “real” state-level performance metrics, but those data belong to the states and many are cautious about publishing. Although Google and Apple have stated that Exposure Notifications was designed for COVID-19, and will not be maintained in its current form after the pandemic ends, the public health and engineering communities show clear interest in using the “lessons learned” from Exposure Notifications and other similar solutions to preserve the capabilities developed and prepare better systems for future public health emergencies. The intent of this report is to document the work that has been completed, as well as to inform where the work could be updated or adapted to meet future needs.

This dataset includes multimodal physiologic, flight performance, and user interaction data streams, collected as participants performed virtual flight tasks of varying difficulty. In virtual reality, individuals flew an "Instrument Landing System" (ILS) protocol, in which they had to land an aircraft mostly relying on the cockpit instrument readings. Participants were presented with four levels of difficulty, which were generated by varying wind speed, turbulence, and visibility. Each of the participants performed 12 runs, split into 3 blocks of four consecutive runs, one run at each difficulty, in a single experimental session. The sequence of difficulty levels was presented in a counterbalanced manner across blocks. Flight performance was quantified as a function of horizontal and vertical deviation from an ideal path towards the runway as well as deviation from the prescribed ideal speed of 115 knots. Multimodal physiological signals were aggregated and synchronized using Lab Streaming Layer. Descriptions of data quality are provided to assess each data stream. The starter code provides examples of loading and plotting the time synchronized data streams, extracting sample features from the eye tracking data, and building models to predict pilot performance from the physiology data streams.

Pre-training on time series poses a unique challenge due to the potential mismatch between pre-training and target domains, such as shifts in temporal dynamics, fast-evolving trends, and long-range and short cyclic effects, which can lead to poor downstream performance. While domain adaptation methods can mitigate these shifts, most methods need examples directly from the target domain, making them suboptimal for pre-training. To address this challenge, methods need to accommodate target domains with different temporal dynamics and be capable of doing so without seeing any target examples during pre-training. Relative to other modalities, in time series, we expect that time-based and frequency-based representations of the same example are located close together in the time-frequency space. To this end, we posit that time-frequency consistency (TF-C) — embedding a time-based neighborhood of a particular example close to its frequency-based neighborhood and back—is desirable for pre-training. Motivated by TF-C, we define a decomposable pre-training model, where the self-supervised signal is provided by the distance between time and frequency components, each individually trained by contrastive estimation. We evaluate the new method on eight datasets, including electrodiagnostic testing, human activity recognition, mechanical fault detection, and physical status monitoring. Experiments against eight state-of-the-art methods show that TF-C outperforms baselines by 15.4% (F1 score) on average in one-to-one settings (e.g., fine-tuning an EEG-pretrained model on EMG data) and by up to 8.4% (F1 score) in challenging one-to-many settings (e.g., fine-tuning an EEG-pretrained model for either hand-gesture recognition or mechanical fault prediction), reflecting the breadth of scenarios that arise in real-world applications. The source code and datasets are available at https://anonymous.4open.science/r/TFC-pretraining-6B07.

As advances in microscopy imaging provide an ever clearer window into the human brain, accurate reconstruction of neural connectivity can yield valuable insight into the relationship between brain structure and function. However, human manual tracing is a slow and laborious task, and requires domain expertise. Automated methods are thus needed to enable rapid and accurate analysis at scale. In this paper, we explored deep neural networks for dense axon tracing and incorporated axon topological information into the loss function with a goal to improve the performance on both voxel-based segmentation and axon centerline detection. We evaluated three approaches using a modified 3D U-Net architecture trained on a mouse brain dataset imaged with light sheet microscopy and achieved a 10% increase in axon tracing accuracy over previous methods. Furthermore, the addition of centerline awareness in the loss function outperformed the baseline approach across all metrics, including a boost in Rand Index by 8%.

Digital games offer many elements to augment traditional classroom lectures and reading assignments. They enable players to explore concepts through repeat play in a low-risk environment, and allow players to integrate feedback given during gameplay and evaluate their own performance. Commercial games leverage a number of features to engage players and hold their attention. But do those engagement-improving methods have a place in instructional environments with a captive and motivated audience? Our experience building a logistics supply chain training game for the Marine Corps University suggests that yes; applying lessons in engagement from commercial games can both help improve player experience with the learning environment, and potentially improve learning outcomes.

Objective This study examined the interaction of gait-synchronized vibrotactile cues with an active ankle exoskeleton that provides plantarflexion assistance. Background An exoskeleton that augments gait may support collaboration through feedback to the user about the state of the exoskeleton or characteristics of the task. Methods Participants (N = 16) were provided combinations of torque assistance and vibrotactile cues at pre-specified time points in late swing and early stance while walking on a self-paced treadmill. Participants were either given explicit instructions (N = 8) or were allowed to freely interpret (N=8) how to coordinate with cues. Results For the free interpretation group, the data support an 8% increase in stride length and 14% increase in speed with exoskeleton torque across cue timing, as well as a 5% increase in stride length and 7% increase in speed with only vibrotactile cues. When given explicit instructions, participants modulated speed according to cue timing-increasing speed by 17% at cues in late swing and decreasing speed 11% at cues in early stance compared to no cue when exoskeleton torque was off. When torque was on, participants with explicit instructions had reduced changes in speed. Conclusion These findings support that the presence of torque mitigates how cues were used and highlights the importance of explicit instructions for haptic cuing. Interpreting cues while walking with an exoskeleton may increase cognitive load, influencing overall human-exoskeleton performance for novice users. Application Interactions between haptic feedback and exoskeleton use during gait can inform future feedback designs to support coordination between users and exoskeletons.

We present a condensed description of the joint effort of JHUCLSP/HLTCOE, MIT-LL and AGH for NIST SRE21. NIST SRE21 consisted of speaker detection over multilingual conversational telephone speech (CTS) and audio from video (AfV). Besides the regular audio track, the evaluation also contains visual (face recognition) and multi-modal tracks. This evaluation exposes new challenges, including cross-source–i.e., CTS vs. AfV– and cross-language trials. Each speaker can speak two or three languages among English, Mandarin and Cantonese. For the audio track, we evaluated embeddings based on Res2Net and ECAPA-TDNN, where the former performed the best. We used PLDA based back-ends trained on previous SRE and VoxCeleb and adapted to a subset of Mandarin/Cantonese speakers. Some novel contributions of this submission are: the use of neural bandwidth extension (BWE) to reduce the mismatch between the AFV and CTS conditions; and invariant representation learning (IRL) to make the embeddings from a given speaker invariant to language. Res2Net with neural BWE was the best monolithic system. We used a pre-trained RetinaFace face detector and ArcFace embeddings for the visual track, following our NIST SRE19 work. We also included a new system using a deep pyramid single shot face detector and face embeddings trained on Crystal loss and probabilistic triplet loss, which performed the best. The number of face embeddings in the test video was reduced by agglomerative clustering or weighting the embedding based on the face detection confidence. Cosine scoring was used to compare embeddings. For the multi-modal track, we just added the calibrated likelihood ratios of the audio and visual conditions, assuming independence between modalities. The multi-modal fusion improved Cprimary by 72% w.r.t. audio.

We present a condensed description of the joint effort of JHUCLSP/HLTCOE and MIT-LL for NIST SRE20. NIST SRE20 CTS consisted of multilingual conversational telephone speech. The set of languages included in the evaluation was not provided, encouraging the participants to develop systems robust to any language. We evaluated x-vector architectures based on ResNet, squeeze-excitation ResNets, Transformers and EfficientNets. Though squeeze-excitation ResNets and EfficientNets provide superior performance in in-domain tasks like VoxCeleb, regular ResNet34 was more robust in the challenge scenario. On the contrary, squeeze-excitation networks over-fitted to the training data, mostly in English. We also proposed a novel PLDA mixture and k-NN PLDA back-ends to handle the multilingual trials. The former clusters the x-vector space expecting that each cluster will correspond to a language family. The latter trains a PLDA model adapted to each enrollment speaker using the nearest speakers–i.e., those with similar language/channel. The k-NN back-end improved Act. Cprimary (Cp) by 68% in SRE16-19 and 22% in SRE20 Progress w.r.t. a single adapted PLDA back-end. Our best single system achieved Act. Cp=0.110 in SRE20 progress. Meanwhile, our best fusion obtained Act. Cp=0.110 in the progress–8% better than single– and Cp=0.087 in the eval set.

We introduce AAM-Gym, a research and development testbed for Advanced Air Mobility (AAM). AAM has the potential to revolutionize travel by reducing ground traffic and emissions by leveraging new types of aircraft such as electric vertical take-off and landing (eVTOL) aircraft and new advanced artificial intelligence (AI) algorithms. Validation of AI algorithms require representative AAM scenarios, as well as a fast time simulation testbed to evaluate their performance. Until now, there has been no such testbed available for AAM to enable a common research platform for individuals in government, industry, or academia. MIT Lincoln Laboratory has developed AAM-Gym to address this gap by providing an ecosystem to develop, train, and validate new and established AI algorithms across a wide variety of AAM use-cases. In this paper, we use AAM-Gym to study the performance of two reinforcement learning algorithms on an AAM use-case, separation assurance in AAM corridors. The performance of the two algorithms is demonstrated based on a series of metrics provided by AAM-Gym, showing the testbed’s utility to AAM research.

BLEMUR, or Bluetooth Low Energy Model of User Risk, is a model of the probability of alert at a given duration and distance of an index case for a specific configuration of settings for an Exposure Notification (EN) system.The Google-Apple EN framework operates in the duration and Bluetooth Low Energy (BLE) signal attenuation domains. However, many public health definitions of "exposure" to a disease are based upon the distance between an index case and another person. To bridge the conceptual gap for public health authorities (PHAs) from the familiar distance-and-duration space to the signal attenuation-and-duration space, BLEMUR uses BLE signal attenuation as a proxy for distance between people, albeit an imprecise one. This paper will discuss the EN settings that can be manipulated, the BLE data collected, how data support a model of the relationship between measured attenuation and distance between phones, and how BLEMUR calculates the probability of alert for a distance and duration based on the settings and data.