Search

Widespread adoption of artificial intelligence (AI) technologies is substantially affecting the human condition in ways that are not yet well understood. Negative unintended consequences abound including the perpetuation and exacerbation of societal inequalities and divisions via algorithmic decision making. We present six grand challenges for the scientific community to create AI technologies that are human-centered, that is, ethical, fair, and enhance the human condition. These grand challenges are the result of an international collaboration across academia, industry and government and represent the consensus views of a group of 26 experts in the field of human-centered artificial intelligence (HCAI). In essence, these challenges advocate for a human-centered approach to AI that (1) is centered in human well-being, (2) is designed responsibly, (3) respects privacy, (4) follows human-centered design principles, (5) is subject to appropriate governance and oversight, and (6) interacts with individuals while respecting human’s cognitive capacities. We hope that these challenges and their associated research directions serve as a call for action to conduct research and development in AI that serves as a force multiplier towards more fair, equitable and sustainable societies.

Training can now be delivered on a large scale through mobile and web-based platforms in which the learner is often distanced from the instructor and their peers. In order to optimize learner engagement and maximize learning in these contexts, instructional content and strategies must be engaging. Key to the development and study of such content and strategies, and adaptation of instructional techniques when learners become disengaged, is the ability to objectively assess engagement in real-time. Previous self-reported metrics, or expensive EEG-based engagement measures are not appropriate for large-scale platforms due to their complexity and cost. Here we describe the development and testing of a measurement and classification technique that utilizes non-invasive physiological and behavioral monitoring technology to directly assess engagement in classroom, simulation, and live training environments. An experimental study was conducted with 45 students and first responders in a unmanned aircraft systems (UAS) training program to assess the ability to accurately assess learner engagement and discriminate between levels of learner engagement within classroom, simulation and live environments via physiological and behavioral inputs. A series of engagement classifiers were developed using cardiovascular, respiratory, electrodermal, movement, and eye-tracking features that were able to successfully classify engagement levels at an accuracy level of 85% with eye-tracking features included or 81% without eye-tracking features. This approach is capable of monitoring, assessing, and tracking learner engagement across learning situations and contexts, and providing real-time and after action feedback to support instructors in modulating learner engagement.

Mobile technology’s ubiquity has caused a shift in how students learn and how pedagogy can take place. Educators have the potential to engage students more fully in the modern educational e...

Myoelectric prostheses provide upper limb amputees with hand and arm movement control using muscle activity of the residual limb, but require intensive training to effectively operate. The result is that many amputees abandon their prosthesis before mastering control of their device. In the present study, we examine a novel, mobile, game-based approach to myoelectric prosthesis training. Using the non-dominant limb in a group of able-bodied participants to model amputee pre-prosthetic training, a significant improvement in factors underlying successful myoelectric prosthesis use, including muscle control, sequencing, and isolation were observed. Participants also reported high levels of usability, and motivation with the game-based approach to training. Given fiscal or geographic constraints that limit pre-prosthetic amputee care, mobile myosite training, as described in the current study, has the potential to improve rehabilitation success rates by providing myosite training outside of the clinical environment. Future research should include longitudinal studies in amputee populations to evaluate the impact of pre-prosthetic training methods on prosthesis acceptance, wear time, abandonment, functional outcomes, quality of life, and return to work.

Sleep impairment significantly alters human brain structure and cognitive function, but available evidence suggests that adults in developed nations are sleeping less. A growing body of research has sought to use sleep to forecast cognitive performance by modeling the relationship between the two, but has generally focused on vigilance rather than other cognitive constructs affected by sleep, such as reaction time, executive function, and working memory. Previous modeling efforts have also utilized subjective, self-reported sleep durations and were restricted to laboratory environments. In the current effort we addressed these limitations by employing wearable systems and mobile applications to gather objective sleep information, assess multi-construct cognitive performance, and model/predict changes to mental acuity. Thirty participants were recruited for participation in the study, which lasted one week. Using the Fitbit Charge HR and a mobile version of the Automated Neuropsychological Assessment Metric (ANAM) called CogGauge, we gathered a series of features and utilized the Unified Model of Performance to predict mental acuity based on sleep records. Our results suggest that individuals poorly rate their sleep duration, supporting the need for objective sleep metrics to model circadian changes to mental acuity. Participant compliance in using the wearable throughout the week and responding to the CogGauge assessments was 80%. Specific biases were identified in temporal metrics across mobile devices and operating systems and were excluded from the mental acuity metric development. Individualized prediction of mental acuity consistently outperformed group modeling. This effort indicates the feasibility of creating an individualized, mobile assessment and prediction of mental acuity, compatible with the majority of current mobile devices.

This paper presents a self-contained, single-chip biosignal monitoring system with wireless programmability and telemetry interface suitable for mainstream healthcare applications. The system consists of low-noise front end amplifiers, ADC, MICS/ISM transmitter and infrared programming capability to configure the state of the chip. An on-chip packetizer ensures easy pairing with standard off-the-shelf receivers. The chip is realized in the IBM 130 nm CMOS process with an area of 2×2 mm2. The entire system consumes 1.07 mW from a 1.2 V supply. It weighs 0.6 g including a zinc-air battery. The system has been extensively tested in in vivo biological experiments and requires minimal human interaction or calibration.

A large number of individuals experience mental health disorders, with cognitive behavioral therapy (CBT) emerging as a standard practice for reduction in psychiatric symptoms, including stress, anger, anxiety, and depression. However, CBT is associated with significant patient dropout and lacks the means to provide objective data regarding a patient’s experience and symptoms between sessions. Emerging wearables and mobile health (mHealth) applications represent an approach that may provide objective data to the patient and provider between CBT sessions. Here, we describe the development of a classifier of real-time physiological stress in a healthy population (n = 35) and apply it in a controlled clinical evaluation for armed forces veterans undergoing CBT for stress and anger management (n = 16). Using cardiovascular and electrodermal inputs from a wearable device, the classifier was able to detect physiological stress in a non-clinical sample with accuracy greater than 90%. In a small clinical sample, patients who used the classifier and an associated mHealth application were less likely to discontinue therapy (p = 0.016, d = 1.34) and significantly improved on measures of stress (p = 0.032, d = 1.61), anxiety (p = 0.050, d = 1.26), and anger (p = 0.046, d = 1.41) compared to controls undergoing CBT alone. Given the large number of individuals that experience mental health disorders and the unmet need for treatment, especially in developing nations, such mHealth approaches have the potential to provide or augment treatment at low cost in the absence of in-person care.

In this study we employed a quantitative immunohistochemical approach to compare the brain tissue response to planar silicon microelectrode arrays that were conformally coated with Parylene-C to uncoated controls at 2, 4, and 12 weeks following implantation into the cortex of adult male Sprague-Dawley rats. We did not find any difference in the relative intensity or the spatial distribution of neuronal or glial markers over the indwelling period, even though Parylene-C-coated substrates supported significantly less cell attachment, indicating that the foreign body response to planar silicon microelectrode arrays has little to do with the composition or decomposition of the silicon electrode. Moreover, our results suggest that changes in microelectrode surface chemistry do not have a strong influence on the cytoarchitectural changes that accompany the brain foreign body response to planar silicon microelectrode arrays. Our quantitative comparison over the indwelling period does not support progressive increases in astrocyte encapsulation and/or progressive neuronal loss in the recording zone as dominant failure mechanisms of the type of chronic recording device. Finally, we found evidence of two potentially new failure mechanisms that were associated with CD68 immunoreactivity including demyelination of adjacent neurons and BBB breakdown surrounding implanted electrodes at long indwelling times.

Human task performance is affected by exposure to physiological and psychological stress. The ability to measure the physiological response to stressors and correlate that to task performance could be used to identify resilient individuals or those at risk for stress-related performance decrements. Accomplishing this prior to performance under severe stress or the development of clinical stress disorders could facilitate focused preparation such as tailoring training to individual needs. Here we measure the effects of stress on physiological response and performance through behavior, physiological sensors, and subjective ratings, and identify which individuals are at risk for stress-related performance decrements. Participants performed military-relevant training tasks under stress in a virtual environment, with autonomic and hypothalamic-pituitary-adrenal axis (HPA) reactivity analyzed. Self-reported stress, as well as physiological indices of stress, increased in the group pre-exposed to socioevaluative stress. Stress response was effectively captured via electrodermal and cardiovascular measures of heart rate and skin conductance level. A resilience classification algorithm was developed based upon physiological reactivity, which correlated with baseline unstressed physiological and self-reported stress values. Outliers were identified in the experimental group that had a significant mismatch between self-reported stress and salivary cortisol. Baseline stress measurements were predictive of individual resilience to stress, including the impact stress had on physiological reactivity and performance. Such an approach may have utility in identifying individuals at risk for problems performing under severe stress. Continuing work has focused on adapting this method for military personnel, and assessing the utility of various coping and decision-making strategies on performance and physiological stress.

Comprehensive knowledge of the brain's wiring diagram is fundamental for understanding how the nervous system processes information at both local and global scales. However, with the singular exception of the C. elegans microscale connectome, there are no complete connectivity data sets in other species. Here we report a brain-wide, cellular-level, mesoscale connectome for the mouse. The Allen Mouse Brain Connectivity Atlas uses enhanced green fluorescent protein (EGFP)-expressing adeno-associated viral vectors to trace axonal projections from defined regions and cell types, and high-throughput serial two-photon tomography to image the EGFP-labelled axons throughout the brain. This systematic and standardized approach allows spatial registration of individual experiments into a common three dimensional (3D) reference space, resulting in a whole-brain connectivity matrix. A computational model yields insights into connectional strength distribution, symmetry and other network properties. Virtual tractography illustrates 3D topography among interconnected regions. Cortico-thalamic pathway analysis demonstrates segregation and integration of parallel pathways. The Allen Mouse Brain Connectivity Atlas is a freely available, foundational resource for structural and functional investigations into the neural circuits that support behavioural and cognitive processes in health and disease.

This paper presents a self-contained, single-chip biosignal monitoring system with wireless programmability and telemetry interface suitable for mainstream healthcare applications. The system consists of low-noise front end amplifiers, ADC, MICS/ISM transmitter and infrared programming capability to configure the state of the chip. An on-chip packetizer ensures easy pairing with standard off-the-shelf receivers. The chip is realized in the IBM 130 nm CMOS process with an area of 2×2 mm(2). The entire system consumes 1.07 mW from a 1.2 V supply. It weighs 0.6 g including a zinc-air battery. The system has been extensively tested in in vivo biological experiments and requires minimal human interaction or calibration.

Resilience is the human ability to adapt in the face of tragedy, trauma, adversity, hardship, and ongoing life stressors. To date, experimental reports on this subject have focused on long-term trajectories (weeks to months) of resilience, with little or no focus on whether significant changes to resilience could be achieved by short-term interventions. Currently, an individual’s resilience is defined either by self-report or by behavioral changes such as the development of depression, post-traumatic stress disorder, or suicide. We propose that the quantification of an individual’s physiological and behavioral response to stress under controlled conditions is an indication of the individual’s level of resilience. To address such real-time resilience, we propose the first in a series of studies to evaluate real-time human resilience by exposing participants to controlled stressors while assessing the stress response. Activation of the hypothalamus-pituitary-adrenal cortex axis and sympathetic branch of the autonomic nervous system via monitoring of the pupil constriction, heart and respiration rate, muscle tonicity, salivary cortisol, and electrodermal activity will be assessed. Stress exposure will consist of virtual stressors presented using Virtual Battlespace 2 software-based scenarios, such as noise exposure, time pressure, and emotion-induction tasks, as well as external stressors such as socio-evaluative stress via the Trier social stress task, while evaluating decision-making and performance. The relationship between performance and the physiological stress response will be quantified, including the creation of a series of stress-performance trajectories based upon individual differences. Such an analysis is similar to probing for resilience in material testing, in which a load is applied to a candidate material, and the resulting forces and observable changes in dimension are quantified and reported via stress-strain curves. Ongoing studies will examine how this resilience measure may be integrated into a closed-loop training system to provide appropriate coping strategies to optimize resilience training. Such training programs, which take into account individual perceptions of stressors and physiological responses, are expected to be effective in helping trainees develop resiliency during high-stress operations.

While human factors has been recognized as a key component in research and development efforts, there is a lack of systematic guidance as to how to insert human factors evaluation outcomes into system development processes. The current effort proposes a systematic scale comparable to existing Technology Readiness Level scales to objectively quantify and track human factors readiness throughout the system development lifecycle. The resultant Human Factors Readiness Levels (HFRLs), iteratively developed with input from government and industry human factors practitioners across a variety of domains, prioritize each identified human factors issue based on its risk level and by the status of any resolution. The overall scoring method utilizes a scale of 1 to 10, with a higher score indicating a higher level of human factors readiness. The HFRL scale has been integrated into a software tool, the System for Human Factors Readiness Evaluation (SHARE), that supports tracking and calculation of system level HFRLs that can be quickly and easily shared to support acquisition decision making and product development in an effort to realize return on investment through early identification, prioritization and rectification of issues avoiding expensive, late design changes.

Craniofacial reconstruction would benefit from a degradable adhesive capable of holding bone fragments in three-dimensional alignment and gradually being replaced by new bone without loss of alignment or volume changes. Modeled after a natural adhesive secreted by the sandcastle worm, we studied the biocompatibility of adhesive complex coacervates in vitro and in vivo with two different rat calvarial models. We found that the adhesive was non-cytotoxic and supported the attachment, spreading, and migration of a commonly used osteoblastic cell line over the course of several days. In animal studies we found that the adhesive was capable of maintaining three-dimensional bone alignment in freely moving rats over a 12 week indwelling period. Histological evidence indicated that the adhesive was gradually resorbed and replaced by new bone that became lamellar across the defect without loss of alignment, changes in volume, or changes in the adjacent uninjured bone. The presence of inflammatory cells was consistent with what has been reported with other craniofacial fixation methods including metal plates, screws, tacks, calcium phosphate cements and cyanoacrylate adhesives. Collectively, the results suggest that the new bioadhesive formulation is degradable, osteoconductive and appears suitable for use in the reconstruction of craniofacial fractures.

Several hypotheses have been proposed to explain how the brain tissue reaction to single unit recording electrodes influences biocompatibility including progressive changes in the spatial distribution of reactive astrocytes, and the loss of neurons over the indwelling period. To examine these hypotheses, the spatial distribution of biomarkers associated with the foreign body response to insulated microwires placed in rat cerebral cortex was analyzed 2, 4, and 12 weeks after implantation using quantitative methods. We observed a stereotypical tissue response that was similar in some aspects to that previously reported for penetrating planar silicon microelectrode arrays with some specific differences including an overall lower degree of cortical tissue reactivity. While we found no evidence that reactive gliosis increases over time or that neuronal loss is progressive, we did find evidence of persistent inflammation and enhanced BBB permeability at the electrode brain tissue interface that extended over the 3 month indwelling period and that exhibited more animal to animal variability at 3 months than at 2 and 4 weeks.