Publications
Energy resilience: exercises for Marine Corps installations
February 1, 2022
Journal Article
Published in:
Marine Corps Gazette, Vol. 106, No. 2, February 2022, p. 20-24.
Summary
Microgrids are areas that are self-sufficient for power that can controllably disconnect from the incoming utility feed and control generation assets in conjunction with changing load requirements. They are increasingly being touted as a way to improve installations energy resilience because they allow installations to decouple from the larger electric grid if it fails and continue to provide power in the face of growing natural and man-made threats to Marine Corps installations. However, before commanders can put resources toward upgrading infrastructure, they need to identify and understand their vulnerabilities. A key way to do this is by holding exercises designed to simulate grid failures and outages either in a tabletop manner or in realtime. These exercises also help personnel train for disruptions, understand their impact on operations, and identify unknown interdependencies that can be just as important as investing in resilient technology and the physical electric grid. In order for the equipment to work, personnel have to know how to employ it and commands need to understand how outages will affect their installations. These types of exercises are as important as the physical infrastructure or ensuring the energy resilience of Marine Corps installations and the missions that depend on them in the future.
Summary
Microgrids are areas that are self-sufficient for power that can controllably disconnect from the incoming utility feed and control generation assets in conjunction with changing load requirements. They are increasingly being touted as a way to improve installations energy resilience because they allow installations to decouple from the larger electric...
READ MORE
Radar-optimized wind turbine siting
January 1, 2022
Journal Article
Published in:
IEEE Trans. Sustain. Energy, Vol. 13, No. 1, January 2022, pp. 403-13.
Summary
A method for analyzing wind turbine-radar interference is presented. A model is used to derive layouts for siting wind turbines that reduces their impact on radar systems, potentially allowing for increased wind turbine development near radar sites. By choosing a specific wind turbine grid stagger based on a wind farm's orientation relative to a radar site, the impacts on that radar can be minimized. The proposed changes to wind farm siting are relatively minor and do not have a significant effect on wind turbine density. With proper optimization of radar clutter mitigation, radar tracking performance above such wind farms can be significantly increased. Both present-day and potential future or upgraded radar systems are analyzed. The reduction in radar performance due to wind turbine clutter is approximately halved using this method. The developed method is robust with respect to controlled variations in wind turbine placement caused by potential obstructions.
Summary
A method for analyzing wind turbine-radar interference is presented. A model is used to derive layouts for siting wind turbines that reduces their impact on radar systems, potentially allowing for increased wind turbine development near radar sites. By choosing a specific wind turbine grid stagger based on a wind farm's...
READ MORE
A hybrid algorithm for parameter estimation (HAPE) for dynamic constant power loads
November 1, 2021
Journal Article
Published in:
IEEE Trans. Ind. Electron., Vol. 68, No. 11, November 2021, pp. 10326-35.
Summary
Low-inertia microgrids may easily have a single load which can make up most of the total load, thereby greatly affecting stability and power quality. Instead of a static load model, a dynamic constant power load (DCPL) model is considered here. Next, a hybrid algorithm for parameter estimation (HAPE) is introduced. In order to verify the load model and the HAPE, two experiments are conducted with different DCPLs using a Power-Hardwarein-the-Loop (PHiL) testbed. The PHiL testbed consists of a real-time computer working with a programmable power amplifier in order to perturb the input voltage's amplitude and frequency. Each connected DCPL in two separate experiments serves as the device under test (DUT). Using the captured experimental data as a reference, the HAPE is then invoked. The resulting parameter estimates are used to define simulation models. Both resulting DCPL models are simulated to produce waveforms that closely resemble experimental waveforms. Finally, the HAPE's resulting parameter estimates are presented, and the performance of the HAPE is discussed.
Summary
Low-inertia microgrids may easily have a single load which can make up most of the total load, thereby greatly affecting stability and power quality. Instead of a static load model, a dynamic constant power load (DCPL) model is considered here. Next, a hybrid algorithm for parameter estimation (HAPE) is introduced...
READ MORE
Utility of inter-subject transfer learning for wearable-sensor-based joint torque prediction models
October 31, 2021
Conference Paper
Published in:
43rd Annual Intl. Conf. of the IEEE Engineering in Medicine & Biology, 31 October 2021-4 November 2021.
Summary
Generalizability between individuals and groups is often a significant hurdle in model development for human subjects research. In the domain of wearable-sensor-controlled exoskeleton devices, the ability to generalize models across subjects or fine-tune more general models to individual subjects is key to enabling widespread adoption of these technologies. Transfer learning techniques applied to machine learning models afford the ability to apply and investigate the viability and utility such knowledge-transfer scenarios. This paper investigates the utility of single- and multi-subject based parameter transfer on LSTM models trained for "sensor-to-joint torque" prediction tasks, with regards to task performance and computational resources required for network training. We find that parameter transfer between both single- and multi-subject models provide useful knowledge transfer, with varying results across specific "source" and "target" subject pairings. This could be leveraged to lower model training time or computational cost in compute-constrained environments or, with further study to understand causal factors of the observed variance in performance across source and target pairings, to minimize data collection and model retraining requirements to select and personalize a generic model for personalized wearable-sensor-based joint torque prediction technologies.
Summary
Generalizability between individuals and groups is often a significant hurdle in model development for human subjects research. In the domain of wearable-sensor-controlled exoskeleton devices, the ability to generalize models across subjects or fine-tune more general models to individual subjects is key to enabling widespread adoption of these technologies. Transfer learning...
READ MORE
Detecting pathogen exposure during the non-symptomatic incubation period using physiological data: proof of concept in non-human primates
September 3, 2021
Journal Article
Published in:
Front Physiol., Vol. 12, September 2021, Article 691074.
Summary
Background and Objectives: Early warning of bacterial and viral infection, prior to the development of overt clinical symptoms, allows not only for improved patient care and outcomes but also enables faster implementation of public health measures (patient isolation and contact tracing). Our primary objectives in this effort are 3-fold. First, we seek to determine the upper limits of early warning detection through physiological measurements. Second, we investigate whether the detected physiological response is specific to the pathogen. Third, we explore the feasibility of extending early warning detection with wearable devices. Research Methods: For the first objective, we developed a supervised random forest algorithm to detect pathogen exposure in the asymptomatic period prior to overt symptoms (fever). We used high-resolution physiological telemetry data (aortic blood pressure, intrathoracic pressure, electrocardiograms, and core temperature) from non-human primate animal models exposed to two viral pathogens: Ebola and Marburg (N = 20). Second, to determine reusability across different pathogens, we evaluated our algorithm against three independent physiological datasets from non-human primate models (N = 13) exposed to three different pathogens: Lassa and Nipah viruses and Y. pestis. For the third objective, we evaluated performance degradation when the algorithm was restricted to features derived from electrocardiogram (ECG) waveforms to emulate data from a non-invasive wearable device. Results: First, our cross-validated random forest classifier provides a mean early warning of 51 ± 12 h, with an area under the receiver-operating characteristic curve (AUC) of 0.93 ± 0.01. Second, our algorithm achieved comparable performance when applied to datasets from different pathogen exposures – a mean early warning of 51 ± 14 h and AUC of 0.95 ± 0.01. Last, with a degraded feature set derived solely from ECG, we observed minimal degradation – a mean early warning of 46 ± 14 h and AUC of 0.91 ± 0.001. Conclusion: Under controlled experimental conditions, physiological measurements can provide over 2 days of early warning with high AUC. Deviations in physiological signals following exposure to a pathogen are due to the underlying host’s immunological response and are not specific to the pathogen. Pre-symptomatic detection is strong even when features are limited to ECG-derivatives, suggesting that this approach may translate to non-invasive wearable devices.
Summary
Background and Objectives: Early warning of bacterial and viral infection, prior to the development of overt clinical symptoms, allows not only for improved patient care and outcomes but also enables faster implementation of public health measures (patient isolation and contact tracing). Our primary objectives in this effort are 3-fold. First...
READ MORE
A neural network estimation of ankle torques from electromyography and accelerometry
August 26, 2021
Journal Article
Published in:
IEEE Trans. Neural Syst. Rehabilitation Eng., Vol. 29, 2021, pp. 1624-33.
Summary
Estimations of human joint torques can provide clinically valuable information to inform patient care, plan therapy, and assess the design of wearable robotic devices. Predicting joint torques into the future can also be useful for anticipatory robot control design. In this work, we present a method of mapping joint torque estimates and sequences of torque predictions from motion capture and ground reaction forces to wearable sensor data using several modern types of neural networks. We use dense feedforward, convolutional, neural ordinary differential equation, and long short-term memory neural networks to learn the mapping for ankle plantarflexion and dorsiflexion torque during standing,walking, running, and sprinting, and consider both single-point torque estimation, as well as the prediction of a sequence of future torques. Our results show that long short-term memory neural networks, which consider incoming data sequentially, outperform dense feedforward, neural ordinary differential equation networks, and convolutional neural networks. Predictions of future ankle torques up to 0.4 s ahead also showed strong positive correlations with the actual torques. The proposed method relies on learning from a motion capture dataset, but once the model is built, the method uses wearable sensors that enable torque estimation without the motion capture data.
Summary
Estimations of human joint torques can provide clinically valuable information to inform patient care, plan therapy, and assess the design of wearable robotic devices. Predicting joint torques into the future can also be useful for anticipatory robot control design. In this work, we present a method of mapping joint torque...
READ MORE
Development of a field artifical intelligence triage tool: Confidence in the prediction of shock, transfusion, and definitive surgical therapy in patients with truncal gunshot wounds
June 1, 2021
Journal Article
Published in:
J. Trauma Acute Care Surg., Vol. 90, No. 6, 1 June 2021.
Topic:
R&D area:
Summary
BACKGROUND: In-field triage tools for trauma patients are limited by availability of information, linear risk classification, and a lack of confidence reporting. We therefore set out to develop and test a machine learning algorithm that can overcome these limitations by accurately and confidently making predictions to support in-field triage in the first hours after traumatic injury. METHODS: Using an American College of Surgeons Trauma Quality Improvement Program-derived database of truncal and junctional gunshot wound (GSW) patients (aged 1~0 years), we trained an information-aware Dirichlet deep neural network (field artificial intelligence triage). Using supervised training, field artificial intelligence triage was trained to predict shock and the need for major hemorrhage control procedures or early massive transfusion (MT) using GSW anatomical locations, vital signs, and patient information available in the field. In parallel, a confidence model was developed to predict the true-dass probability ( scale of 0-1 ), indicating the likelihood that the prediction made was correct, based on the values and interconnectivity of input variables.
Summary
BACKGROUND: In-field triage tools for trauma patients are limited by availability of information, linear risk classification, and a lack of confidence reporting. We therefore set out to develop and test a machine learning algorithm that can overcome these limitations by accurately and confidently making predictions to support in-field triage in...
READ MORE
Geographic source estimation using airborne plant environmental DNA in dust
May 14, 2021
Journal Article
Published in:
Sci. Rep., Vol. 11, No. 1, 10 August 2021, 16238.
Summary
Information obtained from the analysis of dust, particularly biological particles such as pollen, plant parts, and fungal spores, has great utility in forensic geolocation. As an alternative to manual microscopic analysis, we developed a pipeline that utilizes the environmental DNA (eDNA) from plants in dust samples to estimate previous sample location(s). The species of plant-derived eDNA within dust samples were identified using metabarcoding and their geographic distributions were then derived from occurrence records in the USGS Biodiversity in Service of Our Nation (BISON) database. The distributions for all plant species identified in a sample were used to generate a probabilistic estimate of the sample source. With settled dust collected at four U.S. sites over a 15-month period, we demonstrated positive regional geolocation (within 600 km2 of the collection point) with 47.6% (20 of 42) of the samples analyzed. Attribution accuracy and resolution was dependent on the number of plant species identified in a dust sample, which was greatly affected by the season of collection. In dust samples that yielded a minimum of 20 identified plant species, positive regional attribution improved to 66.7% (16 of 24 samples). Using dust samples collected from 31 different U.S. sites, trace plant eDNA provided relevant regional attribution information on provenance in 32.2%. This demonstrated that analysis of plant eDNA in dust can provide an accurate estimate regional provenance within the U.S., and relevant forensic information, for a substantial fraction of samples analyzed.
Summary
Information obtained from the analysis of dust, particularly biological particles such as pollen, plant parts, and fungal spores, has great utility in forensic geolocation. As an alternative to manual microscopic analysis, we developed a pipeline that utilizes the environmental DNA (eDNA) from plants in dust samples to estimate previous sample...
READ MORE
Health-informed policy gradients for multi-agent reinforcement learning
April 1, 2021
Journal Article
Published in:
https://arxiv.org/abs/1908.01022
Summary
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then extended to a multi-agent variant of the proximal policy optimization algorithm and demonstrated on simple particle environments that have elements of system health, risk-taking, semi-expendable agents, and partial observability. We show significant improvement in learning performance compared to policy gradient methods that do not perform multi-agent credit assignment.
Summary
This paper proposes a definition of system health in the context of multiple agents optimizing a joint reward function. We use this definition as a credit assignment term in a policy gradient algorithm to distinguish the contributions of individual agents to the global reward. The health-informed credit assignment is then...
READ MORE
Multimodal representation learning via maximization of local mutual information [e-print]
March 7, 2021
Journal Article
Published in:
Intl. Conf. on Medical Image Computing and Computer Assisted Intervention, MICCAI, 27 September-1 October 2021.
Topic:
R&D area:
Summary
We propose and demonstrate a representation learning approach by maximizing the mutual information between local features of images and text. The goal of this approach is to learn useful image representations by taking advantage of the rich information contained in the free text that describes the findings in the image. Our method learns image and text encoders by encouraging the resulting representations to exhibit high local mutual information. We make use of recent advances in mutual information estimation with neural network discriminators. We argue that, typically, the sum of local mutual information is a lower bound on the global mutual information. Our experimental results in the downstream image classification tasks demonstrate the advantages of using local features for image-text representation learning.
Summary
We propose and demonstrate a representation learning approach by maximizing the mutual information between local features of images and text. The goal of this approach is to learn useful image representations by taking advantage of the rich information contained in the free text that describes the findings in the image...
READ MORE