United States

The Georgia Tech Research Institute has been supporting the JAIC Joint Logistics virtual sensing National Mission Inititive called VSTAR. Through the development of the VSTAR digital twin MBSE and engagement with DoD transition partners, the development team has assembled a discussion on AI/ML transition best practices. The presentation will give a brief VSTAR background for context, why a digital twin virtual sensor was developed for the HH-60G, and the critical lessons learned from development through transition to successfully deliver a new capability to the warfighter.

NAML 2021

Requirements Considerations for AI/ML Digital Twin Model Transition

virtual sensing

mbse

predictive maitenance

ai/ml

digital twin

Naval Information Warfare Center Pacific is partnering with AFCEA San Diego chapter to host the workshop.

The NAML workshop is an opportunity for researchers from Navy research and development centers and our partner organizations to exchange technical ideas and to come together as a team.

The goals of NAML are:

* To spread awareness of current machine learning research relevant to Naval applications

* To connect machine learning researchers with experts in military requirements

* To build and strengthen collaborations within the defense research community

**Watch this video to hear about the AFCEA purpose.**

<iframe width=1280 height=706 frameborder="0" scrolling="no" src="https://screencast-o-matic.com/player/creleVVcvRh?v=6&ff=1&title=0&controls=1" allowfullscreen="true"></iframe>

technical paper

The outbreak of COVID-19 on the USS Theodore Roosevelt in March of 2020 presented the Navy with a challenge: manage a novel disease outbreak with limited resources. In response, Defense Digital Service deployed “My Symptoms”, a system in which sailors reported a variety of symptoms to assess their need for immediate medical intervention. The Cloud and Analysis Support during COVID-19 Response (CASCR) group at the Naval Information Warfare Center (NIWC) Pacific supported the deployment of “My Symptoms” for multiple sites while collecting, visualizing, and analyzing the data; this lead to actionable insights for the care of quarantined sailors. The CASCR group later applied machine learning techniques to the symptom data to and showed that data collected for triage purposes could be used to determine if a sailor was a symptomatic carrier of SARS-CoV-2.

Operational and Investigative Uses of Symptom Tracker Data from USS ROOSEVELT and USS KIDD

This session presents the results of a project to leverage the significant investment that commercial industry is making in AI that is very focused on improving commercial shipping outcomes, and see if similar models and algorithms can be applied to the DoD space. 
This project was planned and executed under the direction and funding of NS2 Labs (https://www.ns2labs.com/). NS2 Labs is a research organization focused on combining capabilities from the government, academia, commercial industry in order to provide solutions for the US DoD and Intelligence Community. 
We selected three use cases to evaluate on this project: Anomaly Detection, Destination Prediction, and Zone Activity Prediction. The hypothesis behind this project was that commercial AI capabilities could be successfully applied to these DoD maritime use cases. We were confident in this hypothesis largely because of scale: as a company, SAP manages over 70% of worldwide logistics data. The resulting large number of commercial customers means that SAP invests significant amounts of capital to optimize the analysis of this logistics data; presumably at least some of the resulting models would be relevant to the DoD maritime domain. Our research identified five primary model sets used extensively by SAP’s commercial customers: 
1. Port Characteristic Modelling - these models account for water level, wind, waves, visibility, vehicle characteristics and congestion in the waters within and surrounding a port. 
2. Automated Maritime Geofencing – these models support geofencing of specialized areas, detection of concealed vessel identity, brushing incidents, pollutant shipping analysis, and correlations between vessels/businesses/individuals. 
3. Port Operations Modelling – these models address the cargo details, vessel details, visitors/staffing, vehicle operations, security operations, and financial/operational performance of the overall facility. 
4. Demand Forecasting for Transport – these models assess more than 1700 worldwide macro-economic factors to predict future activities across the logistics spectrum. 
5. Global Track and Trace – these models assess the entire logistics and delivery process for SAP’s commercial customers to allow shippers to get in front of potential issues. 
Project execution consisted of processing AIS and radar data with the SAP/Intel Corporation data management platform HANA, enhancing data and model environment with subset of the identified commercial capabilities, and training models to determine home/destination ports, normal behavior by region, anomalous behavior, activity expectations by region, and destination prediction with continuously updated confidence values. 
We continue to work through the remaining commercial components. Our next area of research is bringing in more non-traditional data sources based upon mobile device tracking, supply chain interconnectivity, and social media content overlays. 

Adapting Commercial AI Approaches to Support Maritime Domain Awareness

The Digital Aviation Readiness Technology Engine (DARTE) provides unprecedented predictive readiness capabilities for the Naval FA-18 fleet. DARTE focuses on discovering actionable insights in relation to predicting two key readiness metrics: the number of mission capable (MC) aircraft and flight hours. Recent DARTE improvements are particularly noteworthy, including the adoption of cutting edge AI and deep learning techniques such as temporal pattern attention mechanism enhanced long short-term memory (LSTMA) networks, hyper-deep ensembles for enhanced performance, and improved uncertainty estimation and robustness. Hyper-deep ensembles and attention mechanisms have been shown to provide state-of-the art results in industry and academia. Furthermore, their improved uncertainty estimation provides decision makers with an increased level of confidence that allows for better, smarter decisions.

Improving The Digital Aviation Readiness Technology Engine with Temporal Pattern Attention Mechanisms and Hyper-Deep Ensembles

The United States Navy’s stated force-structure goal is a 500-ship fleet by 2045, a significant build-up from today’s 293 ships. The expanded surface fleet will be designed to meet this goal with operational capabilities, and within operational environments, that have evolved since the last surge of naval shipbuilding in the 1980s. These new challenges will likely drive increased diversity in the design characteristics of future surface combatants—a diversity requiring tools able to rapidly inform set-based designs with high-confidence predictions. This research provides such a tool. Utilizing machine learning, the residual resistance coefficients of a new hull form, across a desired range of speed-to-length ratios, are accurately predicted. With parametric, nondimensional hull form coefficients and ratios from historically tested ship hull methodical series, parametric, non-parametric, and ensemble method algorithms were trained, validated, and tested. The research analyzes the necessity of first classifying a hull design to an established methodical series prior to performing regression efforts to predict resistance. Conversely, the research also analyzes the benefit of machine learning regression algorithms to predict resistance from an entire hull design data set, without first classifying. Finally, the research demonstrates the power of machine learning in quickly adapting to small amounts of additional training data to accurately refine the predictions. The intersection of machine learning and hydrodynamics is a little-explored frontier that, even in its infancy, provides dynamic resistance predictions that are more accurate than Holtrop’s statistical method with a speed dependent form factor. Through the establishment of a shared hull form geometry and performance repository, the true power of machine learning may be unleashed, removing the most challenging of obstacles associated with preliminary hull form design.

Machine Learning in the Prediction of Displacement Hull Form Resistance

The understanding of large data sets and developing predictive capabilities is imperative for the understanding of any boosted system.
Currently, sensor data and historical data is underused due to constraints on data processing capabilities. Data from well-sensored static tests or flights can be vast in size, requiring extensive computing capabilities and processing time.
Using machine learning techniques and high processing computers can provide data processing techniques that are the most useful for the user and maximize the results from the data available and provide the most insight on future tests and the effects of physical changes to the hardware. These tools combine to develop a predictive reliability framework for missile-centric propulsion systems. The machine learning approach uses combinations of sensor data, image processing techniques, and acoustic analysis along with the subject matter expertise of aerospace and propulsion engineers to develop a useful data processing system that can be adapted to many applications. This work describes a novel process for the analysis of experimental plume data sets using multimodal machine learning techniques and analytics in order to develop virtual sensors, detect anomalies, and predict performance based on historical data.

This approach will supplement physically acquired data during ground static testing of solid rocket motors, as well as increase performance measurement above the limited numbered of digital flight instrumentation. Data acquisition for the virtual sensing effort is performed using a solid booster static test stand developed at GTRI. In order to capture the plume characterization with physical sensors, the test instrumentation suite includes axial thrust, on-board acceleration and casing temperature and external imaging, temperature, and acoustics measurements. The machine learning approach focuses on developing anomaly detection, shock detection, and sensor reconstruction solutions through virtual sensing and image processing algorithms for predictive performance analysis of a solid booster. Results show the pre-processing of experimental data, including the resulting dynamics during a test fire, and the ability to recreate different sensor signals based on their inherent behaviors. Additionally, the anomaly detection approach gives autonomous detection of off-normal events and different methods of edge detection were used to identify shocks within the plume.

Virtual-Sensing for Predictive Reliability

If a feature in a dataset can be identified as a potential causal factor through an objective process, this data can then be used to feed any number of conceptual approaches to prevention of safety mishaps. One of the many ways in which this analysis can be attempted is via longitudinal analysis of specific traits attributed to personnel, either individually or in aggregate. That is to say, by examining specific traits as they change over time for their predictive value with respect to a specific outcome. Each moment that a variable is measured results in a feature that is highly correlated with the feature derived from the same variable in the previous or next moment. This presents unique challenges for fitting regression models since fitting highly correlated features will muddle the attribution of causal factors and result in a reduced ability to distinguish the relative importance of features. Additional challenges with regard to analyzing safety mishaps are that the data is frequently imbalanced, meaning that there are very few mishaps when compared to the number of instances in which a mishap did not occur, and that it is more important to be correct about the potential causal factors extracted than it is to be quick. This paper will walk through the process of comprehensively sampling the feature space, applying a progressive framework of winnowing tests designed to reduce the number of models considered to a computationally manageable number while removing irrelevant features, and then developing the results into a workable set of models. Case studies for this process using specific examples are available in the appendices.

Longitudinal Analysis of Imbalanced Data Sets Using Logistic Regression for Safety Mishaps

Naval Tactical Messages, a centralized form of text communication capturing essentially every critical element of the Navy at large, are sent rapidly across the Fleet at a high volume on a daily basis. Each command gathers insights from Tactical Messages in a myriad of ways, with the ultimate goal of providing a formalized mean of disseminating action taskers and providing relevant information to necessary stakeholders. Project Hermes, a DON CDO project, seeks to pipeline all Naval Tactical Message traffic into the DON CIO Jupiter Analytics environment, automating the extract, transform, and load process to enable broad Artificial Intelligence (AI), Machine Learning (ML), and Natural Language Processing (NLP) capabilities and applications. Long term vision of Project Hermes seeks to provide Program and Project specific data analytics and visualizations in a rapidly developing tactical and operational situation, aiding Watch Floor situational awareness, enabling real-time analysis, correlating data and features to be utilized in model development of Operational Risk indicators at the unit level, and to apply these broad AI capabilities across the entire catalog of Naval Tactical Messages to be leveraged by the Navy as a whole.

Project Hermes – Naval Messaging

An initiative at NIWC Pacific called Cloud Based Data Analyics Cells (C-DAC) was designed and architected for the pursose of lowering the barrier of entry to world of data analytics. The goal of the project was to create an “Off the Shelf” analytics platform that will be available to any NIWC project. The C-DAC was architected for the cloud (NRD&E AWS) leveraging cloud native services and offerings. The C-DAC will leverage the latest cloud technologies that facilitate on-demand stand-up of unique C-DAC instantiations as well as simplify the maintenance and complience efforts needed to support an operational big data analytics environment. Project deliverables were cloud formation scripts to provision a C-DAC as well as playbooks for using cloud native services to perform data curation, data analysis and machine learning.

Lowering The Barrier Of Entry For Artificial Intelligence And Machine Learning

DISTRIBUTION A. Approved for public releaseas of 24February2021: distribution unlimited.

Cyber threats constantly evolve, making detection of novel attacks difficult. These threats and attacks are often anomalous, especially for large scale networks that generate a significant amount of normal traffic. The ratio of normal to anomalous network traffic can cause extreme dataset imbalances, making them poorly suited for traditional Machine Learning (ML) algorithms. Anomaly detection algorithms provide avenues for identifying these types of cyber threats. Evaluation of features contributing to the identification of anomalous cyber events is critical in determining the type of cyber threat that the anomalous event may represent. 

We evaluate feature contribution using two well-known anomaly detection algorithms, Local Outlier Factor (LOF) and Isolation Forest (IF). Each of these unsupervised learning algorithms identifies anomalous data differently; where LOF uses regional density methods, IF uses decision trees. We evaluated a Euclidean-based measurement for LOF and a localized Depth-based Isolation Forest Feature Importance (DIFFI) method for IF to extract local feature importance. We demonstrate the extent to which feature evaluation methods are dependent on the anomaly detection algorithm used, and provide insight to features important for anomaly detection in cyber data using synthetic and real world data. 

Finally, we discuss the integration of anomaly scoring explainability into a novel cyber platform called the Pacific Ecosystem for Cyber (PEcoC, pronounced “peacock”). PEcoC leverages local explainability to accelerate analyst response, increase the body of knowledge available to analysts, and to lower barriers of entry for trainees and junior analysts. Ultimately, integrating local explainability of anomaly detection provides useful and important context for expert cyber analysts responsible for network defense. Anomaly detection within PEcoC complements existing defensive-cyber TTPs, signature-based detection systems, and augments analysts’ workflows and analytical options.

DISTRIBUTION A. Approved for public releaseas of 24February2021: distribution unlimited.

Feature Evaluation of Anomaly Detection Models for Cyber Data

We discuss issues in trying to apply AI to procurement tasks. We conducted surveys with procurement professionals who had implemented AI methods in procurement to determine their goals with the AI, the obstacles they encountered, and their assessment of the success of their projects.

Premium content

Requirements Considerations for AI/ML Digital Twin Model Transition

Downloads

Next from NAML 2021

Operational and Investigative Uses of Symptom Tracker Data from USS ROOSEVELT and USS KIDD

Similar lecture

Digital Twin Virtual Sensor Development for H-60 Accelerometer Data Reconstruction