Search NASA⌕ Search

SEARCH · Search NASA

Results for “treatment learning”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 19 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2012

Symbolic Execution Enhanced System Testing

We describe a testing technique that uses information computed by symbolic execution of a program unit to guide the generation of inputs to the system containing the unit, in such a way that the unit's, and hence the system's, coverage is increased. The symbolic execution computes unit constraints at run-time, along program paths obtained by system simulations. We use machine learning techniques treatment learning and function fitting to approximate the system input constraints that will lead to the satisfaction of the unit constraints. Execution of system input predictions either uncovers new code regions in the unit under analysis or provides information that can be used to improve the approximation. We have implemented the technique and we have demonstrated its effectiveness on several examples, including one from the aerospace domain.

Davies, Misty D.↗
NASA NTRS2010

Automatically Finding the Control Variables for Complex System Behavior

Testing large-scale systems is expensive in terms of both time and money. Running simulations early in the process is a proven method of finding the design faults likely to lead to critical system failures, but determining the exact cause of those errors is still time-consuming and requires access to a limited number of domain experts. It is desirable to find an automated method that explores the large number of combinations and is able to isolate likely fault points. Treatment learning is a subset of minimal contrast-set learning that, rather than classifying data into distinct categories, focuses on finding the unique factors that lead to a particular classification. That is, they find the smallest change to the data that causes the largest change in the class distribution. These treatments, when imposed, are able to identify the factors most likely to cause a mission-critical failure. The goal of this research is to comparatively assess treatment learning against state-of-the-art numerical optimization techniques. To achieve this, this paper benchmarks the TAR3 and TAR4.1 treatment learners against optimization techniques across three complex systems, including two projects from the Robust Software Engineering (RSE) group within the National Aeronautics and Space Administration (NASA) Ames Research Center. The results clearly show that treatment learning is both faster and more accurate than traditional optimization methods.

Gay, Gregory↗
NASA NTRS2008

Optimizing Requirements Decisions with KEYS

Recent work with NASA's Jet Propulsion Laboratory has allowed for external access to five of JPL's real-world requirements models, anonymized to conceal proprietary information, but retaining their computational nature. Experimentation with these models, reported herein, demonstrates a dramatic speedup in the computations performed on them. These models have a well defined goal: select mitigations that retire risks which, in turn, increases the number of attainable requirements. Such a non-linear optimization is a well-studied problem. However identification of not only (a) the optimal solution(s) but also (b) the key factors leading to them is less well studied. Our technique, called KEYS, shows a rapid way of simultaneously identifying the solutions and their key factors. KEYS improves on prior work by several orders of magnitude. Prior experiments with simulated annealing or treatment learning took tens of minutes to hours to terminate. KEYS runs much faster than that; e.g for one model, KEYS ran 13,000 times faster than treatment learning (40 minutes versus 0.18 seconds). Processing these JPL models is a non-linear optimization problem: the fewest mitigations must be selected while achieving the most requirements. Non-linear optimization is a well studied problem. With this paper, we challenge other members of the PROMISE community to improve on our results with other techniques.

requirements↗
NASA NTRS2009

A New Monte Carlo Filtering Method for the Diagnosis of Mission-Critical Failures

Testing large-scale systems is expensive in terms of both time and money. Running simulations early in the process is a proven method of finding the design faults likely to lead to critical system failures, but determining the exact cause of those errors is still time-consuming and requires access to a limited number of domain experts. It is desirable to find an automated method that explores the large number of combinations and is able to isolate likely fault points. Treatment learning is a subset of minimal contrast-set learning that, rather than classifying data into distinct categories, focuses on finding the unique factors that lead to a particular classification. That is, they find the smallest change to the data that causes the largest change in the class distribution. These treatments, when imposed, are able to identify the settings most likely to cause a mission-critical failure. This research benchmarks two treatment learning methods against standard optimization techniques across three complex systems, including two projects from the Robust Software Engineering (RSE) group within the National Aeronautics and Space Administration (NASA) Ames Research Center. It is shown that these treatment learners are both faster than traditional methods and show demonstrably better results.

Gay, Gregory↗
NASA NTRS2019

MARGInS Model-Based Analysis of Realizable Goals in Systems

The high complexity of modern aircraft and spacecraft requires elaborate Verification and Validation (V&V) approaches to make sure that such complex systems work properly and reliably. MARGInS is a framework for the analysis, understanding, and prediction of the behavior of a complex, hybrid system. MARGInS contains a set of machine learning and statistical algorithms for multivariate clustering, treatment learning, critical factor determination, time-series analysis, event prediction, and safety-boundary detection and characterization. The framework supports system testing and can be configured to find novel features in test suites, determine classes of behavior, propose new experiments that can efficiently explore and characterize the boundaries between classes of system behavior, and to create visualizations and reports.

He, Yuning↗
NASA NTRS2018

Terrestrial Cardiovascular Coronary Artery Disease (CAD) Screening, Treatment and Risk Mitigation - Lessons Learned from Space Medicine

The Bellagio II Summit sought to correlate current ISS (International Space Station) Space Medicine practice in the screening/assessment and management of CAD (Coronary Artery Disease) and to identify terrestrial applications for the general population pertaining to primary, secondary and tertiary diagnoses and treatments. We identified current Space Medicine practice for screening and monitoring cosmonaut and astronaut in the pre-, in-, and post-flight mission phases. We will discuss current Space Medicine standards and guidelines in the recognition and monitoring of CAD development, stabilization, and regression.

Johnston, Smith↗
NASA NTRS2011

A Parametric Testing Environment for Finding the Operational Envelopes of Simulated Guidance Algorithms

The ever-increasing size and complexity of aerospace systems often drive developers to validate using modeling and Monte Carlo simulations confined around expected points of operation in a hyper-dimensional parameter space. This paper describes an alternative that explores large regions of the parameter space with explicit coverage guarantees, searching for n parameter relations that characterize a system's performance envelope.

Parametric testing↗
NASA NTRS2011

A Parametric Testing Environment for Finding the Operational Envelopes of Simulated Guidance Algorithms

The Problem: As NASA missions become ever more complex and subsystems become ever more complicated, testing for correctness becomes progressively more difficult. Exhaustive testing is usually impractical, so how does one select a smaller set of test cases that is effective at finding/analyzing bugs? Solution:(1) Let an analyst pose test-space coverage requirements and then refine these requirements to focus on regions of interest in response to visualized test results. (2) Instead of validating correctness around set points (with Monte Carlo analysis) find and characterize the margins of the performance envelop where the system starts to fail.

treatment learning↗
NASA NTRS1992

Ceramic processing: Experimental design and optimization

The objectives of this paper are to: (1) gain insight into the processing of ceramics and how green processing can affect the properties of ceramics; (2) investigate the technique of slip casting; (3) learn how heat treatment and temperature contribute to density, strength, and effects of under and over firing to ceramic properties; (4) experience some of the problems inherent in testing brittle materials and learn about the statistical nature of the strength of ceramics; (5) investigate orthogonal arrays as tools to examine the effect of many experimental parameters using a minimum number of experiments; (6) recognize appropriate uses for clay based ceramics; and (7) measure several different properties important to ceramic use and optimize them for a given application.

Weiser, Martin W.↗
NASA NTRS1987

Tutoring electronic troubleshooting in a simulated maintenance work environment

A series of intelligent tutoring systems, or intelligent maintenance simulators, is being developed based on expert and novice problem solving data. A graded series of authentic troubleshooting problems provides the curriculum, and adaptive instructional treatments foster active learning in trainees who engage in extensive fault isolation practice and thus in conditionalizing what they know. A proof of concept training study involving human tutoring was conducted as a precursor to the computer tutors to assess this integrated, problem based approach to task analysis and instruction. Statistically significant improvements in apprentice technicians' troubleshooting efficiency were achieved after approximately six hours of training.

Gott, Sherrie P.↗
NASA NTRS2012

Adaptive Sampling of Time Series During Remote Exploration

This work deals with the challenge of online adaptive data collection in a time series. A remote sensor or explorer agent adapts its rate of data collection in order to track anomalous events while obeying constraints on time and power. This problem is challenging because the agent has limited visibility (all its datapoints lie in the past) and limited control (it can only decide when to collect its next datapoint). This problem is treated from an information-theoretic perspective, fitting a probabilistic model to collected data and optimizing the future sampling strategy to maximize information gain. The performance characteristics of stationary and nonstationary Gaussian process models are compared. Self-throttling sensors could benefit environmental sensor networks and monitoring as well as robotic exploration. Explorer agents can improve performance by adjusting their data collection rate, preserving scarce power or bandwidth resources during uninteresting times while fully covering anomalous events of interest. For example, a remote earthquake sensor could conserve power by limiting its measurements during normal conditions and increasing its cadence during rare earthquake events. A similar capability could improve sensor platforms traversing a fixed trajectory, such as an exploration rover transect or a deep space flyby. These agents can adapt observation times to improve sample coverage during moments of rapid change. An adaptive sampling approach couples sensor autonomy, instrument interpretation, and sampling. The challenge is addressed as an active learning problem, which already has extensive theoretical treatment in the statistics and machine learning literature. A statistical Gaussian process (GP) model is employed to guide sample decisions that maximize information gain. Nonsta tion - ary (e.g., time-varying) covariance relationships permit the system to represent and track local anomalies, in contrast with current GP approaches. Most common GP models are stationary, e.g., the covariance relationships are time-invariant. In such cases, information gain is independent of previously collected data, and the optimal solution can always be computed in advance. Information-optimal sampling of a stationary GP time series thus reduces to even spacing, and such models are not appropriate for tracking localized anomalies. Additionally, GP model inference can be computationally expensive.

Thompson, David R.↗
NASA NTRS2013

Advanced Exploration Systems (AES) Logistics Reduction and Repurposing Project: Advanced Clothing Ground Study Final Report

All human space missions require significant logistical mass and volume that will become an excessive burden for long duration missions beyond low Earth orbit. The goal of the Advanced Exploration Systems (AES) Logistics Reduction & Repurposing (LRR) project is to bring new ideas and technologies that will enable human presence in farther regions of space. The LRR project has five tasks: 1) Advanced Clothing System (ACS) to reduce clothing mass and volume, 2) Logistics to Living (L2L) to repurpose existing cargo, 3) Heat Melt Compactor (HMC) to reprocess materials in space, 4) Trash to Gas (TTG) to extract useful gases from trash, and 5) Systems Engineering and Integration (SE&I) to integrate these logistical components. The current International Space Station (ISS) crew wardrobe has already evolved not only to reduce some of the logistical burden but also to address crew preference. The ACS task is to find ways to further reduce this logistical burden while examining human response to different types of clothes. The ACS task has been broken into a series of studies on length of wear of various garments: 1) three small studies conducted through other NASA projects (MMSEV, DSH, HI-SEAS) focusing on length of wear of garments treated with an antimicrobial finish; 2) a ground study, which is the subject of this report, addressing both length of wear and subject perception of various types of garments worn during aerobic exercise; and 3) an ISS study replicating the ground study, and including every day clothing to collect information on perception in reduced gravity in which humans experience physiological changes. The goal of the ground study is first to measure how long people can wear the same exercise garment, depending on the type of fabric and the presence of antimicrobial treatment, and second to learn why. Human factors considerations included in the study consist of the Institutional Review Board approval, test protocol and participants' training, and a web-based data collection questionnaire. Cardiovascular exercise was chosen as the activity in this experiment for its profuse sweating effect and because it is considered a more severe treatment applied to the clothes than every-day usage. Study garments were exercise T-shirts and shorts purchased from various vendors. Fabric construction, fabric composition, and finishing treatment were defined as the key variables. The study was divided into three balanced experiments: a cotton-polyester-wool (CPW) T-shirts study with 61 participants, a polyester-modacrylic-polyester/cocona (PMC) T-shirts study with 40 participants, and a shorts study with 70 participants. In the CPW study, the T-shirts were made of 100% cotton, or of 100% polyester or of 100% wool, and categorized into open and tight knit constructions. In the PMC study, the T-shirts were made of 100% polyester, or of 82% modacrylic, or of 95% polyester with 5% cocona fiber, without construction distinction. The shorts were made either of 100% cotton or of 100% polyester, and were knitted or woven. Some garments were treated with Bio-Protect 500 antimicrobial finish according to the experimental design. The data collected from the questionnaire included garment identification, level of exertion, duration of exercise session, number of exercise sessions, an ordinal preference scale for nine sensory elements, and reason for retiring a used garment. From the analysis of the combined CPW and PMC shirt studies, there are statistically significant differences among the mean lifetimes of various types of shirts. The exercise shirts with the longest mean lifetimes are untreated wool (600 minutes), treated cotton (526 minutes), and untreated modacrylic (515 minutes). From the combined CPW and PMC shirt studies, the most preferred material was untreated open-knit wool, which is one of the two materials that jointly were worn the longest, untreated wool, both open-knit and tight-knit. For the CP shorts study, there were no statistically significant differences in mean lifetimes of the exercise shorts at the 5% significance level due to the treatment combinations. There was therefore no justification to examine differences among levels of main effects or interactions. The preference for shorts was in this order: untreated woven polyester, untreated knitted polyester, untreated woven cotton, and treated knitted cotton. The nine preference scales were tabulated to determine the preference responses at the end of those exercise periods which were prior to the period when a garment was retired and a new garment was started. The assumption is that an unfavorable assessment of a garment leads to its retirement. The scent scale response was predominantly unfavorable at the end of the exercise period immediately prior to the exercise period when a new garment was started.

Byrne, Vicky↗
NASA NTRS2009

Parametric Analysis of a Hover Test Vehicle using Advanced Test Generation and Data Analysis

Large complex aerospace systems are generally validated in regions local to anticipated operating points rather than through characterization of the entire feasible operational envelope of the system. This is due to the large parameter space, and complex, highly coupled nonlinear nature of the different systems that contribute to the performance of the aerospace system. We have addressed the factors deterring such an analysis by applying a combination of technologies to the area of flight envelop assessment. We utilize n-factor (2,3) combinatorial parameter variations to limit the number of cases, but still explore important interactions in the parameter space in a systematic fashion. The data generated is automatically analyzed through a combination of unsupervised learning using a Bayesian multivariate clustering technique (AutoBayes) and supervised learning of critical parameter ranges using the machine-learning tool TAR3, a treatment learner. Covariance analysis with scatter plots and likelihood contours are used to visualize correlations between simulation parameters and simulation results, a task that requires tool support, especially for large and complex models. We present results of simulation experiments for a cold-gas-powered hover test vehicle.

Gundy-Burlet, Karen↗
NASA NTRS2002

Astronauts Need Their Rest Too: Sleep-Wake Actigraphy and Light Exposure During Space Flight

The success and effectiveness of human space flight depends on astronauts' ability to maintain a high level of cognitive performance and vigilance. This alert state ensures the proper operation of sophisticated instrumentation. An important way for humans to remedy fatigue and maintain alertness is to get plenty of rest. Astronauts, however, commonly experience difficulty sleeping while in space. During flight, they may also experience disruption of the body's circadian rhythm - the natural phases the body goes through every day as we oscillate between states of high activity during the waking day and recuperation, rest, and repair during nighttime sleep. Both of these factors are associated with impairment of alertness and performance, which could have important consequences during a mission in space. The human body was designed to sleep at night and be alert and active during the day. We receive these cues from the time of day or amount of light, such as the rising or setting of the sun. However, in the environment of the Space Shuttle or the International Space Station where light levels are highly variable, the characteristics of a 24-hour light/dark cycle are not present to cue the astronauts' bodies about what time of the day it is. Astronauts orbiting Earth see a sunset and sunrise every 90 minutes, sending potentially disruptive signals to the area of the brain that regulates sleep. On STS-107, researchers will measure sleep-wake activity with state-of-the-art technology to quantify how much sleep astronauts obtain in space. Because light is the most powerful time cue to the body's circadian system, individual light exposure patterns of the astronauts will also be monitored to determine if light exposure is associated with sleep disruption. The results of this research could lead to the development of a new treatment for sleep disturbances, enabling crewmembers to avoid the decrements in alertness and performance due to sleep deprivation. What we learn about sleep in space informs treatment for earthbound populations, such as the elderly and insomniacs, who experience frequent sleep disturbances or altered sleep patterns.

Czeisler, Charles↗
NASA NTRS2008

Tool Support for Parametric Analysis of Large Software Simulation Systems

The analysis of large and complex parameterized software systems, e.g., systems simulation in aerospace, is very complicated and time-consuming due to the large parameter space, and the complex, highly coupled nonlinear nature of the different system components. Thus, such systems are generally validated only in regions local to anticipated operating points rather than through characterization of the entire feasible operational envelope of the system. We have addressed the factors deterring such an analysis with a tool to support envelope assessment: we utilize a combination of advanced Monte Carlo generation with n-factor combinatorial parameter variations to limit the number of cases, but still explore important interactions in the parameter space in a systematic fashion. Additional test-cases, automatically generated from models (e.g., UML, Simulink, Stateflow) improve the coverage. The distributed test runs of the software system produce vast amounts of data, making manual analysis impossible. Our tool automatically analyzes the generated data through a combination of unsupervised Bayesian clustering techniques (AutoBayes) and supervised learning of critical parameter ranges using the treatment learner TAR3. The tool has been developed around the Trick simulation environment, which is widely used within NASA. We will present this tool with a GN&C (Guidance, Navigation and Control) simulation of a small satellite system.

Schumann, Johann↗