Search NASA⌕ Search

SEARCH · Search NASA

Results for “TRANSFER OF TRAINING”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
NASA NTRS2010

Sensory Bias Predicts Postural Stability, Anxiety, and Cognitive Performance in Healthy Adults Walking in Novel Discordant Conditions

We designed a gait training study that presented combinations of visual flow and support surface manipulations to investigate the response of healthy adults to novel discordant sensorimotor conditions. We aimed to determine whether a relationship existed between subjects visual dependence and their scores on a collective measure of anxiety, cognition, and postural stability in a new discordant environment presented at the conclusion of training (Transfer Test). A treadmill was mounted to a motion base platform positioned 2 m behind a large visual screen. Training consisted of three walking sessions, each within a week of the previous visit, that presented four 5-minute exposures to various combinations of support surface and visual scene manipulations, all lateral sinusoids. The conditions were scene translation only, support surface translation only, simultaneous scene and support surface translations in-phase, and simultaneous scene and support surface translations 180 out-of-phase. During the Transfer Test, the trained participants received a 2-minute novel exposure. A visual sinusoidal roll perturbation, with twice the original flow rate, was superimposed on a sinusoidal support surface roll perturbation that was 90 out of phase with the scene. A high correlation existed between normalized torso translation, measured in the scene-only condition at the first visit, and a combined measure of normalized heart rate, stride frequency, and reaction time at the transfer test. Results suggest that visually dependent participants experience decreased postural stability, increased anxiety, and increased reaction times compared to their less visually dependent counterparts when negotiating novel discordant conditions.

Brady, Rachel A.↗
NASA NTRS2019

Training, Retention, and Transfer of Data Entry Perceptual and Motor Processes Over Short and Long Retention Intervals

In 2 experiments, subjects trained in a standard data entry task, which involved typing numbers (e.g., 2147) using their right hands. At an initial test (20 min or 6 months after training), subjects completed the standard task, followed by a left-hand variant (typing with their left hands) that involved the same perceptual, but different motoric, processes as the standard task. At a second test (2 days or 8 months after training), subjects completed the standard task, followed by a code variant (translating letters into digits, then typing the digits with their right hands) that involved different perceptual, but the same motoric, processes as the standard task. At test, for each of the three tasks, half the trials were trained numbers (old) and half were new. Repetition priming (faster response times to old than new numbers) was found for each task, with extended delays only slightly decreasing the magnitude of the effect. Repetition priming for the standard task reflects retention of trained numbers, for the left-hand variant reflects transfer of perceptual processes, and for the code variant reflects transfer of motoric processes. There was, thus, evidence for both specificity and generalizability of training data entry perceptual and motoric processes even over very long retention intervals.

transfer↗
NASA NTRS1976

Study of a very low cost air combat maneuvering trainer aircraft

A very low cost aircraft for performing Air Combat Maneuvering (ACM) training was studied using the BD-5J sport plane as a point of departure. The installation of a larger engine and increased fuel capacity were required to meet the performance and mission objectives. Reduced wing area increased the simulation of the ACM engagement, and a comparison with current tactical aircraft is presented. Other factors affecting the training transfer are considered analytically, but a flight evaluation is recommended to determine the concept utility.

Hill, G. C.↗
NASA NTRSDate not supplied

Developing a Motion-Based System for Lunar Vehicle Handling Qualities Testing

— Motion and visual cue influences are critical in any simulator system, as they impact multiple aspects of the human’s neurovestibular and visual systems. Cues of real motion proceeds to the brain before cues of visual change. It is important therefore for simulator motion cues to exist and to match those realistically with those of the real vehicle to provide transferable training of the activity for operations. The United Kingdom’s Royal Air Force Institute of Aviation Medicine (1989)[1] stated that motion platforms are the only simulation devices capable of fully stimulating the body motion sensors. They confirmed that motion platforms can impart accelerations to the whole body and therefore exercise the automatic motion feedback-loop that operators are used to. With both visual and motion cues handling the vehicle becomes more realistic. Strachan (2019)[1] confirms motion cueing from a well set-up motion platform has been found to be important especially in conditions such as night or reduced visibility where motion cues may be more relied upon. As of this writing, the only lunar rover motion simulator is housed at the General Motors (GM) Milford Proving Ground, which only simulates the motions of a traditional car. A NASA Test Team proposed to complete a motion-based simulation system for NASA’s Lunar Terrain Vehicle (LTV) which resides at Johnson Space Center’s Systems Engineering Simulator facility. This activity integrated existing fixed base simulation capabilities with a newly procured six-degree of freedom motion base platform for the design, development, evaluation, and training associated with the LTV project. This would incorporate a South Pole Lunar virtual reality simulation using Lunar Reconnaissance Orbiter 5m/pixel high-resolution imagery and Unreal 5.2 Virtual Shadow Maps, combined with a virtual reality (VR) headset, integrated within a rover cockpit on a Mikrolar Motion Platform for evaluating human performance and vehicle handling qualities for concept roving vehicle designs. The motion-based system received its Human Rating Certification on March 2023. To begin testing the new facility, a preliminary handling qualities study was conducted. The objectives were to determine if there is a correlation amongst three handling quality methods of performance for a lunar vehicle and to understand the effects of a simulated 1/6-g loads and visuals with a motion platform on the operator while in a 1-g physical environment. The capability this system provides directly benefits the NASA’s Extravehicular Activity and Human Surface Mobility Program and NASA’s Flight Operations Directorate in evaluating the driving qualities of vehicle concepts, human performance related to the operating of a lunar surface vehicle, and assessment of suit related driving impacts. It would also provide direct operational benefit by providing a first-in class and unique simulation platform for the lunar astronaut training curriculum. The empirical knowledge of rover and human performance on this scale is paramount as there is currently no other lunar surface simulator with these capabilities. The result of this study ensures a broadly applicable method of testing for shirtsleeve, unpressurized and pressurized suited rover handling qualities.

Test Track↗
NASA NTRS2017

Training, Retention, and Transfer of Data Entry Perceptual and Motoric Processes Over Long Retention Intervals

Subjects trained in a standard data entry task, which involved typing numbers (e.g., 5421) using their right hands. At test (6 months post-training), subjects completed the standard task, followed by a left-hand variant (typing with their left hands) that involved the same perceptual, but different motoric, processes as the standard task. At a second test (8 months post-training), subjects completed the standard task, followed by a code variant (translating letters into digits, then typing the digits with their right hands) that involved different perceptual, but the same motoric, processes as the standard task. For each of the three tasks, half the trials were trained numbers (old) and half were new. Repetition priming (faster response times to old than new numbers) was found for each task. Repetition priming for the standard task reflects retention of trained numbers; for the left-hand variant reflects transfer of perceptual processes; and for the code variant reflects transfer of motoric processes. There was thus evidence for both specificity and generalizability of training data entry perceptual and motoric processes over very long retention intervals.

dat↗
NASA NTRS2020

Effects of Long-Duration Space Flight on Training Retention and Transfer

The space environment imposes on the astronaut crew significant physiological, psycho-social, and cognitive loads that can not be replicated on the ground. These loads likely impact crew performance. To date, no systematic data collection has taken place to understand the effects of such loads on crew members’ ability to retain trained knowledge and skills, and to transfer such knowledge and skills to novel situations. The research described here was originally requested by HRP management to be the first such study to systematically collect data on the effects of long duration space flight on training retention and transfer. Because current theories of retention and transfer are based on results obtained in university laboratories using undergraduate students as research participants, and because crew time in space is very expensive, this study was designed to compare the performance of 4 groups of subjects: crew members in space, crew members on the ground, crew-like subjects, and university undergraduate students. Results from the ground-phase of the study reported here demonstrate that crew members’ performance under cognitive load can not be predicted from the performance of university undergraduate students. It is still an open question the extent to which crew members’ cognitive performance in space can be predicted from the performance of crew members on the ground.

training↗
NASA NTRS2015

Effects of False Tilt Cues on the Training of Manual Roll Control Skills

This paper describes a transfer-of-training study performed in the NASA Ames Vertica lMotion Simulator. The purpose of the study was to investigate the effect of false tilt cues on training and transfer of training of manual roll control skills. Of specific interest were the skills needed to control unstable roll dynamics of a mid-size transport aircraft close to the stall point. Nineteen general aviation pilots trained on a roll control task with one of three motion conditions: no motion, roll motion only, or reduced coordinated roll motion. All pilots transferred to full coordinated roll motion in the transfer session. A novel multimodal pilot model identification technique was successfully applied to characterize how pilots' use of visual and motion cues changed over the course of training and after transfer. Pilots who trained with uncoordinated roll motion had significantly higher performance during training and after transfer, even though they experienced the false tilt cues. Furthermore, pilot control behavior significantly changed during the two sessions, as indicated by increasing visual and motion gains, and decreasing lead time constants. Pilots training without motion showed higher learning rates after transfer to the full coordinated roll motion case.

simulators↗
NASA NTRS2020

Effects of Long-Duration Space Flight on Training Retention and Transfer

The space environment imposes on the astronaut crew significant physiological, psycho-social, and cognitive loads that can not be replicated on the ground. These loads likely impact crew performance. To date, no systematic data collection has taken place to understand the effects of such loads on crew members ability to retain trained knowledge and skills, and to transfer such knowledge and skills to novel situations. The research described here was originally requested by HRP management to be the first such study to systematically collect data on the effects of long duration space flight on training retention and transfer. Because current theories of retention and transfer are based on results obtained in university laboratories using undergraduate students as research participants, and because crew time in space is very expensive, this study was designed to compare the performance of 4 groups of subjects: crew members in space, crew members on the ground, crew-like subjects, and university undergraduate students. Results from the ground-phase of the study reported here demonstrate that crew members performance under cognitive load can not be predicted from the performance of university undergraduate students. It is still an open question the extent to which crew members cognitive performance in space can be predicted from the performance of crew members on the ground.

Barshi, Immanuel↗
NASA NTRS2013

Investigation of Control Inceptor Dynamics and Effect on Human Subject Performance

The control inceptor used in a vehicle simulation is an important part of adequately representing the dynamics of the vehicle. The inceptor characteristics are typically based on a second order spring mass damper system with damping, force gradient, breakout force, and natural frequency parameters. Changing these parameters can have a great effect on pilot control of the vehicle. A quasi transfer of training experiment was performed employing a high fidelity and a low fidelity control inceptor. A disturbance compensatory task was employed which involved a simple horizon line disturbed in roll by a sum of sinusoids presented in an out-the-window display. Vehicle dynamics were modeled as 1/s and 1/s2. The task was to maintain level flight. Twenty subjects were divided between the high and the low fidelity training groups. Each group was trained to a performance asymptote, and then transferred to the high fidelity simulation. RMS tracking error, a PSD analysis, and a workload analysis were performed to quantify the transfer of training effect. Quantitative results of the experiments show that there is no significant difference between the high and low fidelity training groups for 1/s plant dynamics. For 1/s2 plant dynamics there is a greater difference in tracking performance and PSD; and the subjects are less correlated with the input disturbance function

Stanco, Anthony A.↗
NASA NTRS1994

Vertical flight training: An overview of training and flight simulator technology with emphasis on rotary-wing requirements

The principal purpose of this publication is to provide a broad overview of the technology that is relevant to the design of aviation training systems and of the techniques applicable to the development, use, and evaluation of those systems. The issues addressed in our 11 chapters are, for the most part, those that would be expected to surface in any informed discussion of the major characterizing elements of aviation training systems. Indeed, many of the same facets of vertical-flight training discussed were recognized and, to some extent, dealt with at the 1991 NASA/FAA Helicopter Simulator Workshop. These generic topics are essential to a sound understanding of training and training systems, and they quite properly form the basis of any attempt to systematize the development and evaluation of more effective, more efficient, more productive, and more economical approaches to aircrew training. Individual chapters address the following topics: an overview of the vertical flight industry: the source of training requirements; training and training schools: meeting current requirements; training systems design and development; transfer of training and cost-effectiveness; the military quest for flight training effectiveness; alternative training systems; training device manufacturing; simulator aero model implementation; simulation validation in the frequency domain; cockpit motion in helicopter simulation; and visual space perception in flight simulators.

Alderete, Thomas S.↗
DOE OSTI2022

Pre-trained network-based transfer learning: A small-sample machine learning approach to nuclear power plant classification problem

Some research topics belonging to classification problems in the nuclear industry, such as fault diagnosis and accident identification, can be solved by feature extraction and subsequent application of statistical machine learning classifiers. Recently, deep neural network-based methods with automatic feature extraction and high accuracy have gained wide attention. They usually require large-scale training data, however, plant fault or accident data are scarce or difficult to obtain. Here this paper proposes a convolutional network (CNN)-based transfer learning method to solve this problem. The network's shallow layer is derived from a pre-trained CNN based on the ImageNet database to automatically extract features, and the deep layer is customized to match the classification problem. Data in non-image formats are converted to image formats and subsequently used to train the network. Case studies of rotating machines fault diagnosis show that the proposed method requires only limited training data to achieve high accuracy.

22 GENERAL STUDIES OF NUCLEAR REACTORS↗
NASA NTRS2017

Scenario Development Process at the Vertical Motion Simulator

There has been a significant effort within the simulation community to standardize many aspects of flight simulation. More recently, an effort has begun to develop a formal scenario definition language for aviation. A working group within the AIAA Modeling and Simulation Technical Committee has been created to develop a standard aviation scenario definition language, though much of the initial effort has been tailored to training simulators. Research and development (R&D) simulators, like the Vertical Motion Simulator (VMS), and training simulators have different missions and thus have different scenario requirements. The purpose of this paper is to highlight some of the unique tasks and scenario elements used at the VMS so they may be captured by scenario standardization efforts. The VMS most often performs handling qualities studies and transfer of training studies. Three representative handling qualities simulation studies and two transfer of training simulation studies are described in this paper. Unique scenario elements discussed in this paper included special out-the-window (OTW) targets and environmental conditions, motion system parameters, active inceptor parameters, and configurable vehicle math model parameters.

Vertical Motion Simulator↗
DOE OSTI2025

Anomaly Detection in Seismic Data with Deep Learning: Application for Instrument Failure Detection and Forecasting

Seismic data quality assessment (QA) is the first and one of the most important steps before conducting any further data analysis. Traditional methods involve checking various metrics, such as spike detection and power spectral density, by setting strict thresholds or comparing data against synthetic benchmarks. However, these approaches often rely on pre-existing knowledge and assumptions about data anomalies, leading to potential misclassification of unusual cases. Here, in this study, we propose a deep autoencoder model, an unsupervised learning approach that evaluates data quality without making assumptions about normal and anomalous data, which can be used to identify deviations in recorded data that may indicate nascent instrument failure. We test the model with the U.S. International Monitoring System (IMS) seismic stations and demonstrate the capability of detecting anomalies on a monthly scale. This could prompt station operators to examine potential problems early, allowing sufficient time for instrument maintenance to prevent data outages. In addition, we use a new manually selected testing dataset to compare our model performance against two supervised machine learning (ML) approaches and a standard QA package, as baseline models. When applied to the dataset containing known data anomalies, performance of the supervised and unsupervised ML approaches is similar, with an accuracy of 88.1% for our model compared to ∼90% for the supervised ML approach and 78.2% for the standard QA package. Our model outperforms the baseline models when applied to new stations, where new types of data anomalies can be station-specific and not included in the training dataset. Finally, we show model transferability by training the model with data from the Global Seismograph Network only and applying it to the IMS network data. The results suggest that our model is generalizable and can be applied to new stations with good accuracy.

Lin, Jiun-Ting [Lawrence Livermore National Labora↗
DOE OSTI2021

An adaptive adversarial domain adaptation approach for corn yield prediction

Recently, statistical machine learning and deep learning methods have been widely explored for corn yield prediction. Though successful, machine learning models generated within a specific spatial domain often lose their validity when directly applied to new regions. To address this issue, we designed an unsupervised adaptive domain adversarial neural network (ADANN). Specifically, through domain adversarial training, the ADANN model reduced the impact of domain shift by projecting data from different domains into the same subspace. Also, the ADANN model was designed to be trained in an adaptive way, which guaranteed the model can learn the domain-invariant features and perform accurate yield prediction simultaneously. Informative variables including time-series vegetation indices and sequential weather observations were first collected from multiple data sources and aggregated to the county level. Then, we trained the ADANN model with the extracted features and corresponding reported county-level corn yield from the U.S. Department of Agriculture (USDA). Finally, the trained model was evaluated in four testing years 2016–2019. The U.S. corn belt was used as the study area and counties under study were grouped into two diverse ecological regions. Overall, the experimental results showed that the developed ADANN model had better performance than three other state-of-the-art machine learning models in both local experiments (train and test in the same region) and transfer experiments (train and test in different regions). As the first study using adversarial learning for crop yield prediction, this research demonstrates a novel solution for improving model transferability on crop yield prediction.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2020

Automatic Classification of Biological Targets in a Tidal Channel Using a Multibeam Sonar

Multibeam sonars are widely used for environmental monitoring of fauna at marine renewable energy sites. However, they can rapidly accrue vast volumes of data, which poses a challenge for data processing. Here, using data from a deployment in a tidal channel with peak currents of 1–2 m s –1 , we demonstrate the data-reduction benefits of real-time automatic classification of targets detected and tracked in multibeam sonar data. First, we evaluate classification capabilities for three machine learning algorithms: random forests, support vector machines, and k-nearest neighbors. For each algorithm, a hill-climbing search optimizes a set of hand-engineered attributes that describe tracked targets. Here, the random forest algorithm is found to be most effective—in postprocessing, discriminating between biological and nonbiological targets with a recall rate of 0.97 and a precision of 0.60. In addition, 89% of biological targets are correctly classified as either seals, diving birds, fish schools, or small targets. Model dependence on the volume of training data is evaluated. Second, a real-time implementation of the model is shown to distinguish between biological targets and nonbiological targets with nearly the same performance as in postprocessing. From this, we make general recommendations for implementing real-time classification of biological targets in multibeam sonar data and the transferability of trained models.

16 TIDAL AND WAVE POWER↗
DOE OSTI2022

Fed-DeepONet: Stochastic Gradient-Based Federated Training of Deep Operator Networks

The Deep Operator Network (DeepONet) framework is a different class of neural network architecture that one trains to learn nonlinear operators, i.e., mappings between infinite-dimensional spaces. Traditionally, DeepONets are trained using a centralized strategy that requires transferring the training data to a centralized location. Such a strategy, however, limits our ability to secure data privacy or use high-performance distributed/parallel computing platforms. To alleviate such limitations, in this paper, we study the federated training of DeepONets for the first time. That is, we develop a framework, which we refer to as Fed-DeepONet, that allows multiple clients to train DeepONets collaboratively under the coordination of a centralized server. To achieve Fed-DeepONets, we propose an efficient stochastic gradient-based algorithm that enables the distributed optimization of the DeepONet parameters by averaging first-order estimates of the DeepONet loss gradient. Then, to accelerate the training convergence of Fed-DeepONets, we propose a moment-enhanced (i.e., adaptive) stochastic gradient-based strategy. Finally, we verify the performance of Fed-DeepONet by learning, for different configurations of the number of clients and fractions of available clients, (i) the solution operator of a gravity pendulum and (ii) the dynamic response of a parametric library of pendulums.

Moya, Christian↗
NASA NTRS2010

Gait Training Improves Performance in Healthy Adults Exposed to Novel Discordant Conditions

After they return to Earth, astronauts experience sensorimotor disturbances that disrupt their ability to walk. We have previously shown that training with a variety of sensorimotor adaptive challenges enhances the capability of adapting to novel sensorimotor conditions. We are currently developing a sensorimotor adaptability (SA) training program designed to facilitate recovery of function after gravitational transitions. The purpose of this study was to determine whether trained subjects could transfer learned skills from one discordant visuo-proprioceptive environment to another. During three sessions, subjects walked at 2.5 km/h on a treadmill mounted on a motion base platform. Ten subjects trained with a combination of lateral treadmill translation and superimposed sinusoidal lateral optic flow that was presented on a large screen positioned in front of them. Ten controls completed the same training schedule while viewing only the forward optic flow with no visual or physical oscillation. Twenty minutes after the final training session, all subjects completed a 2-minute trial with a novel combination of visual and treadmill roll perturbations not previously experienced during the training (Transfer Test). Compared to the untrained group, participants who received SA training showed faster reaction times and, based on a composite score derived from stride frequency, heart rate, and reaction time, an overall enhanced performance. Our results showed that an SA training program can improve overall walking performance when subjects are exposed to novel incongruent sensory environments. This training has application for both enhancing adaptive responses in astronauts and reducing fall and injury risk in the elderly.

Batson, Crystal D.↗