Engineering PapersSearch

SEARCH · Engineering Papers

Results for “data augmentation”

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

Improving Sim-to-Real Transfer in Vision-Based Robot Navigation Via Instance-Level GAN-Based Data Augmentation

Achieving robust vision-based robotic tasks requires large amounts of data, which are often difficult to obtain in real-world scenarios. Simulators and synthetic data offer a cost-effective alternative, but the visual gap between simulation and reality hinders the performance of models when deployed in real-world environments. In this paper, we present a data augmentation pipeline that integrates a foundation model (Segment Anything Model) with an unsupervised image-to-image translation model (CycleGAN) for instance-level domain transfer from simulation to reality. This pipeline enables the generation of realistic labeled data from synthetic images for training supervised machine learning models in vision-based navigation tasks. We evaluate our approach on real-world data for ego-vehicle pose estimation, a critical autonomous navigation task involving the prediction of cross-track position and heading angle relative to road center line markings. The results of our tests show that our GAN-based data augmentation pipeline significantly outperforms models trained solely on simulation data or on data processed with standard image augmentation methods for sim-to-real transfer, enhancing model robustness and generalizability in real-world scenarios. Our method provides a scalable and flexible data augmentation tool for leveraging large synthetic datasets to enhance vision-based robotic navigation tasks.

artificial intelligence

Data Augmentation for Intelligent Contingency Management Using Generative Adversarial Neural Networks

Artificial intelligence (AI)-based techniques for intelligent contingency management (ICM) require that intelligent agents learn various aspects of system dynamics to create and execute contingencies. For high assurance contingency management, agents achieve the most compelling results through supervised or semi-supervised machine learning, for which agents require large datasets to learn the dynamics of the system. Unfortunately, data collection in aerospace applications can be costly, due to both time and resources. Presented work describes a framework for data augmentation of ICM databases containing training data for machine learning models. This framework populates the database with the outputs of generative adversarial network (GAN) models that were trained on flight data. Methods for evaluating the suitability of these models based on the equations of motion, as well as other physical constraints, are discussed. The paper demonstrates the utility of this database for training intelligent agents on the NASA T2 generic transport aircraft model and experimental vertical takeoff and landing (VTOL) simulation model.

Generative Machine Learning

Data Augmentation for Intelligent Contingency Management Using Generative Adversarial Neural Networks

Artificial intelligence (AI)-based techniques for intelligent contingency management (ICM) require that intelligent agents learn various aspects of system dynamics to create and execute contingencies. For high assurance contingency management, agents achieve the most compelling results through supervised or semi-supervised machine learning, for which agents require large datasets to learn the dynamics of the system. Unfortunately, data collection in aerospace applications can be costly, due to both time and resources. Presented work describes a framework for data augmentation of ICM databases containing training data for machine learning models. This framework populates the database with the outputs of generative adversarial network (GAN) models that were trained on flight data. Methods for evaluating the suitability of these models based on the equations of motion, as well as other physical constraints, are discussed. The paper demonstrates the utility of this database for training intelligent agents on the NASA T2 generic transport aircraft model and experimental vertical takeoff and landing (VTOL) simulation model.

Generative Machine Learning

Automatic Speech Recognition for Launch Control Center Communication Using Recurrent Neural Networks with Data Augmentation and Custom Language Model

Transcribing voice communications in NASA’s launch control center is important for information utilization. However, automatic speech recognition in this environment is particularly challenging due to the lack of training data, unfamiliar words in acronyms, multiple different speakers and accents, and conversational characteristics of speaking. We used bidirectional deep recurrent neural networks to train and test speech recognition performance. We showed that data augmentation and custom language models can improve speech recognition accuracy. Transcribing communications from the launch control center will help the machine analyze information and accelerate knowledge generation.

Chow, Edward

Mining Twitter Data to Augment NASA GPM Validation

The Twitter data stream is an important new source of real-time and historical global information for potentially augmenting the validation program of NASA's Global Precipitation Measurement (GPM) mission. There have been other similar uses of Twitter, though mostly related to natural hazards monitoring and management. The validation of satellite precipitation estimates is challenging, because many regions lack data or access to data, especially outside of the U.S. and in remote and developing areas. The time-varying set of "precipitation" tweets can be thought of as an organic network of rain gauges, potentially providing a widespread view of precipitation occurrence. Twitter provides a large source of crowd for crowdsourcing. During a 24-hour period in the middle of the snow storm this past March in the U.S. Northeast, we collected more than 13,000 relevant precipitation tweets with exact geolocation. The overall objective of our project is to determine the extent to which processed tweets can provide additional information that improves the validation of GPM data. Though our current effort focuses on tweets and precipitation, our approach is general and applicable to other social media and other geophysical measurements. Specifically, we have developed an operational infrastructure for processing tweets, in a format suitable for analysis with GPM data; engaged with potential participants, both passive and active, to "enrich" the Twitter stream; and inter-compared "precipitation" tweet data, ground station data, and GPM retrievals. In this presentation, we detail the technical capabilities of our tweet processing infrastructure, including data abstraction, feature extraction, search engine, context-awareness, real-time processing, and high volume (big) data processing; various means for "enriching" the Twitter stream; and results of inter-comparisons. Our project should bring a new kind of visibility to Twitter and engender a new kind of appreciation of the value of Twitter by the science research communities.

validatio

Augmented Reality Data Generation for Training Deep Learning Neural Network

One of the major challenges in deep learning is retrieving sufficiently large labeled training datasets, which can become expensive and time consuming to collect. A unique approach to training segmentation is to use Deep Neural Network (DNN) models with a minimal amount of initial labeled training samples. The procedure involves creating synthetic data and using image registration to calculate affine transformations to apply to the synthetic data. The method takes a small dataset and generates a highquality augmented reality synthetic dataset with strong variance while maintaining consistency with real cases. Results illustrate segmentation improvements in various target features and increased average target confidence.

Torres, Gil

Navigation for space shuttle approach and landing using an inertial navigation system augmented by data from a precision ranging system or a microwave scan beam landing guidance system

A preliminary study has been made of the navigation performance which might be achieved for the high cross-range space shuttle orbiter during final approach and landing by using an optimally augmented inertial navigation system. Computed navigation accuracies are presented for an on-board inertial navigation system augmented (by means of an optimal filter algorithm) with data from two different ground navigation aids; a precision ranging system and a microwave scanning beam landing guidance system. These results show that augmentation with either type of ground navigation aid is capable of providing a navigation performance at touchdown which should be adequate for the space shuttle. In addition, adequate navigation performance for space shuttle landing is obtainable from the precision ranging system even with a complete dropout of precision range measurements as much as 100 seconds before touchdown.

Mcgee, L. A.

Imbalanced Multi-layer Cloud Classification with Advanced Baseline Imager (ABI) and CloudSat/CALIPSO Data

Clouds at different altitudes play different roles in Earth’s climate. Comprehensive understanding of overlapping clouds is important for climate and weather prediction. The East Pacific region is where El Ni˜no and La Ni˜na originate and where multi-layer clouds frequently occur. The overlap of clouds at different altitudes in this region increases the classification complexity for cloud-based climatological studies. Unlike prior work in cloud layer classification that assumes single layer or two-layer of clouds, in this work, we consider multi-layer cloud classification with 8 cloud-level classes (clear-sky, high, middle, low, high+middle, high+low, middle+low, high+middle+low). We develop and analyze machine learning models on features extracted from satellite images from the East Pacific regions collected by GOES Advanced Baseline Imager (ABI). These are used to classify CloudSat/CALIPSO observed multi-layer clouds. Due to the imbalanced nature of the data, we investigate the adoption of conventional resampling methods, as well as deep learning methods with data augmentation. In our experiments, we utilize the random forest classifier and Multilayer perceptron classifier with data augmentation methods to reduce the class imbalance during training. With these approaches, we achieve a classification accuracy of 83.6% without exploiting any ancillary information.

machine learning

Ground-Based VIS/NIR Reflectance Spectra of 25143 Itokawa: What Hayabusa will See and How Ground-Based Data can Augment Analyses

Planning for the arrival of the Hayabusa spacecraft at asteroid 25143 Itokawa includes consideration of the expected spectral information to be obtained using the AMICA and NIRS instruments. The rotationally-resolved spatial coverage the asteroid we have obtained with ground-based telescopic spectrophotometry in the visible and near-infrared can be utilized here to address expected spacecraft data. We use spectrophotometry to simulate the types of data that Hayabusa will receive with the NIRS and AMICA instruments, and will demonstrate them here. The NIRS will cover a wavelength range from 0.85 m, and have a dispersion per element of 250 Angstroms. Thus, we are limited in coverage of the 1.0 micrometer and 2.0 micrometer mafic silicate absorption features. The ground-based reflectance spectra of Itokawa show a large component of olivine in its surface material, and the 2.0 micrometer feature is shallow. Determining the olivine to pyroxene abundance ratio is critically dependent on the attributes of the 1.0- and 2.0 micrometer features. With a cut-off near 2,1 micrometer the longer edge of the 2.0- feature will not be obtained by NIRS. Reflectance spectra obtained using ground-based telescopes can be used to determine the regional composition around space-based spectral observations, and possibly augment the longer wavelength spectral attributes. Similarly, the shorter wavelength end of the 1.0 micrometer absorption feature will be partially lost to the NIRS. The AMICA filters mimic the ECAS filters, and have wavelength coverage overlapping with the NIRS spectral range. We demonstrate how merging photometry from AMICA will extend the spectral coverage of the NIRS. Lessons learned from earlier spacecraft to asteroids should be considered.

Vilas, Faith

Automated Pneumothorax Diagnosis using Deep Neural Networks

Thoracic ultrasound can provide information leading to rapid diagnosis of pneumothorax with improved accuracy over the standard physical examination and with higher sensitivity than anteroposterior chest radiography. However, the clinical We have Furthermore, remote environments, such as the battlefield or deep-space exploration, may lack expertise for diagnosing developed an automated image interpretation pipeline for the analysis of thoracic ultrasound data and the classification of pneumothorax events to provide decision support in such situations. Our pipeline consists of image preprocessing, data augmentation, and deep learning architectures for medical diagnosis. In this work, we demonstrate that robust, accurate interpretation of chest images and video can be achieved using deep neural networks. A number of novel image processing techniques were employed to achieve this result. Affine transformations were applied for data augmentation. Hyperparameters were optimized for learning rate, dropout regularization, batch size, and epoch iteration by a sequential model-based Bayesian approach. In addition, we utilized pretrained architecturesinterpretation of a patient medical image is highly operator dependent. certain pathologies., applying transfer learning and fine-tuning techniques to fully connected layers. Our pipeline yielded binary classification validation accuracies of 98.3% for M-mode images and 99.8% with B-mode video frames.

US Army collaboration

The interannual variability of polar cap recessions as a measure of Martian climate and weather: Using Earth-based data to augment the time line for the Mars observer mapping mission

The recessions of the polar ice caps are the most visible and most studied indication of seasonal change on Mars. Circumstantial evidence links these recessions to the seasonal cycles of CO2, water, and dust. The possible advent of a planet encircling storm during the Mars Observer (MO) mission will provide a detailed correlation with a cap recession for that one Martian year. That cap recession will then be compared with other storm and nonstorm years. MO data will also provide a stronger link between cap recessions and the water and CO2 cycles. Cap recession variability might also be used to determine the variability of these cycles. After nearly a century of valiant attempts at measuring polar cap recessions, including Mariner 9 and Viking data, MO will provide the first comprehensive dataset. In contrast to MO, the older data are much less detailed and precise and could be forgotten, except that it will still be the only information on interannual variability. By obtaining simultaneous Earth-based observations (including those from Hubble) during the MO mission, direct comparisons can be made between the datasets.

Martin, L. J.

Digital registration of topographic data and satellite MSS data for augmented spectral analysis

Results are presented for a project directed to assess the type and extent of long-term natural and man-made changes in floodplain features of a definite area in the Mississipi River Valley. 1:6000 scale maps were prepared from remotely sensed film/filter photographic coverage of the area at different times to compare changes in such features as channels, backwaters, vegetation as well as changes in the amount, location, and conditions of dredge spoil. Changes observed by this sequential photo comparison include abandonment of agricultural land followed by orderly secondary plant succession, the filling-in of shallows by sediment and the orderly succession of plants from a hydric to a more mesic environment and changes in deltas of small tributary streams in response to agricultural practices occurring at their headwaters. Plant colonization is observed on some spoil, and secondary movement of spoil is revealed in other areas.

Anuta, P. E.

Integration of Optical Coherence Tomography Scan Patterns to Augment Clinical Data Suite

Vision changes identified in long duration spaceflight astronauts has led Space Medicine at NASA to adopt a more comprehensive clinical monitoring protocol. Optical Coherence Tomography (OCT) was recently implemented at NASA, including on board the International Space Station in 2013. NASA is collaborating with Heidelberg Engineering to increase the fidelity of the current OCT data set by integrating the traditional circumpapillary OCT image with radial and horizontal block images at the optic nerve head. The retinal nerve fiber layer was segmented by two experienced individuals. Intra-rater (N=4 subjects and 70 images) and inter-rater (N=4 subjects and 221 images) agreement was performed. The results of this analysis and the potential benefits will be presented.

Mason, S.

A 360-degree and -order model of Venus topography

This report presents the most recent spherical harmonic topography model of Venus developed at Jet Propulsion Laboratory. It was produced by a spherical harmonic analysis of the most complete set of Magellan altimetry data, augmented by Pioneer Venus and Venera data. The harmonic coefficients of the topography were computed to degree and order 360. Compared to previous topography models, this one has the highest correlation with the gravity field of Venus.

Rappaport, Nicole

A 360-Degree and -Order Model of Venus Topography

This report presents the most recent spherical harmonic topography model of Venus developed at Jet Propulsion Laboratory. It was produced by a spherical harmonic analysis of the most complete set of Magellan altimetry data, augmented by Pioneer Venus and Venera data. The harmonic coefficients of the topography were computed to degree and order 360. Compared to previous topography models, this one has the highest correlation with the gravity field of Venus.

Venus venus topgraphy harmonic analysis spherical

NASA Pilot-Engaged Expert Response Using IBM Watson Technology: Prototype Evaluation of Knowledge Retrieval System

NASA Langley Research Center and IBM have been investigating the use of IBM Watson technology in aerospace research and development. One application of Watson technology is the Pilot-Engaged Expert Response (PEER) use case. The PEER system is envisioned as an in-cockpit advisor that will act as a source of situationally-relevant information for pilots and other flight crew members to assist in decision making about real-time events and situations that arise in the course of aircraft operations. PEER will make available vast stores of knowledge and information quickly and directly, putting important informational resources where they are needed most. IBM has worked with NASA to develop an architecture and articulate a roadmap for the development of the PEER system. That vision is built around Watson Discovery Advisor (WDA) software solution, derived from IBM's Jeopardy!-winning automatic question answering system. PEER makes use of WDA's sophisticated question-answering capabilities as its core, adding important User Interface components and other customizations for the cockpit environment, including communication with flight systems and other external data sources. The development plan for PEER includes four development stages, with the current project constituting the first phase. In this project, a prototype instance of PEER was successfully adapted to the aviation domain, enabling users to ask questions about aviation topics and receive useful and accurate answers to these questions. Major tasks accomplished include the development of procedures for domain adaptation through automatic lexicon extraction from domain glossaries; generation of question-answer training data which was used to train the system; and assessment of the effectiveness of domain adaptation, which showed a dramatic improvement in the ability of the PEER system to answer domain-relevant questions. In addition, the vision for the PEER system was pushed forward by the articulation of a plan for the automatic enhancement of question-answering with contextual information. This initial phase focused on two main goals: 1) the targeted domain adaptation of the underlying WDA system to the aviation domain; and, 2) the design of the software systems needed to leverage flight-contextual data. Domain adaptation of the WDA system proceeds via three main activities: Domain data ingestion, lexical customization and model training. A textual corpus consisting of 1,147 individual documents with more than 7.5 million words of text was ingested into the system and this served as the basis of all further development. A domain lexicon of over 3,500 aviation-domain terms was semi-automatically generated from domain documents and used to train the system. In addition, a set of over 500 question-answer (QA) pairs relevant to the PEER use case was developed; these were used to train and assess the system. These important first steps established the basis for the PEER system. In addition, steps were taken towards the integration of the PEER system into the cockpit environment with the development of a functional design for the Contextual Data Augmentation (CDA) subsystem. This subsystem brings to bear contextual data to improve system responses. It has three main submodules: the Contextual Data Collection module, the Contextual Data Selection module, and the Contextual QA Augmentation module. These modules form a processing pipeline that addresses the problems associated with automatically integrating information from external resources into the knowledge-retrieval mechanism.

Machine learning