Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Keywords”

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 361 records · Page 20
All sourcesNASA NTRSDOE OSTI
NASA NTRSDate not supplied

Graph Convolutional Network-Strengthened Topic Modeling for Scientific Papers

Machine learning has been woven into statistics to modernize topic modeling over textual documents written in natural language, and scientific paper search and recommendation can consequently offer higher accuracy instead of counting on traditional keyword-based search. However, topic distribution of a paper resulted from existing topic modeling techniques only relies on the statistics of words contained in the paper itself. We argue that community users’ views of a paper may also provide insights at the time of recommendation. For example, if a paper on fake image detection has been cited heavily by machine learning papers, such a feature should be absorbed in the embedding of this paper, so that it can be recommended for future query on machine learning. In this paper, we present a Graph Convolutional Network-strengthened Topic Modeling (GCN-TM) method, which employs GCN technique to refine topic modeling of scientific papers. A citation-oriented knowledge graph is constructed, and topic modeling is mapped to feature embedding of the comprising papers. On top of its own topics carried in its content, each paper learns topics from its neighbors and revise its embedding accordingly. Our empirical studies over real-life scientific literature has proved the necessity and effectiveness of our proposed approach.

Jia Zhang↗
NASA NTRS2021

Dynamic fire and smoke detection and classification for flashover prediction

Flashover is a dangerous phenomenon caused by near-simultaneous ignition of exposed materials. It is one of the major causes of firefighter fatalities. Research has been done using CMOS vision cameras combined with thermal sensors to perform remote detection and dynamic classification of fire and smoke patterns. Tests and experiments have been done to detect fire and smoke remotely. The inexpensive visible and infrared sensors used in the tests corroborate and closely follow the detailed trends recorded by the more expensive (and less mobile) radiometers and thermocouples. Deep neural networks (DNN) have been used to detect, classify and track fire and smoke areas. Real-time segmentation is utilized to measure the fire and smoke boundaries. The segmentations are used to dynamically monitor fluctuations in temperature, fire size and smoke progression in the monitored areas. A fire and smoke progression curve has been drawn to predict the flashover point. In the paper, data analysis and preliminary results will be shown. Keywords: Flashover, fire, smoke, deep learning, visible and infrared vision

Chow, Edward↗
NASA NTRSDate not supplied

Constructing a Knowledge Graph & Applying Graph Algorithms to Draw Insights about GES-DISC Jira Tickets

In order to assess the complexities of Jira tickets created by NASA Goddard Earth Sciences Data and Information Services Center (GES-DISC), it was beneficial to create a knowledge graph. The knowledge graph receives ticket data through the Jira API. The creation of a knowledge graph will help to answer high-level questions about internal structure, knowledge gaps, and team organization within GES-DISC. To work towards this goal, the knowledge graph was constructed in adockerizedNeo4j graph database. Once the graph had been created, graph algorithms were applied to answer high-level questions, such as exploring the role of staff in relation to projects, which qualities of a ticket contribute to the formation of communities within the graph, etc. To answer these questions, centrality and community detection algorithms were applied using Cypher querying language. The analysis of the results of the algorithms indicated that, as expected, certain individuals were more connected to some projects, while others were serving as hub nodes between two or more projects. Similarly, specific keywords are more likely to increase a Jira ticket’s centrality in the graph. In terms of community detection, when tickets in a community have certain qualities, it is more probable for them to be grouped together. To best visualize which nodes had higher centrality scores or were grouped into certain communities, interactive graphs were created in Python using Plotly and Matplotlib. Ultimately, the project was successful in creating and deploying a knowledge graph to better understand the relationships between data in GES-DISC Jira tickets

Rebecca Lipton↗
NASA NTRSDate not supplied

Influence Network: Network visualization of influence between stories for Earth Science data and information exploration

Using storytelling to present data has been demonstrated as an effective way to help data users gain deeper insight of information. For this purpose, the “Data in Action” story concept has been adopted by NASA Commercial Smallsat Data Acquisition (CSDA) Program to encourage creating and sharing data information in story form. To aid researchers in exploring similar stories and data in their fields of interest, we created an “Influence Network” within the “Data in Action” framework. The Influence Network is a data visualization system component which gathers information of story relationships using a concept called “influence,” which we define based on the number of visits and keyword similarity between stories. The visualization then provides insights into the influence flows between different stories within the system. The visualization of this “Influence Network” focuses on one story at a time, introducing a time series of neighbor stories that have the most influence to the currently focused story. By focusing on views over time and visualizing influence flows between stories, we aim to assist authors in understanding how their readers perceive their stories as well as advancing their methods for delivering more meaningful stories to expand and lower the barrier to use of CSDA datasets.

Dan Pham↗
NASA NTRSDate not supplied

Parametric Analysis of the Charge-Hold-Vent Method for Cryogenic Propellant Tank Chill Down

Abstract. In the absence of external heat exchangers, the on-orbit transfer of cryogenic propellants requires the receiver tank to first be quenched to a sufficiently low energy state to allow for a continuous no-vent fill to avoid unnecessary venting of liquid. One proposed method for tank chilldown that minimizes the potential for venting liquid is the charge hold vent (CHV) method. CHV follows a cyclic process that gradually removes thermal energy from the receiver tank by injecting liquid with the vent valve closed and allowing the fluid and wall to reach near-thermal equilibrium before venting the superheated vapor. However, the CHV method must be optimized to minimize complexity, mass, and time. This paper presents a modular CHV analytical model used to quantify the number of cycles and propellant mass consumed based on first principles. The model is used to examine the effect of eight parameters: receiver tank material, volume, mass, maximum expected operating pressure, and initial pressure, liquid injection pressure and temperature, and the target temperature. The model is validated against the only two available CHV datasets. Based on results, the tank mass-to-volume ratio is the most important factor in determining the number of CHV cycles and thus degree of difficulty in tank chilldown. The model can easily be used for early-stage design, sizing, and analysis of cryogenic propellant transfer systems. Keywords: tank chilldown, charge-hold-vent, no-vent fill

Tank Chilldown↗
NASA NTRSDate not supplied

Utilizing Google Scholar as a Bibliographic Resource for Publications Search

This study focuses on the automated search for publication citations for the Earth Observing System Data and Information System (EOSDIS) datasets. The research investigates the feasibility of using automated search methods to gather published works from various bibliometric databases. A comparison is presented, highlighting the differences in citation counts obtained from Google Scholar compared to established bibliographic databases. The study also introduces a methodology and an open-source tool for getting publication citations from Google Scholar, utilizing dataset DOIs and keyword searches. The findings contribute to understanding the reliability and effectiveness of Google Scholar as a source for dataset citation retrieval and provide researchers with a valuable resource for obtaining comprehensive citation data.

Infometrics↗
NASA NTRSDate not supplied

Engineered Yeast to Test Risks for Human Exploration of the Lunar Surface

Jessica W. Chau, Natalie N. Ball, Aditya Hindupur, Sandra T. Vu, Jennifer Gil Acevedo, Lauren C. Liddell, Chinmayee Govinda Raj, Gentry, Sergio R. Santa Maria, A. Mark Settles Crewed exploration of the Moon carries risks of long duration exposure to reduced gravity and to deep space radiation. The Lunar Explorer Instrument for space biology Applications (LEIA) investigates the effects of increased radiation and reduced gravity on yeast viability and growth in a Commercial Lunar Payload Services (CLPS) surface mission to the south polar region. LEIA conducts yeast genetics experiments to quantify growth, metabolism, and synthetic biology-enabled production of human nutrients, while taking real time measurements of biologically relevant radiation exposure on the lunar surface. We have engineered beta-carotene producing yeast strains to test the importance of selected DNA damage repair and reactive oxygen species (ROS) defense pathways in mitigating cellular damage from lunar surface radiation. Carotenoids are important dietary antioxidants, and beta-carotene is pro-vitamin A, which is needed for vision and immune function. Carotenoids are sensitive to ROS produced by ionizing radiation and NASA is testing on-demand production of carotenoids from yeast in the BioNutrients space flight experiments. In LEIA, we test the effects of deep space on carotenoid yield in engineered yeast strains. The LEIA team uses CRISPR-Cas9 to engineer yeast to express carotenoids as well as to generate loss-of-function mutations. We are generating mutations in the RAD51 DNA damage repair locus and three genes that function to reduce oxidative damage to the cell: SOD1, SOD2, and TSA1. These strains are tested for carotenoid production using microfluidics and LED spectroscopy to allow remote sensing of cellular growth and carotenoid levels. Keywords: synthetic biology, oxidative stress tolerance, biosensors, space radiation, beyond low Earth orbit, lunar surface, CRISPR/Cas9, gene editing, desiccation, carotenoids.

synthetic biology↗
NASA NTRSDate not supplied

Open-source Numerical Modeling of Solidification Cracking Susceptibility: Application to Refractory Alloy Systems

Introduction. Alloys such as aluminum, nickel-base, and austenitic stainless steels are susceptible to solidification cracking during welding and 3D printing. Compositional optimization is one method used to effectively mitigate solidification cracking of those alloy systems. With the surge in hypersonic and in-space propulsion activities, refractory metals (Nb, Mo, Ta, W, and Re) and their alloy derivatives are increasing in importance due to their extreme high melting point and retention of high-temperature strength; however, their chemistry was most typically optimized to promote ductility during mechanical operations such as drawing and forming. Welding of such alloys has been a challenge due to a number of issues including solidification cracking, atmospheric contamination (O, C, and N), as well as a shift in ductile-to-brittle transition to higher temperature following grain growth induced by welding. Compositional optimization of refractory alloys for solidification cracking resistance in particular is desirable as their usage increases with the advent of advanced manufacturing methods such as 3D printing. This work evaluates the effect of compositional variation in refractory metal systems on the solidification cracking susceptibility with the goals of optimizing existing alloys and joining process techniques, and formulating new alloys with increased solidification cracking resistance. Experimental Procedures. A python code was developed in a Jupyter notebook environment (Michael and Sowards, 2023) to facilitate the calculation of crack susceptibility index proposed by Kou (2015). Composition is entered as a single point, or as a 1-D or 2-D array. The notebook calls pycalphad (Otis and Liu, 2017 and Bocklund et al, 2020) to calculate the evolution of fraction solid as a function of temperature (under either Scheil or equilibrium assumptions) and then evaluates steepness of the fraction solid curve near the terminal stage of solidification to predict solidification cracking resistance. Open source thermodynamic databases available at online repositories are used (van de Walle). The process is setup in an automated fashion to generate plots that show variation in solidification cracking susceptibility according to composition on 1-D line plots or 2-D contour plots. The Jupyter notebook and crack susceptibility algorithm was also integrated with a widely used commercial CALPHAD code for validation and alloy exploration. Results and Discussion. The crack susceptibility model was first validated against a series of refractory alloy compositions evaluated in past work which utilized a specialized Varestraint test built inside a vacuum chamber environment (Lessman and Gold, 1971). The alloys tested in the Varestraint apparatus included T-111 (Ta-8W-2Hf), ASTAR-811C (Ta-8W-1Re-0.7Hf-0.025C), FS-85 (Nb-27Ta-10W-1Zr), T-222 (Ta-9.6W-2.4Hf-0.01C), Ta-10W, B-66 (Nb-5Mo-5V-1Zr), and SCb-291 (Nb-10W-10Ta). The initial test of the model showed a strong correlation with empirical Varestraint data, i.e., a Spearman rank correlation between model predictions and hot cracking measurements was observed to be greater than 0.8. Following the validation, a set of refractory metal binary mixtures was investigated to evaluate sensitivity of Nb, Mo, W, and Ta to C, N, and O content. A series of plots were produced that suggest ppmw ranges of C, N, and O where solidification cracking increases significantly and reaches a maximum. Also comparative ranking of each primary refractory metal to each interstitial was produced. For example C produces greater cracking response in Mo whereas O produces greater cracking response in Ta and Nb. Such compositional values have utility in setting limits on pickup of these interstitial elements during welding and printing rather than using a one-size-fits-all approach. Furthermore, the results have use in determining additive powder recycling requirements, which is especially pertinent for refractory metal powders due to their high cost compared to conventional alloys. Another application created thousands of hypothetical alloys within the nominal specified composition range of two widely used refractory alloys C103 (Nb-10Hf-1Ti) and TZM (Mo-0.5Ti-0.1Zr). The cracking index was calculated for the alloys and results were fed into machine learning regression techniques including Multiple Linear Regression, Ridge Regression, and Lasso Regression to determine relative potency each alloying element had on computed solidification cracking index. A series of linear equations were produced that relate composition of C103 and TZM to solidification cracking index. The crack susceptibility of C103 for example is described by an equation of the form: cracking index ~ O + 0.667*C + 0.635*N + 0.00037*Ta – 0.0008*Hf (in wt.%) From that equation, it is clear that O has strong propensity to induce solidification cracking. Interestingly, Hf is shown to reduce calculated cracking response. Finally, realizing the potential of this method to discover new refractory alloy formulations across the period table that have low solidification cracking sensitivity, the code was applied to new untested alloy systems including W-Zr-C, W-Ta-C, and others. Conclusions. In summary, an open source numerical method has been developed using Python code to calculate Kou’s crack susceptibility index. The method was applied to refractory metals which are inherently difficult to study from a weldability testing standpoint since inert shielding gas is not sufficient and welding is typically done in vacuum, especially in light of findings presented here where oxygen has profound influence on solidification cracking. This work revealed the effect of compositional variations on a series of refractory metals and showed the framework defined here will be useful in 1) the development of new alloys that have improved weldability and 3D printability, 2) placing compositional limits on existing alloys, and 3) ensuring adequate controls of manufacturing processes such as 3D printing where powder reuse is critical. Keywords. pycalphad; Python; refractory metals; solidification cracking. References. B. Bocklund et. al. (2020) http://doi.org/10.5281/zenodo.3630657. S. Kou. (2015) https://doi.org/10.1016/j.actamat.2015.01.034. G.G. Lessmann and R.E. Gold. Welding Journal, issue 1, pp. 1-s – 8-s (1971). F.N. Michael and J.W. Sowards. NASA/TM-20230002218 (2023). R. Otis and Z.-K. Liu. (2017) http://doi.org/10.5334/jors.140. A. Van de Wallle et. al. (2018) https://doi.org/10.1016/j.calphad.2018.04.003.

pycalphad↗
NASA NTRSDate not supplied

Harnessing Artificial Intelligence for Medical Diagnosis and Treatment During Space Exploration Missions

BACKGROUND The medical capabilities necessary for long-duration exploration missions (LDEMs) will differ tremendously from those currently available to crew medical officers (CMOs) on the International Space Station (ISS). Ground support will be more challenging due to distance-related communication delays and data transmission, and resource utilization must be optimized given limited ability for resupply. Clinical decision support systems (CDSSs) can help mitigate these limitations. The recent launch of generative artificial intelligence (AI) tools based upon large language models (LLM) support the creation of a smart assistant for onboard triage, diagnosis, and guided treatment of medical conditions during these missions. The Informing Mission Planning via Analysis of Complex Tradespaces (IMPACT) tool can help predict which clinical problems and outcomes are likely to occur for a design reference mission (DRM) and assist Medical Operations and systems engineering teams in creating a medical system that may optimally mitigate the predicted risks. The purpose of this study was to identify AI tools currently available or in development for the assistive diagnosis and care of medical conditions predicted for an extended duration Lunar mission. METHODS The 119 medical conditions currently built into the IMPACT suite were categorized into systems, and these diagnoses were used as keywords for our literature search. Using PubMed and Google Scholar, we performed a literature survey of AI tools applicable to these conditions. Article inclusion criteria included publication between the years 2017-2023, as the sentinel paper discussing the “selective attention” driving ChatGPT and other generative transformer models was published in June 2017. Where applicable, we reviewed only the top 1000 research articles (based on relevance) for each of the keywords/phrases. AI tools whose training sets were exclusive to a pediatric patient population were excluded. We also excluded any medical diagnostic tools (such as CT, MRI, mass spectrometry) or procedures (such as endoscopy, surgery) that are unlikely to be available during LDEMs due to mass and volume constraints, CMO knowledge, skills, and abilities, and/or inherent procedural risks. RESULTS Our survey highlighted several AI-driven tools for the triage, diagnosis, and management of those medical conditions highlighted by IMPACT. Selected publications for each medical condition were then screened for inclusion within ten systems-based categories including: general diagnostic tools (25), tools to diagnose and manage respiratory (40), dermatologic (34), neurologic (28), auditory and vestibular (30), ophthalmic (34), musculoskeletal (104), infection-associated (92), and gynecologic (19) conditions, as well as tools that could be deployed in the setting of trauma and emergency (34). CONCLUSIONS Numerous AI-driven tools were highlighted within this literature survey, ranging from chatbot assistants that triage knee pain to vision transformer models for diagnosis of ophthalmic conditions using ocular surface images captured with a mobile phone. Remaining challenges include optimizing connectivity and integration of existing and developing systems into the vehicles or habitats. Notably, findings from this survey could help guide the initial design of an all-encompassing, onboard medical AI assistant for use during future LDEMs.

R A Lacinski↗
NASA NTRSDate not supplied

Method Development for Experimental Characterization of Dynamic Strength of Aluminum Structures

Space Flight Hardware (SFH) experiences intense vibratory loading during flight, which only lasts a few minutes. When determining the appropriate size of these components to withstand such loading without becoming damaged (plastically deforming or breaking), standard design practice is to assume that the peak dynamic loads are applied statically. In doing so, the resulting stress is compared against a material strength parameter obtained from a quasi-static experiment. Since the near-peak stresses are only experienced over a small fraction of time in reality, this approach leads to design conservatism that unnecessarily increases structural mass as well as the associated inefficiency and financial cost. In an effort to modernize engineering design standards to appropriately consider the higher practical strength of dynamically loaded structures, this overarching research project seeks to develop an experimental test procedure for quantifying the dynamic strength of metallic alloys as a function of excitation frequency. In the ideal case, the characterization test would include an in-situ method for monitoring the onset and progression of plastic deformation of the test specimen undergoing vibratory loading. These new tests are designed to be high intensity (forcing amplitude), short term (60 seconds at full amplitude), and cyclic in nature (sinusoidal excitation via attached stinger to an otherwise cantilevered beam). In addition, the initial metallic alloy under investigation is 6061 aluminum, due to its wide use and applicability for SFH. Thus far, the most promising monitoring method under development with live-capacity is to track hysteresis behavior of the beam from power dissipation trends, calculated via force (from transducer on excitation stinger) and velocity (measurements from Laser Doppler Vibrometer) data and work to distinguish between elastic and plastic features. As a key component of this ongoing method development, any pseudo-live indication of plasticity can be corroborated against the outcome of a pre-post assessment of damage via macroscopic evaluation of beam geometry (i.e. assessing any permanent change in the beam’s tip deflection). Support for experimental design decisions as well as dynamic strength data from tests with excitation frequencies of 10, 40, and 55 Hz will be discussed. This work contributes to the foundation for a new type of vibration-based characterization experiments and generates initial data on the functional strength of 6061 aluminum under the conditions considered. Keywords: vibrations, plastic deformation, aluminum

vibrations↗
NASA NTRSDate not supplied

A HIRF-Map Certification Approach for UAM, AAM, and UAS Vehicles

Advanced Air Mobility (AAM), Urban Air Mobility (UAM), and Unmanned Aerial Systems (UAS) vehicles will fly in airspace similar to Transport Category Rotorcraft, requiring them to meet stringent requirements for High-Intensity Radiated Fields (HIRF) certification. The environment is notably severe, particularly compared to fixed-wing aircraft, due to operations at lower altitudes. This potentially exposes the vehicles to high-power transmitters on the ground, leading to significant challenges. High-level HIRF exposure can result in avionic system upsets, interference, and undesirable effects. Shielding and circuit protection against HIRF pose significant barriers concerning size, weight, and cost, especially for emerging electric vertical take-off and landing (eVTOL) and electric short take-off and landing (eSTOL) vehicles. This paper proposes a novel HIRF protection approach, aiming to reduce costs by certifying vehicles to a "vehicle tolerance level" lower than that required for Transport Category Rotorcraft. The remaining protection is achieved by maintaining a safe distance from known HIRF sources. This distance is calculated based on the vehicle's tolerance level and transmitter characteristics, such as transmit power, antenna beamwidth, and direction. Tailored flight maps are developed to identify transmitters and avoidance zones within an operating area or along a flight path, enabling restricted vehicle operations. Vehicles with higher tolerance levels could have smaller HIRF avoidance zones, allowing them to operate closer to transmitters. Transmitter data are sourced from government databases, such as those of the Federal Communications Commission (FCC) and the National Oceanic and Atmospheric Administration (NOAA). A map tool is developed using Matlab to calculate and visualize HIRF avoidance zones based on available databases. The tool determines stand-off distances based on input vehicle tolerance levels, displaying results on various base maps depicting HIRF-restricted areas. Illustrations cover various FCC transmitters, including AM/FM/TV transmitters, satellite earth stations, and NOAA weather radars. The HIRF zones of smaller transmitters, such as land-mobile radios, pagers, microwave links, and cellular towers, are also illustrated. An example of flight planning around transmitters is provided. For now, airports and government-owned lands are excluded due to limited access to sensitive transmitter data. Despite this approach, a minimum HIRF tolerance level for vehicles may still be necessary to cover mobile devices, cellular base stations, transmitters on other AAM vehicles, and other small power devices not included in the FCC databases. The paper discusses findings and areas for improving existing databases and suggests an approach for better access to sanitized data in more restricted government databases. This method significantly deviates from the standard approach and introduces slightly higher flight-planning complexity. However, the potential cost savings are considerable. Future AAM/UAM/UAS aeronautical charts could potentially incorporate these new HIRF avoidance zones. Keywords—HIRF; Map; AAM; UAM; UAS; Advanced Air Mobility; Urban Air Mobility; Unmanned Aerial Systems; Certification.

HIRF↗
NASA NTRSDate not supplied

Discovering Research Areas in Dataset Applications Through Knowledge Graphs and Large Language Models

Scientific datasets are increasingly cited in peer-reviewed journal publications, facilitating easy access to research utilizing those datasets. Datasets undergo a life cycle where older versions of datasets are replaced by newer versions often due to improvements in data resolution, algorithms, and other factors. Unlike peer reviewed documents registered with a single Digital Unique Identifier (DOI), datasets can be updated over time and the newer version of the datasets are registered with a new DOI which is not necessarily linked to the previous version of the dataset. It is challenging when publications citing a dataset need to be traced over the entire life cycle of that dataset. We provide an innovative approach to link the dataset versions and publications using a knowledge graph (KG). KG can help to trace the dataset cited in publications over the entire dataset life cycle and shed light into dataset usage in various applied research areas. We fine-tuned the pretrained NASA IMPACTINDUS Large Language Model (LLM) on a set of labeled publications abstracts. Our results showed that 87% of the publications were classified into one of twenty applied research areas, while the remaining 13% were classified into non-applied research areas. By linking datasets to applied research areas through the KG and employing Global Change Master Directory(GCMD), a well-established controlled vocabulary of scientific keywords describing Earth science datasets, we contribute to a transparent and advanced search and discovery mechanism for datasets across the Earth data ecosystem. The integrated KG and LLM approach is now incorporated and operational in dataset publication management at one of NASA’s Earth science data archival centers.

data provenance↗
NASA NTRSDate not supplied

Artificial Intelligence (AI) Methods for Augmenting the IMPACT Tool Evidence Library

Development of the Evidence Library for use with the IMPACT probability risk assessment tool took several years and involved a staggering amount of effort from a multi-disciplinary team. A very significant amount of the labor effort to collect, assess and finalize the Clinical Finding Form (CliFF) for each of the 119 medical conditions was provided by physician subject matter experts from the Exploration Medical Capability (ExMC) Element Clinical and Science Team. Many AI tools such as ChatGPT are excellent at summarizing large amounts of information and the current project was initiated to determine how such tools might streamline laborious processes, e.g., review and summarization of many scientific research publications, to execute key steps more efficiently in the process of developing CliFFs. The process for collecting the evidence which is found in the CliFFs is well documented in the Evidence Library Methods document (ELM; HRP-48036*). Using ELM and the CliFF development instructions as a guideline, a team of developers is leveraging Microsoft Azure AI tools and services along with open-source frameworks, to construct an AI-assisted automated pipeline. This pipeline is designed to search, retrieve, and process the necessary data sources, and ultimately help generate the final version of a CliFF. Currently, the large language model evaluates the relevance of each source material to spaceflights, either as direct evidence or as an analog. Additionally, the model assists in extracting keywords and generating brief summaries to enhance augmented retrieval and search processes in later stages of CliFF development. Once the data is ready, the model can perform semantic search and retrieval, generating and extracting valuable information for the CliFF. For instance, it can handle epidemiological statistical data, such as incidence rates and the likelihood of best or worst-case scenarios. The steps that required reading and summarizing articles were viewed as providing the greatest return on investment since large language models are very efficient and accurate in summarizing large amounts of text. Since labor effort to complete the original CliFF was not recorded with sufficient granularity, comparisons with an AI tool-generated CliFF will provide merely an approximation of time saved. Upon completion of the process, the CliFF for the medical condition “appendicitis” generated with the support of AI-based methods will serve as a proof-of-concept and will be compared to the original appendicitis CliFF to determine if use of the tools resulted in content and conclusory similarity. Based upon the results from face validation of the two CliFFs, modifications to the process will be made if necessary and additional condition CliFFs will be evaluated. Ultimately, CliFFs for the entire set of medical conditions will be created with the assistance of AI tools. Depending on the cost savings realized, CliFFs for additional medical conditions can be created to expand the Evidence Library. Future direction includes specifying the characteristics of the reviewer (prompting the AI tools to generate output assuming the reviewer is a sub-specialist physician, or nurse or EMT/medic) to determine if the effects on AI-generated output are different based on knowledge, skills and abilities. *Exploration Medical Capability Evidence Library Methods, HRP-48036 Rev A, July 2022.

Ali Al↗
NASA NTRSDate not supplied

Artificial Intelligence (AI) Methods for Automating the Impact Tool Evidence Library

INTRODUCTION: The development of the Evidence Library for use with the IMPACT (Informing Mission Planning via Analysis of Complex Tradespaces) probability risk assessment tool involved a multilayered, time intensive process of data collection and analysis by subject matter experts from the Exploration Medical Capability (ExMC) Element Clinical and Science Team to produce clinical findings forms (CliFFs) for 120 medical conditions. Artificial Intelligence Large Language Models (LLMs) can be leveraged to facilitate this process, thus reducing labor and time. TOPIC: CliFFs contain information about medical conditions as they pertain to spaceflight. This includes condition definitions, incidence data, crew task impairment estimates caused by conditions, treatment protocols and references to literature used for gathering condition evidence. Guided by the Evidence Library Methods document and the CliFF development instructions, a team has leveraged Microsoft Azure AI services and open-source documentation to construct an AI-assisted automated pipeline for CliFF development. This process is designed to search, retrieve, and evaluate the applicable data, and ultimately generate a completed CliFF. The LLM evaluates the relevance of each of the source materials to spaceflight, either as direct evidence or as an analog. The model extracts keywords and generates brief summaries to enhance search and retrieval in later stages of CliFF development. For instance, it can calculate epidemiological statistical data, such as incidence rates and the likelihood of best or worst-case scenarios. APPLICATION: Large Language Models (LLMs) can efficiently summarize large amounts of text. Leveraging this technology will automate data retrieval and evidence gathering for medical databases, like the IMPACT tool, by aiding in the labor-intensive process of analyzing large bodies of literature and organizing it into a formatted document like a CliFF. This added efficiency will enable expeditious expansion of the Evidence Library with additional medical conditions and update previous CLiFFs as new technology becomes available.

Ali Al↗
NASA NTRS2002

Method for measuring centroid algorithm accuracy

This paper will describe such a method for measuring the accuracy of centroid algorithms using a relatively inexpensive setup consisting of a white light source, lenses, a CCD camea, an electro-strictive actuator, and a DAC (Digital-to-Analog Converter), and employing embedded PowerPC, VxWorks, and Solaris based software.

technical keywords↗