Search NASA⌕ Search

SEARCH · Search NASA

Results for “knowledge discovery”

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 199 records · Page 11

Ask-The-Expert: Minimizing Human Review for Big Data Analytics Through Active Learning

In this CIF project, we worked toward semi-automating knowledge discovery from anomaly detection algorithms through the use of active learning. Active learning is an area of research within machine learning that uses an "expert in the loop" to learn from large data sets that have very few annotations or labels available, and where providing such labels is expensive. In our case, the task can be defined as the identification of safety events from flight operational data. Since traditional anomaly detection algorithms cannot differentiate between operationally relevant and irrelevant statistical anomalies, Subject Matter Experts (SMEs) have a lengthy and expensive burden of investigating every example identified by the detection algorithm, classifying and labeling them as relevant or irrelevant. Active learningidentifies the unlabeled example for which a label would most improve the classifier, asks the domain expert for a label, and repeats this process until there are no more resources (time, budget) available for labeling or a minimum required performance is reached. A positive label indicates an operationally significant safety event whereas a negative label indicates otherwise. Based on these few labels we propose to build an active learning system that utilizes the SME's time in the most effective manner by iteratively asking for labels for as few informative instances as possible. Our work was proposed to be a stepping stone toward implementation and deployment of the system with user interface to be pursued by the Aviation Operations and Safety Program (AOSP) given its interest in safety monitoring and discovery of safety incidents.

aviation safety↗

GeoNEX: A Cloud Gateway for Near Real-time Processing of Geostationary Satellite Products

The emergence of a new generation of geostationary satellite sensors provides land andatmosphere monitoring capabilities similar to MODIS and VIIRS with far greater temporal resolution (5-15 minutes). However, processing such large volume, highly dynamic datasets requires computing capabilities that (1) better support data access and knowledge discovery for scientists; (2) provide resources to enable real-time processing for emergency response (wildfire, smoke, dust, etc.); and (3) provide reliable and scalable services for the broader user community. This paper presents an implementation of GeoNEX (Geostationary NASA-NOAA Earth Exchange) services that integrate scientific algorithms with Amazon Web Services (AWS) to provide near realtime monitoring (~5 minute latency) capability in a hybrid cloud-computing environment. It offers a user-friendly, manageable and extendable interface and benefits from the scalability provided by Amazon Web Services. Four use cases are presented to illustrate how to (1) search and access geostationary data; (2) configure computing infrastructure to enable near real-time processing; (3) disseminate and utilize research results, visualizations, and animations to concurrent users; and (4) use a Jupyter Notebook-like interface for data exploration and rapid prototyping. As an example of (3), the Wildfire Automated Biomass Burning Algorithm (WF_ABBA) was implemented on GOES-16 and -17 data to produce an active fire map every 5 minutes over the conterminous US. Details of the implementation strategies, architectures, and challenges of the use cases are discussed.

GeoNEX↗

NASA’s Human Data Repositories: An In Depth Look at the New Data Request Process

As NASA transitions its focus to travel back to the moon and on to new destinations, the need to ensure the capture, analysis, and application of research and medical data is of greater urgency than at any other previous time. In this era of limited resources and challenging schedules, the Human Research Program (HRP), based at NASA’s Johnson Space Center (JSC), recognizes the need to extract the greatest possible amount of information from the data already captured. To this end, the HRP Chief Scientist Office (CSO), HRP Program Planning and Control (PP&C) Office, and the Space Medicine Operations Division have been working together to make reuse of both research data and medical monitoring data more accessible to the user community through the Life Science Data Archive (LSDA) and the Lifetime Surveillance of Astronaut Health (LSAH) Repositories. The task of both LSDA and LSAH repositories is to acquire, preserve, and distribute retrospective research (LSDA) and medical (LSAH) data and information both within the NASA community and to the science community at large, for knowledge discovery, retrospective analysis, and planning of future research studies. An additional goal is to encourage collaboration with non-NASA institutions also faced with enhancing human performance in extreme environments. In September 2022, the LSDA website and its contents transitioned to a new NASA Life Sciences Portal (https://nlsp.nasa.gov/explore/lsdahome). This site continues to feature publicly releasable information such as non-attributable datasets, experiment descriptions (from Project Mercury to ISS, as well as from multiple flight analog missions), descriptions of medical monitoring data, and LSAH newsletters (1992 - 2022). The website also provides an updated portal to request additional research and medical data not accessible from the public website. This presentation will provide an in-depth look at the new system as it relates to finding and requesting retrospective data. We will also detail processes from making a request to delivering data for different types of data requests (i.e., attributable, or non-attributable). This includes descriptions of various approval boards, what information and actions the requestor is responsible for, and key milestones in making data available for reuse.

D. M. Thomas↗

Spaceflight Environmental-Telemetry Data for Biological Science

There is a critical need for better access and visualization of spaceflight environmental telemetry and mission hardware data from sensors including relative humidity, carbon dioxide, oxygen, radiation, airflow, temperature, acceleration, and acoustics. Under the stewardship of the Ames Life Sciences Data Archive (ALSDA) and GeneLab, an effort is underway to consolidate, normalize and provide accessibility of archived mission environmental data and hardware information, with the purpose of providing important context to biological data. This effort is necessary to provide scientific context of its impact upon biological and biomedical data from spaceflight missions and experiments (genomic, metagenomic, gene expression, proteomic, metabolomic, physiological, phenomics, behavioral; tabular, imaging, video). Environmental spaceflight data is derived from dozens of sources, with various formats, and in the past year a pipeline is in development to collect, curate and present this data efficiently. In the upcoming year, a new Data Visualization Portal will utilize the standardized pipeline data to provide easy user access to compare parameters and environmental conditions between missions, locations, subjects, and durations. Environmental and hardware data enables broad accessibility and analytics, without the need for advanced data informatic expertise. Familiarity with the capabilities and limitations of a variety of existing hardware/tools is a strength that could be applied to creation of improved hardware for future ecosystems on the Moon and Mars. The intention is to make biological and environmental telemetry data maximally open-access and FAIR (findable, accessible, interoperable, reusable) for data mining-informatic approaches to support knowledge discovery necessary for low Earth orbit, cis-Lunar, Mars transit, and Mars surface missions.

Danielle K. Lopez↗

The NASA Open Science Data Repository: Biomedical Data, Analysis Tools, and Informatic Collaborations

Increased biomedical risks and challenges associated with deep space missions require knowledge discovery, health countermeasures, and biomedical support capabilities. Maximally open-access and reusable data is needed by developers, scientists, and engineers to develop these systems. The NASA Open Science Data Repository (OSDR) is a maximally open access and FAIR database (ie., findable, accessible, interoperable, and reusable), and meets various scientific, technical, and operational needs. It offers users and submitters the ability to upload, download, search, share, analyze, cite, and visualize data across ‘omics, physiological, phenotypic, payload, hardware, behavioral, bioimaging, video, and environmental monitoring telemetry datasets. OSDR is an expanded database, based upon the successes of NASA GeneLab. OSDR has >460 studies with datasets covering model organisms to non-NASA human astronauts. There are ~12 datasets from the Inspiration 4 (I4) mission, spanning metagenomics, comprehensive metabolic panels, clonal hematopoiesis, spatial transcriptomics, proteomics, and cytokine panels. In the interest of data privacy, two I4 datasets with raw files relating to the epitranscriptome, and a new request feature is live in OSDR (with a backend review process established) developed from industry norms. OSDR is collecting and curating biomedical human data from a new sub-orbital research flight and is open to more space life science/biomedical submissions from the international and commercial sectors. OSDR also recently began a collaboration with the European Space Agency (ESA) to collect and curate >200 terabytes of human and model organism data. The OSDR submission portal is designed to ingest and curate ~25 ‘omics and ~50 physiological-phenotypic-imaging assay data types. Tools available for OSDR users include: 1) an Environmental Data Application to compare radiation, CO2, relative humidity, temperature, and other telemetry across missions and subjects, 2) the RadLab database, a collaboration between NASA, ESA, the German and Italian Space Agencies, and the Bulgarian Academy of Sciences, and 3) a Multi-study visualization tool which enables users to look across and combine ‘omics datasets. There are ~600 volunteer OSDR Analysis Working Group (AWG) members providing feedback on scientific data/metadata standards and collaborating to mine-reuse OSDR in research. OSDR/GeneLab has enabled ~60 publications reusing data as of October 2023.

space biology↗

Visualization at Supercomputing Centers: The Tale of Little Big Iron and the Three Skinny Guys

Supercomputing Centers (SC's) are unique resources that aim to enable scientific knowledge discovery through the use of large computational resources, the Big Iron. Design, acquisition, installation, and management of the Big Iron are activities that are carefully planned and monitored. Since these Big Iron systems produce a tsunami of data, it is natural to co-locate visualization and analysis infrastructure as part of the same facility. This infrastructure consists of hardware (Little Iron) and staff (Skinny Guys). Our collective experience suggests that design, acquisition, installation, and management of the Little Iron and Skinny Guys does not receive the same level of treatment as that of the Big Iron. The main focus of this article is to explore different aspects of planning, designing, fielding, and maintaining the visualization and analysis infrastructure at supercomputing centers. Some of the questions we explore in this article include:"How should the Little Iron be sized to adequately support visualization and analysis of data coming off the Big Iron?" What sort of capabilities does it need to have?" Related questions concern the size of visualization support staff:"How big should a visualization program be (number of persons) and what should the staff do?" and"How much of the visualization should be provided as a support service, and how much should applications scientists be expected to do on their own?"

97 MATHEMATICS AND COMPUTING↗

Moving from Descriptive to Causal Analytics: Case Study of the Health Indicators Warehouse

The KDD community has described a multitude of methods for knowledge discovery on large datasets. We consider some of these methods and integrate them into an analyst s workflow that proceeds from the data-centric descriptive level to the model-centric causal level. Examples of the workflow are shown for the Health Indicators Warehouse, which is a public database for community health information that is a potent resource for conducting data science on a medium scale. We demonstrate the potential of HIW as a source of serious visual analytics efforts by showing correlation matrix visualizations, multivariate outlier analysis, multiple linear regression of Medicare costs, and scatterplot matrices for a broad set of health indicators. We conclude by sketching the first steps toward a causal dependence hypothesis.

Schryver, Jack C.↗

Computational Methods in Water Resources XIX International Conference June 17-22, 2012 at the University of Illinois at Urbana-Champaign

The XIX International Conference on Computational Methods in Water Resources (CMWR2012) was held at the University of Illinois at Urbana-Champaign on June 17-21, 2012. Based upon overall attendance, the conference was a great success. There were 320 total attendees, which included approximately 110 students and 120 non-US participants representing 28 countries. Registration surpassed that of prior recent meetings in Barcelona (~ 240) and San Francisco (~ 270). There was a deliberate attempt to reach out to new communities of scholars, as represented by special sessions on Data-driven Approaches for Water Resources Forecasting and Knowledge Discovery, Computational Ecohydrology,and Modeling and Analytics for Hydrologic Impact Assessments due to Climate Change. Other special sessions of interest to DOE include: Advances in Heterogeneous Computing for Water Resources, Applying High-Performance Computing for Scientific Discovery within Real-World Problems, CO2 Sequestration, Hybrid Multiscale Models in Subsurface Flow and Transport, and Transforming Water Resource Management with Open-Source Community Tools. Many DOE scientists were involved in the conference as members of the scientific organizing committee, conveners of special sessions, and participants. A complete list of special sessions and other information is posted on the conference web site: http://cmwr2012.cee.illinois.edu. The conference proceedings are also freely available on-line at the web site.

54 ENVIRONMENTAL SCIENCES↗

ORNL Automated-In-Motion Evaluation Environment (AIMVEE) User Training and Testing Materials - U.S. Copyright TXu 1-797-273

The AIMVEE/WIM system electronically retrieves deployment information, identifies vehicle automatically, and determines total weight, individual wheel weight, individual axle weights, axle spacing, and center-of-balance for any wheeled vehicle in motion. The AIMVEE/WIM system can also perform these functions statically for both wheel vehicles and cargo with information. The AIMVEE/WIM system incorporates digital images and applies cubing algorithms to determine length, width, height for cubic dimensions of both vehicle and cargo. Once all this information is stored, it electronically links to data collection and dissemination systems to provide actual weight and measurement information for planning, deployment, and in-transit visibility. The Static Scale Conversion (SSC) system is an unique enhancement to the AIMVEE/WIM system. It enables a SSC to weigh and measure vehicles and cargo dynamically (i.e., as they pass over the large scale and is included in the AIMVEE computer code base. The material copyrighted is the ORNL Automated-In-Motion Vehicle Evaluation Environment (AIMVEE)/Weigh-In-Motion User Training and Testing material. It includes instructional material in the set-up, operation and tear-down of the AIMVEE/WIM system. It also includes a final exam associated with the training.

Automated-in-Motion Evaluation Environment (AIMVEE↗

An Adaptive Memory Interface Controller for Improving Bandwidth Utilization of Hybrid and Reconfigurable Systems

Emerging applications such as data mining, bioinformatics, knowledge discovery, social network analysis are irregular. They use data structures based on pointers or linked lists, such as graphs, unbalanced trees or unstructures grids, which generates unpredictable memory accesses. These data structures usually are large, but difficult to partition. These applications mostly are memory bandwidth bounded and have high synchronization intensity. However, they also have large amounts of inherent dynamic parallelism, because they potentially perform a task for each one of the element they are exploring. Several efforts are looking at accelerating these applications on hybrid architectures, which integrate general purpose processors with reconfigurable devices. Some solutions, which demonstrated significant speedups, include custom-hand tuned accelerators or even full processor architectures on the reconfigurable logic. In this paper we present an approach for the automatic synthesis of accelerators from C, targeted at irregular applications. In contrast to typical High Level Synthesis paradigms, which construct a centralized Finite State Machine, our approach generates dynamically scheduled hardware components. While parallelism exploitation in typical HLS-generated accelerators is usually bound within a single execution flow, our solution allows concurrently running multiple execution flow, thus also exploiting the coarser grain task parallelism of irregular applications. Our approach supports multiple, multi-ported and distributed memories, and atomic memory operations. Its main objective is parallelizing as many memory operations as possible, independently from their execution time, to maximize the memory bandwidth utilization. This significantly differs from current HLS flows, which usually consider a single memory port and require precise scheduling of memory operations. A key innovation of our approach is the generation of a memory interface controller, which dynamically maps concurrent memory accesses to multiple ports. We present a case study on a typical irregular kernel, Graph Breadth First search (BFS), exploring different tradeoffs in terms of parallelism and number of memories.

BFS↗

The Ultra-scale Visualization Climate Data Analysis Tools (UV-CDAT): Data Analysis and Visualization for Geoscience Data

To support interactive visualization and analysis of complex, large-scale climate data sets, UV-CDAT integrates a powerful set of scientific computing libraries and applications to foster more efficient knowledge discovery. Connected through a provenance framework, the UV-CDAT components can be loosely coupled for fast integration or tightly coupled for greater functionality and communication with other components. This framework addresses many challenges in the interactive visual analysis of distributed large-scale data for the climate community.

97 MATHEMATICS AND COMPUTING↗

Machine Learning in the Big Data Era: Are We There Yet?

In this paper, we discuss the machine learning challenges of the Big Data era. We observe that recent innovations in being able to collect, access, organize, integrate, and query massive amounts of data from a wide variety of data sources have brought statistical machine learning under more scrutiny and evaluation for gleaning insights from the data than ever before. In that context, we pose and debate the question - Are machine learning algorithms scaling with the ability to store and compute? If yes, how? If not, why not? We survey recent developments in the state-of-the-art to discuss emerging and outstanding challenges in the design and implementation of machine learning algorithms at scale. We leverage experience from real-world Big Data knowledge discovery projects across domains of national security and healthcare to suggest our efforts be focused along the following axes: (i) the data science challenge - designing scalable and flexible computational architectures for machine learning (beyond just data-retrieval); (ii) the science of data challenge the ability to understand characteristics of data before applying machine learning algorithms and tools; and (iii) the scalable predictive functions challenge the ability to construct, learn and infer with increasing sample size, dimensionality, and categories of labels. We conclude with a discussion of opportunities and directions for future research.

Big Data↗

Joint the Center for Applied Scientific Computing

The Center for Applied Scientific Computing serves as Livermore Lab’s window to the broader computer science, computational physics, applied mathematics, and data science research communities. In collaboration with academic, industrial, and other government laboratory partners, we conduct world-class scientific research and development on problems critical to national security. CASC applies the power of high-performance computing and the efficiency of modern computational methods to the realms of stockpile stewardship, cyber and energy security, and knowledge discovery for intelligence applications.

97 MATHEMATICS AND COMPUTING↗

A Scalable Parallel Hypergraph Generator (HyGen)

Graphs are extensively used to model real-world complex systems. An edge in a graph can model pairwise relationships. However, multiway relationships (connections between three or more vertices) are common in many complex systems such as cellular process, image segmentation, and circuit design. A graph edge cannot model multiway relationships. A hypergraph, which can connect more than two vertices, is thus a better option to model multiway relationships. A large-scale hypergraph analysis has the potential to find useful insights from a complex system and assist in knowledge discovery. Currently a limited number of hypergraphs exists that are representative of real-world datasets. Moreover, real-world hypergraph datasets are small in size and inadequate to incorporate future needs. A graph generator that can produce large-scale synthetic hypergraphs can solve the above mentioned problems. In this paper, we present a scalable parallel hypergraph generator (HyGen) based on the Message Passing Interface (MPI) standard. To generate hypergraphs, HyGen takes the following parameter values as inputs: i) number of vertices, ii) number of hyperedges, iii) number of clusters, iv) vertex distribution, v) hyperedge distribution, vi) local cluster cardinality, and vii) global cluster cardinality. We have demonstrated that HyGen can generate hypergraphs of various sizes in a scalable fashion. HyGen takes approximately four minutes to generate a hypergraph with 4.8 million vertices, 1.6 million hyperedges, and 800 clusters using 1,024 processes on a leadership class computing platform. Our strong and weak scaling experiments on supercomputers demonstrate that HyGen can quickly create large-scale hypergraphs in a parallel manner, thus providing a useful capability for hypergraph analysis.

Hasan, S M Shamimul↗

AMIA KDDM Working Group Collaborative Workshop: Enriching Electronic Health Records with Social Determinants of Health to Improve Outcomes and Health Equity

Prior research has demonstrated that social determinants of health (SDoH) are major drivers of health outcomes and contributors to widespread health inequities. It was estimated that, in the United States, SDoH could be responsible for up to 40% of all preventable deaths, significantly higher than the 10-15% for which better medical care is responsible. Public health interventions that target SDoH are instrumental for improving health outcomes and reducing long-standing health inequities. Currently, most mainstream EHR vendors have implemented SDoH screeners in their EHR systems. However, the utility of the screeners is low, rendering patient-level SDoH still widely unavailable in the structured fields. SDoH are sometimes mentioned in free-text clinical notes (e.g., social context section) where natural language processing (NLP) can be applied to extract relevant information. Contextual-level SDoH can be identified from multiple data sources, many of which are publicly available and spatiotemporally linked to EHR data. As such, there is an opportunity for the KDDM research community to create innovative solutions to draw meaningful insights by creating and using rich data with SDoH to improve health outcomes while reducing disparities. In this workshop organized by AMIA Knowledge Discovery and Data Mining Working Group (AMIA KDDM WG), we will invite world-leading experts from academia, national laboratories, and life science industry with varied backgrounds in biomedical informatics, epidemiology, data science, machine learning, natural language processing, and pediatric cardiology to discuss the best practice of capturing, standardizing, and using SDoH information in various applications aiming at improving outcomes and health equity.

He, Zhe↗

Requirement Discovery Using Embedded Knowledge Graph with ChatGPT

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) concept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze requirements within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗

Requirement Discovery Using Embedded Knowledge Graph With ChatGPT

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗

Requirement Discovery Using Embedded Knowledge Graph With ChatGPT - Poster

The field of Advanced Air Mobility (AAM) is witnessing a transformation with innovations such as electric aircraft and increasingly automated airspace operations. Within AAM, the Urban Air Mobility (UAM) con-cept focuses on providing air-taxi services in densely populated urban areas. This research introduces the utilization of Large Language Models (LLMs), such as OpenAI's GPT-4, to enhance the UAM Requirement discovery process. This study explores two distinct approaches to leverage LLMs in the context of UAM Requirement discovery. The first approach evaluates the LLM's ability to provide responses without relying on additional outside systems, such as a relational or graph database. Instead, a vector store provides relevant information to the LLM based on the user’s question, a process known as Retrieval Augmented Generation (RAG). The second approach integrates the LLM with a graph database. The LLM acts as an intermediary between the user and the graph database, translating user questions into cypher queries for the database and database responses into human-readable answers for the user. Our team implemented and tested both solutions to analyze require-ments within a UAM dataset. This paper will talk about our approaches, implementations, and findings related to both approaches.

systems engineering↗