Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “annotations”

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 505 records · Page 28
All sourcesNASA NTRSDOE OSTI
NASA NTRS2012

Rapid Diagnostics of Onboard Sequences

Keeping track of sequences onboard a spacecraft is challenging. When reviewing Event Verification Records (EVRs) of sequence executions on the Mars Exploration Rover (MER), operators often found themselves wondering which version of a named sequence the EVR corresponded to. The lack of this information drastically impacts the operators diagnostic capabilities as well as their situational awareness with respect to the commands the spacecraft has executed, since the EVRs do not provide argument values or explanatory comments. Having this information immediately available can be instrumental in diagnosing critical events and can significantly enhance the overall safety of the spacecraft. This software provides auditing capability that can eliminate that uncertainty while diagnosing critical conditions. Furthermore, the Restful interface provides a simple way for sequencing tools to automatically retrieve binary compiled sequence SCMFs (Space Command Message Files) on demand. It also enables developers to change the underlying database, while maintaining the same interface to the existing applications. The logging capabilities are also beneficial to operators when they are trying to recall how they solved a similar problem many days ago: this software enables automatic recovery of SCMF and RML (Robot Markup Language) sequence files directly from the command EVRs, eliminating the need for people to find and validate the corresponding sequences. To address the lack of auditing capability for sequences onboard a spacecraft during earlier missions, extensive logging support was added on the Mars Science Laboratory (MSL) sequencing server. This server is responsible for generating all MSL binary SCMFs from RML input sequences. The sequencing server logs every SCMF it generates into a MySQL database, as well as the high-level RML file and dictionary name inputs used to create the SCMF. The SCMF is then indexed by a hash value that is automatically included in all command EVRs by the onboard flight software. Second, both the binary SCMF result and the RML input file can be retrieved simply by specifying the hash to a Restful web interface. This interface enables command line tools as well as large sophisticated programs to download the SCMF and RMLs on-demand from the database, enabling a vast array of tools to be built on top of it. One such command line tool can retrieve and display RML files, or annotate a list of EVRs by interleaving them with the original sequence commands. This software has been integrated with the MSL sequencing pipeline where it will serve sequences useful in diagnostics, debugging, and situational awareness throughout the mission.

Starbird, Thomas W.↗
NASA NTRS2013

SequenceL: Automated Parallel Algorithms Derived from CSP-NT Computational Laws

With the introduction of new parallel architectures like the cell and multicore chips from IBM, Intel, AMD, and ARM, as well as the petascale processing available for highend computing, a larger number of programmers will need to write parallel codes. Adding the parallel control structure to the sequence, selection, and iterative control constructs increases the complexity of code development, which often results in increased development costs and decreased reliability. SequenceL is a high-level programming language that is, a programming language that is closer to a human s way of thinking than to a machine s. Historically, high-level languages have resulted in decreased development costs and increased reliability, at the expense of performance. In recent applications at JSC and in industry, SequenceL has demonstrated the usual advantages of high-level programming in terms of low cost and high reliability. SequenceL programs, however, have run at speeds typically comparable with, and in many cases faster than, their counterparts written in C and C++ when run on single-core processors. Moreover, SequenceL is able to generate parallel executables automatically for multicore hardware, gaining parallel speedups without any extra effort from the programmer beyond what is required to write the sequen tial/singlecore code. A SequenceL-to-C++ translator has been developed that automatically renders readable multithreaded C++ from a combination of a SequenceL program and sample data input. The SequenceL language is based on two fundamental computational laws, Consume-Simplify- Produce (CSP) and Normalize-Trans - pose (NT), which enable it to automate the creation of parallel algorithms from high-level code that has no annotations of parallelism whatsoever. In our anecdotal experience, SequenceL development has been in every case less costly than development of the same algorithm in sequential (that is, single-core, single process) C or C++, and an order of magnitude less costly than development of comparable parallel code. Moreover, SequenceL not only automatically parallelizes the code, but since it is based on CSP-NT, it is provably race free, thus eliminating the largest quality challenge the parallelized software developer faces.

Cooke, Daniel↗
NASA NTRS2013

One Small Step for Creo Modelers, One Giant Leap for "Grey Beards": Using MBD Methodologies to Launch Astronauts and Hardware to Near-Earth Objects such as Asteroids, the Moon and Mars

This presentation will focus on the modernization of design and engineering practices through the use of Model Based Definition methodology. By gathering important engineering data into one 3D digital data set, applying model annotations, and setting up model view states directly in the 3D CAD model, model-specific information can be published to Windchill and CreoView for use during the Design Review Process. This presentation will describe the methods that have been incorporated into the modeling.

Jones, Corey↗
NASA NTRS2013

Adaptive Distributed Environment for Procedure Training (ADEPT)

ADEPT (Adaptive Distributed Environment for Procedure Training) is designed to provide more effective, flexible, and portable training for NASA systems controllers. When creating a training scenario, an exercise author can specify a representative rationale structure using the graphical user interface, annotating the results with instructional texts where needed. The author's structure may distinguish between essential and optional parts of the rationale, and may also include "red herrings" - hypotheses that are essential to consider, until evidence and reasoning allow them to be ruled out. The system is built from pre-existing components, including Stottler Henke's SimVentive instructional simulation authoring tool and runtime. To that, a capability was added to author and exploit explicit control decision rationale representations. ADEPT uses SimVentive's Scalable Vector Graphics (SVG)- based interactive graphic display capability as the basis of the tool for quickly noting aspects of decision rationale in graph form. The ADEPT prototype is built in Java, and will run on any computer using Windows, MacOS, or Linux. No special peripheral equipment is required. The software enables a style of student/ tutor interaction focused on the reasoning behind systems control behavior that better mimics proven Socratic human tutoring behaviors for highly cognitive skills. It supports fast, easy, and convenient authoring of such tutoring behaviors, allowing specification of detailed scenario-specific, but content-sensitive, high-quality tutor hints and feedback. The system places relatively light data-entry demands on the student to enable its rationale-centered discussions, and provides a support mechanism for fostering coherence in the student/ tutor dialog by including focusing, sequencing, and utterance tuning mechanisms intended to better fit tutor hints and feedback into the ongoing context.

Domeshek, Eric↗
NASA NTRS2014

Property Differencing for Incremental Checking

This paper introduces iProperty, a novel approach that facilitates incremental checking of programs based on a property di erencing technique. Speci cally, iProperty aims to reduce the cost of checking properties as they are initially developed and as they co-evolve with the program. The key novelty of iProperty is to compute the di erences between the new and old versions of expected properties to reduce the number and size of the properties that need to be checked during the initial development of the properties. Furthermore, property di erencing is used in synergy with program behavior di erencing techniques to optimize common regression scenarios, such as detecting regression errors or checking feature additions for conformance to new expected properties. Experimental results in the context of symbolic execution of Java programs annotated with properties written as assertions show the e ectiveness of iProperty in utilizing change information to enable more ecient checking.

Yang, Guowei↗
NASA NTRS2014

NASA GeneLab Concept of Operations

NASA's GeneLab aims to greatly increase the number of scientists that are using data from space biology investigations on board ISS, emphasizing a systems biology approach to the science. When completed, GeneLab will provide the integrated software and hardware infrastructure, analytical tools and reference datasets for an assortment of model organisms. GeneLab will also provide an environment for scientists to collaborate thereby increasing the possibility for data to be reused for future experimentation. To maximize the value of data from life science experiments performed in space and to make the most advantageous use of the remaining ISS research window, GeneLab will apply an open access approach to conducting spaceflight experiments by generating, and sharing the datasets derived from these biological studies in space.Onboard the ISS, a wide variety of model organisms will be studied and returned to Earth for analysis. Laboratories on the ground will analyze these samples and provide genomic, transcriptomic, metabolomic and proteomic data. Upon receipt, NASA will conduct data quality control tasks and format raw data returned from the omics centers into standardized, annotated information sets that can be readily searched and linked to spaceflight metadata. Once prepared, the biological datasets, as well as any analysis completed, will be made public through the GeneLab Space Bioinformatics System webb as edportal. These efforts will support a collaborative research environment for spaceflight studies that will closely resemble environments created by the Department of Energy (DOE), National Center for Biotechnology Information (NCBI), and other institutions in additional areas of study, such as cancer and environmental biology. The results will allow for comparative analyses that will help scientists around the world take a major leap forward in understanding the effect of microgravity, radiation, and other aspects of the space environment on model organisms. These efforts will speed the process of scientific sharing, iteration, and discovery.

Space Life Science↗
NASA NTRS2009

Towards a Certified Lightweight Array Bound Checker for Java Bytecode

Dynamic array bound checks are crucial elements for the security of a Java Virtual Machines. These dynamic checks are however expensive and several static analysis techniques have been proposed to eliminate explicit bounds checks. Such analyses require advanced numerical and symbolic manipulations that 1) penalize bytecode loading or dynamic compilation, 2) complexify the trusted computing base. Following the Foundational Proof Carrying Code methodology, our goal is to provide a lightweight bytecode verifier for eliminating array bound checks that is both efficient and trustable. In this work, we define a generic relational program analysis for an imperative, stackoriented byte code language with procedures, arrays and global variables and instantiate it with a relational abstract domain as polyhedra. The analysis has automatic inference of loop invariants and method pre-/post-conditions, and efficient checking of analysis results by a simple checker. Invariants, which can be large, can be specialized for proving a safety policy using an automatic pruning technique which reduces their size. The result of the analysis can be checked efficiently by annotating the program with parts of the invariant together with certificates of polyhedral inclusions. The resulting checker is sufficiently simple to be entirely certified within the Coq proof assistant for a simple fragment of the Java bytecode language. During the talk, we will also report on our ongoing effort to scale this approach for the full sequential JVM.

Pichardie, David↗
NASA NTRS2015

Data Mining and Analysis

The Data Mining project seeks to bring the capability of data visualization to NASA anomaly and problem reporting systems for the purpose of improving data trending, evaluations, and analyses. Currently NASA systems are tailored to meet the specific needs of its organizations. This tailoring has led to a variety of nomenclatures and levels of annotation for procedures, parts, and anomalies making difficult the realization of the common causes for anomalies. Making significant observations and realizing the connection between these causes without a common way to view large data sets is difficult to impossible. In the first phase of the Data Mining project a portal was created to present a common visualization of normalized sensitive data to customers with the appropriate security access. The tool of the visualization itself was also developed and fine-tuned. In the second phase of the project we took on the difficult task of searching and analyzing the target data set for common causes between anomalies. In the final part of the second phase we have learned more about how much of the analysis work will be the job of the Data Mining team, how to perform that work, and how that work may be used by different customers in different ways. In this paper I detail how our perspective has changed after gaining more insight into how the customers wish to interact with the output and how that has changed the product.

iss↗
NASA NTRS2015

Curating Virtual Data Collections

NASAs Earth Observing System Data and Information System (EOSDIS) contains a rich set of datasets and related services throughout its many elements. As a result, locating all the EOSDIS data and related resources relevant to particular science theme can be daunting. This is largely because EOSDIS data's organizing principle is affected more by the way they are produced than around the expected end use. Virtual collections oriented around science themes can overcome this by presenting collections of data and related resources that are organized around the user's interest, not around the way the data were produced. Virtual collections consist of annotated web addresses (URLs) that point to data and related resource addresses, thus avoiding the need to copy all of the relevant data to a single place. These URL addresses can be consumed by a variety of clients, ranging from basic URL downloaders (wget, curl) and web browsers to sophisticated data analysis programs such as the Integrated Data Viewer.

data integration↗
NASA NTRS2016

Capturing Safety Requirements to Enable Effective Task Allocation Between Humans and Automaton in Increasingly Autonomous Systems

There is a current drive towards enabling the deployment of increasingly autonomous systems in the National Airspace System (NAS). However, shifting the traditional roles and responsibilities between humans and automation for safety critical tasks must be managed carefully, otherwise the current emergent safety properties of the NAS may be disrupted. In this paper, a verification activity to assess the emergent safety properties of a clearly defined, safety critical, operational scenario that possesses tasks that can be fluidly allocated between human and automated agents is conducted. Task allocation role sets were proposed for a human-automation team performing a contingency maneuver in a reduced crew context. A safety critical contingency procedure (engine out on takeoff) was modeled in the Soar cognitive architecture, then translated into the Hybrid Input Output formalism. Verification activities were then performed to determine whether or not the safety properties held over the increasingly autonomous system. The verification activities lead to the development of several key insights regarding the implicit assumptions on agent capability. It subsequently illustrated the usefulness of task annotations associated with specialized requirements (e.g., communication, timing etc.), and demonstrated the feasibility of this approach.

Neogi, Natasha A.↗
NASA NTRS2016

Exploration Clinical Decision Support System: Medical Data Architecture

The Exploration Clinical Decision Support (ECDS) System project is intended to enhance the Exploration Medical Capability (ExMC) Element for extended duration, deep-space mission planning in HRP. A major development guideline is the Risk of "Adverse Health Outcomes & Decrements in Performance due to Limitations of In-flight Medical Conditions". ECDS attempts to mitigate that Risk by providing crew-specific health information, actionable insight, crew guidance and advice based on computational algorithmic analysis. The availability of inflight health diagnostic computational methods has been identified as an essential capability for human exploration missions. Inflight electronic health data sources are often heterogeneous, and thus may be isolated or not examined as an aggregate whole. The ECDS System objective provides both a data architecture that collects and manages disparate health data, and an active knowledge system that analyzes health evidence to deliver case-specific advice. A single, cohesive space-ready decision support capability that considers all exploration clinical measurements is not commercially available at present. Hence, this Task is a newly coordinated development effort by which ECDS and its supporting data infrastructure will demonstrate the feasibility of intelligent data mining and predictive modeling as a biomedical diagnostic support mechanism on manned exploration missions. The initial step towards ground and flight demonstrations has been the research and development of both image and clinical text-based computer-aided patient diagnosis. Human anatomical images displaying abnormal/pathological features have been annotated using controlled terminology templates, marked-up, and then stored in compliance with the AIM standard. These images have been filtered and disease characterized based on machine learning of semantic and quantitative feature vectors. The next phase will evaluate disease treatment response via quantitative linear dimension biomarkers that enable image content-based retrieval and criteria assessment. In addition, a data mining engine (DME) is applied to cross-sectional adult surveys for predicting occurrence of renal calculi, ranked by statistical significance of demographics and specific food ingestion. In addition to this precursor space flight algorithm training, the DME will utilize a feature-engineering capability for unstructured clinical text classification health discovery. The ECDS backbone is a proposed multi-tier modular architecture providing data messaging protocols, storage, management and real-time patient data access. Technology demonstrations and success metrics will be finalized in FY16.

Biomedical support↗
NASA NTRS2016

Heuristics for Relevancy Ranking of Earth Dataset Search Results

As the Variety of Earth science datasets increases, science researchers find it more challenging to discover and select the datasets that best fit their needs. The most common way of search providers to address this problem is to rank the datasets returned for a query by their likely relevance to the user. Large web page search engines typically use text matching supplemented with reverse link counts, semantic annotations and user intent modeling. However, this produces uneven results when applied to dataset metadata records simply externalized as a web page. Fortunately, data and search provides have decades of experience in serving data user communities, allowing them to form heuristics that leverage the structure in the metadata together with knowledge about the user community. Some of these heuristics include specific ways of matching the user input to the essential measurements in the dataset and determining overlaps of time range and spatial areas. Heuristics based on the novelty of the datasets can prioritize later, better versions of data over similar predecessors. And knowledge of how different user types and communities use data can be brought to bear in cases where characteristics of the user (discipline, expertise) or their intent (applications, research) can be divined. The Earth Observing System Data and Information System has begun implementing some of these heuristics in the relevancy algorithm of its Common Metadata Repository search engine.

science data management↗
NASA NTRS2017

Relevancy Ranking of Satellite Dataset Search Results

As the Variety of Earth science datasets increases, science researchers find it more challenging to discover and select the datasets that best fit their needs. The most common way of search providers to address this problem is to rank the datasets returned for a query by their likely relevance to the user. Large web page search engines typically use text matching supplemented with reverse link counts, semantic annotations and user intent modeling. However, this produces uneven results when applied to dataset metadata records simply externalized as a web page. Fortunately, data and search provides have decades of experience in serving data user communities, allowing them to form heuristics that leverage the structure in the metadata together with knowledge about the user community. Some of these heuristics include specific ways of matching the user input to the essential measurements in the dataset and determining overlaps of time range and spatial areas. Heuristics based on the novelty of the datasets can prioritize later, better versions of data over similar predecessors. And knowledge of how different user types and communities use data can be brought to bear in cases where characteristics of the user (discipline, expertise) or their intent (applications, research) can be divined. The Earth Observing System Data and Information System has begun implementing some of these heuristics in the relevancy algorithm of its Common Metadata Repository search engine.

science data management↗
NASA NTRS2017

Designing Flightdeck Procedures: Literature Resources

This technical publication contains the titles, abstracts, summaries, descriptions, and/or annotations of available literature sources on procedure design and development, requirements, and guidance. It is designed to provide users with an easy access to available resources on the topic of procedure design, and with a sense of the contents of these sources. This repository of information is organized into the following publication sources: Research (e.g., journal articles, conference proceedings), Manufacturers' (e.g., operation manuals, newsletters), and Regulatory and/or Government (e.g., advisory circulars, reports). An additional section contains synopses of Accident/Incident Reports involving procedures. This work directly supports a comprehensive memorandum by Barshi, Mauro, Degani, & Loukopoulou (2016) that summarizes the results of a multi-year project, partially funded by the FAA, to develop technical reference materials that support guidance on the process of developing cockpit procedures (see "Designing Flightdeck Procedures" https://ntrs.nasa.gov/archive/nasa/casi.ntrs.nasa.gov/20160013263.pdf). An extensive treatment of this topic is presented in a forthcoming book by the same authors.

flightdeck↗
NASA NTRS2014

Improving Coverage of Test Cases Generated by Symbolic PathFinder for Programs with Loops

Symbolic execution is a program analysis technique that is used for many purposes, one of which is test-case generation. For loop-free programs, this generates a test-set that achieves path coverage. Program loops, however, imply exponential growth of the number of paths in the best case and non-termination in the worst case. In practice, the number of loop unwindings needs to be bounded for analysis. We consider symbolic execution in the context of the tool Symbolic Pathfinder. This tool extends the model-checker Java Pathfinder and relies on its bounded state-space exploration for termination. We present an implementation of k-bounded loop unwinding, which increases the amount of user-control over the symbolic execution of loops. Bounded unwinding can be viewed as a naive way to prune paths through loops. When using symbolic execution for test-case generation, naively pruning paths is likely at the cost of coverage. In order to improve coverage of branches within a loop body, we present a technique that semi-automatically concretizes variables used in a loop. The basic technique is limited and we therefore present annotations to manually steer symbolic execution towards certain branches, as well as ideas on how the technique can be extended to be more widely applicable.

Programs With Loops↗
NASA NTRS2014

Sharepoint Team Site Configuration

The Data Mining project seeks to bring the capability of data visualization to NASA anomaly and problem reporting systems for the purpose of improving data trending, evaluations, and analyses. Currently NASA systems are tailored to meet the specific needs of its organizations. This tailoring has led to a variety of nomenclatures and levels of annotation for procedures, parts and anomalies making difficult the realization of the common causes for anomalies. Making significant observations and realizing the connection between these causes without a common way to view data is difficult to impossible. The Data Mining project is in its early stages of presenting a common visualization of normalized data through a web based portal. In this paper I detail what I have learned and what I have accomplished during my time as an intern toward the purpose of creating the project portal. I have gone through an iterative process of familiarization with the project and its goals, site design, research, modification and review on the road to creating a common method and location to view the visualized data created under this project.

iss↗
NASA NTRS2019

Design of a Nozzle for the Spyder 2nd Stage Solid Rocket Motor

During the 2019 summer term, the author worked with a group of four interns to complete the preliminary design of a 2nd stage solid rocket motor for Up Aerospace’s Spyder Launch Vehicle. The Spyder vehicle is a four stage, solid fuel rocket designed as part of collaboration between NASA and Up Aerospace to develop a vehicle capable of delivering a 10 kg, 6U CubeSat into a 350 km, circular, low Earth orbit. As part of the agreement, NASA is tasked with designing high performance 2nd, 3rd, and 4th stages while Up Aerospace will provide the 1st stage, derived from the first stage of the company’s sub-orbital Spaceloft XL vehicle. Previous intern teams have designed the 3rd and 4th stages, which left the preliminary design of the 2nd stage motor to be completed this summer. The purpose of this report is to highlight a trade study which the author conducted to determine the nozzle geometry which would most benefit the performance of the 2nd stage motor. In this study, various nozzle parameters such as throat radius (RSI), expansion ratio, mass and their effects on the Isp and Delta V of the 2nd Stage were investigated. From this study, a nozzle geometry providing the necessary performance was chosen and implemented as part of the preliminary design of the 2nd stage motor. To mature the 2nd stage motor design, a trade space was needed to determine the nozzle configuration which would most benefit the performance of the 2nd stage. The trade space established did not only evaluate different expansion ratios for the same throat radius, but also investigated the possible performance gained from decreasing the throat radius to increase the expansion ratio and Isp capable of being delivered by the nozzle. Decreasing the throat radius would cause the chamber pressure to increase, consequently increasing the case and insulation mass required to safely operate a motor at higher pressures. To account for this factor, accurate estimates of inert mass first needed to be established. After doing so, the effects of varying nozzle expansion ratios, exit half angles, and subsequently length and mass were evaluated against motor and nozzle performance factors such as delta V and Isp. For this study, four throat radii ranging from 1.75” to 2.375” and consequently four different chamber pressures ranging 550 psia to 1200 psia were investigated. BACKGROUND To launch into Low Earth Orbit, a payload needs to be accelerated to the orbital velocity necessary to keep it from falling back to Earth. The change in velocity required between launch and orbital insertion is known as Delta V. The Delta V which a rocket or stage can deliver can be calculated using the Ideal Rocket equation, 𝛥𝑉=−𝑔0∗𝐼𝑠𝑝∗ln(𝑀𝑓𝑀𝑖) (3) Where 𝑔0 is the acceleration due to gravity at the earth’s surface, 𝐼𝑠𝑝 is the specific impulse of the rocket, 𝑀𝑖 is the initial mass of the rocket, and 𝑀𝑓 is the final mass of the rocket after burnout. From preliminary calculations beyond the scope of this paper, it was determined that 30500 ft/s of delta V would be required for a payload to be inserted into a 350 km circular orbit around the Earth. Using the known masses and Isp values of the 1st, 3rd, and 4th stages and equation 3, the delta V of each stage was calculated. The delta V required by the 2nd stage could then be found by taking the difference between the total delta V required and the delta V of the 1st, 3rd, and 4th stages. From this, the required delta V of the 2nd Stage was calculated to be 7340 ft/s. Specific impulse is an efficiency factor of the nozzle which defines the impulse delivered by the motor per unit of propellant weight. The main variables of a nozzle’s specific impulse investigated in this trade were exit cone half angle, throat radius, and expansion ratio which is affected by the throat radius. The expansion ratio, ε, of a nozzle is defined as the ratio between the nozzle exit area and throat area, and can be calculated using the equation, ε=𝑅𝑒𝑥𝑖𝑡2𝑅𝑠𝑖2 (2) Where 𝑅𝑒𝑥𝑖𝑡 is the radius of the nozzle’s exit and 𝑅𝑠𝑖 is the radius of the nozzle’s throat. A larger expansion ratio and smaller exit half angle will increase the Isp of a nozzle by allowing the gas to expand more and by allowing more of the exhaust gas to produce thrust in the direction of the motor’s central axis. A cross section view of the 2nd Stage motor with the major components annotated is provided in figure 1.

Bennett, Daniel↗
NASA NTRS2019

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↗