SEARCH · Search NASA
Results for “ITN”
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.
Inverse Text Normalization of Air Traffic Control System Command Center Planning Telecon Transcriptions
We present a hybrid neural network and rule-based Inverse Text Normalization (ITN) method for domains containing unique technical phraseology, specifically Air Traffic Control System Command Center (ATCSCC) planning telecon audio transcriptions. The ATCSCC hosts bi-hourly planning telephone conferences (or planning telecons) to ensure smooth operations within the National Airspace (NAS). Access to both live and post meeting transcripts of this speech audio would enable quick review of meetings. Provided speech transcripts, ITN is the process of converting unformatted raw Automated Speaker Recognition (ASR) model transcripts into a human (expert) readable written form. Our hybrid ITN framework utilizes a fine-tuned Bidirectional Encoder Representations from Transformers neural network to format conversational English, and rule-based methods to format domain-specific aviation text. With an overall Punctuation Error Rate (PER) of 25.56 and Word Error Rate with Punctuation and Capitalization (WER PC) of 5.47, we show that this method has vast potential in being applied to ATCSCC planning telecon audio and other audio/text based data available in ATM.
Inverse Text Normalization of Air Traffic Control System Command Center Planning Telecon Transcriptions
We present a hybrid neural network and rule-based Inverse Text Normalization (ITN) method for domains containing unique technical phraseology, specifically Air Traffic Control System Command Center (ATCSCC) planning telecon audio transcriptions. The ATCSCC hosts bi-hourly planning telephone conferences (or planning telecons) to ensure smooth operations within the National Airspace (NAS). Access to both live and post meeting transcripts of this speech audio would enable quick review of meetings. Provided speech transcripts, ITN is the process of converting unformatted raw Automated Speaker Recognition (ASR) model transcripts into a human (expert) readable written form. Our hybrid ITN framework utilizes a fine-tuned Bidirectional Encoder Representations from Transformers neural network to format conversational English, and rule-based methods to format domain-specific aviation text. With an overall Punctuation Error Rate (PER) of 25.56 and Word Error Rate with Punctuation and Capitalization (WER PC) of 5.47, we show that this method has vast potential in being applied to ATCSCC planning telecon audio and other audio/text based data available in ATM.
Human behavior determinants of exposure to Anopheles vectors of malaria in Sumba, Indonesia
Malaria vector control interventions in Sumba, Indonesia, have not been able to eliminate malaria. Human drivers of exposure to Anopheles bites were investigated as part of a larger clinical trial evaluating the impact of a spatial repellent product on malaria incidence. Human behavioral observations (HBOs) evaluating temporal and spatial presence, sleeping behaviors, and insecticide treated net (ITN) use, were collected parallel to entomological collections—indoor and outdoor human landing catches (HLCs), and house hold surveys. Data demonstrates that mosquito access to humans, enabled by structurally open houses, is evident by the similar entomological landing rates both inside and outside households. The presence of animals inside houses was associated with increased mosquito entry–however, the number of humans present inside houses was not related to increased mosquito landing. Analyzing mosquito landing rates with human behavior data enables the spatial and temporal estimation of exposure to Anopheles bites, accounting for intervention (ITN) presence and usage. Human behavior adjusted exposure to Anopheles bites was found to be highest in the early in the evening, but continued at lower levels throughout the night. Over the night, most exposure (53%) occurred when people were indoors and not under the protection of nets (asleep or awake) followed by exposure outside (44%). Characterized gaps in protection are outdoor exposure as well as exposure indoors–when awake, and when asleep and not using ITNs. Interestingly, in the primary trial, even though there was not a significant impact of the spatial repellent on vector biting rates by themselves (16%), when factoring in human behavior, there was approximately 28% less exposure in the intervention arm than in the placebo arm. The treated arm had less human behavior adjusted bites in all spaces evaluated though there was proportionally higher exposure indoors. This analysis points to the importance of using HBOs both towards understanding gaps in protection as well as how interventions are evaluated. To mitigate ongoing transmission, understanding context specific spatial and temporal exposure based on the interactions of vectors, humans and interventions would be vital for a directed evidence-based control or elimination strategy.
Exploration of CIGAS Alloy System for Thin-Film Photovoltaics on Novel Lightweight and Flexible Substrates
Thin-film photovoltaics (TFPV) on lightweight and flexible substrates offer the potential for very high solar array specific power (W/kg). ITN Energy Systems, Inc. (ITN) is developing flexible TFPV blanket technology that has potential for specific power greater than 2000 W/kg (including space coatings) that could result in solar array specific power between 150 and 500 W/kg, depending on array size, when mated with mechanical support structures specifically designed to take advantage of the lightweight and flexible substrates.(1) This level of specific power would far exceed the current state of the art for spacecraft PV power generation, and meet the needs for future spacecraft missions.(2) Furthermore the high specific power would also enable unmanned aircraft applications and balloon or high-altitude airship (HAA) applications, in addition to modular and quick deploying tents for surface assets or lunar base power, as a result of the high power density (W/sq m) and ability to be integrated into the balloon, HAA or tent fabric. ITN plans to achieve the high specific power by developing single-junction and two-terminal monolithic tandem-junction PV cells using thin-films of high-efficiency and radiation resistant CuInSe2 (CIS) partnered with bandgap-tunable CIS-alloys with Ga (CIGS) or Al (CIAS) on novel lightweight and flexible substrates. Of the various thin-film technologies, single-junction and radiation resistant CIS and associated alloys with gallium, aluminum and sulfur have achieved the highest levels of TFPV device performance, with the best efficiency reaching 19.5% under AM1.5 illumination conditions and on thick glass substrates.(3) Thus, it is anticipated that single- and tandem-junction devices with flexible substrates and based on CIS and related alloys will achieve the highest levels of thin-film space and HAA solar array performance.
Inverse Text Normalization of Air Traffic Control System Command Center Planning Telecon Transcriptions
We present a hybrid neural network and rule-based Inverse Text Normalization (ITN) method for domains containing unique technical phraseology, specifically ATCSCC planning telecon audio transcriptions. The Air Traffic Control System Command Center (ATCSCC) hosts bihourly planning telephone conferences (or planning telecons) to ensure smooth operations within the National Airspace (NAS). Access to both live and post meeting transcripts of this speech audio would enable quick review of meetings. ITN is the process of converting un-formatted "raw'' speech-to-text transcripts into a human (expert) readable written form. Our hybrid ITN framework utilizes a neural network to format conversational English, and rule-based methods to format domain-specific aviation text. With a preliminary overall Word Error Rate with Punctuation and Capitalization (WER PC) of 8.26, we show that this method has vast potential in being applied to ATCSCC planning telecon audio and other audio/text based data available in ATM.