Search NASA⌕ Search

SEARCH · Search NASA

Results for “Signal Intelligence”

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 37 records · Page 2
All sourcesNASA NTRSDOE OSTI
DOE OSTI2025

Contrasting Time-Frequency Representations for Unknown Waveform Detection

In real-world applications like spectrum management and interference detection, dealing with unseen electromagnetic waveforms is critical. Although some methods attempt to simulate open set data using generator models, they face challenges in generating synthetic samples for open set while simultaneously selecting an optimal discriminator for accurate classification. This results in difficulties capturing distinctive features across classes, especially in dynamic scenarios where new classes emerge. To detect unseen waveforms, we propose combining time and frequency domain features with cosine similarity loss to enhance feature distinctiveness and enabling more accurate predictions. This approach efficiently captures more comprehensive information than single-domain representations or approaches without cosine loss. Additionally, our model avoids generic feature vectors by extracting class-specific features during training, resulting in improved class representation. The experiment results show that this combined feature approach with cosine loss outperforms single-domain models and improves accuracy by 10\% over models without cosine loss.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Contrasting Time-Frequency Representations for Unknown Waveform Detection

Identifying unseen electromagnetic waveforms is critical for many applications, like interference management, electronic warfare and spectrum management. Traditionally this is done using statistical methods for anomaly detection, which has evolved to deep learning models for identifying the unseen data, formally termed as open set recognition. Some prior methods use a generative model to emulate open set data, which face challenges in generating synthetic samples for open set while simultaneously selecting an optimal discriminator for accurate classification. To alleviate this issue, we propose a discriminative model that effectively combines time and frequency domain features of communication signals for accurate predictions. We further introduce a cosine similarity loss that makes the domain specific features unique to enhance the prediction rate. Additionally, our model avoids generic feature vectors by extracting class-specific features during training, resulting in improved class representation. The experiment results show that this combined feature approach with cosine loss outperforms single-domain models and improves accuracy by 10% over models without cosine loss.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2025

Detecting Unclassified Electromagnetic Signals for Secure Wireless Communication Using Open Set Recognition

We developed multiple machine learning methods for the detection and classification of new wireless communication waveforms, which is critical for targeted attacks in wireless networks and electronic warfare. Our machine learning models are capable of dynamically detecting security threats in near real time through our advanced open set recognition (OSR) approach. This model has demonstrated significant improvements in the detection of unknown waveforms, thereby enhancing the security and reliability of mission critical communications. Our approach to detecting uncertain security threats is novel; we advanced OSR techniques by incorporating domain knowledge of wireless signals. Specifically, we combined time and frequency domain model features to enhance the model’s performance. Utilizing an OSR approach eliminates the need for training data to be distributed similarly to the deployment environment and removes the requirement for the training set to contains all possible threat classes. This is crucial because it is often infeasible to determine and characterize all potential security threats in advance. Our model were trained on simulated data, generated in partnership with the University at Albany, State of New York. The data set contained a diverse array of wireless signals, including those with additive white Gaussian noise and multipath signals, with and without line of sight. This comprehensive training set allowed us to optimize our models to detect unknown waveforms under various challenging scenarios, such as low signal-to-noise ratios. By training on various waveforms, varying signal-to-noise ratio, and different sample sizes under normal conditions, our models were fine tuned to perform effectively in challenging environments.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2023

Cutting-Edge Operations Concepts: Intelligent Infrastructure, Cooperative Driving, Signal Control, and Curbside Management

The objective of this breakout session at the NREL Mobility workshop was to examine emerging traffic operations concepts built on key detection technology such as radars, lidars, and imaging recognition - and identify challenges and paths forward to integrate into our current roadway system. The key objective were to identify the opportunities for intelligent infrastructure to support near-term safety, equity, energy, and congestion mitigation goals, while supporting longer term connected-automated vehicle objectives. In the plenary session, Eric Raamot, from the USDOT Highly Automated Safety Systems Office challenged the participants to think broadly about the roll of standards and reference architecture to provide both an accelerated rollout of intelligent infrastructure, but also a repeatable and supportable framework upon which many infrastructure owners and operators (IOOs) could utilize for their implementation purposes.

ADVANCED PROPULSION SYSTEMS↗
NASA NTRS1974

The design of a device for hearer and feeler differentiation, part A

A speech modulated white noise device is reported that gives the rhythmic characteristics of a speech signal for intelligible reception by deaf persons. The signal is composed of random amplitudes and frequencies as modulated by the speech envelope characteristics of rhythm and stress. Time intensity parameters of speech are conveyed through the vibro-tactile sensation stimuli.

Creecy, R.↗
DOE OSTI2024

Exploiting Multi-Domain Features for Detection of Unclassified Electromagnetic Signals

Deep Learning based classification techniques have shown excellent performance in static environments, where the training and testing samples are drawn from the same distribution. However, real world scenarios often present samples that do not belong to the known set of classes chosen during training. This is quite common for electromagnetic signals, where it is impractical to assume that all possible waveforms are known a-priori, specially in scenarios like warfare. To address this problem, we propose a deep learning based adversarial model where the generator learns to generate waveform features that can deceive the discriminator model as true samples. We introduce domain knowledge of wireless signals by decomposing the signal into a lower dimensional unique feature set, which is used for classifying known versus unknown signals. We further introduce multiple domain representations of the signal to extract features and combine them together to accurately classify new waveforms as an unknown class. Our results show that combined features from multiple domains outperform any single domain representation, especially at low SNR regimes with fewer number of samples to classify.

99 - GENERAL AND MISCELLANEOUS↗
DOE OSTI2024

Exploiting Multi-Domain Features for Detection of Unclassified Electromagnetic Signals (Presentation)

Deep Learning based classification techniques have shown excellent performance in static environments, where the training and testing samples are drawn from the same distribution. However, real world scenarios often present samples that do not belong to the known set of classes chosen during training. This is quite common for electromagnetic signals, where it is impractical to assume that all possible waveforms are known a-priori, specially in scenarios like warfare. To address this problem, we propose a deep learning based adversarial model where the generator learns to generate waveform features that can deceive the discriminator model as true samples. We introduce domain knowledge of wireless signals by decomposing the signal into a lower dimensional unique feature set, which is used for classifying known versus unknown signals. We further introduce multiple domain representations of the signal to extract features and combine them together to accurately classify new waveforms as an unknown class. Our results show that combined features from multiple domains outperform any single domain representation, especially at low SNR regimes with fewer number of samples to classify.

99 - GENERAL AND MISCELLANEOUS↗
NASA NTRS1988

Artificial intelligence applied to process signal analysis

Many space station processes are highly complex systems subject to sudden, major transients. In any complex process control system, a critical aspect of the human/machine interface is the analysis and display of process information. Human operators can be overwhelmed by large clusters of alarms that inhibit their ability to diagnose and respond to a disturbance. Using artificial intelligence techniques and a knowledge base approach to this problem, the power of the computer can be used to filter and analyze plant sensor data. This will provide operators with a better description of the process state. Once a process state is recognized, automatic action could be initiated and proper system response monitored.

Corsberg, Dan↗
NASA NTRS1986

Ultranarrowband searches for extraterrestrial intelligence with dedicated signal-processing hardware

An evaluation is made of the prospects for SETI applications of multichannel spectroscopy, assuming narrowband RF beacon transmission, with a mHz resolution that matches interstellar medium properties. Receiver Doppler corrections must furnish substantial interference rejection. Results are presented from an Arecibo antenna search of 250 sunlike stars at 1.4 and 2.8 GHz. A meridian transit search of the northern sky is also in progress with the Harvard-Smithsonian 26-m antenna.

Horowitz, P.↗
NASA NTRS2015

IYL Blog: Astronomers travel in time and space with light

As an astronomer, I use light to travel through the universe, and to look back in time to when the universe was young. So do you! All of us see things as they were when the light was emitted, not as they are now. The farthest thing you can easily see without a telescope is the Andromeda Nebula, which is a galaxy like the Milky Way, about 2.5 million light years away. You see it as it was 2.5 million years ago, and we really don't know what it looks like today; the disk will have rotated a bit, new stars will have been born, there could have been all kinds of exploding stars, and the black hole in the middle could be lighting up. People may be skeptical of the Big Bang theory, even though we have a TV show named for it, but we (I should say Penzias and Wilson) measured its heat radiation 51 years ago at Bell Telephone Labs in New Jersey. Their discovery marks the beginning of the era of cosmology as a measurement science rather than speculation. Penzias and Wilson received the Nobel Prize in 1978 for their finding, which had been predicted in 1948 by Alpher and Herman. By the way, heat radiation is just another form of light - we call it radiation because we can't see it, but it's exactly the same phenomenon of electromagnetic waves, and the only difference is the wavelength. In the old days of analog television, if you tuned your TV in between channels, about 1% of the snow that you could see came from the Big Bang. So when we look at the heat radiation of the early universe, we really are gazing right at what seems to us a cosmic fireball, which surrounds us completely. It's a bit of an illusion; if you can imagine what astronomers in other galaxies would see, they would also feel surrounded by the fireball, and they would also think they were in the middle. So from a mathematical version of imagination, we conclude that there is no observable center and no edge of our universe, and that the heat of the fireball fills the entire universe uniformly. Astronomers are also using light to find out whether we are alone in the universe. The Kepler observatory showed that thousands of stars blink a little when their orbiting planets pass between us and them, and other observatories use light to measure the wobble of stars as their planets pull on them. Eventually, we will find out whether planets like Earth have atmospheres like Earth's too - with water, carbon dioxide, oxygen, methane, and other gases that would be evidence of photosynthetic life. I think in a few decades we will have evidence that some planets do have life, and it will be done using light for remote chemical analysis. Also, astronomers at the SETI project are using light (long wavelength light we can pick up with radio telescopes) to look for signals from intelligent civilizations. That's a harder project because we don't know what to look for. But if we wanted to send signals all the way across the Milky Way, we could do it with laser beams, and if somebody over there knew what to look for, he or she could decode the message. On with the search! Dr. John C. Mather is a Senior Astrophysicist and is the Senior Project Scientist for the James Webb Space Telescope at NASA's Goddard Space Flight Center in Greenbelt, MD. His research centers on infrared astronomy and cosmology. With the Cosmic Background Explorer (COBE) team, he showed that the cosmic microwave background radiation has a blackbody spectrum within 50 parts per million, confirming the expanding universe model (aka the Big Bang Theory) to extraordinary accuracy, and initiating the study of cosmology as a precision science. The COBE team also made the first map of the hot and cold spots in the background radiation. The COBE maps have been confirmed and improved by two succeeding space missions, the Wilkinson Microwave Anisotropy Probe (WMAP, built by GSFC with Princeton University), and the Planck mission built by ESA. Based on these maps, astronomers have now developed a "standard model" of cosmology and have built detailed numerical simulations that begin to match Hubble observations, and require the existence of both "dark matter" and "dark energy", neither of which has been detected or deduced in laboratory experiments. Dr. Mather is the recipient of numerous awards, including the Nobel Prize in Physics (2006) with George Smoot, for the COBE work, and the NASA Distinguished Service Medal (2007). He is a member of many professional societies including the National Academy of Sciences and the American Academy of Arts and Sciences. Dr. Mather is now working with teams and committees to develop plans for a future great telescope capable of observing signs of life on planets orbiting other stars.

telescopes↗
NASA NTRS1977

On the timing of an interstellar communication

By considering prominent events that are observable from both earth and nearby stellar systems it is possible to establish common clocks that may be useful in estimating arrival times for signals of intelligent extraterrestrial origin. The geometry and statistics of a timing strategy are developed together with quantitative estimates of its effectiveness and limits on its application. Effectiveness is measured by comparing the timing strategy with one randomized in time. Limitations arise from inaccuracies inherent in the determination of stellar parallaxes and result in standard deviations of the order of weeks to months for time estimates. The problem can be alleviated by choosing clocks close to Sender in angular distance. Signal opportunities for several nearby sun-like stars are calculated using the bright Nova Cygni 1975 as a clock.

Mclaughlin, W. I.↗
NASA NTRS1986

A decade of SETI observations

A full time dedicated search for extraterrestrial radio signals of intelligent origin has been in progress at the Ohio State University Radio Observatory since 1973. The radio telescope has a collecting area of 2200 square meters, which is equivalent to a circular dish 175 feet in diameter. The search concentrates on a 500 kHz bandwidth centered on the 1420 MHz hydrogen line, Doppler corrected to the galactic standard of rest. A large portion of the sky visible from Ohio was searched, with particulat emphasis on the galactic center region and the M31 Andromeda galaxy. The survey is largely computer automated, and all data reduction is done in real time. Two distinct populations of signals were detected. The first is a relatively small number of signals which persist for over a minute and which are clearly extraterrestrial in origin. The second is the large number of signals which persist less than 10 seconds whose locations are anticorrelated with the galactic plane but show clumps along the galactic axis. None of these signals were observed to recur, despite repeated observations. The cause of these signals were not determined.

Dixon, R. S.↗
NASA NTRS1984

Speech communications in noise

The physical characteristics of speech, the methods of speech masking measurement, and the effects of noise on speech communication are investigated. Topics include the speech signal and intelligibility, the effects of noise on intelligibility, the articulation index, and various devices for evaluating speech systems.

Source record↗
NASA NTRS1980

A search strategy for SETI - The search for extraterrestrial intelligence

A search strategy is proposed for the detection of signals of extraterrestrial intelligent origin. It constitutes an exploration of a well defined volume of search space in the microwave region of the spectrum and envisages the use of a combination of sky survey and targeted star approaches. It is predicated on the use of existing antennas equipped with sophisticated multichannel spectrum analyzers and signal processing systems operating in the digital mode. The entire sky would be surveyed between 1 and 10 GHz with resolution bin widths down to 32 Hz. More than 700 nearby solar type stars and other selected interesting directions would be searched between 1 GHz and 3 GHz with bin widths down to 1 Hz. Particular emphasis would be placed on those solar type stars that are within 20 light years of earth.

Billingham, J.↗
DOE OSTI2023

Traffic Signal Optimization by Integrating Reinforcement Learning and Digital Twins

Machine learning (ML) methods, especially reinforcement learning (RL), have been widely considered for traffic signal optimization in intelligent transportation systems. Most of these ML methods are centralized, lacking in scalability and adaptability in large traffic networks. Further, it is challenging to train such ML models due to the lack of training platforms and/or the cost of deploying and training in a real traffic networks. This paper presents an approach for the integration of decentralized graph-based multi-agent reinforcement learning (DGMARL) with a Digital Twin (DT) to optimize traffic signals for the reduction of traffic congestion and network-wide fuel consumption related to stopping. Specifically, the DGMARL agents learn traffic state patterns and make decisions regarding traffic signal control with assistance from a Digital Twin module, which simulates and replicates the traffic behaviors of a real traffic network. The proposed approach was evaluated using PTV-Vissim [1], a microscopic traffic simulation platform. PTV-Vissim is also the simulation engine of the DT, enabling emulation and optimization of the traffic signals on the MLK Smart Corridor in Chattanooga, Tennessee. Compared to an actuated signal control baseline approach, experiment results show that Eco_PI, a developed performance measure capturing the impact of stops on fuel consumption, was reduced by 44.27% in a 24-hour and an average of 29.88% in a PM-peak-hour scenario.

Multi-Agent Reinforcement Learning, Digital Twin, ↗