Search NASA⌕ Search

SEARCH · Search NASA

Results for “network embeddings”

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 163 records · Page 9

Software Development Technologies for Reactive, Real-Time, and Hybrid Systems: Summary of Research

This research is directed towards the implementation of a comprehensive deductive-algorithmic environment (toolkit) for the development and verification of high assurance reactive systems, especially concurrent, real-time, and hybrid systems. For this, we have designed and implemented the STCP (Stanford Temporal Prover) verification system. Reactive systems have an ongoing interaction with their environment, and their computations are infinite sequences of states. A large number of systems can be seen as reactive systems, including hardware, concurrent programs, network protocols, and embedded systems. Temporal logic provides a convenient language for expressing properties of reactive systems. A temporal verification methodology provides procedures for proving that a given system satisfies a given temporal property. The research covered necessary theoretical foundations as well as implementation and application issues.

Manna, Zohar↗

Implementation of a High-Speed FPGA and DSP Based FFT Processor for Improving Strain Demodulation Performance in a Fiber-Optic-Based Sensing System

NASA's Aviation Safety and Security Program is pursuing research in on-board Structural Health Management (SHM) technologies for purposes of reducing or eliminating aircraft accidents due to system and component failures. Under this program, NASA Langley Research Center (LaRC) is developing a strain-based structural health-monitoring concept that incorporates a fiber optic-based measuring system for acquiring strain values. This fiber optic-based measuring system provides for the distribution of thousands of strain sensors embedded in a network of fiber optic cables. The resolution of strain value at each discrete sensor point requires a computationally demanding data reduction software process that, when hosted on a conventional processor, is not suitable for near real-time measurement. This report describes the development and integration of an alternative computing environment using dedicated computing hardware for performing the data reduction. Performance comparison between the existing and the hardware-based system is presented.

Farley, Douglas L.↗

A Distributed Prognostic Health Management Architecture

This paper introduces a generic distributed prognostic health management (PHM) architecture with specific application to the electrical power systems domain. Current state-of-the-art PHM systems are mostly centralized in nature, where all the processing is reliant on a single processor. This can lead to loss of functionality in case of a crash of the central processor or monitor. Furthermore, with increases in the volume of sensor data as well as the complexity of algorithms, traditional centralized systems become unsuitable for successful deployment, and efficient distributed architectures are required. A distributed architecture though, is not effective unless there is an algorithmic framework to take advantage of its unique abilities. The health management paradigm envisaged here incorporates a heterogeneous set of system components monitored by a varied suite of sensors and a particle filtering (PF) framework that has the power and the flexibility to adapt to the different diagnostic and prognostic needs. Both the diagnostic and prognostic tasks are formulated as a particle filtering problem in order to explicitly represent and manage uncertainties; however, typically the complexity of the prognostic routine is higher than the computational power of one computational element ( CE). Individual CEs run diagnostic routines until the system variable being monitored crosses beyond a nominal threshold, upon which it coordinates with other networked CEs to run the prognostic routine in a distributed fashion. Implementation results from a network of distributed embedded devices monitoring a prototypical aircraft electrical power system are presented, where the CEs are Sun Microsystems Small Programmable Object Technology (SPOT) devices.

Bhaskar, Saha↗

Semi-Autonomous Vehicle Project

The primary objective this summer is "evaluating standards for wireless architecture for the internet of things". The Internet of Things is the network of physical objects or "things" embedded with electronics, software, sensors and network connectivity which enables these objects to collect and exchange data and make decisions based on said data. This was accomplished by creating a semi-autonomous vehicle that takes advantage of multiple sensors, cameras, and onboard computers and combined them with a mesh network which enabled communication across large distances with little to no interruption. The mesh network took advantage of what is known as DTN - Disruption Tolerant Networking which according to NASA is the new communications protocol that is "the first step towards interplanetary internet." The use of DTN comes from the fact that it will store information if an interruption in communications is detected and even forward that information via other relays within range so that the data is not lost. This translates well into the project because as the car moves further away from whatever is sending it commands (in this case a joystick), the information can still be forwarded to the car with little to no loss of information thanks to the mesh nodes around the driving area.

Stewart, Christopher↗

Inverse Estimation of Mars 2020 Entry Aeroheating Environments Using MEDLI2 Flight Data

The Mars Entry, Descent, and Landing Instrumentation 2 (MEDLI2) sensor suite collected heating and pressure data during entry into Mars' atmosphere of the Mars 2020 Perseverance rover. MEDLI2 included thermocouples, heat flux sensors, and pressure transducers on both the heatshield and the backshell. This paper covers the inverse estimation of heatshield and backshell surface heating based on the MEDLI2 Instrumented Sensor Plugs (MISPs), a network of thermocouples embedded in thermal protection system plugs across the aeroshell. Monte Carlo analysis was conducted to assess the sensitivity of the surface heat rate and temperature to uncertainties in thermocouple depth and material properties such as density, specific heat capacity, and thermal conductivity. Data from each MISP was also used to estimate the local time of transition from laminar to turbulent flow at each plug location.

Hannah S Alpert↗

Variance Decomposition of MEDLI2 Reconstructed Heating Using Neural Networks

The Mars Entry, Descent, and Landing Instrumentation (MEDLI2) sensor suite collected data during entry of the Mars 2020 Perseverance rover into Mars’ atmosphere. An inverse estimation of the backshell and heatshield surface aeroheating was performed, using the data from the MEDLI2 Instrumented Sensor Plugs, a network of thermocouples embedded within the thermal protection system across the aeroshell. Monte Carlo analysis was conducted to assess the sensitivity of the surface heat rate, temperature, and heat load to uncertainties in thermocouple depth and material properties. In this paper, a variance decomposition method using Sobol indices was employed to understand the relative contributions of each uncertainty parameter. Performing this analysis using results from the inverse analysis tool FIAT_Opt was found to require incredibly high computation time, and thus machine learning models were trained and evaluated as a surrogate model for FIAT_Opt. This paper demonstrates that machine learning models can be an efficient, accurate alternative to state-of-the-art inverse analysis tools like FIAT_Opt, especially for computationally-expensive processes. Using these models, the sensitivity analysis showed that uncertainties in heat capacity and thermal conductivity were the main drivers for the overall uncertainty in peak reconstructed heating and heat load.

H S Alpert↗

Low power and privacy preserving sensor platform for occupancy detection

A low-cost, low-power, stand-alone sensor platform having a visible-range camera sensor, a thermopile array, a microphone, a motion sensor, and a microprocessor that is configured to perform occupancy detection and counting while preserving the privacy of occupants. The platform is programmed to extract shape/texture from images in spatial domain; motion from video in time domain; and audio features in frequency domain. Embedded binarized neural networks are used for efficient object of interest detection. The platform is also programmed with advanced fusion algorithms for multiple sensor modalities addressing dependent sensor observations. The platform may be deployed for (i) residential use in detecting occupants for autonomously controlling building systems, such as HVAC and lighting systems, to provide energy savings, (ii) security and surveillance, such as to detect loitering and surveil places of interest, (iii) analyzing customer behavior and flows, (iv) identifying high performing stores by retailers.

Velipasalar, Senem↗

Multi-resolution partial differential equations preserved learning framework for spatiotemporal dynamics

Traditional data-driven deep learning models often struggle with high training costs, error accumulation, and poor generalizability in complex physical processes. Physics-informed deep learning (PiDL) addresses these challenges by incorporating physical principles into the model. Most PiDL approaches regularize training by embedding governing equations into the loss function, yet this depends heavily on extensive hyperparameter tuning to weigh each loss term. To this end, we propose to leverage physics prior knowledge by “baking” the discretized governing equations into the neural network architecture via the connection between the partial differential equations (PDE) operators and network structures, resulting in a PDE-preserved neural network (PPNN). This method, embedding discretized PDEs through convolutional residual networks in a multi-resolution setting, largely improves the generalizability and long-term prediction accuracy, outperforming conventional black-box models. The effectiveness and merit of the proposed methods have been demonstrated across various spatiotemporal dynamical systems governed by spatiotemporal PDEs, including reaction-diffusion, Burgers’, and Navier-Stokes equations.

97 MATHEMATICS AND COMPUTING↗

A case study in contrastive learning information combination: Application to technical forensics of additive manufacturing filament source identification

Combination of information from disparate data sources into a single decision is a core challenge in many fields, including the field of technical forensics. Technical forensics (TF) utilizes technical characterization of questioned samples to determine properties of that sample; these properties are then used to infer information of forensic interest, such as provenance, age, or attribution. TF is utilized in traditional forensic applications, such as the attribution of material fragments from an explosive, and in nuclear forensic applications, such as the attribution of actinides which have been interdicted out of regulatory control. The challenge of combining information from disparate sources, described alternately by many terms including “Data Fusion” and “Data Integration”, is exacerbated in the technical forensics domain due to at least two factors: the challenge of interpreting each information source singularly, and the relatively small data set sizes available. Extensive literature exists attempting to combine technical forensics information sources, both in manual and automated processes. These attempts are often bespoke to the specific information sources (such as the bi-, tri-, or quad-isotope chart (Moody, Grant, and Hutcheon 2005)), with some emerging examples of simple early- and late- fusion (, respectively). Simultaneous to the information combination efforts described in the previous paragraph, the field of natural language processing attempted (and largely succeeded) in combining information from multiple non-technical information sources. The ecosystem of “multi-modal” language models, which can take text and images as input, and generate text and images as output, became large and diverse by 2025 (Khan et al. 2025). In a generalized sense, many of these methods are trained by learning neural networks which can convert raw text or images into a vector of numbers describing the text or image, hereafter called “embeddings” and the neural networks performing the conversion are called “embedders”. By using a separate embedder for text and images, finding coincident text and images (such as images with their captions), and optimizing the parameters of the embedders such that the embeddings for the text and the image are similar, the field has found a bridge between text and images (Girdhar et al. 2023). It is the contention of the authors of this report that this insight is not limited to text and images but instead can be extended to any modality which can be found coincidently. The subject of the rest of this report is the application of this method to example multi-modal technical forensic data. Some details about the data used in this report are not appropriate for this report, and are included in a companion report (PNNL-38669).

36 MATERIALS SCIENCE↗

Real Time Mars Approach Navigation Aided by the Mars Network

A NASA Mars technology project is described that is building a prototype embedded real time Mars approach navigation capability which can be hosted on the Mars Network's Electra transceiver. The paper motivates the reason for doing real time Mars approach navigation via a set of analyses demonstrating its utility for enabling Mars pin-point landing (less than 1-km landing error). The development approach, software design, and test results are discussed. Finally, the way forward towards a flight demonstration on the Mars Science Laboratory (MSL) is presented.

Mars Network↗

Classification of Wildfires from MODIS Data Using Neural Networks

Wildfires are destructive to both life and property, which necessitates an approach to quickly and autonomously detect these events from orbital observatories. This talk will introduce a neural network based approach for classifying wildfires in MODIS multispectral data, and will show how it could be applied to a constellation of low-cost CubeSats. The approach combines training a deep neural network on the ground using high performance consumer GPUs, with a highly optimized inference system running on a flight-proven embedded processor. Normally neural networks execute on hardware orders of magnitude more powerful than anything found in a space-based computer, therefore the inference system is designed to be performance even on the most modest of platforms. This implementation is able to be significantly more accurate than previous neural network implementations, while also approaching the accuracy of the state-of-the-art MODFIRE data products.

Artificial Intelligence↗

Multimodal Data Representation with Deep Learning for Extracting Cancer Characteristics from Clinical Text

This paper presents a multimodal data representation to improve the performance of deep learning models for extracting cancer key characteristics from unstructured text in pathology reports. Specifically, in addition to using the text as the input to deep learning models, we use concept unique identifiers (CUIs) as another source of information to the models. We analyze the performance of different text and CUI data representations, including word embeddings and bag of embeddings (BOE), with a convolutional neural network (CNN) and a fully connected multilayer perceptron neural network (MLP-NN). The high level document embeddings from text and CUI inputs are combined by concatenating them and then applying a classifier. The model is used for extracting cancer subsite and histology from pathology reports. These two classification tasks have a large number of labels, i.e. 317 for subsite and 556 for histology, with extreme class imbalance. We compare the performance of the developed DL models across the two tasks based on micro- and macro-F1 scores. The evaluation shows that a multi-channel DL model that utilizes text represented by word embeddings and CUIs represented by BOE outperforms other DL models. Also, this approach significantly improves the model performance on low prevalence classes.

Alawad, Mohammed↗

Justifying the need for forensically ready protocols: A case study of identifying malicious web servers using client honeypots

Abstract: Client honeypot technology can find malicious web servers that attack web browsers and push malware, so called drive-by-downloads, to the client machine. Merely recording the network traffic is insufficient to perform an efficient forensic analysis of the attack. Custom tools need to be developed to access and examine the embedded data of the network protocols. Once the information is extracted from the network data, it cannot be used to perform a behavioral analysis on the attack, therefore limiting the ability to answer what exactly happened on the attacked system. Implementation of a record/ replay mechanism is proposed that allows the forensic examiner to easily extract application data from recorded network streams and allows applications to interact with such data for behavioral analysis purposes. A concrete implementation of such a setup for HTTP and DNS protocols using the HTTP proxy Squid and DNS proxy pdnsd is presented and its effect on digital forensic analysis demonstrated.

97 MATHEMATICS AND COMPUTING↗

Smart pixel sensors: towards on-sensor filtering of pixel clusters with deep learning

Highly granular pixel detectors allow for increasingly precise measurements of charged particle tracks. Next-generation detectors require that pixel sizes will be further reduced, leading to unprecedented data rates exceeding those foreseen at the High- Luminosity Large Hadron Collider. Signal processing that handles data incoming at a rate of $\mathcal{O}$(40 MHz) and intelligently reduces the data within the pixelated region of the detector at rate will enhance physics performance at high luminosity and enable physics analyses that are not currently possible. Using the shape of charge clusters deposited in an array of small pixels, the physical properties of the traversing particle can be extracted with locally customized neural networks. In this first demonstration, we present a neural network that can be embedded into the on-sensor readout and filter out hits from low momentum tracks, reducing the detector's data volume by 57.1%–75.7%. The network is designed and simulated as a custom readout integrated circuit with 28 nm CMOS technology and is expected to operate at less than 300 μW with an area of less than 0.2 mm 2 . The temporal development of charge clusters is investigated to demonstrate possible future performance gains, and there is also a discussion of future algorithmic and technological improvements that could enhance efficiency, data reduction, and power per area.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Smart pixel sensors Towards on-sensor filtering of pixel clusters with deep learning

High granularity silicon pixel sensors are at the heart of energy frontier particle physics collider experiments. At an collision rate of 40\,MHz, these detectors create massive amounts of data. Signal processing that handles data incoming at those rate and intelligently reduces the data within the pixelated region of the detector \textit{at rate} will enhance physics performance and enable physics analyses that are not currently possible. Using the shape of charge clusters deposited in an array of small pixels, the physical properties of the traversing particle can be extracted with locally customized neural networks. In this first work, we present a neural network that can be embedded into the on-sensor readout and filter out hits from low momentum tracks, reducing the detector's data volume by 54.4-75.4\%. The network is designed and simulated as a custom readout integrated circuit with 28\,nm CMOS technology and is expected to operate at less than 300\,$\mu W$ with an area of less than 0.2\,mm$^2$.

43 PARTICLE ACCELERATORS↗

GenomeFace v1.0

GenomeFace is meta-genome binning software. Metagenomic binning, the process of grouping DNA sequences into taxonomic units, is critical for understanding the functions, interactions, and evolutionary dynamics of microbial communities. We propose a deep learning approach to binning using two neural networks, one based on composition and another on environmental abundance, dynamically weighting the contribution of each based on characteristics of the input data. Trained on over 43,000 prokaryotic genomes, our network for composition-based binning is inspired by metric learning techniques used for facial recognition. Using a task-specific, multi-GPU accelerated algorithm to cluster the embeddings produced by our network, our binner leverages marker genes observed to be universally present in nearly all taxa to grade and select optimal clusters of sequences from a hierarchy of candidates. We evaluate our approach on four simulated datasets with known ground truth. Our linear time integration of marker genes recovers more near complete genomes than state of the art but computationally infeasible solutions using them, while being over an order of magnitude faster. Finally, we demonstrate the scalability and acuity of our approach by testing it on three of the largest metagenome assemblies ever performed. Compared to other binners, we produced 47%-183% more near complete genomes. From these datasets, we find over the genomes of over 3000 new candidate species which have never been previously cataloged, representing a potential 4% expansion of the known bacterial tree of life.

Lettich, Richard [Lawrence Berkeley National Labor↗

Thermodynamic Consistent Neural Networks for Learning Material Interfacial Mechanics

For multilayer materials in thin substrate systems, interfacial failure is one of the most challenges. The traction-separation relations (TSR) quantitatively describe the mechanical behavior of a material interface undergoing openings, which is critical to understand and predict interfacial failures under complex loadings. However, existing theoretical models have limitations on enough complexity and flexibility to well learn the real-world TSR from experimental observations. A neural network can fit well along with the loading paths but often fails to obey the laws of physics, due to a lack of experimental data and understanding of the hidden physical mechanism. In this paper, we propose a thermodynamic consistent neural network (TCNN) approach to build a data-driven model of the TSR with sparse experimental data. The TCNN leverages recent advances in physics-informed neural networks (PINN) that encode prior physical information into the loss function and efficiently train the neural networks using automatic differentiation. We investigate three thermodynamic consistent principles, i.e., positive energy dissipation, steepest energy dissipation gradient, and energy conservative loading path. All of them are mathematically formulated and embedded into a neural network model with a novel defined loss function. A real-world experiment demonstrates the superior performance of TCNN, and we find that TCNN provides an accurate prediction of the whole TSR surface and significantly reduces the violated prediction against the laws of physics.

Zhang, Jiaxin↗

Intelligent Software Agents: Sensor Integration and Response

Abstract In a post Macondo world the buzzwords are Integrity Management and Incident Response Management. The twin processes are not new but the opportunity to link the two is novel. Intelligent software agents can be used with sensor networks in distributed and centralized computing systems to enhance real-time monitoring of system integrity as well as manage the follow-on incident response to changing, and potentially hazardous, environmental conditions. The software components are embedded at the sensor network nodes in surveillance systems used for monitoring unusual events. When an event occurs, the software agents establish a new concept of operation at the sensing node, post the event status to a blackboard for software agents at other nodes to see , and then react quickly and efficiently to monitor the scale of the event. The technology addresses a current challenge in sensor networks that prevents a rapid and efficient response when a sensor measurement indicates that an event has occurred. By using intelligent software agents - which can be stationary or mobile, interact socially, and adapt to changing situations - the technology offers features that are particularly important when systems need to adapt to active circumstances. For example, when a release is detected, the local software agent collaborates with other agents at the node to exercise the appropriate operation, such as: targeted detection, increased detection frequency, decreased detection frequency for other non-alarming sensors, and determination of environmental conditions so that adjacent nodes can be informed that an event is occurring and when it will arrive. The software agents at the nodes can also post the data in a targeted manner, so that agents at other nodes and the command center can exercise appropriate operations to recalibrate the overall sensor network and associated intelligence systems. The paper describes the concepts and provides examples of real-world implementations including the Threat Detection and Analysis System (TDAS) at the International Port of Memphis and the Biological Warning and Incident Characterization System (BWIC) Environmental Monitoring (EM) Component. Technologies developed for these 24/7 operational systems have applications for improved real-time system integrity awareness as well as provide incident response (as needed) for production and field applications.

emergency response↗