SEARCH · Search NASA

Results for “hidden Markov model”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4

All sources NASA NTRS DOE OSTI

NASA NTRS2020

Exploring Cognitive States: Methods for Detecting Physiological Temporal Fingerprints

Cognitive state detection and its relationship to observable physiologically telemetry has been utilized for many human-machine and human-cybernetic applications. This paper aims at understanding and addressing if there are unique psychophysiological patterns over time, a ”physiological temporal fingerprint”, that is associated with specific cognitive states. This preliminary work involves commercial airline pilots completing experimental benchmark task inductions of three cognitive states: 1) Channelized Attention (CA); 2) High Workload (HW); and 3) Low Workload (LW). We approach this objective by modeling these "fingerprints" through the use of Hidden Markov Models and Entropy analysis to evaluate if the transitions over time are complex or rhythmic/predictable by nature. Our results indicate that cognitive states do have unique complexity of physiological sequences that are statistically different from other cognitive states. More specifically, CA has a significantly higher temporal psychophysiological complexity than HW and LW in EEG and ECG telemetry signals. With regards to respiration telemetry, CA has a lower temporal psychophysiological complexity than HW and LW. Through our preliminary work, addressing this unique underpinning can inform whether these underlying dynamics can be utilized to understand how humans transition between cognitive states and for improved detection of cognitive states.

Napoli, Nicholas J.↗

DOE OSTI2020

Data-driven Detection and Early Prediction of Thermoacoustic Instability in a Multi-nozzle Combustor

Thermoacoustic instability (TAI) is a critical issue in modern lean-burn gas-turbine combustors, which is induced by a strong coupling between the resonant combustor acoustics and fluctuations in the heat release rate. This instability may lead to high-amplitude pressure waves that generate undesirable noise levels as well as fatigue stresses in mechanical structures of the combustor. The intense pressure fluctuations due to TAI may also cause large flow perturbations and possibly flow reversal that may lead to flame oscillations, flame liftoff, and even flame blow-out. Hence, there is a strong need for exercising control actions in a timely fashion to mitigate the TAI phenomena. Anomaly detection is an essential prerequisite to the design of a good controller and such a detector must be able to reliably predict a forthcoming TAI. To detect and predict the onset of a TAI from an ensemble of pressure time series, this paper investigates three data-driven methods: Fast Fourier transform (FFT), symbolic time series analysis (STSA), and hidden Markov modeling (HMM). The main focus of the paper is to make a comparative evaluation of these three anomaly detection methods for classification of the current regime of operation into stable and unstable categories as well as for real-time identification of precursors to impending instabilities with short-length time series of measured variables (e.g., pressure oscillations). Finally, the results, generated on experimental data from a multi-nozzle combustor apparatus, have been compared to evaluate the performance of FFT, STSA, and HMM methods for TAI analysis.

42 ENGINEERING↗

DOE OSTI2025

Conin

SAND2025-07645O Conin is a Python library that supports constrained analysis of probabilistic graphical models (PGMs). It enables constrained inference and learning for hidden Markov models, Bayesian networks, dynamic Bayesian networks, and Markov networks. Conin interfaces with the pgmpy library to specify general probabilistic graphical models with a variety of optimization solvers to support learning and inference. Sandia National Laboratories is a multimission laboratory managed and operated by National Technology & Engineering Solutions of Sandia, LLC, a wholly owned subsidiary of Honeywell International Inc., for the U.S. Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.

Hart, William [Sandia National Lab. (SNL-CA), Live↗

DOE OSTI2022

Classification of Nuclear Reactor Operations Using Spatial Importance and Multisensor Networks

Distributed multisensor networks record multiple data streams that can be used as inputs to machine learning models designed to classify operations relevant to proliferation at nuclear reactors. The goal of this work is to demonstrate methods to assess the importance of each node (a single multisensor) and region (a group of proximate multisensors) to machine learning model performance in a reactor monitoring scenario. This, in turn, provides insight into model behavior, a critical requirement of data-driven applications in nuclear security. Using data collected at the High Flux Isotope Reactor at Oak Ridge National Laboratory via a network of Merlyn multisensors, two different models were trained to classify the reactor’s operational state: a hidden Markov model (HMM), which is simpler and more transparent, and a feed-forward neural network, which is less inherently interpretable. Traditional wrapper methods for feature importance were extended to identify nodes and regions in the multisensor network with strong positive and negative impacts on the classification problem. These spatial-importance algorithms were evaluated on the two different classifiers. The classification accuracy was then improved relative to baseline models via feature selection from 0.583 to 0.839 and from 0.811 ± 0.005 to 0.884 ± 0.004 for the HMM and feed-forward neural network, respectively. While some differences in node and region importance were observed when using different classifiers and wrapper methods, the nodes near the facility’s cooling tower were consistently identified as important—a conclusion further supported by studies on feature importance in decision trees. Node and region importance methods are model-agnostic, inform feature selection for improved model performance, and can provide insight into opaque classification models in the nuclear security domain.

Tibbetts, Jake↗

NASA NTRS2007

Hierarchically Structured Non-Intrusive Sign Language Recognition

This work presents a hierarchically structured approach at the nonintrusive recognition of sign language from a monocular frontal view. Robustness is achieved through sophisticated localization and tracking methods, including a combined EM/CAMSHIFT overlap resolution procedure and the parallel pursuit of multiple hypotheses about hands position and movement. This allows handling of ambiguities and automatically corrects tracking errors. A biomechanical skeleton model and dynamic motion prediction using Kalman filters represents high level knowledge. Classification is performed by Hidden Markov Models. 152 signs from German sign language were recognized with an accuracy of 97.6%.

Zieren, Jorg↗

DOE OSTI2024

De novo atomic protein structure modeling for cryoEM density maps using 3D transformer and HMM

Accurately building 3D atomic structures from cryo-EM density maps is a crucial step in cryo-EM-based protein structure determination. Converting density maps into 3D atomic structures for proteins lacking accurate homologous or predicted structures as templates remains a significant challenge. Here, we introduce Cryo2Struct, a fully automated de novo cryo-EM structure modeling method. Cryo2Struct utilizes a 3D transformer to identify atoms and amino acid types in cryo-EM density maps, followed by an innovative Hidden Markov Model (HMM) to connect predicted atoms and build protein backbone structures. Cryo2Struct produces substantially more accurate and complete protein structural models than the widely used ab initio method Phenix. Additionally, its performance in building atomic structural models is robust against changes in the resolution of density maps and the size of protein structures.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS2013

Evaluating Downscaling Methods for Seasonal Climate Forecasts over East Africa

The U.S. National Multi-Model Ensemble seasonal forecasting system is providing hindcast and real-time data streams to be used in assessing and improving seasonal predictive capacity. The NASA / USAID SERVIR project, which leverages satellite and modeling-based resources for environmental decision making in developing nations, is focusing on the evaluation of NMME forecasts specifically for use in impact modeling within hub regions including East Africa, the Hindu Kush-Himalayan (HKH) region and Mesoamerica. One of the participating models in NMME is the NASA Goddard Earth Observing System (GEOS5). This work will present an intercomparison of downscaling methods using the GEOS5 seasonal forecasts of temperature and precipitation over East Africa. The current seasonal forecasting system provides monthly averaged forecast anomalies. These anomalies must be spatially downscaled and temporally disaggregated for use in application modeling (e.g. hydrology, agriculture). There are several available downscaling methodologies that can be implemented to accomplish this goal. Selected methods include both a non-homogenous hidden Markov model and an analogue based approach. A particular emphasis will be placed on quantifying the ability of different methods to capture the intermittency of precipitation within both the short and long rain seasons. Further, the ability to capture spatial covariances will be assessed. Both probabilistic and deterministic skill measures will be evaluated over the hindcast period.

Robertson, Franklin R.↗

NASA NTRS2013

Evaluating Downscaling Methods for Seasonal Climate Forecasts over East Africa

Roberts, J. Brent↗

NASA NTRS2006

Modeling and Classifying Six-Dimensional Trajectories for Teleoperation Under a Time Delay

Within the context of teleoperating the JSC Robonaut humanoid robot under 2-10 second time delays, this paper explores the technical problem of modeling and classifying human motions represented as six-dimensional (position and orientation) trajectories. A dual path research agenda is reviewed which explored both deterministic approaches and stochastic approaches using Hidden Markov Models. Finally, recent results are shown from a new model which represents the fusion of these two research paths. Questions are also raised about the possibility of automatically generating autonomous actions by reusing the same predictive models of human behavior to be the source of autonomous control. This approach changes the role of teleoperation from being a stand-in for autonomy into the first data collection step for developing generative models capable of autonomous control of the robot.

SunSpiral, Vytas↗

DOE OSTI2021

Searching for Dark Matter with Superconducting Qubits

Dark matter is an enduring mystery in our quest to understand the fundamental constituents of our universe. Low mass bosons, such the axion or hidden photon, are compelling dark matter candidates. We leverage their potential interactions with electromagnetic fields, whereby the dark matter (of unknown mass) on rare occasion converts into a single photon, to devise a method of detecting these candidates. Current dark matter searches operating at microwave frequencies use a resonant cavity to coherently accumulate the field sourced by the dark matter and a near standard quantum limited (SQL) linear amplifier to read out the cavity signal. To further increase sensitivity to the dark matter signal and enable future searches, sub-SQL detection techniques are required.In this thesis, I report the development of a novel microwave photon counting technique and a new exclusion limit on hidden photon dark matter. We operate a superconducting qubit to make repeated quantum non-demolition measurements of cavity photons and apply a hidden Markov model analysis to reduce the noise to 15.7 dB below the quantum limit, with overall detector performance limited by a residual background of real photons. With the present device, we perform a hidden photon search and constrain the kinetic mixing angle to less than 1.68 x 10-15 in a band around 6.011 GHz (24.86 micro-eV) with an integration time of 8.33 s. This demonstrated noise reduction technique enables future dark matter searches to be sped up by a factor of 1300. By coupling a qubit to an arbitrary quantum sensor, more general sub-SQL metrology is possible with the techniques presented in this work.

72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗

DOE OSTI2025

NEAR: Neural Embeddings for Amino acid Relationships

Protein language models (PLMs) have recently demonstrated potential to supplant classical protein database search methods based on sequence alignment, but are slower than common alignment-based tools and appear to be prone to a high rate of false labeling. Here, we present NEAR, a method based on neural representation learning that is designed to improve both speed and accuracy of search for likely homologs in a large protein sequence database. NEAR’s ResNet embedding model is trained using contrastive learning guided by trusted sequence alignments. It computes per-residue embeddings for target and query protein sequences, and identifies alignment candidates with a pipeline consisting of residue-level k-NN search and a simple neighbor aggregation scheme. Tests on a benchmark consisting of trusted remote homologs and randomly shuffled decoy sequences reveal that NEAR substantially improves accuracy relative to state-of-the-art PLMs, with lower memory requirements and faster embedding and search speed. While these results suggest that the NEAR model may be useful for standalone homology detection with increased sensitivity over standard alignment-based methods, in this manuscript we focus on a more straightforward analysis of the model’s value as a high-speed pre-filter for sensitive annotation. In that context, NEAR is at least 5x faster than the pre-filter currently used in the widely-used profile hidden Markov model (pHMM) search tool HMMER3, and also outperforms the pre-filter used in our fast pHMM tool, nail.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Snekmer: a scalable pipeline for protein sequence fingerprinting based on amino acid recoding

Abstract Motivation The vast expansion of sequence data generated from single organisms and microbiomes has precipitated the need for faster and more sensitive methods to assess evolutionary and functional relationships between proteins. Representing proteins as sets of short peptide sequences (kmers) has been used for rapid, accurate classification of proteins into functional categories; however, this approach employs an exact-match methodology and thus may be limited in terms of sensitivity and coverage. We have previously used similarity groupings, based on the chemical properties of amino acids, to form reduced character sets and recode proteins. This amino acid recoding (AAR) approach simplifies the construction of protein representations in the form of kmer vectors, which can link sequences with distant sequence similarity and provide accurate classification of problematic protein families. Results Here, we describe Snekmer, a software tool for recoding proteins into AAR kmer vectors and performing either (i) construction of supervised classification models trained on input protein families or (ii) clustering for de novo determination of protein families. We provide examples of the operation of the tool against a set of nitrogen cycling families originally collected using both standard hidden Markov models and a larger set of proteins from Uniprot and demonstrate that our method accurately differentiates these sequences in both operation modes. Availability and implementation Snekmer is written in Python using Snakemake. Code and data used in this article, along with tutorial notebooks, are available at http://github.com/PNNL-CompBio/Snekmer under an open-source BSD-3 license. Supplementary information Supplementary data are available at Bioinformatics Advances online.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS2017

Application of Machine Learning to Rotorcraft Health Monitoring

Machine learning is a powerful tool for data exploration and model building with large data sets. This project aimed to use machine learning techniques to explore the inherent structure of data from rotorcraft gear tests, relationships between features and damage states, and to build a system for predicting gear health for future rotorcraft transmission applications. Classical machine learning techniques are difficult, if not irresponsible to apply to time series data because many make the assumption of independence between samples. To overcome this, Hidden Markov Models were used to create a binary classifier for identifying scuffing transitions and Recurrent Neural Networks were used to leverage long distance relationships in predicting discrete damage states. When combined in a workflow, where the binary classifier acted as a filter for the fatigue monitor, the system was able to demonstrate accuracy in damage state prediction and scuffing identification. The time dependent nature of the data restricted data exploration to collecting and analyzing data from the model selection process. The limited amount of available data was unable to give useful information, and the division of training and testing sets tended to heavily influence the scores of the models across combinations of features and hyper-parameters. This work built a framework for tracking scuffing and fatigue on streaming data and demonstrates that machine learning has much to offer rotorcraft health monitoring by using Bayesian learning and deep learning methods to capture the time dependent nature of the data. Suggested future work is to implement the framework developed in this project using a larger variety of data sets to test the generalization capabilities of the models and allow for data exploration.

machine learning↗

DOE OSTI2021

CLM simulated data at three FLUXNET sites and three SNOTEL sites in the Colorado River Basin

This data package includes 6 csv files that include Community Land Model (CLM) simulations for three Fluxnet sites (i.e., US-NR1, US-GLE and US-VCM) and three SNOTEL sites (i.e., ER-BT, ER-SP and ER-PK) in the Upper Colorado River Basin area. Data inputs include meteorological forcing data (obtained from Fluxnet and SNOTEL databases) and CLM-simulated evapotranspiration (ET) data from 2005 to 2016. These datasets support the development of subseasonal regime approach based on statistics driven Hidden Markov Model to assess intra- and inter-annual variability of ET, which improves our understanding of climate change's impacts on water resources and ecosystem dynamics in the Colorado River Basin.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2026

Oil price states and drivers: An analysis of the second-month spot-futures price differential

Oil remains a dominant component of global energy use, and its price, characterized by frequent changes and an ever-present potential for large swings, continues to be a focus of industry participants, policymakers and analysts attention. Here, this study examines the behavior of future spot oil prices using a continuous-time hidden Markov model (HMM) and daily price data spanning years 2007 to 2024. We identify six states in the second-month WTI spot-futures price differential and assess the roles of eleven futures price, quantity, financial market, and geopolitical/volatility variables in each state. The model yields several insights into the workings of the oil market and the relative roles of these drivers. We find support for several theoretical and empirical findings in the oil market literature, including the role of inventory, volatility/risk, and market responses to contango/backwardation in futures markets. A novel finding is that “normal contango” conditions represent a significant portion of next-day states in our in-sample data. Under the most volatile normal contango state, many of the oil market drivers differ markedly in coefficient signs and magnitudes from those in other states. The resulting model also performed well out-of-sample and would, in addition to understanding the impact of market drivers, be useful for short-term forecasting. Overall, the findings highlight the highly non-linear, regime-dependent interactions of the oil price and its drivers, emphasizing the importance of detailed information to market stakeholders.

Oladosu, Gbadebo A. [Oak Ridge National Laboratory↗

DOE OSTI2023

Improving Estimation of the Koopman Operator with Kolmogorov–Smirnov Indicator Functions

It has become common to perform kinetic analysis using approximate Koopman operators that transform high-dimensional timeseries of observables into ranked dynamical modes. The key to the practical success of the approach is the identification of a set of observables that form a good basis on which to expand the slow relaxation modes. Good observables are, however, difficult to identify a priori and suboptimal choices can lead to significant underestimations of characteristic time scales. Leveraging the representation of slow dynamics in terms of Hidden Markov Models (HMM), we propose a simple and computationally efficient clustering procedure to infer surrogate observables that form a good basis for slow modes. Here, we apply the approach to an analytically solvable model system as well as on three protein systems of different complexities. We consistently demonstrate that the inferred indicator functions can significantly improve the estimation of the leading eigenvalues of Koopman operators and correctly identify key states and transition time scales of stochastic systems, even when good observables are not known a priori.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2025

Machine Learning-Guided Identification of PET Hydrolases from Natural Diversity

The enzymatic depolymerization of poly(ethylene terephthalate) (PET) is emerging as a leading chemical recycling technology for waste polyester. As part of this endeavor, new candidate enzymes identified from natural diversity can serve as useful starting points for enzyme evolution and engineering. In this study, we improved upon HMM searches by applying an iterative machine learning strategy to identify 400 putative PET-degrading enzymes (PET hydrolases) from naturally occurring homologs. Using high-throughput (HTP) experimental techniques, we successfully expressed and purified >200 enzyme candidates and assayed them for PET hydrolysis activity as a function of pH, temperature, and substrate crystallinity. From this library, we discovered 91 previously unknown PET hydrolases, 35 of which retain activity at pH 4.5 on crystalline material, which are conditions relevant to developing more efficient commercial processes. Notably, four enzymes showed equal to or higher activity than LCC-ICCG, a benchmark PET hydrolase, at this challenging condition in our screening assay, and 11 of which have pH optima <7. Using these data, we identified regions of PETases statistically correlated to activity at lower pH. We additionally investigated the effect of condition-specific activity data on trained machine learning predictors and found a precision (putative hit rate) improvement of up to 30% compared to a Hidden Markov Model alone. Our findings show that by pointing enzyme discovery toward conditions of interest with multiple rounds of experimental and machine learning, we can discover large sets of active enzymes and explore factors associated with activity at those conditions.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

DOE OSTI2026

Engineering and Application of a Thermostable MHETase for PET Depolymerization

Enzymatic hydrolysis of poly(ethylene terephthalate) (PET) releases mono(2-hydroxyethyl) terephthalate (MHET) as a major product, the accumulation of which can prolong reactor residence times and complicate downstream monomer separations. The use of a MHETase enzyme can enable MHET hydrolysis to the monomers, terephthalic acid and ethylene glycol, but industrial PETases typically operate at thermophilic temperatures and the well-known MHETase from Ideonella sakaiensis is a mesophilic enzyme, thus warranting the development of thermophilic MHETases. Here, we characterize thermostable MHET-active enzymes from a natural diversity screen by applying a hidden Markov model based on the previously reported, archaeal ferulic acid esterase, PET46. We identified enzymes with higher thermostability than PET46 and quantified their MHETase activity in reactions at 70 °C. The crystal structure of MHT077, the homologue with the highest MHETase activity and an apparent melting temperature (T m,app ) of 94.6 °C, informed site saturation mutagenesis in the active site and lid-domain interface. MHT077 exhibited a ∼100-fold slower unfolding rate at 65 °C than PET46, indicating substantially greater kinetic stability. In parallel, we applied evolution-informed design, a probabilistic model that leverages coevolutionary patterns in large multiple sequence alignments, to improve the activity and thermostability of five ferulic acid esterases. One design, EV-MHT043–5 was identified with a comparable thermostability (T m,app = 96.1 °C) and a 3-fold improvement in its MHETase activity relative to the wildtype enzyme, MHT043. Combination variants of beneficial mutations were screened and afforded a variant, MHT077 LFK , which reduced MHET accumulation in bioreactor experiments with postconsumer PET waste. Overall, this study expands the known MHET-hydrolyzing protein scaffolds available for enzymatic PET recycling.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗