Decision-Making and Statistical Standards
NASA speech on use of statistical methods in governmental decision making
SPEECH↗
SEARCH · Engineering Papers
Results for “Speech”
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.
Electrical method of recording tongue movements during articulation of cosmonauts
Electric recording method to study speech formation mechanisms
RECORDING INSTRUMENT↗
Virtual acoustics, aeronautics, and communications
An optimal approach to auditory display design for commercial aircraft would utilize both spatialized (3-D) audio techniques and active noise cancellation for safer operations. Results from several aircraft simulator studies conducted at NASA Ames Research Center are reviewed, including Traffic alert and Collision Avoidance System (TCAS) warnings, spoken orientation "beacons" for gate identification and collision avoidance on the ground, and hardware for improved speech intelligibility. The implications of hearing loss among pilots is also considered.
NASA Center ARC↗
Elastomeric Nanocomposite with Solvent‐Free, One Step, In Situ Shear Exfoliation of Graphite to Graphene
A graphene nanoflake (GNF)‐enhanced elastomeric nanocomposite (G‐EMC) is fabricated following an innovative, cost‐effective, single‐step, in situ shear exfoliation (ISE) method from low‐cost bulk material, graphite, where uniform mixing happens simultaneously within the elastomer matrix. Electron microscopy, atomic force microscopy, and photo‐induced force microscopy results show good dispersion of GNFs with exfoliation to a few layers and uniform distribution in the elastomer matrix. X‐ray photoelectron spectroscopy analysis shows less than 1% oxygen‐containing functional groups/impurity, enhanced bonding through the formation of edge sites as fracture occurs across the GNF basal plane, and pi‐pi interactions with newly exfoliated planar basal plane surfaces of the GNFs. Raman spectroscopy results confirm the formation of GNFs with only a few layers of graphene formed by the ISE process. Fabricated 10 wt.% G‐EMC nanocomposites show a 400%–500% increase in strength and fracture toughness. And 35 wt.% G‐EMCs provide an electrical conductivity of 25.64 S m −1 and a sensor gauge factor of 45. The resulting intrinsic piezo resistivity of the fabricated nanocomposite has been exploited to fabricate a multi‐functional wired and wireless sensor for detecting different body movements, speech, human vital functions, solvents, and biomolecules.
36 MATERIALS SCIENCE↗
Deep Generative Models in Energy System Applications: Review, Challenges, and Future Directions
In recent years, with the advent of mature machine learning products like ChatGPT, Stable Diffusion, and Sora, the world has witnessed tremendous changes driven by the rapid development of generative artificial intelligence (GAI). Beyond applications in text, speech, image, and video creation, deep generative models (DGMs) underpinning these cutting-edge technologies have also been employed by domain researchers to address scientific and engineering challenges. This paper aims to fill a gap in the research community by providing a systematic review of how DGMs have been utilized in energy system applications. After introducing four most popular DGMs, we review and categorize 196 research articles into five focus areas: data generation, forecasting, situational awareness, modeling, and optimal decision-making. Through this classification, we uncover trends in how DGMs are employed for each type of problem, highlighting GAI techniques that contribute to breakthroughs over traditional methods. We discuss limitations in existing literature, engineering challenges, and propose future directions, all tailored to the unique nature of problems in energy system engineering. Our goal is to offer insights for energy system domain researchers, providing a comprehensive view of existing studies and potential future opportunities.
32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗
Neural-based time series forecasting of loss of coolant accidents in nuclear power plants
During the last few years, deep learning in neural networks has demonstrated impressive successes in the areas of computer vision, speech and image recognition, text generation, and many others. However, sensitive engineering areas such as nuclear engineering benefited less from these efficient techniques. In this work, deep learning expert systems are utilized to model and predict time series progression of a design-basis nuclear accident, featuring a loss of coolant accident. Two major findings are accomplished in this work. First, the ability to train expert systems with high accuracy, which could help nuclear power plant operators to figure out plant responses during the accident. Second, building fast, efficient, and accurate deep models to simulate nuclear phenomena, which could be valuable to nuclear computational science. In this work, large amount of time series data is obtained from simulation tools by simulating different conditions of the base-case/nominal accident scenario. Four critical outputs/responses are monitored during the accident (e.g. temperature, pressure, break flow rate, water level). Two approaches are adopted in this work. The first approach is to use feedforward deep neural networks (DNN) to fit all time steps and outputs in a single model. The second approach is to use long short-term memory (LSTM) to fit all time steps together for each reactor response separately. Both DNN and LSTM demonstrate very good performance in predicting the test and base-case scenarios, with accuracy as low as 92% and as high as 99%, where these test scenarios are unknown to the expert systems and are not included in the model training. In addition, both approaches demonstrate a significant reduction in computational costs, as the deep expert system is able to accurately predict the accident 100,000 times faster than the original simulation tool. Given sufficient data, the methodology adopted in this study demonstrates that DNN/LSTM expert systems can be used as a decision support system to model advanced time series phenomena within nuclear power plants with high accuracy and negligible computational costs.
42 ENGINEERING↗
InteraChem: Virtual Reality Visualizer for Reactive Interactive Molecular Dynamics
Interactive molecular dynamics in virtual reality (IMD-VR) simulations provide a digital molecular playground for students as an alternative or complement to traditional molecular modeling kits or 2D illustrations. Previous IMD-VR studies have used molecular mechanics to enable simulations of macromolecules such as proteins and nanostructures for the classroom setting with considerable success. Here, we present the InteraChem molecular visualizer, intended for reactive IMD-VR simulation using semiempirical and ab initio methods. InteraChem visualizes not only the molecular geometry but also (1) isosurfaces such as molecular orbitals and electrostatic potentials and (2) two-dimensional graphs of time-varying simulation quantities such as kinetic/potential energy, internal coordinates, and user-applied force. Additionally, InteraChem employs speech recognition to facilitate user interaction and introduces a novel “atom happiness” visualization using emojis to indicate the energetic feasibility of a particular bonding arrangement. Furthermore, we include a set of accompanying exercises that we have used to teach chemical reactivity in small molecular systems.
37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
COVID-19: Effects of Environmental Conditions on the Propagation of Respiratory Droplets
As coronavirus disease 2019 (COVID-19) continues to spread, a detailed understanding on the transmission mechanisms is of paramount importance. The disease transmits mainly through respiratory droplets and aerosol. Although models for the evaporation and trajectory of respiratory droplets have been developed, how the environment impacts the transmission of COVID-19 is still unclear. In this study, we investigate the propagation of respiratory droplets and aerosol particles generated by speech under a wide range of temperatures (0–40 °C) and relative humidity (0–92%) conditions. We show that droplets can travel three times farther in low-temperature and high-humidity environment, whereas the number of aerosol particles increases in high-temperature and low-humidity environments. The results also underscore the importance of proper ventilation, as droplets and aerosol spread significantly farther in airstreams. This study contributes to the understanding of the environmental impact on COVID-19 transmission.
60 APPLIED LIFE SCIENCES↗
Wearable Sweat Band for Noninvasive Levodopa Monitoring
Levodopa is the standard medication clinically prescribed to patients afflicted with Parkinson's disease. In particular, the monitoring and optimization of levodopa dosage are critical to mitigate the onset of undesired fluctuations in the patients' physical and emotional conditions such as speech function, motor behavior, and mood stability. The traditional approach to optimize levodopa dosage involves evaluating the subjects' motor function, which has many shortcomings due to its subjective and limited quantifiable nature. In this paper, we present a wearable sweat band on a nanodendritic platform that quantitatively monitors levodopa dynamics in the body. Both stationary iontophoretic induction and physical exercise are utilized as our methods of sweat extraction. The sweat band measures real-time pharmacokinetic profiles of levodopa to track the dynamic response of the drug metabolism. We demonstrated the sweat band's functionalities on multiple subjects with implications toward the systematic administering of levodopa and routine management of Parkinson's disease.
47 OTHER INSTRUMENTATION↗
Off-the-shelf deep learning is not enough, and requires parsimony, Bayesianity, and causality
Abstract Deep neural networks (‘deep learning’) have emerged as a technology of choice to tackle problems in speech recognition, computer vision, finance, etc. However, adoption of deep learning in physical domains brings substantial challenges stemming from the correlative nature of deep learning methods compared to the causal, hypothesis driven nature of modern science. We argue that the broad adoption of Bayesian methods incorporating prior knowledge, development of solutions with incorporated physical constraints and parsimonious structural descriptors and generative models, and ultimately adoption of causal models, offers a path forward for fundamental and applied research.
97 MATHEMATICS AND COMPUTING↗
Converting tabular data into images for deep learning with convolutional neural networks
Abstract Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features, such as speech and imaging. However, most tabular data do not assume a spatial relationship between features, and thus are unsuitable for modeling using CNNs. To meet this challenge, we develop a novel algorithm, image generator for tabular data (IGTD), to transform tabular data into images by assigning features to pixel positions so that similar features are close to each other in the image. The algorithm searches for an optimized assignment by minimizing the difference between the ranking of distances between features and the ranking of distances between their assigned pixels in the image. We apply IGTD to transform gene expression profiles of cancer cell lines (CCLs) and molecular descriptors of drugs into their respective image representations. Compared with existing transformation methods, IGTD generates compact image representations with better preservation of feature neighborhood structure. Evaluated on benchmark drug screening datasets, CNNs trained on IGTD image representations of CCLs and drugs exhibit a better performance of predicting anti-cancer drug response than both CNNs trained on alternative image representations and prediction models trained on the original tabular data.
59 BASIC BIOLOGICAL SCIENCES↗
Quantum machine learning with differential privacy
Abstract Quantum machine learning (QML) can complement the growing trend of using learned models for a myriad of classification tasks, from image recognition to natural speech processing. There exists the potential for a quantum advantage due to the intractability of quantum operations on a classical computer. Many datasets used in machine learning are crowd sourced or contain some private information, but to the best of our knowledge, no current QML models are equipped with privacy-preserving features. This raises concerns as it is paramount that models do not expose sensitive information. Thus, privacy-preserving algorithms need to be implemented with QML. One solution is to make the machine learning algorithm differentially private, meaning the effect of a single data point on the training dataset is minimized. Differentially private machine learning models have been investigated, but differential privacy has not been thoroughly studied in the context of QML. In this study, we develop a hybrid quantum-classical model that is trained to preserve privacy using differentially private optimization algorithm. This marks the first proof-of-principle demonstration of privacy-preserving QML. The experiments demonstrate that differentially private QML can protect user-sensitive information without signficiantly diminishing model accuracy. Although the quantum model is simulated and tested on a classical computer, it demonstrates potential to be efficiently implemented on near-term quantum devices [noisy intermediate-scale quantum (NISQ)]. The approach’s success is illustrated via the classification of spatially classed two-dimensional datasets and a binary MNIST classification. This implementation of privacy-preserving QML will ensure confidentiality and accurate learning on NISQ technology.
97 MATHEMATICS AND COMPUTING↗
Provider Perspectives: Identification and Follow-up of Infants who Are Deaf or Hard of Hearing
Objective Without timely screening, diagnosis, and intervention, hearing loss can cause significant delays in a child's speech, language, social, and emotional development. In 2019, Texas had nearly twice the average rate of loss to follow-up (LFU) or loss to documentation (LTD; i.e., missing documentation of services received) among infants who did not pass their newborn hearing screening compared to the United States overall (51.1 vs. 27.5%). We aimed to identify factors contributing to LFU/LTD among infants who do not pass their newborn hearing screening in Texas. Study Design Data were collected through semistructured qualitative interviews with 56 providers along the hearing care continuum, including hospital newborn hearing screening program staff, audiologists, primary care physicians, and early intervention (EI) program staff located in three rural and urban public health regions in Texas. Following recording and transcription of the interviews, we used qualitative data analysis software to analyze themes using a conventional content analysis approach. Results Frequently cited barriers included problems with family access to care, difficulty contacting patients, problems with communication between providers and referrals, lack of knowledge among providers and parents, and problems using the online reporting system. Providers in rural areas more often mentioned problems with family access to care and contacting families compared to providers in urban areas. Conclusion These findings provide insight into strategies that public health professionals and health care providers can use to work together to help further increase the number of children identified early who may benefit from EI services. Key Points
Obstetrics & Gynecology↗
Audible enclaves crafted by nonlinear self-bending ultrasonic beams
Delivering audible content to a targeted listener without disturbing others is paramount in audio engineering. However, achieving this goal has long been challenging due to the diffraction of low-frequency (long-wavelength) audio waves in linear acoustics. Here, we introduce an approach for creating remote audio spots, dubbed audible enclaves, by harnessing the local nonlinear interaction of two self-bending ultrasonic beams with distinct spectra. The self-bending ultrasonic beams created by acoustic metasurfaces, though inaudible, can bypass obstacles such as human heads. At their intersection behind obstacles, highly localized audible enclaves are formed due to the local nonlinear interactions. Additionally, we demonstrate the ultrabroadband capabilities of our metasurface-based implementation both numerically and experimentally, spanning from 125 Hz to 4 kHz (6 octave bands), covering the majority of the audible frequency range. The practicality of our proposed technique is underscored by its compact implementation size (0.16 m, equivalent to 0.06 wavelengths at 125 Hz), as well as its robust performance under wideband transient audio signal excitation and in a common room with reverberations. Our proposed audible enclaves hold significant potential for various applications in advanced audio engineering, including private speech communications, immersive spatial audio reproduction, and high-resolution sound/quiet zone control.
Science & Technology - Other Topics↗
Accelerating accurate simulations of calorimeter showers with normalizing flows and probability density distillation
Recently, we introduced caloflow, a high-fidelity generative model for GEANT4 calorimeter shower emulation based on normalizing flows. Here, we present caloflow v2, an improvement on our original framework that speeds up shower generation by a further factor of 500 relative to the original. The improvement is based on a technique called probability density distillation, originally developed for speech synthesis in the machine learning literature, and which we develop further by introducing a set of powerful new loss terms. We demonstrate that caloflow v2 preserves the same high fidelity as the original using qualitative (average images, histograms of high-level features) and quantitative (classifier metric between geant4 and generated samples) measures. The result is a generative model for calorimeter showers that matches the state of the art in speed (a factor of 10 4 faster than GEANT4) and greatly surpasses the previous state of the art in fidelity.
72 PHYSICS OF ELEMENTARY PARTICLES AND FIELDS↗
Train Like a (Var)Pro: Efficient Training of Neural Networks with Variable Projection
Deep neural networks (DNNs) have achieved state-of-the-art performance across a variety of traditional machine learning tasks, e.g., speech recognition, image classification, and segmentation. The ability of DNNs to efficiently approximate high-dimensional functions has also motivated their use in scientific applications, e.g., to solve partial differential equations and to generate surrogate models. In this paper, we consider the supervised training of DNNs, which arises in many of the above applications. We focus on the central problem of optimizing the weights of the given DNN such that it accurately approximates the relation between observed input and target data. Devising effective solvers for this optimization problem is notoriously challenging due to the large number of weights, nonconvexity, data sparsity, and nontrivial choice of hyperparameters. To solve the optimization problem more efficiently, we propose the use of variable projection (VarPro), a method originally designed for separable nonlinear least-squares problems. Our main contribution is the Gauss--Newton VarPro method (GNvpro) that extends the reach of the VarPro idea to nonquadratic objective functions, most notably cross-entropy loss functions arising in classification. These extensions make GNvpro applicable to all training problems that involve a DNN whose last layer is an affine mapping, which is common in many state-of-the-art architectures. In our four numerical experiments from surrogate modeling, segmentation, and classification, GNvpro solves the optimization problem more efficiently than commonly used stochastic gradient descent (SGD) schemes. Finally, GNvpro finds solutions that generalize well, and in all but one example better than well-tuned SGD methods, to unseen data points.
97 MATHEMATICS AND COMPUTING↗
Application of a convolutional neural network in permeability prediction: A case study in the Jacksonburg-Stringtown oil field, West Virginia, USA
Permeability is a critical parameter for understanding subsurface fluid flow behavior, managing reservoirs, enhancing hydrocarbon recovery, and sequestering carbon dioxide. In general, permeability is measured in the laboratory based on subsurface core samples, calculated from well logs or estimated from well tests. However, laboratory measurements and well tests are expensive, time-consuming, and usually limited to a few core samples or wells in a hydrocarbon field or carbon storage site. Machine-learning techniques are good options for generating a rapid, robust, and cost-effective permeability prediction model because of their strengths to recognize the potential interrelationships between input and output variables. Convolutional neural networks (CNN), as a good pattern recognition algorithm, are widely used in image processing, natural language processing, and speech recognition, but are rarely used with regression problems and even less often in reservoir characterization. We have developed a CNN regression model to estimate the permeability in the Jacksonburg-Stringtown oil field, West Virginia, which is a potential carbon storage site and enhanced oil recovery operations field. We also evaluate the concept of the geologic feature image, which is converted from geophysical well logs. Five variables, including two commonly available conventional well logs (the gamma rays [GRs] and bulk density) and three well-log-derived variables (the slopes of the GR and bulk density curves, and shale content), are used to generate a geologic feature image. The CNN treats the geologic feature image as the input and the permeability as the desired output. In addition, the permeability predicted using traditional backpropagation artificial neural networks, which are optimized by genetic algorithms and particle swarm optimization, is compared with the permeability estimated using our CNN. Our results indicate that the CNN regression model provides more accurate permeability predictions than the traditional neural network.
Geochemistry & Geophysics↗
A pilot study: Auditory steady-state responses (ASSR) can be measured in human fetuses using fetal magnetoencephalography (fMEG)
Auditory steady-state responses (ASSRs) are ongoing evoked brain responses to continuous auditory stimuli that play a role for auditory processing of complex sounds and speech perception. Transient auditory event-related responses (AERRs) have previously been recorded using fetal magnetoencephalography (fMEG) but involve different neurological pathways. Previous studies in children and adults demonstrated that the cortical components of the ASSR are significantly affected by state of consciousness and by maturational changes in neonates and young infants. To our knowledge, this is the first study to investigate ASSRs in human fetuses. 47 fMEG sessions were conducted with 24 healthy pregnant women in three gestational age groups (30–32 weeks, 33–35 weeks and 36–39 weeks). The stimulation consisted of amplitude-modulated (AM) tones with a duration of one second, a carrier frequency (CF) of 500 Hz and a modulation frequency (MF) of 27 Hz or 42 Hz. Both tones were presented in a random order with equal probability adding up to 80–100 repetitions per tone. The ASSR across trials was quantified by assessing phase synchrony in the cortical signals at the stimulation frequency. Ten out of 47 recordings were excluded due to technical problems or maternal movements. Analysis of the included 37 fetal recordings revealed a statistically significant response for the phase coherence between trials for the MF of 27 Hz but not for 42 Hz. An exploratory subgroup analysis moreover suggested an advantage in detectability for fetal behavioral state 2F (active asleep) compared to 1F (quiet asleep) detected using fetal heart rate. In conclusion, this pilot study is the first description of a method to detect human ASSRs in fetuses. The findings warrant further investigations of the developing fetal brain.
59 BASIC BIOLOGICAL SCIENCES↗