On feature reduction with application to electroencephalograms
Random process model and feature reduction of spontaneous and alpha frequency electroencephalograms
Prabhu, K. P. S.↗
SEARCH · Search NASA
Results for “feature reduction”
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.
Analysis and Benchmarking of feature reduction for classification under computational constraints
Abstract Machine learning is most often expensive in terms of computational and memory costs due to training with large volumes of data. Current computational limitations of many computing systems motivate us to investigate practical approaches, such as feature selection and reduction, to reduce the time and memory costs while not sacrificing the accuracy of classification algorithms. In this work, we carefully review, analyze, and identify the feature reduction methods that have low costs/overheads in terms of time and memory. Then, we evaluate the identified reduction methods in terms of their impact on the accuracy, precision, time, and memory costs of traditional classification algorithms. Specifically, we focus on the least resource intensive feature reduction methods that are available in Scikit-Learn library. Since our goal is to identify the best performing low-cost reduction methods, we do not consider complex expensive reduction algorithms in this study. In our evaluation, we find that at quadratic-scale feature reduction, the classification algorithms achieve the best trade-off among competitive performance metrics. Results show that the overall training times are reduced 61%, the model sizes are reduced 6×, and accuracy scores increase 25% compared to the baselines on average with quadratic scale reduction.
97 MATHEMATICS AND COMPUTING↗
High dimensional feature reduction via projection pursuit
The recent development of more sophisticated remote sensing systems enables the measurement of radiation in many more spectral intervals than previously possible. An example of that technology is the AVIRIS system, which collects image data in 220 bands. As a result of this, new algorithms must be developed in order to analyze the more complex data effectively. Data in a high dimensional space presents a substantial challenge, since intuitive concepts valid in a 2-3 dimensional space to not necessarily apply in higher dimensional spaces. For example, high dimensional space is mostly empty. This results from the concentration of data in the corners of hypercubes. Other examples may be cited. Such observations suggest the need to project data to a subspace of a much lower dimension on a problem specific basis in such a manner that information is not lost. Projection Pursuit is a technique that will accomplish such a goal. Since it processes data in lower dimensions, it should avoid many of the difficulties of high dimensional spaces. In this paper, we begin the investigation of some of the properties of Projection Pursuit for this purpose.
Jimenez, Luis↗
Analytical Fuel Property Effects - Small Combustors. Phase II
A test program was conducted to study the effects of non-standard aviation fuels on a typical small gas turbine combustor, and to evaluate the effectiveness of design changes intended to counter the effects of these fuels. This study was a follow on to an earlier analytical study to predict the fuel effects and generate the design modifications evaluated in this program. The T700/CT7 engine family was chosen for both studies as being representative of the class of aircraft power plants desired for this study. Fuel properties, as specified by NASA, are characterized by low hydrogen content and high aromatics levels. No. 2 diesel fuel was also evaluated in this program. The tests demonstrated the anticipated higher than normal smoke output and flame radiation intensity with resulting increased metal temperatures on the baseline T700 combustor. Three new designs were evaluated using the non standard fuels. The three designs incorporated enhanced cooling features and smoke reduction features. All three designs, when burning the broad specification fuels, exhibited metal temperatures at or below the baseline combustor temperatures on JP-5. Smoke levels were acceptable but higher than predicted. This was partly due to the increase in baseline combustor smoke levels with the broad spec fuels being higher than anticipated. One combustor of the three clearly demonstrated the best smoke and metal temperature characteristics. It was also easiest to manufacture and incorporate into a production design. GE with NASA's concurrence selected and subjected this combustor to a final component test program.
Monty, J.↗
Free-jet acoustic investigation of high-radius-ratio coannular plug nozzles
The experimental and analytical results of a scale model simulated flight acoustic exploratory investigation of high radius ratio coannular plug nozzles with inverted velocity and temperature profiles are summarized. Six coannular plug nozzle configurations and a baseline convergent conical nozzle were tested for simulated flight acoustic evaluation. The nozzles were tested over a range of test conditions that are typical of a Variable Cycle Engine for application to advanced high speed aircraft. It was found that in simulate flight, the high radius ratio coannular plug nozzles maintain their jet noise and shock noise reduction features previously observed in static testing. The presence of nozzle bypass struts will not significantly affect the acousticn noise reduction features of a General Electric type nozzle design. A unique coannular plug nozzle flight acoustic spectral prediction method was identified and found to predict the measured results quite well. Special laser velocimeter and acoustic measurements were performed which have given new insights into the jet and shock noise reduction mechanisms of coannular plug nozzles with regard to identifying further benificial research efforts.
Knott, P. R.↗
Free-jet acoustic investigation of high-radius-ratio coannular plug nozzles. Comprehensive data report, volume 1
Six coannular plug nozzle configurations having inverted velocity and temperature profiles, and a baseline convergent conical nozzle were tested for simulated flight acoustic evaluation in General Electric's Anechoic Free-Jet Acoustic Facility. The nozzles were tested over a range of test conditions that are typical of a Variable Cycle Engine for application to advanced high speed aircraft. The outer stream radius ratio for most of the configurations was 0.853, and the inner-stream-outer-stream area ratio was tested in the range of 0.54. Other variables investigated were the influence of bypass struts, a simple noncontoured convergent-divergent outer stream nozzle for forward quadrant shock noise control, and the effects of varying outer stream radius and inner-stream-to-outer-stream velocity ratios on the flight noise signatures of the nozzles. It was found that in simulated flight, the high-radius-ratio coannular plug nozzles maintain their jet noise and shock noise reduction features previously observed in static testing. The presence of nozzle bypass structs will not significantly effect the acoustic noise reduction features of a General Electric-type nozzle design. A unique coannular plug nozzle flight acoustic spectral prediction method was identified and found to predict the measured results quite well. Special laser velocimeter and acoustic measurements were performed which have given new insight into the jet and shock noise reduction mechanisms of coannular plug nozzles with regard to identifying further beneficial research efforts.
Knott, P. R.↗
Monitoring the propagation of mechanical discontinuity using data-driven causal discovery and supervised learning
Mechanical wave transmission through a material is influenced by the mechanical discontinuity in the material. The propagation of embedded discontinuities can be monitored by analyzing the wave-transmission measurements recorded by a multipoint sensor system placed on the surface of the material. The proposed workflow monitors the propagation of mechanical discontinuity through three stages, namely initial, intermediate, and final stages, by using supervised learning followed by data-driven causal discovery. To the end, the workflow processes the multipoint waveform measurements resulting from a single impulse source, while considering the effects of wave attenuation, dispersion and multiple wave-propagation modes due to the discontinuity and material boundaries. Among various feature reduction techniques ranging from decomposition methods to manifold approximation methods, the features derived based on statistical parameterizations of the measured waveforms lead to reliable monitoring that is robust to changes in precision, resolution, and signal-to-noise ratio of the multipoint sensor measurements. The numbers of zero-crossing, negative-turning, and positive turning in the waveforms are the strongest causal signatures of the propagation of mechanical discontinuity. Higher order moments of the waveforms, such as variance, skewness and kurtosis, are also strong causal signatures of the propagation. Finally, the newly discovered causal signatures confirm that the statistical correlations and conventional feature rankings are not always statistically significant indicators of causality.
42 ENGINEERING↗
Low-Noise Rotorcraft Blades
Blades of helicopter rotors, tilt rotors, and like reshaped to reduce noise, according to proposal. Planform features combination of rearward and forward sweep. Forward sweep over large outer portion of blade constitutes primary noise-reduction feature. Relieves some of compressive effect in tip region, with consequent reduction of noise from compressive sources. Performance at high advance ratio improved. Cabin vibration and loading noise reduced by load-averaging effect of double-sweep planform. Aft-swept section provides balancing of aerodynamic and other dynamic forces on blade along 1/4-chord line of straight inboard section and along projection of line to outermost blade radius. Possible for hub-hinge forces and moments to remain within practical bounds. Provides stabilizing blade forces and moments to counteract any instability caused by forward sweep.
Brooks, Thomas F.↗
Quiet clean short-haul experimental engine /QCSEE/ design rationale
The principal design features of the NASA QCSEE Under-The-Wing and Over-The-Wing powered lift propulsion systems are given. In the UTW engine, these include noise reduction features, a variable pitch low pressure ratio fan, a fan drive reduction gear, an advanced core and low pressure turbine with a low pollution combustor, a digital control, and advanced composite construction for the inlet, fan frame, fan exhaust duct, and variable area fan exhaust nozzle. The OTW engine is similar but has higher fan pressure and a fixed pitch fan. Both engines are scheduled to be fabricated and tested starting in 1976.
Adamson, A. P.↗
Preliminary noise tradeoff study of a Mach 2.7 cruise aircraft
NASA computer codes in the areas of preliminary sizing and enroute performance, takeoff and landing performance, aircraft noise prediction, and economics were used in a preliminary noise tradeoff study for a Mach 2.7 design supersonic cruise concept. Aerodynamic configuration data were based on wind-tunnel model tests and related analyses. Aircraft structural characteristics and weight were based on advanced structural design methodologies, assuming conventional titanium technology. The most advanced noise prediction techniques available were used, and aircraft operating costs were estimated using accepted industry methods. The 4-engines cycles included in the study were based on assumed 1985 technology levels. Propulsion data was provided by aircraft manufacturers. Additional empirical data is needed to define both noise reduction features and other operating characteristics of all engine cycles under study. Data on VCE design parameters, coannular nozzle inverted flow noise reduction and advanced mechanical suppressors are urgently needed to reduce the present uncertainties in studies of this type.
Mascitti, V. R.↗
AiResearch QCGAT engine, airplane, and nacelle design features
The quiet, clean, general aviation turbofan engine and nacelle system was designed and tested. The engine utilized the core of the AiResearch model TFE731-3 engine and incorporated several unique noise- and emissions-reduction features. Components that were successfully adapted to this core include the fan, gearbox, combustor, low-pressure turbine, and associated structure. A highly versatile workhorse nacelle incorporating interchangeable acoustic and hardwall duct liners, showed that large-engine attenuation technology could be applied to small propulsion engines. The application of the mixer compound nozzle demonstrated both performance and noise advantages on the engine. Major performance, emissions, and noise goals were demonstrated.
Heldenbrand, R. W.↗
Cognitive IoT and Edge Computing for Intrusion Detection with Federated TinyML
Internet of Things (IoT) and Edge Computing (EC) are rapidly becoming an integral part of the modern society. By 2030, there is estimated to be over 40 billion active and connected IoT devices [1]. This rapid progress also comes with a significant implication on cybersecurity. Back-end infrastructure and systems have a much broader attack than they did previously due to vulnerable IoT/EC devices being connected to wireless networks. This expanding attack surface is a growing concern because IoT/EC are increasingly being used in critical systems such as power grids, health care, and smart homes. To effectively address a problem of this scale, cognitive cyber methods—which can autonomously detect and react to cyber attacks as they develop—are needed. To address this, we bring Artificial Intelligence (AI) and Machine Learning (ML) to IoT/EC devices, using tinyML to monitor voluminous IoT data against cyber threats, and using Federated Learning (FL) to share local detection knowledge across the system while preserving privacy. We propose a novel three-layer architecture: (1) an IoT layer for tinyML-based inference, (2) an edge layer for ML model training, and (3) a cloud layer for FL operations. Using the publicly available 11-class N-BaIoT dataset [2], we demonstrate that this architecture mitigates resource constraints at the IoT layer while improving detection accuracy over standard two-layer designs. An outlier-resistant scaler, feature reduction, and quantization enable the tinyML model to maintain detection accuracy with a reduced model size. Additionally, federated learning that only utilizes the intersection (across heterogenous devices) of the reduced feature set achieves superior detection accuracy compared to locally trained models.
Li, Mingyan [ORNL] (ORCID:0009000569532640)↗
Forward sweep, low noise rotor blade
A forward-swept, low-noise rotor blade includes an inboard section, an aft-swept section, and a forward-swept outboard section. The rotor blade reduces the noise of rotorcraft, including both standard helicopters and advanced systems such as tiltrotors. The primary noise reduction feature is the forward sweep of the planform over a large portion of the outer blade radius. The rotor blade also includes an aft-swept section. The purpose of the aft-swept region is to provide a partial balance to pitching moments produced by the outboard forward-swept portion of the blade. The noise source showing maximum noise reduction is blade-vortex interaction (BVI) noise. Also reduced are thickness, noise, high speed impulsive noise, cabin vibration, and loading noise.
Brooks, Thomas F.↗
Forward sweep, low noise rotor blade
A forward-swept, low-noise rotor blade includes an inboard section, an aft-swept section and a forward-swept outboard section. The rotor blade reduces the noise of rotorcraft, including both standard helicopters and advanced systems such as tiltrotors. The primary noise reduction feature is the forward sweep of the planform over a large portion of the outer blade radius. The rotor blade also includes an aft-swept section. The purpose of the aft-swept region is to provide a partial balance to pitching moments produced by the outboard forward-swept portion of the blade. The rotor blade has a constant chord width; or has a chord width which decreases linearly along the entire blade span; or combines constant and decreasing chord widths, wherein the blade is of constant chord width from the blade root to a certain location on the rotor blade, then decreases linearly to the blade tip thereafter. The noise source showing maximum noise reduction is blade-vortex interaction (BVI) noise. Also reduced are thickness, noise, high speed impulsive noise, cabin vibration and loading noise.
Brooks, Thomas F.↗
Highly efficient CO 2 electrochemical reduction on dual metal (Co–Ni)–nitrogen sites
A new Co–Ni–N–C electrocatalyst for CO 2 reduction, featuring diatomic metal-nitrogen sites on N-doped carbon, has been developed. It shows high CO yield and faradaic efficiency, promising for various electrochemical reactions.
36 MATERIALS SCIENCE↗
Experimental quiet engine program. Predicted engine performance
Three turbofan configurations, each incorporating alternative noise reduction features, were tested under the Quiet Engine Program. Performance data for these engines are shown over a range of flight conditions. The data are presented in tabular form for standard day flight inlet conditions. Procedures for estimating nonstandard day performance are shown. Tabular data and calculation procedures to allow determination of ram recovery, customer bleed, and customer shaft power extraction effects on engine performance can be found in the original Performance Brochure titled, Experimental Quiet Engine Program, Predicted Engine Performance, dated April 8, 1970. Predicted engine noise levels for representative take-off and approach conditions are provided.
Source record↗
Classification improvement by optimal dimensionality reduction when training sets are of small size
A computer simulation was performed to test the conjecture that, when the sizes of the training sets are small, classification in a subspace of the original data space may give rise to a smaller probability of error than the classification in the data space itself; this is because the gain in the accuracy of estimation of the likelihood functions used in classification in the lower dimensional space (subspace) offsets the loss of information associated with dimensionality reduction (feature extraction). A number of pseudo-random training and data vectors were generated from two four-dimensional Gaussian classes. A special algorithm was used to create an optimal one-dimensional feature space on which to project the data. When the sizes of the training sets are small, classification of the data in the optimal one-dimensional space is found to yield lower error rates than the one in the original four-dimensional space.
Starks, S. A.↗
Demonstration of short-haul aircraft aft noise reduction techniques on a twenty inch (50.8 cm) diameter fan, volume 1
Tests of a 20 inch diameter, low tip speed, low pressure ratio fan which investigated aft fan noise reduction techniques are reported. These techniques included source noise reduction features of selection of vane-blade ratio to reduce second harmonic noise, spacing effects, and lowering the Mach number through a vane row. Aft suppression features investigated included porosity effects, variable depth treatment, and treatment regenerated flow noise. Initial results and selected comparisons are presented.
Stimpert, D. L.↗