Search NASA⌕ Search

SEARCH · Search NASA

Results for “evaluation datasets”

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 667 records · Page 37

An Evaluation of Advanced Tools for Distributed Wind Turbine Performance Estimation: Preprint

We evaluate various classes of distributed wind turbine performance tools across two sites in the USA. The tools class ranges from the simple mass conservation model to coupled Reynolds Averaged Navier-Stokes (RANS) model, all initiated by the WIND Toolkit dataset. The resource estimation at the site is evaluated against measured data at the mast location. Taking a sample 100 kW wind turbine and constant losses, we evaluate Openwind, Continuum, and WindNinja tools and document Annual Energy Production (AEP) and time series statistics associated with the performance estimation of the wind turbine. Using a methodology that is consistent and unbiased across the three advance options currently available in the industry, we elaborate results at the two sample locations and discuss the probable sources of discrepancy in the AEP estimates. The discussion includes additional values these tools may bring into the energy assessment process to enhance the owners' confidence over the distributed wind power systems.

17 WIND ENERGY↗

Time-Based CAN Intrusion Detection Benchmark

Modern vehicles are complex cyber-physical systems made of hundreds of electronic control units (ECUs) that communicate over controller area networks (CANs). This inherited complexity has expanded the CAN attack surface by the injection of malicious messages that vary their time-based characteristics. To detect these malicious messages, time-based intrusion detection systems (IDS) have been proposed. However, time-based IDS are usually trained and tested on low-fidelity datasets with unrealistic labeled attacks. This makes difficult the task of evaluating, comparing, and validating IDS. Here we detail and benchmark four time-based IDS in a dataset with real and advanced attacks. We found that methods with strong assumptions regarding the distribution of inter-arrival times have lower performance than distribution agnostic based methods. In particular, distribution agnostic based methods outperform distribution based methods at least on $55\%$ in area under the precision-recall (AUC-PR) curve. Our results expand the body of knowledge of CAN time-based IDS by providing details of these methods and reporting their results when tested on datasets with real and advanced attacks. We describe limitations, open challenges, and how lessons learnt from this research can inform the design of deployable time-based IDS in modern vehicles.

Blevins, Deborah↗

SZ3: A Modular Framework for Composing Prediction-Based Error-Bounded Lossy Compressors

Today's scientific simulations require a significant reduction of data volume because of extremely large amounts of data they produce and the limited I/O bandwidth and storage space. Here, error-bounded lossy compression has been considered one of the most effective solutions to the above problem. In practice, however, the best-fit compression method often needs to be customized or optimized in particular because of diverse characteristics in different datasets and various user requirements on the compression quality and performance. In this paper, we address this issue with a novel modular, composable compression framework named SZ3. Our contributions are four-folds. (1) We develop SZ3 which features an innovative modular abstraction for the prediction-based compression framework, such that compression modules can be plugged in easily to create new compressors based on characteristics of data and user requirements. (2) We create a new compression pipeline by SZ3 for GAMESS data, which significantly improves the compression ratios over state-of-the-art compressors. (3) We develop an adaptive compression pipeline by SZ3 for APS data with minimal efforts, which leads to the best rate-distortion among all existing error-bounded lossy compressors for any bit-rate. (4) We compare the sustainability of SZ3 with leading error-bounded prediction-based compressors, and then demonstrate the necessity of diverse pipelines by integrating and evaluating several compression pipelines on diverse scientific datasets from multiple disciplines. Experiments show that SZ3 incurs very limited overhead in compressor integration and our customized compression pipelines lead to up to 20% improvement in compression ratios under the same data distortion, when compared with the best existing approach.

97 MATHEMATICS AND COMPUTING↗

Pulmonary Inflammatory Responses to Acute Meteorite Dust Exposures - to Acute Meteorite Dust Exposures - Exploration

New initiatives to begin lunar and martian colonization within the next few decades are illustrative of the resurgence of interest in space travel. One of NASA's major concerns with extended human space exploration is the inadvertent and repeated exposure to unknown dust. This highly interdisciplinary study evaluates both the geochemical reactivity (e.g. iron solubility and acellular reactive oxygen species (ROS) generation) and the relative toxicity (e.g. in vitro and in vivo pulmonary inflammation) of six meteorite samples representing either basalt or regolith breccia on the surface of the Moon, Mars, and Asteroid 4Vesta. Terrestrial mid-ocean ridge basalt (MORB) is also used for comparison. The MORB demonstrated higher geochemical reactivity than most of the meteorite samples but caused the lowest acute pulmonary inflammation (API). Notably, the two martian meteorites generated some of the highest API but only the basaltic sample is significantly reactive geochemically. Furthermore, while there is a correlation between a meteorite's soluble iron content and its ability to generate acellular ROS, there is no direct correlation between a particle's ability to generate ROS acellularly and its ability to generate API. However, assorted in vivo API markers did demonstrate strong positive correlations with increasing bulk Fenton metal content. In summary, this comprehensive dataset allows for not only the toxicological evaluation of astromaterials but also clarifies important correlations between geochemistry and health.

Harrington, A. D.↗

High throughput calculations for a dataset of bilayer materials

Bilayer materials made of 2D monolayers are emerging as new systems creating diverse opportunities for basic research and applications in optoelectronics, thermoelectrics, and topological science among others. Herein, we present a computational bilayer materials dataset containing 760 structures with their structural, electronic, and transport properties. Different stacking patterns of each bilayer have been framed by analyzing their monolayer symmetries. Density functional theory calculations including van der Waals interactions are carried out for each stacking pattern to evaluate the corresponding ground states, which are correctly identified for experimentally synthesized transition metal dichalcogenides, graphene, boron nitride, and silicene. Binding energies and interlayer charge transfer are evaluated to analyze the interlayer coupling strength. Our dataset can be used for materials screening and data-assisted modeling for desired thermoelectric or optoelectronic applications.

36 MATERIALS SCIENCE↗

Spectrally Simplified Approach for Leveraging Legacy Geostationary Oceanic Observations

The use of multispectral geostationary satellites to study aquatic ecosystems improves the temporal frequency of observations and mitigates cloud obstruction, but no operational capability presently exists for the coastal and inland waters of the United States. The Advanced Baseline Imager (ABI) on the current iteration of the Geostationary Operational Environmental Satellites, termed the R Series (GOES-R), however, provides sub-hourly imagery and the opportunity to overcome this deficit and to leverage a large repository of existing GOES-R aquatic observations. The fulfillment of this opportunity is assessed herein using a spectrally simplified, two-channel aquatic algorithm consistent with ABI wave bands to estimate the diffuse attenuation coefficient for photosynthetically available radiation, K(d)(PAR). First, an in situ ABI dataset was synthesized using a globally representative dataset of above- and in-water radiometric data products. Values of K(d)(PAR) were estimated by fitting the ratio of the shortest and longest visible wave bands from the in situ ABI dataset to coincident, in situ K(d)(PAR) data products. The algorithm was evaluated based on an iterative cross-validation analysis in which 80% of the dataset was randomly partitioned for fitting and the remaining 20% was used for validation. The iteration producing the median coefficient of determination (R2) value (0.88) resulted in a root mean square difference of 0.319 m−1, or 8.5% of the range in the validation dataset. Second, coincident mid-day images of central and southern California from ABI and from the Moderate Resolution Imaging Spectroradiometer (MODIS) were compared using Google Earth Engine (GEE). GEE default ABI reflectance values were adjusted based on a near infrared signal. Matchups between the ABI and MODIS imagery indicated similar spatial variability (R2 = 0.60) between ABI adjusted blue-to-red reflectance ratio values and MODIS default diffuse attenuation coefficient for spectral downward irradiance at 490 nm, K(d)(490), values. This work demonstrates that if an operational capability to provide- ABI aquatic data products was realized, the spectral configuration of ABI would potentially support a sub-hourly, visible aquatic data product that is applicable to water-mass tracing and physical oceanography research.

Advanced Baseline Imager↗

Global Assimilation of Multi-Sensor Snow Observations for Improved Characterization of Snow Processes

Snow conditions on the land surface are recognized to be key components of the global hydrological cycle as they play a critical role in the determination of local and regional climate. In many mid-latitude and high-latitude regions, the seasonal water storage and associated spring snowmelt dominate the local hydrology. The contribution to the runoff and moisture conditions from snow is vital in supporting agriculture and in determining water resources management practices. Consequently, accurate characterization of snow properties becomes important for both end-use applications and weather and climate research. Recently a joint effort between the u.S. Air Force and NASA has enabled a blended, multi-sensor snow product known as the AFWA NASA Snow Algorithm (ANSA). This global snow dataset has been generated by utilizing the Earth Observation System (EOS) Moderate Resolution Imaging Spectroradiometer (MODIS) and Advanced Microwave Scanning Radiometer for EOS (AMSR-E) datasets. ANSA product includes estimates of snow cover extent, snow water equivalent (SWE) and SWE-derived snow depth fields. The MODIS-based products enable snow cover mappings under cloud-free conditions whereas the passive microwave data from AMSR-E provides measurements under cloudy conditions. These remotely-sensed snow observations are further augmented with the information from ground-based snow measurements through data fusion techniques. The resulting ANSA products are employed in the NASA Land Information System (LIS) data assimilation framework, which provides a comprehensive environment for integrating community land surface models, ground and satellite-based observations, and ensemble-based data assimilation tools. LIS incorporates the multisensor ANSA snow retrievals with the land surface model estimates to generate spatially and temporally continuous estimates of snow states, through data assimilation. A suite of experiments to assimilate ANSA snow cover, SWE and snow depth estimates with different land surface models in LIS are conducted and the resulting estimates of snow conditions are evaluated against a number of in-situ observational datasets, over several regions of the world. These evaluations are used to compare and contrast the advantages and disadvantages of these multi-sensor snow observations.

Kumar, Sujay↗

Augmenting Topic Finding in the NASA Aviation Safety Reporting System using Topic Modeling

Context: The NASA Aviation and Safety Reporting System (ASRS) provides various publications to the aviation community (including individual anonymous reports, Callback, Database Search Requests, Directline, and Alerting Messages). Key to these publications are the timely processing of new reports, which is currently done mostly manually by ASRS staff, and which the volume increases yearly. Aim: We investigate whether existing topic modelling techniques are suitable to ease some of the manual effort, and to enhance it with additional visual cues regarding the process of grouping, sense making and labeling incoming (and previous) reports. Method: We evaluate the applicability of WarpLDA topic modelling results combined with three visualization tools, the first two of which have been extended by us in this work for ASRS: Termite, TopicFlow, and LDAVis. Based on the identified limitations in these tools, we propose a methodology for improving them, and evaluate their outputs using ASRS as our test dataset. Results: The user interfaces of Termite, Topicflow and LDAVis were found insufficient for sense-making of the narratives. Moreover, concerns regarding the stability of results due to the inherent randomness of topic modelling, and the lack of a measurable approach for evaluation against the existing ASRS manual workflow were also noted. Conclusion: While many tools to topic modeling and visualization have been proposed, more work is necessary before they can be applied in practical situations to improve existing manual workflows. The methodology presented and applied in this work contribute towards this effort.

ASRS↗

Mortar: An Open Testbed for Portable Building Analytics

Access to large amounts of real-world data has long been a barrier to the development and evaluation of analytics applications for the built environment. Open datasets exist, but they are limited in their span (how much data is available) and context (what kind of data is available and how it is described). Evaluation of such analytics is also limited by how the analytics themselves are implemented, often using hard-coded names of building components, points and locations, or unique input data formats. To advance the methodology for how such analytics are implemented and evaluated, we present Mortar: an open testbed for portable building analytics, currently spanning 90 buildings and containing over 9.1 billion data points. All buildings in the testbed are described using Brick, a recently developed metadata schema, providing rich functional descriptions of building assets and subsystems. We also propose a simple architecture for writing portable analytics applications that are robust to the diversity of buildings and can configure themselves based on context. We demonstrate the utility of Mortar by implementing 11 applications from the literature.

47 OTHER INSTRUMENTATION↗

Nuclear Structure and Decay Data for A=149 Isobars

Here, experimental nuclear structure and decay data are evaluated for all the 17 known nuclides of mass 149 (Xe, Cs, Ba, La, Ce, Pr, Nd, Pm, Sm, Eu, Gd, Tb, Dy, Ho, Er, Tm, Yb). Detailed compiled and evaluated spectroscopic information is presented for each reaction and decay dataset, and recommended values are provided for level properties, α, β and γ radiations, and other spectroscopic parameters, based on an evaluation of all the available experimental data for A=149 isobaric nuclides. Although large amounts of nuclear spectroscopic data are available for nuclides of A=149, yet large gaps in knowledge exist, as described below. For the lowest atomic number nuclide 149 Xe, only the isotopic identification has been made, with no data for its ground-state half-life. For 149 Cs, 149 Tm and 149 Yb information is available for only the respective ground states. For 149 Ba, 149 La and 149 Er, limited data exist for excited states. Many of the decay schemes of radioactive nuclei of A=149 are considered as incomplete, either due to large energy differences between the highest observed excited states in daughter nuclides and the respective Q-values, or due to the lack of confirmed γ-ray data, as listed below: 149 Cs → 149 Ba, 149 Ba → 149 La, 149 La → 149 Ce, 149 Ce → 149 Pr, 149 Pr → 149 Nd, 149 Tb(4.17 min) → 149 Gd, 149 Ho(21.0 s and 56 s) → 149 Dy, 149 Er(4 s and 9.6 s) → 149 Ho, and 149 Tm → 149 Er. No data exist for the decay of 149 Yb to 149 Tm. Data for half-lives of the excited states in this mass chain are generally lacking as given below by the number of excited levels of known half-life / approximate number of known levels in a nuclide: 2/17 for 149 Ba, 0/18 for 149 La, 3/53 for 149 Ce, 3/44 for 149 Pr, 17/110 for 149 Nd, 9/90 for 149 Pm, 10/210 for 149 Sm, 2/125 for 149 Eu, 6/270 for 149 Gd, 5/200 for 149 Tb, 3/80 for 149 Dy, 3/90 for 149 Ho, and 3/14 for 149 Er. This work supersedes earlier evaluations of A=149 nuclides published by 2004Si16, 1994Si18, 1985Sz01 and 1976Ho17.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

Influence of Lake Ice Biases in Reanalysis Data on Downscaled Climate Simulations over the Great Lakes Region

This data package contains observation-based and model-simulated datasets (all provided in NetCDF format) for evaluating how wintertime lake-ice representation affects regional weather and climate over the Laurentian Great Lakes (freshwater lake ecosystem) during the high–ice-cover winter of 2009. The observational component includes: (1) Stage IV gridded precipitation at 4 km, hourly resolution for January–February 2009 over the Great Lakes region (radar–gauge multisensor precipitation analyses); (2) Great Lakes Surface Environmental Analysis (GLSEA) satellite-derived lake-ice coverage at 1.3 km, daily resolution for the 2009 winter months, providing ice coverage over Lakes Superior, Michigan, Huron, Erie, and Ontario; and (3) in situ measurements at the Standard Rock site on Lake Superior from the Great Lakes Evaporation Network (GLEN) at hourly resolution, including near-surface atmospheric variables and sensible and latent heat fluxes (air–lake exchange) at a fixed point location. The modeling component provides corresponding fields from two simulations, both archived at 4 km, hourly resolution: a standalone Weather Research Forecasting model (WRF) run driven by the European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis 5 (ERA5), and a two-way coupled model using WRF and the Finite Volume Community Ocean Model (WRF-FVCOM, a 3-D hydrodynamic lake model). These outputs include variables relevant to air–lake interaction and lake-effect processes (e.g., near-surface temperature, humidity, wind, precipitation, and surface turbulent fluxes), enabling direct comparison with the observational datasets. Users can analyze and visualize these NetCDF files with common tools such as Python (e.g., xarray, netCDF4, numpy, pandas), NCO/CDO, Panoply, or ncview; NetCDF variables can also be converted to other formats (e.g., CSV, GeoTIFF) using these utilities.

EARTH SCIENCE > ATMOSPHERE > ATMOSPHERIC TEMPERATU↗

REMODEL: Rethinking Deep CNN Models to Detect and Count on a NeuroSynaptic System

In this work, we perform analysis of detection and counting of cars using a low-power IBM TrueNorth Neurosynaptic System. For our evaluation we looked at a publicly-available dataset that has overhead imagery of cars with context present in the image. The trained neural network for image analysis was deployed on the NS16e system using IBM's EEDN training framework. Through multiple experiments we identify the architectural bottlenecks present in TrueNorth system that does not let us deploy large neural network structures. Following these experiments we propose changes to CNN model to circumvent these architectural bottlenecks. The results of these evaluations have been compared with caffe-based implementations of standard neural networks that were deployed on a Titan-X GPU. Results showed that TrueNorth can detect cars from the dataset with 97.60% accuracy and can be used to accurately count the number of cars in the image with 69.04% accuracy. The car detection accuracy and car count (–/+ 2 error margin) accuracy are comparable to high-precision neural networks like AlexNet, GoogLeNet, and ResCeption, but show a manifold improvement in power consumption.

97 MATHEMATICS AND COMPUTING↗

Proxy-based Bayesian inversion of strain tensor data measured during well tests

Recent instrument developments have made it possible to measure the strain tensor caused by injecting or pumping fluid from aquifers or reservoirs, but the full value of these data is limited because the long runtimes of poroelastic forward models makes it impractical to use many inversion schemes. This limits the interpretation of strain data for managing the recovery of resources or storage of wastes in the subsurface. This paper describes a method of inverting deformation data using a poroelastic numerical simulator so the results can be used to manage reservoirs or aquifers. We developed a workflow designed to reduce the number of simulations sufficiently to make it feasible to use DREAMzs, an advanced Bayesian inversion method that translates the uncertainties from different sources into unbiased posterior parameter distributions and uncertainty envelopes around the field data. Using a KNN proxy model for the poroelastic simulator is key to reducing the overall computations, and the workflow includes a strategy for ensuring the proxy model results converge on the results from the simulator. The workflow is tested using an idealized example that verifies the ability to correctly identify parameters and characterize noise used to perturb the data. Field data from an injection test at an oil reservoir near Tulsa, Oklahoma, are also used to evaluate the efficacy of the workflow with a real dataset. The workflow identified 265 history matching solutions out of 1240 total simulation runs (21% acceptance ratio), where the results were used to characterize posterior parameter distribution and evaluate the prediction uncertainty. Furthermore, this workflow is significant because it enables strain tensor, or other geomechanical measurements to be interpreted to guide decision-making during energy and environmental processes in the subsurface.

42 ENGINEERING↗

Web-based Preprocessing and Visualization of 3D FIB Tomography Data for Nuclear Fuel Characterization

Three-dimensional (3D) focused ion beam (FIB) tomography enables reconstruction of internal nuclear fuel features that can't be fully evaluated through surface imaging alone. This capability supports characterization of fuel constituents and defects under thermal and irradiation conditions relevant to microreactor development. However, large tomography datasets can create data-handling, loading, and visualization challenges, especially when image-stack preparation and file conversion must be completed with separate tools. The Computational Ultraspatial Tomography Toolkit for High-Resolution Object Analysis Tools (CUTTRHOAT) is an open-source web application being developed to display FIB tomography datasets available through the Nuclear Research Data System (NRDS). The current alpha version requires prepared HDF5 datasets and has limited integrated data-preparation capabilities. This project improves CUTTHROAT by adding dataset-folder selection, automatic input detection, dataset scanning, missing-slice identification, blank-slice insertion, and image-stack-to-HDF5 conversion. Two applications will be compared: the baseline CUTTHROAT alpha workflow and the updated application containing the integrated data-handling and preprocessing functions. Evaluation will consider dataset detection accuracy, conversion success, loading time, rendering responsiveness, application stability, and user interaction. Preliminary results demonstrate successful loading of existing HDF5 files and converted image stacks, while testing also identified performance reductions caused by excessive blank-slice generation. The updated workflow reduces reliance on external preparation tools and supports more direct movement from image stacks to color-code 3D visualization. Future work includes refining missing-slice handling, integrating additional preprocessing functions, like a denoising feature, parsing TIFF metadata for automatic voxel scaling, and adding manual X, Y, and Z voxel-spacing inputs for PNG and JPEG.

36 - MATERIALS SCIENCE↗

Microstructure Segmentation with Deep Learning Encoders Pre-Trained on a Large Microscopy Dataset

This study examined the improvement of microscopy segmentation accuracy by transfer learning from a large dataset of microscopy images called MicroNet. Many neural network encoder architectures, including VGG, Inception, and ResNet, were trained on over 100,000 labelled microscopy images from 54 classes. These pre-trained encoders were then embedded into multiple segmentation architectures including U-Net and DeepLabV3+ to evaluate segmentation performance on newly created benchmark microscopy datasets. Compared to ImageNet pre-training, models pre-trained on MicroNet generalized better to out-of-distribution micrographs taken under different imaging and sample conditions and were more accurate with less training data. When training with only a single Ni-superalloy image, pre-training on MicroNet produced a 72.2 percent reduction in relative segmentation error. These results suggest that transfer learning from large in-domain datasets generate models with learned feature representations that are more useful for downstream tasks and will likely improve any microscopy image analysis technique that can leverage pre-trained encoders.

machine learning↗

ARM Climate Modeling Best Estimate Data - A new data product for climate modelers

This paper provides an overview of a new data product, named the Climate Modeling Best Estimate (CMBE) dataset, developed by the U.S. Department of Energy (DOE)’s Atmospheric Radiation Measurement (ARM) Program in order to better serve the need of climate model developers and encourage greater use of ARM data by modelers. The CMBE dataset contains those quantities that are often used in model evaluation and reflect unique ARM measurements of clouds and radiation (e.g., cloud occurrence, liquid water path, and surface radiative fluxes) from the highest quality data that ARM has for many years. The data are averaged over one hour period, which is comparable to a typical temporal resolution used in climate model output. They are currently available at five ARM Climate Research Facility (ACRF) sites located at the Southern Great Plains, North Slope of Alaska, and Tropic Western Pacific, and can be obtained from the ACRF data archive. The long-term continuous ARM data provide invaluable information to improve our understanding of the interaction between clouds and radiation and a solid observational basis for model validation and improvement. This paper shows some examples to demonstrate its unique values in studies of cloud processes, climate variability and change, and climate modeling. Plans for future enhancements of the CMBE product are also discussed.

54 ENVIRONMENTAL SCIENCES↗

WE-DE-207B-12: Scatter Correction for Dedicated Cone Beam Breast CT Based On a Forward Projection Model

Purpose: The image quality of dedicated cone-beam breast CT (CBBCT) is fundamentally limited by substantial x-ray scatter contamination, resulting in cupping artifacts and contrast-loss in reconstructed images. Such effects obscure the visibility of soft-tissue lesions and calcifications, which hinders breast cancer detection and diagnosis. In this work, we propose to suppress x-ray scatter in CBBCT images using a deterministic forward projection model. Method: We first use the 1st-pass FDK-reconstructed CBBCT images to segment fibroglandular and adipose tissue. Attenuation coefficients are assigned to the two tissues based on the x-ray spectrum used for imaging acquisition, and is forward projected to simulate scatter-free primary projections. We estimate the scatter by subtracting the simulated primary projection from the measured projection, and then the resultant scatter map is further refined by a Fourier-domain fitting algorithm after discarding untrusted scatter information. The final scatter estimate is subtracted from the measured projection for effective scatter correction. In our implementation, the proposed scatter correction takes 0.5 seconds for each projection. The method was evaluated using the overall image spatial non-uniformity (SNU) metric and the contrast-to-noise ratio (CNR) with 5 clinical datasets of BI-RADS 4/5 subjects. Results: For the 5 clinical datasets, our method reduced the SNU from 7.79% to 1.68% in coronal view and from 6.71% to 3.20% in sagittal view. The average CNR is improved by a factor of 1.38 in coronal view and 1.26 in sagittal view. Conclusion: The proposed scatter correction approach requires no additional scans or prior images and uses a deterministic model for efficient calculation. Evaluation with clinical datasets demonstrates the feasibility and stability of the method. These features are attractive for clinical CBBCT and make our method distinct from other approaches. Supported partly by NIH R21EB019597, R21CA134128 and R01CA195512.The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

60 APPLIED LIFE SCIENCES↗

On the Selection of Dimension Reduction Techniques for Scientific Applications

Many dimension reduction methods have been proposed to discover the intrinsic, lower dimensional structure of a high-dimensional dataset. However, determining critical features in datasets that consist of a large number of features is still a challenge. In this paper, through a series of carefully designed experiments on real-world datasets, we investigate the performance of different dimension reduction techniques, ranging from feature subset selection to methods that transform the features into a lower dimensional space. We also discuss methods that calculate the intrinsic dimensionality of a dataset in order to understand the reduced dimension. Using several evaluation strategies, we show how these different methods can provide useful insights into the data. These comparisons enable us to provide guidance to a user on the selection of a technique for their dataset.

97 MATHEMATICS AND COMPUTING↗