Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “image recognition”

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 55 records · Page 3
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

Quantum Annealing for Real-World Machine Learning Applications

Optimizing the training of a machine learning pipeline is important for reducing training costs and improving model performance. One such optimizing strategy is quantum annealing, which is an emerging computing paradigm that has shown potential in optimizing the training of a machine learning model. The implementation of a physical quantum annealer has been realized by D-Wave systems and is available to the research community for experiments. Recent experimental results on a variety of machine learning applications have shown interesting results especially under the conditions where the performance of classical machine learning techniques are limited such as limited training data and high dimensional features. This chapter explores the application of D-Wave’s quantum annealer for optimizing machine learning pipelines for real-world classification problems. We review the application domains on which a physical quantum annealer has been used to train machine learning classifiers. We discuss and analyze the experiments performed on the D-Wave quantum annealer for applications such as image recognition, remote sensing imagery, security, computational biology, biomedical sciences, and physics. We discuss the possible advantages and the problems for which quantum annealing is likely to be advantageous over classical computation.

Kumar nath, Rajdeep↗
DOE OSTI2023

Understanding hadronic interactions using advanced reconstruction techniques

ProtoDUNE-SP served as the prototype of the future Deep Underground Neutrino Experiment (DUNE). With a total liquid argon mass of 0.77 kt, it stood as the most extensive monolithic single-phase Liquid Argon Time Projection Chamber (LArTPC) ever constructed. Strategically located and operated at CERN, ProtoDUNE-SP benefited from a specialized charged-particle test beam, offering a momentum range of 0.3 - 7 GeV/c. This setup provided a unique opportunity to conduct in-depth studies on hadronic interactions within argon. Hadronic interactions play a fundamental role in neutrino physics, particularly in the intricacies of neutrino detection. We depend on analyzing the outcomes of these interactions to accurately determine both the flavor and energy of the interacting neutrinos. Pions, as one of the primary byproducts of neutrino interactions, are crucial for understanding the overall dynamics and kinematics of these processes. Accurately characterizing and understanding the interaction of pions with argon can significantly enhance the precision of neutrino simulations and measurements.Being a Liquid Argon Time Projection Chamber (LArTPC), ProtoDUNE-SP is distinguished by its ability to produce high-definition images of charged particles as they traverse through the detector's active volume. Yet, accurately reconstructing these particle interactions and determining their kinematic attributes remains a challenging task. The successes of deep learning in diverse domains, especially in image recognition, provide a promising approach for addressing this challenge in ProtoDUNE. This thesis discusses a measurement of the Piplus - argon inelastic cross section in the energy range of 2400 to 3000 MeV, using data taken by protoDUNE during the fall of 2018. Additionally, panoptic segmentation, a machine learning technique, is introduced and validated through its application in the reconstruction of the neutral pion rest mass. The aim is to showcase how these advanced methods can enhance the quality of event reconstruction.

Sarasty Segura, Carlos Eduardo↗
DOE OSTI2023

Coarse-to-fine Task-driven Inpainting for Geoscience Images

The processing and recognition of geoscience images have wide applications. Most of existing researches focus on understanding the high-quality geoscience images by assuming that all the images are clear. However, in many real-world cases, the geoscience images might contain occlusions during the image acquisition. This problem actually implies the image inpainting problem in computer vision and multimedia. As far as we know, all the existing image inpainting algorithms learn to repair the occluded regions for a better visualization quality, they are excellent for natural images but not good enough for geoscience images, and they never consider the following geoscience task when developing inpainting methods. Here, this paper aims to repair the occluded regions for a better geoscience task performance and advanced visualization quality simultaneously, without changing the current deployed deep learning based geoscience models. Because of the complex context of geoscience images, we propose a coarse-to-fine encoder-decoder network with the help of designed coarse-to-fine adversarial context discriminators to reconstruct the occluded image regions. Due to the limited data of geoscience images, we propose a MaskMix based data augmentation method, which augments inpainting masks instead of augmenting original images, to exploit the limited geoscience image data. The experimental results on three public geoscience datasets for remote sensing scene recognition, cross-view geolocation and semantic segmentation tasks respectively show the effectiveness and accuracy of the proposed method. The code is available at: https://github.com/HMS97/Task-driven-Inpainting.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2021

Deep learning for lipid droplet recognition in quantitative phase images

This library of Python code is used for performing semantic segmentation of images using 6 different machine learning methods. Five of the methods are implemented entirely within the scikit-learn framework. The Convolutional Neural Network (CNN) method requires Keras with a TensorFlow backend and generally uses a different set of scripts in order to perform the complete training and evaluation.

Sheneman, Lucas↗
DOE OSTI2020

Determination of the Maturation Status of Dendritic Cells by Applying Pattern Recognition to High-Resolution Images

The maturation or activation status of dendritic cells (DCs) directly correlates with their behavior and immunofunction. A common means to determine the maturity of dendritic cells is from high-resolution images acquired via scanning electron microscopy (SEM) or atomic force microscopy (AFM). While direct and visual, the determination has been made by directly looking at the images by researchers. Here we report a machine learning approach using pattern recognition in conjunction with cellular biophysical knowledge of dendritic cells to determine the maturation status of dendritic cells automatically. The determination from AFM images reaches 100% accuracy. The results from SEM images reaches 94.9%. The results demonstrate the accuracy of using machine learning for accelerating data analysis, extracting information, and drawing conclusions from high-resolution cellular images, paving the way for future applications requiring high-throughput and automation, such as cellular sorting and selection based on morphology, quantification of cellular structure, and DC-based immunotherapy.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Optical recognition of constructs using hyperspectral imaging and detection (ORCHID)

Abstract Challenges to deep sample imaging have necessitated the development of special techniques such as spatially offset optical spectroscopy to collect signals that have travelled through several layers of tissue. However, these techniques provide only spectral information in one dimension (i.e., depth). Here, we describe a general and practical method, referred to as Optical Recognition of Constructs Using Hyperspectral Imaging and Detection (ORCHID). The sensing strategy integrates (1) the spatial offset detection concept by computationally binning 2D optical data associated with digital offsets based on selected radial pixel distances from the excitation source; (2) hyperspectral imaging using tunable filter; and (3) digital image binding and collation. ORCHID is a versatile modality that is designed to collect optical signals deep inside samples across three spatial (X, Y, Z) as well as spectral dimensions. The ORCHID method is applicable to various optical techniques that exhibit narrow-band structures, from Raman scattering to quantum dot luminescence. Samples containing surface-enhanced Raman scattering (SERS)-active gold nanostar probes and quantum dots embedded in gel were used to show a proof of principle for the ORCHID concept. The resulting hyperspectral data cube is shown to spatially locate target emitting nanoparticle volumes and provide spectral information for in-depth 3D imaging.

47 OTHER INSTRUMENTATION↗
DOE OSTI2023

Sharing leaky-integrate-and-fire neurons for memory-efficient spiking neural networks

Spiking Neural Networks (SNNs) have gained increasing attention as energy-efficient neural networks owing to their binary and asynchronous computation. However, their non-linear activation, that is Leaky-Integrate-and-Fire (LIF) neuron, requires additional memory to store a membrane voltage to capture the temporal dynamics of spikes. Although the required memory cost for LIF neurons significantly increases as the input dimension goes larger, a technique to reduce memory for LIF neurons has not been explored so far. To address this, we propose a simple and effective solution, EfficientLIF-Net, which shares the LIF neurons across different layers and channels. Our EfficientLIF-Net achieves comparable accuracy with the standard SNNs while bringing up to ~4.3× forward memory efficiency and ~21.9× backward memory efficiency for LIF neurons. We conduct experiments on various datasets including CIFAR10, CIFAR100, TinyImageNet, ImageNet-100, and N-Caltech101. Furthermore, we show that our approach also offers advantages on Human Activity Recognition (HAR) datasets, which heavily rely on temporal information. The code has been released at https://github.com/Intelligent-Computing-Lab-Yale/EfficientLIF-Net.

60 APPLIED LIFE SCIENCES↗
DOE OSTI2020

Deep learning approaches for neural decoding across architectures and recording modalities

Decoding behavior, perception or cognitive state directly from neural signals is critical for brain–computer interface research and an important tool for systems neuroscience. In the last decade, deep learning has become the state-of-the-art method in many machine learning tasks ranging from speech recognition to image segmentation. The success of deep networks in other domains has led to a new wave of applications in neuroscience. In this article, we review deep learning approaches to neural decoding. Here, we describe the architectures used for extracting useful features from neural recording modalities ranging from spikes to functional magnetic resonance imaging. Furthermore, we explore how deep learning has been leveraged to predict common outputs including movement, speech and vision, with a focus on how pretrained deep networks can be incorporated as priors for complex decoding targets like acoustic speech or images. Deep learning has been shown to be a useful tool for improving the accuracy and flexibility of neural decoding across a wide range of tasks, and we point out areas for future scientific development.

59 BASIC BIOLOGICAL SCIENCES↗
DOE OSTI2021

Improving the Accuracy of Nearest-Neighbor Classification Using Principled Construction and Stochastic Sampling of Training-Set Centroids

A conceptually simple way to classify images is to directly compare test-set data and training-set data. The accuracy of this approach is limited by the method of comparison used, and by the extent to which the training-set data cover configuration space. Here we show that this coverage can be substantially increased using coarse-graining (replacing groups of images by their centroids) and stochastic sampling (using distinct sets of centroids in combination). We use the MNIST and Fashion-MNIST data sets to show that a principled coarse-graining algorithm can convert training images into fewer image centroids without loss of accuracy of classification of test-set images by nearest-neighbor classification. Distinct batches of centroids can be used in combination as a means of stochastically sampling configuration space, and can classify test-set data more accurately than can the unaltered training set. On the MNIST and Fashion-MNIST data sets this approach converts nearest-neighbor classification from a mid-ranking- to an upper-ranking member of the set of classical machine-learning techniques.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2020

Artificial Intelligence Application to D and D - 20492

As aging facilities across the DOE complex await decommissioning, there is an ongoing need to understand any changes in the structural conditions. Many of these facilities were built over 50 years ago and, in some cases, these facilities have gone beyond the expected operational lifetime. Many facilities have been placed in a state of 'cold and dark,' sitting unused and awaiting decommissioning. Especially challenging are the aging facilities that provide unique operational/production capabilities to support critical DOE missions and cannot be shut down. In any of these scenarios, the structural integrity of these facilities may become compromised as time passes. It is critical that adequate inspections be performed on a continual basis and that the data collected undergoes sufficient analysis to support timely identification of any new or worsening structural issues as well as prompt needed maintenance and repairs to maintain the facilities in a safe condition. In recent days, Artificial Intelligence (AI) [1] and its application to various domains are growing at fast speed. FIU is performing research in this area and exploring the associated technologies to solve nuclear decommissioning problems. Artificial intelligence refers to the capability of a program to autonomously act, react and adapt to the working environment. AI enables the machine to behave like humans and perform the cognitive functions such as 'learning' and 'problem solving'. AI systems gradually moving from traditional approaches (algorithms and expert systems) towards more efficient and advanced technologies (machine learning [1] and deep learning [2] [3]). AI is the study of algorithms and statistical models that is being used by computers to perform specific tasks without using explicit instructions. FIU is working to develop a pilot-scale infrastructure to implement structural health monitoring using AI technologies with focus on machine learning, deep learning. This research is focused on Computer Vision/Image Classification area of AI applications. This can also be expanded to other areas of AI related to Object Recognition and Character Recognition in images. In addition to utilizing existing data sets, FIU will collect and investigate image and video data using FIU test-bed mockups to monitor structural health of the facility. Resulting data will be processed and analyzed using machine learning/deep learning technologies. The proposed pilot system is intended to serve as a starting point to engage the DOE field sites on related data sets and their decision making needs. It is anticipated that proposed machine learning/deep learning technologies can be effectively employed using anomaly detection to solve EM challenges in surveillance and maintenance of the D and D facilities. FIU will work with research stakeholders to identify applications at various sites and other DOE facilities. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2023

Versatile recognition of graphene layers from optical images under controlled illumination through green channel correlation method

In this study, a simple yet versatile method is proposed for identifying the number of exfoliated graphene layers transferred on an oxide substrate from optical images, utilizing a limited number of input images for training, paired with a more traditional number of a few thousand well-published Github images for testing and predicting. Two thresholding approaches, namely the standard deviation-based approach and the linear regression-based approach, were employed in this study. The method specifically leverages the red, green, and blue color channels of image pixels and creates a correlation between the green channel of the background and the green channel of the various layers of graphene. This method proves to be a feasible alternative to deep learning-based graphene recognition and traditional microscopic analysis. The proposed methodology performs well under conditions where the effect of surrounding light on the graphene-on-oxide sample is minimum and allows rapid identification of the various graphene layers. Here, the study additionally addresses the functionality of the proposed methodology with nonhomogeneous lighting conditions, showcasing successful prediction of graphene layers from images that are lower in quality compared to typically published in literature. In all, the proposed methodology opens up the possibility for the non-destructive identification of graphene layers from optical images by utilizing a new and versatile method that is quick, inexpensive, and works well with fewer images that are not necessarily of high quality.

36 MATERIALS SCIENCE↗
DOE OSTI2022

Automatic threat recognition system and method using material disambiguation informed by physics in x-ray CT images of baggage

An automatic threat recognition (ATR) system is disclosed for scanning an article to recognize contraband items or items of interest contained within the article. The ATR system uses a CAT scanner to obtain a CT image scan of objects within the article, representing a plurality of 2D image slices of the article and its contents. Each 2D image slice includes information forming a plurality of voxels. The ATR system includes a computer and determines which voxels have a likelihood of representing materials of interest. It then aggregates those voxels to produce detected objects. The detected objects are further classified as items of interest vs. not of interest. The ATR system is based on learned parameters for a novel interaction of global and object context mechanisms. ATR system performance may be optimized by using jointly optimal global and object context parameters learned during training. The global context parameters may apply to the article as a whole and facilitate object detection. The object context parameters may apply to the individual object detections.

Paglieroni, David W.↗
DOE OSTI2022

Artificial Intelligence for imaging Cherenkov detectors at the EIC

Abstract Imaging Cherenkov detectors form the backbone of particle identification (PID) at the future Electron Ion Collider (EIC). Currently all the designs for the first EIC detector proposal use a dual Ring Imaging CHerenkov (dRICH) detector in the hadron endcap, a Detector for Internally Reflected Cherenkov (DIRC) light in the barrel, and a modular RICH (mRICH) in the electron endcap. These detectors involve optical processes with many photons that need to be tracked through complex surfaces at the simulation level, while for reconstruction they rely on pattern recognition of ring images. This proceeding summarizes ongoing efforts and possible applications of AI for imaging Cherenkov detectors at EIC. In particular we will provide the example of the dRICH for the AI-assisted design and of the DIRC for simulation and particle identification from complex patterns and discuss possible advantages of using AI.

Instruments & Instrumentation↗
DOE OSTI2020

Layer-Parallel Training of Deep Residual Neural Networks

Residual neural networks (ResNets) are a promising class of deep neural networks that have shown excellent performance for a number of learning tasks, e.g., image classification and recognition. Mathematically, ResNet architectures can be interpreted as forward Euler discretizations of a nonlinear initial value problem whose time-dependent control variables represent the weights of the neural network. Hence, training a ResNet can be cast as an optimal control problem of the associated dynamical system. For similar time-dependent optimal control problems arising in engineering applications, parallel-in-time methods have shown notable improvements in scalability. This paper demonstrates the use of those techniques for efficient and effective training of ResNets. The proposed algorithms replace the classical (sequential) forward and backward propagation through the network layers with a parallel nonlinear multigrid iteration applied to the layer domain. This adds a new dimension of parallelism across layers that is attractive when training very deep networks. From this basic idea, we derive multiple layer-parallel methods. The most efficient version employs a simultaneous optimization approach where updates to the network parameters are based on inexact gradient information in order to speed up the training process. Finally, using numerical examples from supervised classification, we demonstrate that the new approach achieves a training performance similar to that of traditional methods, but enables layer-parallelism and thus provides speedup over layer-serial methods through greater concurrency.

97 MATHEMATICS AND COMPUTING↗