Results for “Automatic Labeling” — Page 3

DOE OSTI2020

A semi-supervised machine learning detector for physics events in tokamak discharges

Databases of physics events have been used in various fusion research applications, including the development of scaling laws and disruption avoidance algorithms, yet they can be time-consuming and tedious to construct. This paper presents a novel application of the label spreading semi-supervised learning algorithm to accelerate this process by detecting distinct events in a large dataset of discharges, given few manually labeled examples. A high detection accuracy (> 85%) for H-L back transitions and initially rotating locked modes is demonstrated on a dataset of hundreds of discharges from DIII-D with manually identified events for which only 3 discharges are initially labeled by the user. Lower yet reasonable performance (~75%) is also demonstrated for the core radiative collapse, an event with a much lower prevalence in the dataset. Additionally, analysis of the performance sensitivity indicates that the same set of algorithmic parameters is optimal for each event. Furthermore, this suggests that the method can be applied to detect a variety of other events not included in this paper, given that the event is well described by a set of 0D signals robustly available on many discharges. Procedures for analysis of new events are demonstrated, showing automatic event detection with increasing fidelity as the user strategically adds manually labeled examples. Detections on Alcator C-Mod and EAST are also shown, demonstrating the potential for this to be used on a multi-tokamak dataset.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2019

Sequential Learning with Active Partial Labeling for Building Metadata

Modern buildings are instrumented with thousands of sensing and control points. The ability to automatically extract the physical context of each point, e.g., the type, location, and relationship with other points, is the key to enabling building analytics at scale. However, this process is costly as it usually requires domain expertise with a deep understanding of the building system and its point naming scheme. In this study, we aim to reduce the human effort required for mapping sensors to their context, i.e., metadata mapping. We formulate the problem as a sequential labeling process and use the conditional random field to exploit the regular and dependent structures observed in the metadata. We develop a suite of active learning strategies to adaptively select the most informative subsequences in point names for human labeling, which significantly reduces the inputs from domain experts.We evaluated our approach on three different buildings and observed encouraging performance in metadata mapping from the proposed solution.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2013

Automated Tracing and Segmentation Tool for Migrating Neurons in 4D Confocal Imagery

Accurate tracing and segmentation of subcellular components of migrating neurons in confocal image sequences are prerequisite steps in many neurobiology studies to understand the biological machinery behind the movement of developing neurons. In this paper, we present an automated tracking, tracing, and segmentation tool for soma, leading, and trailing process of migrating neurons in time-lapse image stacks acquired with a confocal fluorescence microscope. In our approach, we first localize each neuron in the maximum intensity projection of the first frame using manual labeling of the soma and end points of the leading and trailing process. By using each soma position at the first frame, we automatically track the somas in rest of the frames. Then, leading and trailing process are traced in each frame from the soma center to the labeled end tip of the process by using fast marching algorithm. Finally, the soma, leading and trailing processes of each neuron are segmented by using the soma center and traces as seed points, and their boundaries are separated from each other. Based on qualitative results, we demonstrate the capability to automatically track, trace, and segment the soma, leading, and trailing processes of a migrating neuron with minimal user input.

Karakaya, Mahmut↗

DOE OSTI2021

Metabolic Source Isotopic Pair Labeling and Genome-Wide Association Are Complementary Tools for the Identification of Metabolite-Gene Associations in Plants

The optimal extraction of information from untargeted metabolomics analyses is a continuing challenge. Here, we describe an approach that combines stable isotope labeling, liquid chromatography– mass spectrometry (LC–MS), and a computational pipeline to automatically identify metabolites produced from a selected metabolic precursor. Here, we identified the subset of the soluble metabolome generated from phenylalanine (Phe) in Arabidopsis thaliana, which we refer to as the Phe-derived metabolome (FDM) In addition to identifying Phe-derived metabolites present in a single wild-type reference accession, the FDM was established in nine enzymatic and regulatory mutants in the phenylpropanoid pathway. To identify genes associated with variation in Phe-derived metabolites in Arabidopsis, MS features collected by untargeted metabolite profiling of an Arabidopsis diversity panel were retrospectively annotated to the FDM and natural genetic variants responsible for differences in accumulation of FDM features were identified by genome-wide association. Large differences in Phe-derived metabolite accumulation and presence/absence variation of abundant metabolites were observed in the nine mutants as well as between accessions from the diversity panel. Many Phe-derived metabolites that accumulated in mutants also accumulated in non-Col-0 accessions and was associated to genes with known or suspected functions in the phenylpropanoid pathway as well as genes with no known functions. Overall, we show that cataloguing a biochemical pathway’s products through isotopic labeling across genetic variants can substantially contribute to the identification of metabolites and genes associated with their biosynthesis.

09 BIOMASS FUELS↗

DOE OSTI2019

Passively-Powered Adaptively-Located Flexible Hybrid Sensors Final Report

PARC, a Xerox Company, is developing a low-cost system of peel-and-stick wireless sensors that will enable widespread building environment sensor deployment with the potential to deliver up to 30% energy savings. The system is embodied by a set of RF hubs that provide power to the automatically located sensor nodes, and relays data wirelessly to the building management system (BMS). The sensor nodes are flexible electronic labels powered by rectified RF energy transmitted by a RF hub and can contain multiple printed and conventional sensors. The system design overcomes limitations in wireless sensors related to power delivery, lifetime, and cost by eliminating batteries and photovoltaic devices. The sensor label can be equipped with a variety of printed and conventional sensors for building energy optimization, including lighting, occupancy, temperature, humidity, motion, and air quality. A key advantage of this system is its ability to automatically locate multiple sensor nodes to within 0.5 m (at a 5-m read distance) for simplified commissioning, as well as its interoperability with a wide range of existing BMS hardware and software. This enables automatic sensor reconfiguration and recommissioning, which is an important cost reduction driver. Moreover, the sensors are compatible with low-cost-, high-throughput roll-to-roll manufacturing, further reducing system costs. Upon successfully developing, manufacturing and deploying the system with optimized control, it can lead to annual primary energy savings >280 TBtu in offices, and up to ~1850 TBtu in combined offices and residences. The technology is based on PARC innovations in small antenna design, efficient RF energy capture, and flexible electronics. PARC is a leader in flexible hybrid integration similar to what is used in current RFID tags, which will provide a low-cost system in a flexible form factor. Our team member, Energy ETC, is a leader in supplier-agnostic BMS deployments, and will design the commissioning and deployment procedures to maximize system interoperability. The project will result in a demonstrator that will provide temperature and humidity data and will be wirelessly integrated into PARC’s BMS.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2022

EXSCLAIM!

Due to recent improvements in image resolution and acquisition speed, materials microscopy is experiencing an explosion of published imaging data. The standard publication format, while sufficient for traditional data ingestion scenarios where a select number of images can be critically examined and curated manually, is not conducive tolarge-scale data aggregation or analysis, hindering data sharing and reuse. Most images in publications are presented as components of a larger figure with their explicit context buried in the main body or caption text, so even if aggregated, collections of images with weak or no digitized contextual labels have limited value. To solve the problem of curating labeled microscopy data from literature, we introduce the EXSCLAIM! Python toolkit for the automatic EXtraction, Separation, and Caption-based natural Language Annotation of IMages from scientific literature. The software is implemented through a three part pipeline: the JournalScraper, which searches the web and downloads figures and captions based on a user provided query, the CaptionDistributor, which separates caption text based on the subfigure each portion of the caption refers to, and the FigueSeparator, which separates figures into component subfigures and extracts other visual information. Also included is a Django user interface for exploring the resulting dataset.

CHAN, MARIA↗

DOE OSTI2023

Deep learning-enabled natural language processing to identify directional pharmacokinetic drug–drug interactions

Background. During drug development, it is essential to gather information about the change of clinical exposure of a drug (object) due to the pharmacokinetic (PK) drug-drug interactions (DDIs) with another drug (precipitant). While many natural language processing (NLP) methods for DDI have been published, most were designed to evaluate if (and what kind of) DDI relationships exist in the text, without identifying the direction of DDI (object vs. precipitant drug). Here we present a method for the automatic identification of the directionality of a PK DDI from literature or drug labels. Methods. We reannotated the Text Analysis Conference (TAC) DDI track 2019 corpus for identifying the direction of a PK DDI and evaluated the performance of a fine-tuned BioBERT model on this task by following the training and validation steps prespecified by TAC. Results. This initial attempt showed the model achieved an F-score of 0.82 in identifying sentences as containing PK DDI and an F-score of 0.97 in identifying object versus precipitant drugs in those sentences. Discussion and conclusion. Despite a growing list of NLP methods for DDI extraction, most of them use a common set of corpora to perform general purpose tasks (e.g., classifying a sentence into one of several fixed DDI categories). There is a lack of coordination between the drug development and biomedical informatics method development community to develop corpora and methods to perform specific tasks (e.g., extract clinical exposure changes due to PK DDI). We hope that our effort can encourage such a coordination so that more “fit for purpose” NLP methods could be developed and used to facilitate the drug development process.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2021

Open Data and Deep Semantic Segmentation for Automated Extraction of Building Footprints

Advances in machine learning and computer vision, combined with increased access to unstructured data (e.g., images and text), have created an opportunity for automated extraction of building characteristics, cost-effectively, and at scale. These characteristics are relevant to a variety of urban and energy applications, yet are time consuming and costly to acquire with today’s manual methods. Several recent research studies have shown that in comparison to more traditional methods that are based on features engineering approach, an end-to-end learning approach based on deep learning algorithms significantly improved the accuracy of automatic building footprint extraction from remote sensing images. However, these studies used limited benchmark datasets that have been carefully curated and labeled. How the accuracy of these deep learning-based approach holds when using less curated training data has not received enough attention. The aim of this work is to leverage the openly available data to automatically generate a larger training dataset with more variability in term of regions and type of cities, which can be used to build more accurate deep learning models. In contrast to most benchmark datasets, the gathered data have not been manually curated. Thus, the training dataset is not perfectly clean in terms of remote sensing images exactly matching the ground truth building’s foot-print. A workflow that includes data pre-processing, deep learning semantic segmentation modeling, and results post-processing is introduced and applied to a dataset that include remote sensing images from 15 cities and five counties from various region of the USA, which include 8,607,677 buildings. The accuracy of the proposed approach was measured on an out of sample testing dataset corresponding to 364,000 buildings from three USA cities. The results favorably compared to those obtained from Microsoft’s recently released US building footprint dataset.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2017

Peel-and-Stick Sensors Powered by Directed RF Energy

PARC, a Xerox Company, is developing a low-cost system of peel-and-stick wireless sensors that will enable widespread building environment sensor deployment with the potential to deliver up to 30% energy savings. The system is embodied by a set of RF hubs that provide power to automatically located sensor nodes, and relay data wirelessly to the building management system (BMS). The sensor nodes are flexible electronic labels powered by rectified RF energy transmitted by an RF hub and can contain multiple printed and conventional sensors. The system design overcomes limitations in wireless sensors related to power delivery, lifetime, and cost by eliminating batteries and photovoltaic devices. Sensor localization is performed automatically by the inclusion of a programmable multidirectional antenna array in the RF hub. Comparison of signal strengths while the RF beam is swept allows for sensor localization, reducing installation effort and enabling automatic recommissioning of sensors that have been relocated, overcoming a significant challenge in building operations. PARC has already demonstrated wireless power and temperature data transmission up to a distance of 20m with less than one minute between measurements, using power levels well within the FCC regulation limits in the 902-928 MHz ISM band. The sensor’s RF energy harvesting antenna achieves high performance with dimensions below 5cm x 9cm

Lalau-Keraly, Christopher↗

DOE OSTI2017

PEEL-AND-STICK SENSORS POWERED BY DIRECTED RF ENERGY

PARC, a Xerox Company, is developing a low-cost system of peel-and-stick wireless sensors that will enable widespread building environment sensor deployment with the potential to deliver up to 30% energy savings. The system is embodied by a set of RF hubs that provide power to automatically located sensor nodes, and relay data wirelessly to the building management system (BMS). The sensor nodes are flexible electronic labels powered by rectified RF energy transmitted by an RF hub and can contain multiple printed and conventional sensors. The system design overcomes limitations in wireless sensors related to power delivery, lifetime, and cost by eliminating batteries and photovoltaic devices. Sensor localization is performed automatically by the inclusion of a programmable multidirectional antenna array in the RF hub. Comparison of signal strengths while the RF beam is swept allows for sensor localization, reducing installation effort and enabling automatic recommissioning of sensors that have been relocated, overcoming a significant challenge in building operations. PARC has already demonstrated wireless power and temperature data transmission up to a distance of 20m with less than one minute between measurements, using power levels well within the FCC regulation limits in the 902-928 MHz ISM band. The sensor’s RF energy harvesting antenna achieves high performance with dimensions below 5cm x 9cm.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2017

RF Energy Harvesting Peel-and-Stick Sensors

PARC, a Xerox Company, is developing a low-cost system of peel-and-stick wireless sensors that will enable widespread building environment sensor deployment with the potential to deliver up to 30% energy savings. The system is embodied by a set of RF hubs that provide power to the automatically located sensor nodes, and relays data wirelessly to the building management system (BMS). The sensor nodes are flexible electronic labels powered by rectified RF energy transmitted by a RF hub and can contain multiple printed and conventional sensors. The system design overcomes limitations in wireless sensors related to power delivery, lifetime, and cost by eliminating batteries and photovoltaic devices. The sensor localization is performed automatically by the inclusion of a programmable multidirectional antenna array in the RF hub. Comparison of signal strengths when the RF beam is swept allows for sensor localization, further reducing installation effort and enabling automatic recommissioning of sensors that have been relocated, overcoming a significant challenge in building operations. PARC has already demonstrated wireless power and temperature data transmission up to a distance of 20m with a duty cycle less than a minute between measurements, using power levels well within the FCC regulation limits in the 902-928 MHz ISM band. The sensor’s RF energy harvesting antenna dimensions was less than 5cmx9cm, demonstrating the possibility of small form factor for the sensor nodes.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

DOE OSTI2020

Root identification in minirhizotron imagery with multiple instance learning

In this study, multiple instance learning (MIL) algorithms to automatically perform root detection and segmentation in minirhizotron imagery using only image-level labels are proposed. Root and soil characteristics vary from location to location, and thus, supervised machine learning approaches that are trained with local data provide the best ability to identify and segment roots in minirhizotron imagery. However, labeling roots for training data (or otherwise) is an extremely tedious and time-consuming task. This paper aims to address this problem by labeling data at the image level (rather than the individual root or root pixel level) and train algorithms to perform individual root pixel level segmentation using MIL strategies. Three MIL methods (multiple instance adaptive cosine coherence estimator, multiple instance support vector machine, multiple instance learning with randomized trees) were applied to root detection and compared to non-MIL approaches. The results show that MIL methods improve root segmentation in challenging minirhizotron imagery and reduce the labeling burden. In our results, multiple instance support vector machine outperformed other methods. The multiple instance adaptive cosine coherence estimator algorithm was a close second with an added advantage that it learned an interpretable root signature which identified the traits used to distinguish roots from soil and did not require parameter selection.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2011

Quantitative Tracking of Isotope Flows in Proteomes of Microbial Communities

Stable isotope probing (SIP) has been used to track nutrient flows in microbial communities, but existing protein-based SIP methods capable of quantifying the degree of label incorporation into peptides and proteins have been demonstrated only by targeting usually less than 100 proteins per sample. Our method automatically (i) identifies the sequence of and (ii) quantifies the degree of heavy atom enrichment for thousands of proteins from microbial community proteome samples. These features make our method suitable for comparing isotopic differences between closely related protein sequences, and for detecting labeling patterns in low-abundance proteins or proteins derived from rare community members. The proteomic SIP method was validated using proteome samples of known stable isotope incorporation levels at 0.4%, 50%, and 98%. The method was then used to monitor incorporation of 15N into established and regrowing microbial biofilms. The results indicate organism-specific migration patterns from established communities into regrowing communities and provide insights into metabolism during biofilm formation. The proteomic SIP method can be extended to many systems to track fluxes of 13C or 15N in microbial communities. Molecular & Cellular Proteomics 10: 10.1074/mcp.M110.006049, 1–11, 2011.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2024

Automated annotation of scientific texts for ML-based keyphrase extraction and validation

Advanced omics technologies and facilities generate a wealth of valuable data daily; however, the data often lack the essential metadata required for researchers to find, curate, and search them effectively. The lack of metadata poses a significant challenge in the utilization of these data sets. Machine learning (ML)–based metadata extraction techniques have emerged as a potentially viable approach to automatically annotating scientific data sets with the metadata necessary for enabling effective search. Text labeling, usually performed manually, plays a crucial role in validating machine-extracted metadata. However, manual labeling is time-consuming and not always feasible; thus, there is a need to develop automated text labeling techniques in order to accelerate the process of scientific innovation. This need is particularly urgent in fields such as environmental genomics and microbiome science, which have historically received less attention in terms of metadata curation and creation of gold-standard text mining data sets. In this paper, we present two novel automated text labeling approaches for the validation of ML-generated metadata for unlabeled texts, with specific applications in environmental genomics. Our techniques show the potential of two new ways to leverage existing information that is only available for select documents within a corpus to validate ML models, which can then be used to describe the remaining documents in the corpus. The first technique exploits relationships between different types of data sources related to the same research study, such as publications and proposals. The second technique takes advantage of domain-specific controlled vocabularies or ontologies. In this paper, we detail applying these approaches in the context of environmental genomics research for ML-generated metadata validation. Our results show that the proposed label assignment approaches can generate both generic and highly specific text labels for the unlabeled texts, with up to 44% of the labels matching with those suggested by a ML keyword extraction algorithm.

96 KNOWLEDGE MANAGEMENT AND PRESERVATION↗

DOE OSTI2011

Quantitative tracking of isotope flows in proteomes of microbial communities

Stable isotope probing (SIP) has been used to track nutrient flows in microbial communities, but existing protein-based SIP methods capable of quantifying the degree of label incorporation into peptides and proteins have been demonstrated only by targeting usually less than 100 proteins per sample. Our method automatically (i) identifies the sequence of and (ii) quantifies the degree of heavy atom enrichment for thousands of proteins from microbial community proteome samples. These features make our method suitable for comparing isotopic differences between closely related protein sequences, and for detecting labeling patterns in low-abundance proteins or proteins derived from rare community members. The proteomic stable isotope probing (SIP) method was validated using proteome samples of known stable isotope incorporation levels at 0.4%, {approx}50%, and {approx}98%. The method was then used to monitor incorporation of 15N into established and regrowing microbial biofilms. The results indicate organism-specific migration patterns from established into regrowing communities and provides insight into metabolism during biofilm formation. The SIP-proteomics method can be extended to many systems to track fluxes of 13C or 15N in microbial communities.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

A hybrid machine-learning approach for analysis of methane hydrate formation dynamics in porous media with synchrotron CT imaging

Fast multi-phase processes in methane hydrate bearing samples pose a challenge for quantitative micro-computed tomography study and experiment steering due to complex tomographic data analysis involving time-consuming segmentation procedures. This is because of the sample's multi-scale structure, which changes over time, low contrast between solid and fluid materials, and the large amount of data acquired during dynamic processes. Here, a hybrid approach is proposed for the automatic segmentation of tomographic data from time-resolved imaging of methane gas-hydrate formation in sandy granular media, which includes a deep-learning 3D U-Net model. To prepare a training dataset for the 3D U-Net, a technique to automate data labeling based on sample-specific information about the mineral matrix immobility and occasional fluid movement in pores is proposed. Automatic segmentation allowed for studying properties of the hydrate growth in pores, as well as dynamic processes such as incremental flow and redistribution of pore brine. Results of the quantitative analysis showed that for typical gas-hydrate stability parameters (100 bar methane pressure, 7°C temperature) the rate of formation is slow (less than 1% per hour), after which the surface area of contact between brine and gas increases, resulting in faster formation (2.5% per hour). Hydrate growth reaches the saturation point after 11 h of the experiment. Finally, the efficacy of the proposed segmentation scheme in on-the-fly automatic data analysis and experiment steering with zooming to regions of interest is demonstrated.

73 NUCLEAR PHYSICS AND RADIATION PHYSICS↗

DOE OSTI2021

Deep-learning-aided forward optical coherence tomography endoscope for percutaneous nephrostomy guidance

Percutaneous renal access is the critical initial step in many medical settings. In order to obtain the best surgical outcome with minimum patient morbidity, an improved method for access to the renal calyx is needed. In our study, we built a forward-view optical coherence tomography (OCT) endoscopic system for percutaneous nephrostomy (PCN) guidance. Porcine kidneys were imaged in our experiment to demonstrate the feasibility of the imaging system. Three tissue types of porcine kidneys (renal cortex, medulla, and calyx) can be clearly distinguished due to the morphological and tissue differences from the OCT endoscopic images. To further improve the guidance efficacy and reduce the learning burden of the clinical doctors, a deep-learning-based computer aided diagnosis platform was developed to automatically classify the OCT images by the renal tissue types. Convolutional neural networks (CNN) were developed with labeled OCT images based on the ResNet34, MobileNetv2 and ResNet50 architectures. Nested cross-validation and testing was used to benchmark the classification performance with uncertainty quantification over 10 kidneys, which demonstrated robust performance over substantial biological variability among kidneys. ResNet50-based CNN models achieved an average classification accuracy of 82.6%±3.0%. The classification precisions were 79%±4% for cortex, 85%±6% for medulla, and 91%±5% for calyx and the classification recalls were 68%±11% for cortex, 91%±4% for medulla, and 89%±3% for calyx. Interpretation of the CNN predictions showed the discriminative characteristics in the OCT images of the three renal tissue types. The results validated the technical feasibility of using this novel imaging platform to automatically recognize the images of renal tissue structures ahead of the PCN needle in PCN surgery.

Wang, Chen↗

DOE OSTI2020

Reinforcement learning based automated history matching for improved hydrocarbon production forecast

History matching aims to find a numerical reservoir model that can be used to predict the reservoir performance. An engineer and model calibration (data inversion) method are required to adjust various parameters/properties of the numerical model in order to match the reservoir production history. In this study, we develop deep neural networks within the reinforcement learning framework to achieve automated history matching that will reduce engineers’ efforts, human bias, automatically and intelligently explore the parameter space, and remove the need of large set of labeled training data. To that end, a fast-marching-based reservoir simulator is encapsulated as an environment for the proposed reinforcement learning. The deep neural-network-based learning agent interacts with the reservoir simulator within reinforcement learning framework to achieve the automated history matching. Reinforcement learning techniques, such as discrete Deep Q Network and continuous Deep Deterministic Policy Gradients, are used toth, used to train the learning agents. The continuous actions enable the Deep Deterministic Policy Gradients to explore more states at each iteration in a a learning episode; consequently, a better history matching is achieved using this algorithm as compared to Deep Q Network. For simplified dual-target composite reservoir models, the best history-matching performances of the discrete and continuous learning methods in terms of normalized root mean square errors are 0.0447 and 0.0038, respectively. Furthermore, our study shows that continuous action space achieved by the deep deterministic policy gradient drastically outperforms deep Q network.

42 ENGINEERING↗