SEARCH · Search NASA

Results for “Bayesian classification”

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.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 73 records · Page 4

All sources NASA NTRS DOE OSTI

DOE OSTI2023

Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial

On top of machine learning (ML) models, uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making by enabling sound risk assessment and management. The safety and reliability improvement of ML models empowered by UQ has the potential to significantly facilitate the broad adoption of ML solutions in high-stakes decision settings, such as healthcare, manufacturing, and aviation, to name a few. In this tutorial, we aim to provide a holistic lens on emerging UQ methods for ML models with a particular focus on neural networks and the applications of these UQ methods in tackling engineering design as well as prognostics and health management problems. Towards this goal, we start with a comprehensive classification of uncertainty types, sources, and causes pertaining to UQ of ML models. Next, we provide a tutorial-style description of several state-of-the-art UQ methods: Gaussian process regression, Bayesian neural network, neural network ensemble, and deterministic UQ methods focusing on spectral-normalized neural Gaussian process. Established upon the mathematical formulations, we subsequently examine the soundness of these UQ methods quantitatively and qualitatively (by a toy regression example) to examine their strengths and shortcomings from different dimensions. Then, we review quantitative metrics commonly used to assess the quality of predictive uncertainty in classification and regression problems. Afterward, we discuss the increasingly important role of UQ of ML models in solving challenging problems in engineering design and health prognostics. In conclusion, two case studies with source codes available on GitHub are used to demonstrate these UQ methods and compare their performance in the life prediction of lithium-ion batteries at the early stage (case study 1) and the remaining useful life prediction of turbofan engines (case study 2).

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Characterization of Coal Refuse Sites in West Virginia: Stream Loss, Volume Estimation, and Land Cover Analysis for Restoration Feasibility

Coal refuse disposal across Appalachia has resulted in widespread environmental degradation, including stream burial, landscape destabilization, and long-term hydrologic impacts. This study provides a GIS-based spatial characterization of 623 coal refuse sites in West Virginia, evaluating their potential for ecological and economic restoration. Stream loss was quantified through digitization of historic topographic maps, revealing over 194,500 meters of historically present streams lost, with 105,000 meters directly buried beneath refuse piles. Volume estimation using empirical Bayesian kriging and modern LiDAR surfaces indicated approximately 1.96 billion cubic meters of deposited refuse. Land cover analysis based on NAIP-derived classification showed that 48% of the total site area was forested, while 15% remained barren. These results highlight not only the environmental footprint of legacy refuse deposits but also their potential for restoration through stream daylighting and beneficial reuse. Emerging opportunities, including rare earth element recovery and mitigation banking, may offer economic incentives to facilitate reclamation. This work establishes a spatial framework to prioritize refuse sites for restoration, balancing ecological uplift with feasible material management strategies.

58 GEOSCIENCES↗

DOE OSTI2014

WE-E-BRE-05: Ensemble of Graphical Models for Predicting Radiation Pneumontis Risk

Purpose: We propose a prior knowledge-based approach to construct an interaction graph of biological and dosimetric radiation pneumontis (RP) covariates for the purpose of developing a RP risk classifier. Methods: We recruited 59 NSCLC patients who received curative radiotherapy with minimum 6 month follow-up. 16 RP events was observed (CTCAE grade ≥2). Blood serum was collected from every patient before (pre-RT) and during RT (mid-RT). From each sample the concentration of the following five candidate biomarkers were taken as covariates: alpha-2-macroglobulin (α2M), angiotensin converting enzyme (ACE), transforming growth factor β (TGF-β), interleukin-6 (IL-6), and osteopontin (OPN). Dose-volumetric parameters were also included as covariates. The number of biological and dosimetric covariates was reduced by a variable selection scheme implemented by L1-regularized logistic regression (LASSO). Posterior probability distribution of interaction graphs between the selected variables was estimated from the data under the literature-based prior knowledge to weight more heavily the graphs that contain the expected associations. A graph ensemble was formed by averaging the most probable graphs weighted by their posterior, creating a Bayesian Network (BN)-based RP risk classifier. Results: The LASSO selected the following 7 RP covariates: (1) pre-RT concentration level of α2M, (2) α2M level mid- RT/pre-RT, (3) pre-RT IL6 level, (4) IL6 level mid-RT/pre-RT, (5) ACE mid-RT/pre-RT, (6) PTV volume, and (7) mean lung dose (MLD). The ensemble BN model achieved the maximum sensitivity/specificity of 81%/84% and outperformed univariate dosimetric predictors as shown by larger AUC values (0.78∼0.81) compared with MLD (0.61), V20 (0.65) and V30 (0.70). The ensembles obtained by incorporating the prior knowledge improved classification performance for the ensemble size 5∼50. Conclusion: We demonstrated a probabilistic ensemble method to detect robust associations between RP covariates and its potential to improve RP prediction accuracy. Our Bayesian approach to incorporate prior knowledge can enhance efficiency in searching of such associations from data. The authors acknowledge partial support by: 1) CREATE Medical Physics Research Training Network grant of the Natural Sciences and Engineering Research Council (Grant number: 432290) and 2) The Terry Fox Foundation Strategic Training Initiative for Excellence in Radiation Research for the 21st Century (EIRR21)

60 APPLIED LIFE SCIENCES↗

DOE OSTI2015

Quasar classification using color and variability

We conduct a pilot investigation to determine the optimal combination of color and variability information to identify quasars in current and future multi-epoch optical surveys. We use a Bayesian quasar selection algorithm to identify 35,820 type 1 quasar candidates in a 239 deg{sup 2} field of the Sloan Digital Sky Survey (SDSS) Stripe 82, using a combination of optical photometry and variability. Color analysis is performed on 5-band single- and multi-epoch SDSS optical photometry to a depth of r∼22.4. From these data, variability parameters are calculated by fitting the structure function of each object in each band with a power-law model using 10 to >100 observations over timescales from ∼1 day to ∼8 years. Selection was based on a training sample of 13,221 spectroscopically confirmed type-1 quasars, largely from the SDSS. Using variability alone, colors alone, and combining variability and colors we achieve 91%, 93%, and 97% quasar completeness and 98%, 98%, and 97% efficiency, respectively, with particular improvement in the selection of quasars at 2.7<z<3.5 where quasars and stars have similar optical colors. The 22,867 quasar candidates that are not spectroscopically confirmed reach a depth of i∼22.0; 21,876 (95.7%) are dimmer than coadded i-band magnitude of 19.9, the cutoff for spectroscopic follow-up for SDSS on Stripe 82. Brighter than 19.9, we find 5.7% more quasar candidates without confirming spectra in sky regions otherwise considered complete. The resulting quasar sample has sufficient purity (and statistically correctable incompleteness) to produce a luminosity function comparable to those determined by spectroscopic investigations. We discuss improvements that can be made to the process in preparation for performing similar photometric selection and science on data from post-SDSS sky surveys.

79 ASTRONOMY AND ASTROPHYSICS↗

DOE OSTI2024

Multivariate Testing of Sampling Techniques to Address Class Imbalance in Building Use Type Classification

This study addresses the challenges inherent in building use type classification, particularly focusing on the issue of class imbalance in the training datasets for machine learning classifiers. We comprehensively analyze the efficacy of various class-balancing sampling techniques. Employing Monte Carlo simulations and Bayesian optimization, we evaluated the performance of multiple sampling methods, including Random Oversampling, Random Undersampling, SMOTE, Borderline-SMOTE, and ADASYN, across a dataset encompassing nine southeastern coastal states of the United States. Our findings reveal that simple random over- and undersampling techniques outperform more sophisticated methods. Additionally, we show inherent value in creating an imbalance in training data to effectively train a machine learning classifier for distinguishing between residential and nonresidential buildings. This study provides valuable guidance for future research on building use type classification research and lays essential groundwork for developing attribute-rich building stock datasets.

Adams, Daniel↗

DOE OSTI2023

Adaptive Discovery and Mixed-Variable Optimization of Next Generation Synthesizable Microelectronic Materials

Design of new microelectronic materials is characterized by several challenges such as high-dimensionality of the atomic structure-composition variable space, formidable cost of directly using high-fidelity simulations for design optimization, dispersity in literature-reported similar materials and synthesis methods, complex physical mechanisms, and mixed qualitative and quantitative design variables that lead to a disjointed design space. Even though machine learning (ML) techniques have been employed to expedite materials innovation, existing methods treat ML and design optimization as two separate processes, failing to resolve the fundamental challenges associated with high dimensionality and mixed-variable complexity. We have developed a ML enhanced mixed-variable material design optimization framework to efficiently extract useful information from existing data in literature and physics-based simulations to guide the autonomous search for optimal materials. Our proposed framework is composed of four computational modules: (1) a natural language processing (NLP) based virtual screening module, (2) classification based concept exploration module, (3) a density functional theory (DFT)-based high-fidelity evaluation model, and (4) a novel latent-variable Gaussian process (LVGP) ML model for mixed-variable problems with uncertainty quantification, which seamlessly integrates with Bayesian Optimization (BO) and achieves superb efficiency through embedded physics-based dimension reduction. Our approach is demonstrated and validated using the testbed of functional materials exhibiting metal-insulation transitions (MITs), with the targeted reversible resistivity changes (∼10^5) near room temperature. At the end of the 30-month project, we have developed a series of new ML techniques using NLP, conditional variational autoencoders, active learning, latent-variable Gaussian processes, integrated with Bayesian optimization. Our project has resulted in new predicted MITs compounds and improved understanding of MITs microscopic mechanisms, which in turn will revolutionize microelectronics science to provide energy-saving solutions. Our research has improved both creativity and efficiency in transforming rare-event discoveries of new functional materials to persistent innovations. In addition to open-sourcing the online MIT database and the classification model, the LVGP open source code has been downloaded more than 15,000 times within two years. More than 40 MIT compounds have been identified and many have been pursued experimentally via collaborators. The research results are published in close to 20 collaborative papers in high-impact journals, such as Chem. Mater., Appl. Phys. Rev., Sci. Rep., among others of design space.

36 MATERIALS SCIENCE↗

DOE OSTI2015

SPEQTACLE: An automated generalized fuzzy C-means algorithm for tumor delineation in PET

Purpose: Accurate tumor delineation in positron emission tomography (PET) images is crucial in oncology. Although recent methods achieved good results, there is still room for improvement regarding tumors with complex shapes, low signal-to-noise ratio, and high levels of uptake heterogeneity. Methods: The authors developed and evaluated an original clustering-based method called spatial positron emission quantification of tumor—Automatic Lp-norm estimation (SPEQTACLE), based on the fuzzy C-means (FCM) algorithm with a generalization exploiting a Hilbertian norm to more accurately account for the fuzzy and non-Gaussian distributions of PET images. An automatic and reproducible estimation scheme of the norm on an image-by-image basis was developed. Robustness was assessed by studying the consistency of results obtained on multiple acquisitions of the NEMA phantom on three different scanners with varying acquisition parameters. Accuracy was evaluated using classification errors (CEs) on simulated and clinical images. SPEQTACLE was compared to another FCM implementation, fuzzy local information C-means (FLICM) and fuzzy locally adaptive Bayesian (FLAB). Results: SPEQTACLE demonstrated a level of robustness similar to FLAB (variability of 14% ± 9% vs 14% ± 7%, p = 0.15) and higher than FLICM (45% ± 18%, p < 0.0001), and improved accuracy with lower CE (14% ± 11%) over both FLICM (29% ± 29%) and FLAB (22% ± 20%) on simulated images. Improvement was significant for the more challenging cases with CE of 17% ± 11% for SPEQTACLE vs 28% ± 22% for FLAB (p = 0.009) and 40% ± 35% for FLICM (p < 0.0001). For the clinical cases, SPEQTACLE outperformed FLAB and FLICM (15% ± 6% vs 37% ± 14% and 30% ± 17%, p < 0.004). Conclusions: SPEQTACLE benefitted from the fully automatic estimation of the norm on a case-by-case basis. This promising approach will be extended to multimodal images and multiclass estimation in future developments.

60 APPLIED LIFE SCIENCES↗

DOE OSTI2015

Mechanism-based classification of PAH mixtures to predict carcinogenic potential

We have previously shown that relative potency factors and DNA adduct measurements are inadequate for predicting carcinogenicity of certain polycyclic aromatic hydrocarbons (PAHs) and PAH mixtures, particularly those that function through alternate pathways or exhibit greater promotional activity compared to benzo[ a ]pyrene (BaP). Therefore, we developed a pathway based approach for classification of tumor outcome after dermal exposure to PAH/mixtures. FVB/N mice were exposed to dibenzo[ def,p ]chrysene (DBC), BaP or environmental PAH mixtures (Mix 1-3) following a two-stage initiation/promotion skin tumor protocol. Resulting tumor incidence could be categorized by carcinogenic potency as DBC>>BaP=Mix2=Mix3>Mix1=Control, based on statistical significance. Gene expression profiles measured in skin of mice collected 12 h post-initiation were compared to tumor outcome for identification of short-term bioactivity profiles. A Bayesian integration model was utilized to identify biological pathways predictive of PAH carcinogenic potential during initiation. Integration of probability matrices from four enriched pathways (p<0.05) for DNA damage, apoptosis, response to chemical stimulus and interferon gamma signaling resulted in the highest classification accuracy with leave-one-out cross validation. This pathway-driven approach was successfully utilized to distinguish early regulatory events during initiation prognostic for tumor outcome and provides proof-of-concept for using short-term initiation studies to classify carcinogenic potential of environmental PAH mixtures. As a result, these data further provide a ‘source-to outcome’ model that could be used to predict PAH interactions during tumorigenesis and provide an example of how mode-of-action based risk assessment could be employed for environmental PAH mixtures.

59 BASIC BIOLOGICAL SCIENCES↗

DOE OSTI2023

Ensemble models for circuit topology estimation, fault detection and classification in distribution systems

This paper presents a methodology for simultaneous fault detection, classification, and topology estimation for adaptive protection of distribution systems. The methodology estimates the probability of the occurrence of each one of these events by using a hybrid structure that combines three sub-systems, a convolutional neural network for topology estimation, a fault detection based on predictive residual analysis, and a standard support vector machine with probabilistic output for fault classification. The input to all these sub-systems is the local voltage and current measurements. A convolutional neural network uses these local measurements in the form of sequential data to extract features and estimate the topology conditions. The fault detector is constructed with a Bayesian stage (a multitask Gaussian process) that computes a predictive distribution (assumed to be Gaussian) of the residuals using the input. Since the distribution is known, these residuals can be transformed into a Standard distribution, whose values are then introduced into a one-class support vector machine. The structure allows using a one-class support vector machine without parameter cross-validation, so the fault detector is fully unsupervised. Finally, a support vector machine uses the input to perform the classification of the fault types. All three sub-systems can work in a parallel setup for both performance and computation efficiency. In conclusion, we test all three sub-systems included in the structure on a modified IEEE123 bus system, and we compare and evaluate the results with standard approaches.

24 POWER TRANSMISSION AND DISTRIBUTION↗

DOE OSTI2018

Star-galaxy classification in the Dark Energy Survey Y1 dataset

Here, we perform a comparison of different approaches to star-galaxy classification using the broad-band photometric data from Year 1 of the Dark Energy Survey. We explore and compare different techniques to address this problem: morphological versus using additional flux information, differences between machine-learning, cut based and template fitting including Hierarchical Bayesian methods and catalogue-based versus image-based analyses. This is done by performing a wide range of tests with and without external ‘truth’ information, which can be ported to other similar datasets. We make a broad evaluation of the performance of the classifiers in two science cases with DES data that are most affected by this systematic effect: large-scale structure and Milky Way studies. In general, even though the default morphological classifiers used for DES Y1 cosmology studies are sufficient to maintain a low level of systematic contamination from stellar mis-classification, contamination can be reduced to the O (1%) level by using multi-epoch and infrared information from external datasets. For Milky Way studies the stellar sample can be augmented by ~20% for a given flux limit. Reference catalogues used in this work are available at http://des.ncsa.illinois.edu/releases/y1a1.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2025

Counterpart identification and classification for eRASS1 and characterisation of the active galactic nuclei content

Context. Accurately accounting for the Active Galactic Nucleus (AGN) phase in galaxy evolution requires a large, clean AGN sample. This is now possible with SRG/eROSITA, which completed its first all-sky X-ray survey (eRASS1) on June 12, 2020. The public Data Release 1 (DR1, Jan 31, 2024) includes 930,203 sources from the western Galactic hemisphere. Aims. The data enable the selection of a large AGN sample and the discovery of rare sources. However, scientific return depends on accurate characterisation of the X-ray emitters, requiring high-quality multi-wavelength data. This paper presents the identification and classification of optical and infrared counterparts to eRASS1 sources. Methods. Counterparts to eRASS1 X-ray point sources were identified using Gaia DR3, CatWISE2020, and Legacy Survey DR10 (LS10) with the Bayesian NWAY algorithm and trained priors. Sources were classified as Galactic or extragalactic via a machine-learning model combining optical/IR and X-ray properties, trained on a reference sample. For extragalactic LS10 sources, photometric redshifts were computed using CIRCLEZ. Results. Within the LS10 footprint, all 656,614 eROSITA/DR1 sources have at least one possible optical counterpart; ∼570 000 are extragalactic and likely AGN. Half are new detections compared to AllWISE, Gaia, and Quaia AGN catalogues. Gaia and CatWISE2020 counterparts are less reliable, due to the survey’s shallowness and the limited amount of features available to assess the probability of being an X-ray emitter. In the Galactic plane, where the overdensity of stellar sources also increases the chance of associations, using conservative reliability cuts, we identified approximately 18 000 Gaia and 55 000 CatWISE2020 extragalactic sources. Conclusions. We have released three high-quality counterpart catalogues – plus the training and validation sets – as a benchmark for the field. These datasets have many applications, but in particular, they empower researchers to build AGN samples tailored for completeness and purity, accelerating the hunt for the Universe’s most energetic engines.

X-rays: general↗

DOE OSTI2025

Jensen–Shannon divergence based novel loss functions for Bayesian neural networks

Bayesian neural networks (BNNs) are state-of-the-art machine learning methods that can naturally regularize and systematically quantify uncertainties using their stochastic parameters. Kullback–Leibler (KL) divergence-based variational inference used in BNNs suffer from unstable optimization and challenges in approximating light-tailed posteriors due to the unbounded nature of the KL divergence. To resolve these issues, we formulate a novel loss function for BNNs based on a new modification to the generalized Jensen–Shannon (JS) divergence, which is bounded. In addition, we propose a Geometric JS divergence-based loss, which is computationally efficient since it can be evaluated analytically. We found that the JS divergence-based variational inference is intractable, and hence employed a constrained optimization framework to formulate these losses. Our theoretical analysis and empirical experiments on multiple regression and classification data sets suggest that the proposed losses perform better than the KL divergence-based loss, especially when the data sets are noisy or biased. Specifically, there are approximately 5% and 8% improvements in accuracy for a noise-added CIFAR-10 dataset and a regression dataset, respectively. There is about 13% reduction in false negative predictions of a biased histopathology dataset. Additionally, we quantify and compare the uncertainty metrics for the regression and classification tasks.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2025

Confidence-weighted integration of human and machine judgments for superior decision-making

Large language models (LLMs) can surpass humans in certain forecasting tasks. What role does this leave for humans in the overall decision process? One possibility is that humans, despite performing worse than LLMs, can still add value when teamed with them. A human and machine team can surpass each individual teammate when team members’ confidence is well calibrated and team members diverge in which tasks they find difficult (i.e., calibration and diversity are needed). We simplified and extended a Bayesian approach to combining judgments using a logistic regression framework that integrates confidence-weighted judgments for any number of team members. Using this straightforward method, we demonstrated its effectiveness in both image classification and neuroscience forecasting tasks. Combining human judgments with one or more machines consistently improved overall team performance. Our hope is that this simple and effective strategy for integrating the judgments of humans and machines will lead to productive collaborations.

97 MATHEMATICS AND COMPUTING↗

DOE OSTI2018

HyperSpace: Distributed Bayesian Hyperparameter Optimization

As machine learning models continue to increase in complexity, so does the potential number of free model parameters commonly known as hyperparameters. While there has been considerable progress toward finding optimal configurations of these hyperparameters, many optimization procedures are treated as black boxes. We believe optimization methods should not only return a set of optimized hyperparameters, but also give insight into the effects of model hyperparameter settings. To this end, we present HyperSpace, a parallel implementation of Bayesian sequential model-based optimization. HyperSpace leverages high performance computing (HPC) resources to better understand unknown, potentially non-convex hyperparameter search spaces. We show that it is possible to learn the dependencies between model hyperparameters through the optimization process. By partitioning large search spaces and running many optimization procedures in parallel, we also show that it is possible to discover families of good hyperparameter settings over a variety of models including unsupervised clustering, regression, and classification tasks.

Computer Science↗

DOE OSTI2016

A path towards uncertainty assignment in an operational cloud-phase algorithm from ARM vertically pointing active sensors

Abstract. Knowledge of cloud phase (liquid, ice, mixed, etc.) is necessary to describe the radiative impact of clouds and their lifetimes, but is a property that is difficult to simulate correctly in climate models. One step towards improving those simulations is to make observations of cloud phase with sufficient accuracy to help constrain model representations of cloud processes. In this study, we outline a methodology using a basic Bayesian classifier to estimate the probabilities of cloud-phase class from Atmospheric Radiation Measurement (ARM) vertically pointing active remote sensors. The advantage of this method over previous ones is that it provides uncertainty information on the phase classification. We also test the value of including higher moments of the cloud radar Doppler spectrum than are traditionally used operationally. Using training data of known phase from the Mixed-Phase Arctic Cloud Experiment (M-PACE) field campaign, we demonstrate a proof of concept for how the method can be used to train an algorithm that identifies ice, liquid, mixed phase, and snow. Over 95 % of data are identified correctly for pure ice and liquid cases used in this study. Mixed-phase and snow cases are more problematic to identify correctly. When lidar data are not available, including additional information from the Doppler spectrum provides substantial improvement to the algorithm. This is a first step towards an operational algorithm and can be expanded to include additional categories such as drizzle with additional training data.

54 ENVIRONMENTAL SCIENCES↗

DOE OSTI2016

Learning Weight Uncertainty with Stochastic Gradient MCMC for Shape Classification

Learning the representation of shape cues in 2D & 3D objects for recognition is a fundamental task in computer vision. Deep neural networks (DNNs) have shown promising performance on this task. Due to the large variability of shapes, accurate recognition relies on good estimates of model uncertainty, ignored in traditional training of DNNs, typically learned via stochastic optimization. This paper leverages recent advances in stochastic gradient Markov Chain Monte Carlo (SG-MCMC) to learn weight uncertainty in DNNs. It yields principled Bayesian interpretations for the commonly used Dropout/DropConnect techniques and incorporates them into the SG-MCMC framework. Extensive experiments on 2D & 3D shape datasets and various DNN models demonstrate the superiority of the proposed approach over stochastic optimization. Our approach yields higher recognition accuracy when used in conjunction with Dropout and Batch-Normalization.

convolutional neural network↗

DOE OSTI2015

Application of Bayes' theorem for pulse shape discrimination

A Bayesian approach is proposed for pulse shape discrimination of photons and neutrons in liquid organic scinitillators. Instead of drawing a decision boundary, each pulse is assigned a photon or neutron confidence probability. In addition, this allows for photon and neutron classification on an event-by-event basis. The sum of those confidence probabilities is used to estimate the number of photon and neutron instances in the data. An iterative scheme, similar to an expectation-maximization algorithm for Gaussian mixtures, is used to infer the ratio of photons-to-neutrons in each measurement. Therefore, the probability space adapts to data with varying photon-to-neutron ratios. A time-correlated measurement of Am–Be and separate measurements of 137 Cs, 60 Co and 232 Th photon sources were used to construct libraries of neutrons and photons. These libraries were then used to produce synthetic data sets with varying ratios of photons-to-neutrons. Probability weighted method that we implemented was found to maintain neutron acceptance rate of up to 90% up to photon-to-neutron ratio of 2000, and performed 9% better than the decision boundary approach. Furthermore, the iterative approach appropriately changed the probability space with an increasing number of photons which kept the neutron population estimate from unrealistically increasing.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2020

Non-Intrusive Appliance Identification with Appliance-Specific Networks

The problem of noninstrusive load monitoring (NILM) is usually formulated as a single-channel blind source separation task, whose successful solution enable fast and convenient load identification and energy disaggregation. When applied at test time, NILM algorithms aim to identify the operating characteristics of individual appliances from an aggregate power measurement of the entire house. Recent advances in deep learning gave rise to many methods that mostly focus on learning a direct mapping from aggregate measurement to individual appliance power. However, these methods are not only computationally expensive, but they often suffer from overfitting and do not generalize very well. In this article, we propose a novel NILM method that leverages advances in statistical learning that have not been properly applied in this domain before. The proposed method consists of three stages: first, a Bayesian nonparametric learning-based approach for appliance state extraction; second, synthetic minority oversampling technique for data augmentation and mitigating the heavy imbalance in switching events; and third, appliance-specific lightweight long short-term memory networks for status classification for each appliance. Here, we adopt a “differential” input (the difference before and after the switching event) to reduce the complexity of network training and make the proposed method robust to multiappliance switching events. Experiments are conducted to demonstrate the effectiveness of the proposed method, achieving superior performance when compared to recent methods. An ablation study is conducted to demonstrate the effectiveness of each module of our method. Finally, we investigate the quality of generated synthetic samples.

42 ENGINEERING↗