Efficient Estimation Method Research Articles

A Marginal Maximum Likelihood Approach for Hierarchical Simultaneous Autoregressive Models with Missing Data

Efficient estimation methods for simultaneous autoregressive (SAR) models with missing data in the response variable have been well explored in the literature. A common practice is introducing measurement error into SAR models to separate the noise component from the spatial process. However, prior studies have not considered incorporating measurement error into SAR models with missing data. Maximum likelihood estimation for such models, especially with large datasets, poses significant computational challenges. This paper proposes an efficient likelihood-based estimation method, the marginal maximum likelihood (ML), for estimating SAR models on large datasets with measurement errors and a high percentage of missing data in the response variable. The spatial autoregressive model (SAM) and the spatial error model (SEM), two popular SAR model types, are considered. The missing data mechanism is assumed to follow a missing-at-random (MAR) pattern. We propose a fast method for marginal ML estimation with a computational complexity of O(n3/2), where n is the total number of observations. This complexity applies when the spatial weight matrix is constructed based on a local neighbourhood structure. The effectiveness of the proposed methods is demonstrated through simulations and real-world data applications.

Clinical and Epidemiological Information Required for Lyme Disease Surveillance in a Low-Incidence State, California 2011-2017.

Background: Between January 1, 2011, and December 31, 2017, over 12,000 case reports of Lyme disease (LD) were submitted to the California Reportable Disease Information Exchange for further investigation. The number of case reports has tripled compared to previous years, emphasizing the need for efficient estimation and classification methods. We evaluated whether estimation procedures can be implemented in a low-incidence state such as California to correctly classify a case of LD, similar to those procedures used in high-incidence states. Objective: The purpose of this study was to identify whether a minimum number of variables was sufficient to reliably classify cases in California and potentially reduce workload while maintaining the ability to track LD trends in California. Methods: To determine the relative value of diagnostic information, we compared five candidate logistic regression models that were used to classify cases based on information that varied in its degree of difficulty for collection. Results: Our results using California's surveillance data showed that automatically reported data were not sufficient, additional information such as, a patient's clinical presentation and travel history were necessary in a low-incidence state to improve the overall sensitivity of the models. Conclusion: This study may help inform public health surveillance efforts by demonstrating that both clinical and travel information are required to accurately classify a case of LD in a low-incidence state.

Fast DOA Estimation of IGS Noncircular Signals Under Coprime Arrays

Traditional direction-of-arrival (DOA) estimation methods often encounter challenges such as low accuracy and high computational complexity, particularly in complex signal environments with multiple sources. To address these issues, this paper proposes a fast DOA estimation method for improper Gaussian signaling (IGS) non-circular signals, based on a coprime array; this approach involves extending the array model by leveraging the unique properties of non-circular signals. Subsequently, this study introduces the ANCM algorithm, a method designed for fast DOA estimation of IGS non-circular signals within a non-uniform noise background. The proposed ANCM algorithm is then compared to classical algorithms, through simulations in a non-uniform noise environment. Experimental results demonstrate that the ANCM algorithm significantly outperforms traditional methods in such conditions. Therefore, the development of new, efficient DOA estimation methods holds substantial theoretical and practical value.

Direct Estimation for Commonly Used Pattern-Mixture Models in Clinical Trials

Pattern-mixture models have received increasing attention as they are commonly used to assess treatment effects in primary or sensitivity analyses for clinical trials with nonignorable missing data. Pattern-mixture models have traditionally been implemented using multiple imputation, where the variance estimation may be a challenge because the Rubin’s approach of combining between- and within-imputation variance may not provide consistent variance estimation while bootstrap methods may be time-consuming. Direct likelihood-based approaches have been proposed in the literature and implemented for some pattern-mixture models, but the assumptions are sometimes restrictive and the theoretical framework is fragile. In this article, we propose an analytical framework for an efficient direct likelihood estimation method for commonly used pattern-mixture models corresponding to return-to-baseline, jump-to-reference, placebo washout, and retrieved dropout imputations. A parsimonious tipping point analysis is also discussed and implemented. Results from simulation studies demonstrate that the proposed methods provide consistent estimators. We further illustrate the utility of the proposed methods using data from a clinical trial evaluating a treatment for type 2 diabetes.

Inverse Open Circuit Voltage Curve Model for LiCoO2 Battery at Different Temperatures

Lithium-ion batteries are widely used in a variety of applications. For effective battery management, accurate estimation of the state of charge (SOC) is essential. One of the most commonly employed methods for SOC estimation relies on the open circuit voltage (OCV) curve with respect to SOC. However, inverting the OCV-SOC function is not always straightforward. This paper proposes a novel analytical function that directly models the inverse OCV-SOC function, providing a more efficient and reliable method for SOC estimation. Moreover, the dependency of the proposed function on battery temperature is also being investigated, allowing for a wider application of the method under different OCV measuring conditions.

Using query semantic and feature transfer fusion to enhance cardinality estimating of property graph queries

With the increasing complexity and diversity of query tasks, cardinality estimation has become one of the most challenging problems in query optimization. In this study, we propose an efficient and accurate cardinality estimation method to address the cardinality estimation problem in property graph queries, particularly in response to the current research gap regarding the neglect of contextual semantic features. We first propose formal representations of the property graph query and define its cardinality estimation problem. Then, through the query featurization, we transform the query into a vector representation that can be learned by the estimation model, and enrich the feature vector representation by the context semantic information of the query. We finally propose an estimation model for property graph queries, specifically introducing a feature information transfer module to dynamically control the information flow meanwhile achieving the model’s feature fusion and inference. Experimental results on three datasets show that the estimation model can accurately and efficiently estimate the cardinality of property graph queries, the mean Q_error and RMSE are reduced by about 30% and 25% than the state-of-art estimation models. The context semantics features of queries can improve the model’s estimation accuracy, the mean Q_error result is reduced by about 20% and the RMSE result is about 5%.

Estimation of SOC for Li-ion battery-powered three-wheeled electric vehicle using machine learning methods

Abstract The Battery Management System (BMS) serves as the heart of the electric vehicle system, in which estimating the state of charge (SOC) is the crucial part of the BMS to ensure the durability, reliability, and sustainability of the battery pack. Due to its nonlinear characteristics, accurately estimating the SOC for a slow degradation of the charge is highly cumbersome. The literature provides a series of machine learning algorithms (MLA) to estimate and predict the SOC of lithium-ion (Li-ion) battery systems for electric vehicle (EV) applications. The literature has proposed various MLA, coulomb counting, and different Kalman filter methods to address this challenge and estimate the SOC of Li-ion battery systems for EV applications. This research looks at the differences and similarities between the coulomb counting method, the unscented Kalman filter method, and a number of machine learning algorithms. These include linear regression, polynomial linear regression, support vector regression, decision trees, random forests, artificial neural networks (ANN), and long short-term memory (LSTM). The goal is to assess the MLAs' accuracy in estimating battery SOC. Analyzing model errors optimizes the battery's performance parameter. We identify ANN and LSTM as the two most efficient methods for accurate SOC estimation in an EV-operated BMS system by evaluating the performance indices of the aforementioned machine learning methodologies. Once again, the LSTM model for SOC estimation has proven to be highly accurate in analyzing the discrepancy between the actual and predicted traveling ranges of the designed prototype. We design a MATLAB/SIMULINK EV powertrain by collecting realtime data from the Li-ion battery pack, analyzing the SOC variation data, and using the previously mentioned MLA in the Python platform to estimate the SOC and its accuracy. It highlights the effectiveness of advanced MLAs in improving SOC estimation, thereby enhancing the performance and reliability of EV battery systems.

FAStEN: An Efficient Adaptive Method for Feature Selection and Estimation in High-Dimensional Functional Regressions

Functional regression analysis is an established tool for many contemporary scientific applications. Regression problems involving large and complex data sets are ubiquitous, and feature selection is crucial for avoiding overfitting and achieving accurate predictions. We propose a new, flexible and ultra-efficient approach to perform feature selection in a sparse high dimensional function-on-function regression problem, and we show how to extend it to the scalar-on-function framework. Our method, called FAStEN, combines functional data, optimization, and machine learning techniques to perform feature selection and parameter estimation simultaneously. We exploit the properties of Functional Principal Components and the sparsity inherent to the Dual Augmented Lagrangian problem to significantly reduce computational cost, and we introduce an adaptive scheme to improve selection accuracy. In addition, we derive asymptotic oracle properties, which guarantee estimation and selection consistency for the proposed FAStEN estimator. Through an extensive simulation study, we benchmark our approach to the best existing competitors and demonstrate a massive gain in terms of CPU time and selection performance, without sacrificing the quality of the coefficients’ estimation. The theoretical derivations and the simulation study provide a strong motivation for our approach. Finally, we present an application to brain fMRI data from the AOMIC PIOP1 study. Complete FAStEN code is provided at https://github.com/IBM/funGCN. Supplementary materials for this article are available online.

Multivariate Scalar on Multidimensional Distribution Regression With Application to Modeling the Association Between Physical Activity and Cognitive Functions

ABSTRACTWe develop a new method for multivariate scalar on multidimensional distribution regression. Traditional approaches typically analyze isolated univariate scalar outcomes or consider unidimensional distributional representations as predictors. However, these approaches are suboptimal because (i) they fail to utilize the dependence between the distributional predictors and (ii) neglect the correlation structure of the response. To overcome these limitations, we propose a multivariate distributional analysis framework that harnesses the power of multivariate density functions and multitask learning. We develop a computationally efficient semiparametric estimation method for modeling the effect of the latent joint density on the multivariate response of interest. Additionally, we introduce a new conformal prediction algorithm for quantifying the uncertainty of our multivariate predictions based on subject characteristics and individualized distributional predictors, providing valuable insights into the conditional distribution of the response. We validate the effectiveness of our proposed method through comprehensive numerical simulations, clearly demonstrating its superior performance compared to traditional methods. The application of the proposed method is demonstrated on triaxial accelerometer data from the National Health and Nutrition Examination Survey 2011–2014 for modeling the association between cognitive scores across various domains and distributional representation of physical activity among the older adult population. Our results highlight the advantages of the proposed approach, emphasizing the significance of incorporating multidimensional distributional information in the triaxial accelerometer data.

An efficient method for water content estimation of building materials from spectral reflectance

We propose a nondestructive methodology to accurately estimate the water content of building materials from spectral reflectance in the shortwave infrared. The water content of a wet sample is estimated from the relative position of its reflectance spectrum on the curve between 2 reference spectra with known water content. By design, the approach is invariant to variations in illumination and acquisition conditions. Validation is done on datasets of clay powders and bricks. The experimental results provide confirmation of the effectiveness of the proposed method.

Real-Time Estimation of Origin–Destination Matrices Using a Deep Neural Network for Digital Twins

The digital twin, a real-time replica of physical systems, has garnered attention as a promising tool to strategize and evaluate solutions for complex real-world issues. However, developing digital twins in the field of transportation faces significant challenges related to the real-time estimation of dynamic origin–destination (OD) matrices constrained by computation time. To bridge this gap, microscopic traffic simulations with real-time synchronization are being researched. Nonetheless, the computational issue persists, emphasizing the need for more efficient OD estimation methods. In this regard, our objective is to reduce computation time in simulation-based methods by developing a data-driven metamodel using a deep neural network. The proposed model serves to map the correlation between the OD matrix and detector data. This model simplifies the computational process using hidden layers, rather than calculating complex interactions between vehicles in the traffic simulation. Compared to conventional methods, we evaluate the capability to estimate a reasonable OD matrix within a restricted time and validate our approach using detector data from Daejeon City, South Korea. The findings indicate that by combining our data-driven metamodel with the simultaneous perturbation stochastic approximation, it becomes feasible to estimate a reasonable OD matrix within a stipulated time frame, compared to the conventional method. Given a 1-min time frame, the proposed method outperforms the conventional simulation-based method by improving the calibration performance of traffic flow by 44.5 percentage points. This paper proposes a practical and versatile approach for real-time OD estimation, laying the foundation for extending microscopic traffic simulation into the digital twin.

Pore‐Morphology‐Based Estimation of the Freezing Characteristic Curve of Water‐Saturated Porous Media

AbstractAssessment of freezing effects on soil requires estimating the soil freezing characteristic curve (SFCC)—the variation of unfrozen water content with temperature. The existing methods for obtaining SFCCs often involve either costly experiments or heuristic inference from water retention data. Here, we propose a pore‐morphology‐based method for simple and efficient estimation of the freezing characteristic curve of water‐saturated porous media, whereby the pore‐scale configurations of water and ice phases are simulated in a digital image of porous microstructure. Idealizing the pore space as a system of overlapping spherical pores, the method simulates the freezing process with the Gibbs‐Thomson equation that can consider freezing‐point depression—a decrease in the freezing point due to spatial confinement—based on thermodynamics. For validation, we apply the proposed method to estimate the SFCC of a field soil for which the experimental freezing characteristics data are available. Results show that even with a digital pore image extracted from a surrogate discrete‐element packing of the soil, the proposed method provides an SFCC very close to the experimental data.

Enhanced SOC estimation in Lithium-ion Batteries using GRU Neural Networks with GSA

State of charge (SOC) is one of the most important metrics to evaluate the performance of the battery management system (BMS) in electric vehicles (EVs). Lithium-ion batteries have been utilized often for SOC estimates in EV applications because of its attractive characteristics such as extended lifespans, high voltages, energy, and capacities. However, dynamic charging and discharging profiles, material degradation, battery aging, chemical reaction, and temperature fluctuations would diverge the accuracy of SOC estimation. Deep learning has proven to become an efficient method for SOC estimation in EVs due to its strong computational capabilities, enhanced generalization performance, and excellent accuracy under dynamic loading profiles. Therefore, this study proposes the use of the gated recurrent unit neural network (GRUNN) for estimating SOC in lithium-ion batteries. The best hyperparameters of GRUNN that enable improving SOC accuracy are found using gravitational search optimization (GSA). To evaluate the functional sustainability of the suggested method, a full battery test bench model is created and accordingly, robustness of the proposed approach is verified under diverse EV drive cycles and aging impacts. The effectiveness of the proposed approach is evaluated by comparing with several existing approaches. The results demonstrate that the suggested method archives SOC error and RMSE in EV driving cycles and ageing effects below 5% and 2%, respectively. The excellent outcomes obtained by the proposed method would certainly enhance the battery charging and discharging profile and EV performance. GUB JOURNAL OF SCIENCE AND ENGINEERING, Vol 9(1), 2022 P 1-12

Sampling and active learning methods for network reliability estimation using K-terminal spanning tree

Network reliability analysis remains a challenge due to the increasing size and complexity of networks. This paper presents a novel sampling method and an active learning method for efficient and accurate network reliability estimation under node failure and edge failure scenarios. The proposed sampling method adopts Monte Carlo technique to sample component lifetimes and the K-terminal spanning tree algorithm to accelerate structure function computation. Unlike existing methods that compute only one structure function value per sample, our method generates multiple component state vectors and corresponding structure function values from each sample. Network reliability is estimated based on survival signatures derived from these values. A transformation technique extends this method to handle both node failure and edge failure. To enhance efficiency of proposed sampling method and achieve adaptability to network topology changes, we introduce an active learning method utilizing a random forest (RF) classifier. This classifier directly predicts structure function values, integrates network behaviors across diverse topologies, and undergoes iterative refinement to enhance predictive accuracy. Importantly, the trained RF classifier can directly predict reliability for variant networks, a capability beyond the sampling method alone. Through investigating several network examples and two practical applications, the effectiveness of both proposed methods is demonstrated.

OptimalNN: A Neural Network Architecture to Monitor Chemical Contamination in Cancer Alley

The detrimental impact of toxic chemicals, gas, and oil spills in aquatic environments poses a severe threat to plants, animals, and human life. Regions such as Cancer Alley exemplify the profound consequences of inadequately controlled chemical spills, significantly affecting the local community. Given the far-reaching effects of these spills, it has become imperative to devise an efficient method for early monitoring, estimation, and cleanup, utilizing affordable and effective techniques. In this research, we explore the application of U-shaped neural Network (UNET) and U-shaped neural network transformer (UNETR) neural network models designed for the image segmentation of chemical and oil spills. Our models undergo training using the Commonwealth Scientific and Industrial Research Organization (CSIRO) dataset and the Oil Spill Detection dataset, employing a specialized filtering technique to enhance detection accuracy. We achieved training accuracies of 95.35% and 91% by applying UNET on the Oil Spill and the CSIRO datasets after 50 epochs of training, respectively. We also achieved a training accuracy of 75% by applying UNETR to the Oil Spill dataset. Additionally, we integrated mixed precision to expedite the model training process, thus maximizing data throughput. To further accelerate our implementation, we propose the utilization of the Field Programmable Gate Array (FPGA) architecture. The results obtained from our study demonstrate improvements in inference latency on FPGA.

Bayesian Safety Validation for Failure Probability Estimation of Black-Box Systems

Estimating the probability of failure is an important step in the certification of safety-critical systems. Efficient estimation methods are often needed due to the challenges posed by high-dimensional input spaces, risky test scenarios, and computationally expensive simulators. This work frames the problem of black-box safety validation as a Bayesian optimization problem and introduces a method that iteratively fits a probabilistic surrogate model to efficiently predict failures. The algorithm is designed to search for failures, compute the most-likely failure, and estimate the failure probability over an operating domain using importance sampling. We introduce three acquisition functions that aim to reduce uncertainty by covering the design space, optimize the analytically derived failure boundaries, and sample the predicted failure regions. Results show this Bayesian safety validation approach provides a more accurate estimate of failure probability with orders of magnitude fewer samples and performs well across various safety validation metrics. We demonstrate this approach on three test problems, a stochastic decision-making system, and a neural-network-based runway detection system. This work is open-sourced (https://github.com/sisl/BayesianSafetyValidation.jl) and is currently being used to supplement the FAA certification process of the machine learning components for an autonomous cargo aircraft.

OA-Pose: Occlusion-aware monocular 6-DoF object pose estimation under geometry alignment for robot manipulation

Object pose estimation is the fundamental technology of robot manipulation systems. Recently, various learning-based monocular pose estimation methods have achieved outstanding performance by establishing sparse/dense 2D–3D correspondences. However, in cluttered environments, occlusion has been a challenging problem for pose estimation due to limited information provided by visible parts. In this work, we propose an efficient occlusion-aware monocular pose estimation method, called OA-Pose, to learn geometric feature information of occluded objects from cluttered scenes. Our framework takes RGB images as input and generates 2D–3D correspondences of visible and invisible parts based on the proposed Occlusion-aware Geometry Alignment Module. Extensive experiments show that our method is superior and competitive with state-of-the-art on multiple public datasets. We also conduct grasping experiments with different degrees of object occlusion, demonstrating the usability of our algorithm to deploy on robots in unstructured environments.

Identification and Semiparametric Efficiency Theory of Nonignorable Missing Data with a Shadow Variable

We consider identification and estimation with an outcome missing not at random (MNAR). We study an identification strategy based on a so-called shadow variable . A shadow variable is assumed to be correlated with the outcome but independent of the missingness process conditional on the outcome and fully observed covariates. We describe a general condition for nonparametric identification of the full data law under MNAR using a valid shadow variable. Our condition is satisfied by many commonly used models; moreover, it is imposed on the complete cases, and therefore has testable implications with observed data only. We characterize the semiparametric efficiency bound for the class of regular and asymptotically linear estimators and derive a closed form for the efficient influence function. We describe a doubly robust and locally efficient estimation method and evaluate its performance on both simulation data and a real data example about home pricing.

Field estimation of fallen deadwood volume under different management approaches in two European protected forested areas

Abstract Fallen deadwood is essential for biodiversity and nutrient cycling in forest ecosystems. In modern forest management, there is growing interest in developing accurate and efficient methods for field estimation of deadwood volume due to its many benefits (e.g. carbon storage, habitat creation, erosion control). The most common methods for deadwood inventories are fixed-area sampling (FAS) and line-intersect sampling (LIS) methods. While the estimations of deadwood volume by LIS generally show results comparable to FAS estimations, active management (e.g. production forestry clearcutting, logging, and thinning activities) can impair LIS accuracy by changing local deadwood patterns. Yet, the comparison of LIS and FAS methods has typically focused on production forests where deadwood is limited and deadwood volumes are comparably low. In this study, we assessed fallen deadwood volume in two large national parks—one being a more actively managed landscape (including, e.g., selective thinning for maintaining cultural–historical values and enhancing recreational opportunities) with overall lower levels of fallen deadwood, and the other having a strict non-intervention approach with higher levels of deadwood. No significant differences between average FAS and LIS estimations of deadwood volumes were detected. Additional experimentations using simulated data under varied stand conditions confirmed these results. Although line-intersect sampling showed a slight overestimation and some variability at the individual plot level, it remains an efficient, time-saving field sampling method providing comparable results to the more laborious fixed-area sampling. Line-intersect sampling may be especially suitable for rapid field inventories where relative changes in deadwood volume rather than absolute deadwood volumes are of large interest. Due to its practicality, flexibility, and relative accuracy, line-intersect sampling may gain wider use in natural resource management to inform national park managers, foresters, and ecologists.

An efficient and accurate 2D human pose estimation method using VTTransPose network

Human pose estimation is a crucial area of study in computer vision. Transformer-based pose estimation algorithms have gained popularity for their excellent performance and relatively compact parameterization. However, these algorithms often face challenges including high computational demands and insensitivity to local details. To address these problems, the Twin attention module was introduced in TransPose to improve model efficiency and reduce resource consumption. Additionally, to address issues related to insufficient joint feature representation and poor network recognition performance, the enhanced TransPose model, named VTTransPose, replaced the basic block in the third subnet with the intra-level feature fusion module V block. The performance of the proposed VTTransPose model was validated on the public datasets COCO val2017 and COCO test-dev2017. The experimental results on COCO val2017 and COCO test-dev2017 indicate that the AP evaluation index scores of the VTTransPose network proposed are 76.5 and 73.6 respectively, marking improvements of 0.4 and 0.2 over the original TransPose network. Additionally, VTTransPose exhibited a reduction of 4.8G FLOPs, 2M parameters, and approximately 40% lower memory usage during training compared to the original TransPose model. All the experimental results demonstrate that the proposed VTTransPose is more accurate, efficient, and lightweight compared to the original TransPose model.