Traditional Estimation Research Articles

Position and Orientation Determination using Quadric Fitting Optimization for Object’s Motion Analyzing

Abstract The accurate determination of the position and orientation of moving objects from images is a critical challenge in visual sensing, with significant implications for robotics, augmented reality and computer vision. Traditional pose estimation methods often fail in complex scenarios due to inconsistent and imprecise feature extraction. This research introduces a novel quadric fitting optimization framework that exploits the compact representation of ellipsoids for robust motion analysis. We propose Manhattan and Euclidean norm-based solvers, designed to optimize quadric fitting for varying object scales and distances. A hybrid approach is developed to strategically fuse these solvers to maximize accuracy and efficiency in various practical applications. Theoretical analysis and extensive experimental validation demonstrate the significant improvements offered by our method over conventional techniques, particularly under challenging conditions. This work not only advances the state of the art in object pose determination, but also provides a solid foundation for improved manipulation and understanding of moving objects in dynamic environments.

Development of Predictive Model of Surgical Case Durations Using Machine Learning Approach

Optimizing operating room (OR) utilization is critical for enhancing hospital management and operational efficiency. Accurate surgical case duration predictions are essential for achieving this optimization. Our study aimed to refine the accuracy of these predictions beyond traditional estimation methods by developing Random Forest models tailored to specific surgical departments. Utilizing a comprehensive dataset, we applied several machine learning algorithms, including RandomForest, XGBoost, Linear Regression, LightGBM, and CatBoost, and assessed their performance using Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and R-Squared (R2) metrics. Our findings highlighted that Random Forest models excelled in department-specific applications, achieving an MAE of 16.32, an RMSE of 31.19, and an R2 of 0.92, significantly outperforming general models and conventional estimates. This improvement emphasizes the advantage of customizing models to fit the distinct characteristics and data patterns of each department. Additionally, our SHAP-based feature importance analysis identified morning operation timing, ICU ward assignments, operation codes, and surgeon IDs as key factors influencing surgical duration. This suggests that a detailed and nuanced approach to model development can substantially increase prediction accuracy. By providing a more accurate, reliable tool for predicting surgical case durations, our department-specific Random Forest models promise to enhance surgical scheduling, leading to more effective OR management. This approach underscores the importance of leveraging tailored, data-driven models to improve healthcare outcomes and operational efficiency.

Pessimistic Cardinality Estimation

Cardinality Estimation is to estimate the size of the output of a query without computing it, by using only statistics on the input relations. Existing estimators try to return an unbiased estimate of the cardinality: this is notoriously difficult. A new class of estimators have been proposed recently, called pessimistic estimators, which compute a guaranteed upper bound on the query output. Two recent advances have made pessimistic estimators practical. The first is the recent observation that degree sequences of the input relations can be used to compute query upper bounds. The second is a long line of theoretical results that have developed the use of information theoretic inequalities for query upper bounds. This paper is a short overview of pessimistic cardinality estimators, contrasting them with traditional estimators.

All-breed single-step genomic best linear unbiased predictor evaluations for fertility traits in US dairy cattle.

The US dairy cattle genetic evaluation is currently a multistep process, including multibreed traditional BLUP estimations followed by single-breed SNP effects estimation. Single-step GBLUP (ssGBLUP) combines pedigree and genomic data for all breeds in one analysis. Unknown parent groups (UPG) or metafounders (MF) can be used to address missing pedigree information. Fertility traits are notably difficult to evaluate due to low heritabilities, changing management, and a higher recent emphasis on selection to move in a favorable direction. We assessed bias, dispersion, and accuracy of fertility traits in all-breed US dairy cattle using pedigree-based BLUP (PBLUP) and ssGBLUP with UPG or MF; with 5% or 10% residual polygenic effect. Validation methods included the linear regression method and comparison of early and late deregressed proofs for Holstein and Jersey breeds. By comparing MF or UPG in PBLUP, we observed similar results in terms of bias, dispersion, and correlations between early and recent predictions. When genomics was used, ssGBLUP with MF and 10% residual polygenic effect consistently outperformed other models regarding bias, dispersion, and correlations. Compared with multistep results, ssGBLUP with MF and 10% residual polygenic effect showed less bias and increased correlations but slightly overdispersed estimates. Overall, genomic prediction of fertility traits using ssGBLUP was accurate and unbiased, more so with MF than with UPG.

An improved estimation of remote sensing-based ecological index for tracking continuous changes in eco-environmental quality

ABSTRACT Remote sensing-based ecological index (RSEI) is a widely used index for monitoring eco-environmental quality (EEQ). However, the traditional estimations usually face poor stability in tracking the continuous EEQ changes. To overcome this issue, this study introduces an improved framework for RSEI estimation to enhance the temporal comparability of EEQ assessments. It incorporates annual mean values and temporal normalization of key ecological indicators to address limitations, including susceptibility to seasonal variability and reliance on single-phase data. Through applying to Liangshan Prefecture, a mountainous region in Southwest China, the improved RSEI captures both long-term trends and short-term ecological dynamics from 2001 to 2020, revealing relatively stable EEQ, with mean values ranging from 0.465–0.470. Regions experiencing significant improvement or degradation accounted for less than 10% of the total area. Environmental improvements were largely attributed to human disturbance reduction and ecological restoration projects in high-altitude areas, while degraded regions were concentrated in the Anning River Valley, driven by population growth and urban expansion, affecting 51% of the area. The assessments demonstrate that the improved method shows greater stability and spatial coherence than the traditional ones, providing a robust metric for tracking EEQ trends for environmental monitoring and sustainable development planning.

Toward spatio-temporal models to support national-scale forest carbon monitoring and reporting

Abstract National forest inventory (NFI) programs provide vital information on forest parameters’ status, trend, and change. Most NFI designs and estimation methods are tailored to estimate status over large areas but are not well suited to estimate trend and change, especially over small spatial areas and/or over short time periods (e.g. annual estimates). Fine-scale space-time indexed estimates are critical to a variety of environmental, ecological, and economic monitoring efforts. In the United States, for example, NFI data are used to estimate forest carbon status, trend, and change to support national, state, and local user group needs. Increasingly, these users seek finer spatial and temporal scale estimates to evaluate existing land use policies and management practices, and inform future activities. Here we propose a spatio-temporal Bayesian small area estimation modeling framework that delivers statistically valid estimates with complete uncertainty quantification for status, trend, and change. The framework accommodates a variety of space and time dependency structures, and we detail model configurations for different settings. The proposed framework is used to quantify forest carbon dynamics at an annual county-level across a 14 year period for the contiguous United States. Also, using an analysis of simulated data, we compare the proposed framework with traditional NFI estimators and offer computationally efficient algorithms, software, and data to reproduce results for benchmarking.

LSTM-based estimation of lithium-ion battery SOH using data characteristics and spatio-temporal attention.

As the primary power source for electric vehicles, the accurate estimation of the State of Health (SOH) of lithium-ion batteries is crucial for ensuring the reliable operation of the power system. Long Short-Term Memory (LSTM), a special type of recurrent neural network, achieves sequence information estimation through a gating mechanism. However, traditional LSTM-based SOH estimation methods do not account for the fact that the degradation sequence of battery SOH exhibits trend-like nonlinearity and significant dynamic variations between samples. Therefore, this paper proposes an LSTM-based lithium-ion SOH estimation method incorporating data characteristics and spatio-temporal attention. First, considering the trend-like nonlinearity of the degradation sequence, which is initially gradual and then rapid, input features are filtered and divided into trend and non-trend features. Then, to address the significant dynamic variations between samples, especially for capacity regeneration,a spatio-temporal attention mechanism is designed to extract spatio-temporal features from multidimensional non-trend features. Subsequently, an LSTM model is built with trend features, spatio-temporal features, and actual capacity as inputs to estimate capacity. Finally, the model is trained and tested on different datasets. Experimental results demonstrate that the proposed method outperforms traditional methods in terms of SOH estimation accuracy and robustness.

Integration of partially observed multimodal and multiscale neural signals for estimating a neural circuit using dynamic causal modeling.

Integrating multiscale, multimodal neuroimaging data is essential for a comprehensive understanding of neural circuits. However, this is challenging due to the inherent trade-offs between spatial coverage and resolution in each modality, necessitating a computational strategy that combines modality-specific information effectively. This study introduces a dynamic causal modeling (DCM) framework designed to address the challenge of combining partially observed, multiscale signals across a larger-scale neural circuit by employing a shared neural state model with modality-specific observation models. The proposed method achieves robust circuit inference by iteratively integrating parameter estimates from local microscale and global meso- or macroscale circuits, derived from signals across various scales and modalities. Parameters estimated from high-resolution data within specific regions inform global circuit estimation by constraining neural properties in unobserved regions, while large-scale circuit data help elucidate detailed local circuitry. Using a virtual ground truth system, we validated the method across diverse experimental settings, combining calcium imaging (CaI), voltage-sensitive dye imaging (VSDI), and blood-oxygen-level-dependent (BOLD) signals-each with distinct coverage and resolution. Our reciprocal and iterative parameter estimation approach markedly improves the accuracy of neural property and connectivity estimates compared to traditional one-step estimation methods. This iterative integration of local and global parameters presents a reliable approach to inferring extensive, complex neural circuits from partially observed, multimodal, and multiscale data, showcasing how information from different scales reciprocally enhances entire circuit parameter estimation.

Based on the N2N-SAMP for sparse underwater acoustic channel estimation

IntroductionOrthogonal Frequency Division Multiplexing (OFDM) is widely recognized for its high efficiency in modulation techniques and has been extensively applied in underwater acoustic communication. However, the unique sparsity and noise interference characteristics of the underwater channel pose significant challenges to the performance of traditional channel estimation methods.MethodsTo address these challenges, we propose a sparse underwater channel estimation method that combines the Noise2Noise (N2N) algorithm with the Sparsity Adaptive Matching Pursuit (SAMP) algorithm. This novel approach integrates the N2N technique from image denoising theory with the SAMP algorithm, utilizing a constant iteration termination threshold that does not require prior information. The method leverages the U-net neural network structure to denoise noisy pilot signals, thereby restoring channel sparsity and enhancing the accuracy of channel estimation.ResultsSimulation results indicate that our proposed method demonstrates commendable channel estimation performance across various signal-to-noise ratio (SNR) conditions. Notably, in low SNR environments, the N2N-SAMP algorithm significantly outperforms the traditional SAMP algorithm in terms of Mean Squared Error (MSE) and Bit Error Rate (BER). Specifically, at SNR levels of 0 dB, 10 dB, and 20 dB, the MSE of channel estimation is reduced by 58.95%, 76.08%, and 19.42%, respectively, compared to the SAMP algorithm that selects the optimal threshold based on noise power. Furthermore, the system’s BER is decreased by 12.35%, 26.41%, and 29.62%, respectively.DiscussionThe findings suggest that the integration of N2N and SAMP algorithms offers a promising solution for improving channel estimation in underwater communication channels, especially under low SNR conditions. The significant reduction in MSE and BER highlights the effectiveness of our proposed method in enhancing the reliability and accuracy of underwater communication systems.

Rainfall data modeling using improved adaptive type-II progressively censored Weibull-exponential samples

To get enough data from experiments that last for a long time, a recently unique improved adaptive Type-II progressive censoring technique has been suggested. This study, taking this scheme into consideration, concentrates on some conventional and Bayesian estimation tasks for parameter and reliability indicators, where the underlying distribution is the Weibull-exponential. From a traditional point of view, the likelihood methodology is explored for gaining point and approximate confidence interval estimates. Apart from the standard method, the Bayesian methodology is investigated to obtain the Bayesian point and credible intervals by taking advantage of the Markov chain Monte Carlo technique and the squared error loss function. To differentiate between the traditional and Bayesian estimates, a simulation analysis proceeds under various conditions. In order to put the suggested strategies into application, a pair of rainfall data sets are evaluated and numerous precision criteria are employed to pick the best progressive censoring plan.

Enhanced FFT-Root-MUSIC Algorithm Based on Signal Reconstruction via CEEMD-SVD for Joint Range and Velocity Estimation for FMCW Radar.

Frequency-modulated continuous-wave (FMCW) radar is used to extract range and velocity information from the beat signal. However, the traditional joint range-velocity estimation algorithms often experience significant performances degradation under low signal-to-noise ratio (SNR) conditions. To address this issue, this paper proposes a novel approach utilizing the complementary ensemble empirical mode decomposition (CEEMD) combined with singular value decomposition (SVD) to reconstruct the beat signal prior to applying the FFT-Root-MUSIC algorithm for joint range and velocity estimation. This results in a novel joint range-velocity estimation algorithm termed as the CEEMD-SVD-FFT-Root-MUSIC (CEEMD-SVD-FRM) algorithm. First, the beat signal contaminated with additive white Gaussian noise is decomposed using CEEMD, and an appropriate autocorrelation coefficient threshold is determined to select the highly correlated intrinsic mode functions (IMFs). Then, the SVD is applied to the selected highly correlated IMFs for denoising the beat signal. Subsequently, the denoised IMFs and signal residuals are combined to reconstruct the beat signal. Finally, the FFT-Root-MUSIC algorithm is applied to the reconstructed beat signal to estimate both the range and Doppler frequencies, which are then used to calculate the range and velocity estimates of the targets. The proposed CEEMD-SVD-FRM algorithm is validated though simulations and experiments, demonstrating significant improvement in the robustness and accuracy of range and velocity estimates for the FMCW radar due to the effective denoising of the reconstructed beat signal. Moreover, it substantially outperforms the traditional methods in low SNR environments.

A Novel Doppler Estimation Approach Using ORBCOMM Signals for High-Precision Positioning

Positioning based on Low Earth Orbit (LEO) satellite Signals of Opportunity (SOP) often relies on Doppler observations. Therefore, the accuracy of Doppler frequency measurements significantly impacts the positioning performance. Traditional frequency estimation methods for ORBCOMM satellite signals are typically implemented in the frequency domain and neglect the impact of the “frequency chirp” effect on measurement accuracy, which leads to low computational efficiency, poor noise resistance, and limited estimation accuracy. To address this issue, a high-precision frequency estimation method combining a “coarse and fine” process is proposed. In the coarse estimation process, ephemeris prior information is combined with matched filtering to effectively separate the Doppler rate, thereby mitigating the spectral broadening caused by the Doppler rate. In the fine estimation process, ORBCOMM signal characteristics are fully exploited. Single-sideband filtering is applied to improve noise resistance, followed by precise frequency discrimination of the delayed signal. Experimental results demonstrate that the proposed method outperforms the state-of-the-art “FFT + MLE” approach, achieving a frequency measurement accuracy on the order of 0.01 Hz while requiring fewer computational resources. Furthermore, this method improves estimation performance by approximately 12 dB without compromising frequency measurement accuracy.

Deep Neural Network-Based Channel Estimation Scheme in Massive MIMO Systems

Channel estimation is one of the most essential technologies of wireless communication, as well as necessary indicators to measure the system’s quality. In recent years, the combination of channel estimation and deep learning techniques has raised wide attention and become one of the most popular research directions of machine learning applications in the wireless communication area. However, in wireless communication systems such as massive MIMO, it’s too complicated to take traditional channel estimation methods with shortcomings like insufficient precision or increased cost. With the combination of deep neural networks (DDN) and the least squares (LS) method, this paper focuses on the deep learning-based channel estimation for massive MIMO systems. Compared with traditional algorithms such as LS or minimum mean-square error method, the loss function of the results is significantly reduced while simulating for the same analog channel. The problem of lack of precision has been improved efficiently and the performance has been improved substantially, which can prove the adequacy of the design of the channel estimator.

Exploring the Hydraulic Properties of Unsaturated Soil Using Deep Learning and Digital Imaging Measurement

This work aims to improve the accuracy of traditional models for analyzing the hydraulic properties of unsaturated soil by integrating digital imaging measurement with deep learning techniques. The work first reviews current research on the basic characteristics of unsaturated soil and the applications of deep learning in this field. Next, it examines the impact of soil specimens’ physical properties on their hydraulic properties. This includes acquiring hydraulic parameters and the soil-water characteristic curve through full-surface digital imaging measurements. Finally, a soil hydraulic property model based on the backpropagation neural network (BPNN) is implemented, trained, and validated. Results indicate that the model’s predicted soil-water characteristic curve aligns closely with the experimental findings from previous studies. Moreover, the proposed BPNN-based unsaturated soil hydraulic property model uses the Levenberg–Marquardt algorithm, which reduces computational time and noise compared to alternative algorithms. Meanwhile, analysis of the model parameters suggests that ten neurons in the hidden layer provide optimal performance. By incorporating correlations between physical parameters, such as soil particle size and soil hydraulic properties, the model demonstrates lower error rates compared to other literature models. Overall, this BPNN model effectively represents the relationship between soil’s physical and hydraulic parameters, streamlining traditional soil correlation coefficient estimation.

Enhancing Software Effort Estimation with Pre-Trained Word Embeddings: A Small-Dataset Solution for Accurate Story Point Prediction

Traditional software effort estimation methods, such as term frequency–inverse document frequency (TF-IDF), are widely used due to their simplicity and interpretability. However, they struggle with limited datasets, fail to capture intricate semantics, and suffer from dimensionality, sparsity, and computational inefficiency. This study used pre-trained word embeddings, including FastText and GPT-2, to improve estimation accuracy in such cases. Seven pre-trained models were evaluated for their ability to effectively represent textual data, addressing the fundamental limitations of TF-IDF through contextualized embeddings. The results show that combining FastText embeddings with support vector machines (SVMs) consistently outperforms traditional approaches, reducing the mean absolute error (MAE) by 5–18% while achieving accuracy comparable to deep learning models like GPT-2. This approach demonstrated the adaptability of pre-trained embeddings for small datasets, balancing semantic richness with computational efficiency. The proposed method optimized project planning and resource allocation while enhancing software development through accurate story point prediction while safeguarding privacy and security through data anonymization. Future research will explore task-specific embeddings tailored to software engineering domains and investigate how dataset characteristics, such as cultural variations, influence model performance, ensuring the development of adaptable, robust, and secure machine learning models for diverse contexts.

Deep optimal experimental design for parameter estimation problems

Abstract Optimal experimental design is a well studied field in applied science and engineering. Techniques for estimating such a design are commonly used within the framework of parameter estimation. Nonetheless, in recent years parameter estimation techniques are changing rapidly with the introduction of deep learning techniques to replace traditional estimation methods. This in turn requires the adaptation of optimal experimental design that is associated with these new techniques. In this paper we investigate a new experimental design methodology that uses deep learning. We show that the training of a network as a Likelihood Free Estimator can be used to significantly simplify the design process and circumvent the need for the computationally expensive bi-level optimization problem that is inherent in optimal experimental design for non-linear systems. Furthermore, deep design improves the quality of the recovery process for parameter estimation problems. As proof of concept we apply our methodology to two different systems of Ordinary Differential equations.

Optimal fidelity estimation for density matrix

Fidelity estimation is a necessary tool for evaluating noise in quantum measurement and quantum computation. The traditional fidelity estimation is to calculate the distance between two density matrices by employing direct fidelity estimation, which consumes too much copies of state. To reduce the number of copies of the state, we develop optimal fidelity estimation by proposing an optimal model. It calculates the minimum number of copies of state given a fixed value for the fidelity deviation. The result shows it saves a large number of copies of state compared with traditional approach (Direct Fidelity estimation) that is developed several years ago.The number of copies of the state employed increases slower than linear increase with increase of the dimension of density matrix when pauli measurement basis is applied. In addition, it consumes roughly a constant number of copies of the state with the increase of dimension of density matrix when the measurement bases are freely chosen.

Comparing NIRA and Traditional Network Approaches: AStudy Case With Antisocial Personality Disorder Traits.

This study explores the NodeIdentifyR algorithm (NIRA) as a novel network analysis method for examining Antisocial Personality Disorder (ASPD) traits. Using a sample of 2230 Brazilian adults (aged 18-73 years) who responded to ASPD-related factors of the Personality Inventory for DSM-5 (PID-5), we applied NIRA to an ASPD network and compared its results with traditional network analysis methods. Our findings revealed that deceitfulness emerged as the most central trait across both methodologies. NIRA provided additional insights, indicating that simulated decreases in the likelihood of irresponsibility reduced the presence of other traits, while a simulated increase in deceitfulness amplified the likelihood of other ASPD pathological traits. Our results suggest that traditional network centrality measures converge with NIRA's simulated increase results, but NIRA's simulated decrease provides additional information not captured by traditional centrality estimates. We recommend further research to validate these findings across different psychopathologies and refine NIRA use in clinical settings. The insights from this study could serve as a foundation for developing targeted interventions and enhancing our understanding of ASPD trait dynamics.

Longitudinal Monitoring of Electric Vehicle Travel Trends Using Connected Vehicle Data

Historically, practitioners and researchers have used selected count station data and survey-based methods along with demand modeling to forecast vehicle miles traveled (VMT). While these methods may suffer from self-reporting bias or spatial and temporal constraints, the widely available connected vehicle (CV) data at 3 s fidelity, independent of any fixed sensor constraints, present a unique opportunity to complement traditional VMT estimation processes with real-world data in near real-time. This study developed scalable methodologies and analyzed 238 billion records representing 16 months of connected vehicle data from January 2022 through April 2023 for Indiana, classified as internal combustion engine (ICE), hybrid (HVs) or electric vehicles (EVs). Year-over-year comparisons showed a significant increase in EVMT (+156%) with minor growth in ICEVMT (+2%). A route-level analysis enables stakeholders to evaluate the impact of their charging infrastructure investments at the federal, state, and even local level, unbound by jurisdictional constraints. Mean and median EV trip lengths on the six longest interstate corridors showed a 7.1 and 11.5 mile increase, respectively, from April 2022 to April 2023. Although the current CV dataset does not randomly sample the full fleet of ICE, HVs, and EVs, the methodologies and visuals in this study present a framework for future evaluations of the return on charging infrastructure investments on a regular basis using real-world data from electric vehicles traversing U.S. roads. This study presents novel contributions in utilizing CV data to compute performance measures such as VMT and trip lengths by vehicle type—EV, HV, or ICE, unattainable using traditional data collection practices that cannot differentiate among vehicle types due to inherent limitations. We believe the analysis presented in this paper can serve as a framework to support dialogue between agencies and automotive Original Equipment Manufacturers in developing an unbiased framework for deriving anonymized performance measures for agencies to make informed data-driven infrastructure investment decisions to equitably serve ICE, HV, and EV users.

An Ensemble Learning Method for SOC Estimation of Lithium-Ion Batteries Using Machine Learning

Accurately assessing the State of Charge (SOC) is paramount for optimizing battery management systems, a cornerstone for ensuring peak battery performance and safety across diverse applications, encompassing vehicle powertrains and renewable energy storage systems. Confronted with the challenges of traditional SOC estimation methods, which often struggle with accuracy and cost-effectiveness, this research endeavors to elevate the precision of SOC estimation to a new level, thereby refining battery management strategies. Leveraging the power of integrated learning techniques, the study fuses Random Forest Regressor, Gradient Boosting Regressor, and Linear Regression into a comprehensive framework that substantially enhances the accuracy and overall performance of SOC predictions. By harnessing the publicly accessible National Aeronautics and Space Administration (NASA) Battery Cycle dataset, our analysis reveals that these integrated learning approaches significantly outperform traditional methods like Coulomb counting and electrochemical models, achieving remarkable improvements in SOC estimation accuracy, error reduction, and optimization of key metrics like R2 and Adjusted R2. This pioneering work propels the development of innovative battery management systems grounded in machine learning and deepens our comprehension of how this cutting-edge technology can revolutionize battery technology.