Estimation Performance Research Articles

CAP-UDF: Learning Unsigned Distance Functions Progressively From Raw Point Clouds With Consistency-Aware Field Optimization.

Surface reconstruction for point clouds is an important task in 3D computer vision. Most of the latest methods resolve this problem by learning signed distance functions from point clouds, which are limited to reconstructing closed surfaces. Some other methods tried to represent open surfaces using unsigned distance functions (UDF) which are learned from ground truth distances. However, the learned UDF is hard to provide smooth distance fields due to the discontinuous character of point clouds. In this paper, we propose CAP-UDF, a novel method to learn consistency-aware UDF from raw point clouds. We achieve this by learning to move queries onto the surface with a field consistency constraint, where we also enable to progressively estimate a more accurate surface. Specifically, we train a neural network to gradually infer the relationship between queries and the approximated surface by searching for the moving target of queries in a dynamic way. Meanwhile, we introduce a polygonization algorithm to extract surfaces using the gradients of the learned UDF. We conduct comprehensive experiments in surface reconstruction for point clouds, real scans or depth maps, and further explore our performance in unsupervised point normal estimation, which demonstrate non-trivial improvements of CAP-UDF over the state-of-the-art methods.

Operational Support Estimator Networks.

In this work, we propose a novel approach called Operational Support Estimator Networks (OSENs) for the support estimation task. Support Estimation (SE) is defined as finding the locations of non-zero elements in sparse signals. By its very nature, the mapping between the measurement and sparse signal is a non-linear operation. Traditional support estimators rely on computationally expensive iterative signal recovery techniques to achieve such non-linearity. Contrary to the convolutional layers, the proposed OSEN approach consists of operational layers that can learn such complex non-linearities without the need for deep networks. In this way, the performance of non-iterative support estimation is greatly improved. Moreover, the operational layers comprise so-called generative super neurons with non-local kernels. The kernel location for each neuron/feature map is optimized jointly for the SE task during training. We evaluate the OSENs in three different applications: i. support estimation from Compressive Sensing (CS) measurements, ii. representation-based classification, and iii. learning-aided CS reconstruction where the output of OSENs is used as prior knowledge to the CS algorithm for enhanced reconstruction. Experimental results show that the proposed approach achieves computational efficiency and outperforms competing methods, especially at low measurement rates by significant margins.

Carotid-femoral pulse wave velocity score, an estimator of cognitive performance in the elderly: results from the Toledo Study for Healthy Aging.

Ageing-related changes in the vascular wall influence the function of different organs; for this reason, we assessed how arterial stiffness measured by carotid-femoral pulse wave velocity (cf-PWV) modulates: the basal cognitive performance and the change in cognitive performance over the follow-up time. We developed a prospective, population-based cohort study with 1581 participants aged > 65years were obtained from the Toledo Study for Healthy Aging. Participants from the second wave (2011-2013) were selected for the cross-sectional analysis. Those who also performed the cognitive assessment in the third wave (2015-2017) were selected for the prospective analysis. Arterial stiffness was evaluated by cf-PWV. Multivariate segmented regression models were used to evaluate the association between cf-PWV scores and basal neuropsychological evaluation scores and change of neuropsychological evaluation scores along follow-up. Cross-sectional analysis showed that as cf-PWV grew within the cf-PWV (5- < 10) category an improvement was observed in 7-min test, free short-term memory, and hole peg test. Furthermore, in the cf-PWV (> 13-18) category a decrease was observed in total short-term memory, free long-term memory, and total long-term memory. Prospective analysis showed a progressive worsening of cognitive function as cf-PWV increases within the cf-PWV (> 13-18) category in 7-min test, object denomination, immediate and short-term memory, and hole peg test, while in the cf-PWV (5- < 10) category, there was observed a decrease in Cumulative Executive Dysfunction Index score and short-term memory. In conclusion, a higher cf-PWV score is associated with worse cognitive performance, and with a worse evolution, reinforcing the need to plan interventions to delay arterial stiffness and its consequences.

Functional Concurrent Regression Mixture Models Using Spiked Ewens-Pitman Attraction Priors.

Functional concurrent, or varying-coefficient, regression models are a form of functional data analysis methods in which functional covariates and outcomes are collected concurrently. Two active areas of research for this class of models are identifying influential functional covariates and clustering their relations across observations. In various applications, researchers have applied and developed methods to address these objectives separately. However, no approach currently performs both tasks simultaneously. In this paper, we propose a fully Bayesian functional concurrent regression mixture model that simultaneously performs functional variable selection and clustering for subject-specific trajectories. Our approach introduces a novel spiked Ewens-Pitman attraction prior that identifies and clusters subjects' trajectories marginally for each functional covariate while using similarities in subjects' auxiliary covariate patterns to inform clustering allocation. Using simulated data, we evaluate the clustering, variable selection, and parameter estimation performance of our approach and compare its performance with alternative spiked processes. We then apply our method to functional data collected in a novel, smartphone-based smoking cessation intervention study to investigate individual-level dynamic relations between smoking behaviors and potential risk factors.

A Survey on Efficient Vision Transformers: Algorithms, Techniques, and Performance Benchmarking.

Vision Transformer (ViT) architectures are becoming increasingly popular and widely employed to tackle computer vision applications. Their main feature is the capacity to extract global information through the self-attention mechanism, outperforming earlier convolutional neural networks. However, ViT deployment and performance have grown steadily with their size, number of trainable parameters, and operations. Furthermore, self-attention's computational and memory cost quadratically increases with the image resolution. Generally speaking, it is challenging to employ these architectures in real-world applications due to many hardware and environmental restrictions, such as processing and computational capabilities. Therefore, this survey investigates the most efficient methodologies to ensure sub-optimal estimation performances. More in detail, four efficient categories will be analyzed: compact architecture, pruning, knowledge distillation, and quantization strategies. Moreover, a new metric called Efficient Error Rate has been introduced in order to normalize and compare models' features that affect hardware devices at inference time, such as the number of parameters, bits, FLOPs, and model size. Summarizing, this paper first mathematically defines the strategies used to make Vision Transformer efficient, describes and discusses state-of-the-art methodologies, and analyzes their performances over different application scenarios. Toward the end of this paper, we also discuss open challenges and promising research directions.

Multimodal Data Fusion for Precise Lettuce Phenotype Estimation Using Deep Learning Algorithms

Effective lettuce cultivation requires precise monitoring of growth characteristics, quality assessment, and optimal harvest timing. In a recent study, a deep learning model based on multimodal data fusion was developed to estimate lettuce phenotypic traits accurately. A dual-modal network combining RGB and depth images was designed using an open lettuce dataset. The network incorporated both a feature correction module and a feature fusion module, significantly enhancing the performance in object detection, segmentation, and trait estimation. The model demonstrated high accuracy in estimating key traits, including fresh weight (fw), dry weight (dw), plant height (h), canopy diameter (d), and leaf area (la), achieving an R2 of 0.9732 for fresh weight. Robustness and accuracy were further validated through 5-fold cross-validation, offering a promising approach for future crop phenotyping.

Performance of Forensic Age Estimation by Aspartic Acid Racemization and DNA Methylation: A Systematic Review

Background Forensic age estimation is not difficult when the body is found in good condition, but in cases of severe decomposition or damage, such as burnt or separated body parts, then the analysis can only be done with bones and teeth. There has been abundant research and development in the field of related biochemistry over the years. Various molecular changes occur in hard tissues and long-lived proteins, such as those in bones and teeth during the physiological process of aging. Aspartic acid racemization and DNA methylation are still the most frequently used age estimation methods because of their advantages in accuracy. Method This study aimed to compare the accuracy of DNA methylation and aspartic acid racemization methods for age estimation. Journal articles were searched in the electronic databases PubMed, Scopus, and Semantic Scholar of 2017-2022 according to PRISMA guidelines. Result Twelve journal articles were eligible for review. The DNA methylation method is quite simple to use because of commercially available methylation kits. Furthermore, the results can be obtained relatively quickly without requiring many samples, and the method is less sensitive to thermal and other damage than the aspartic acid racemization method. Conclusion The aspartic acid racemization method for age estimation has high accuracy, especially in determining age at death. However, temperature and the condition of the teeth affect the racemization of aspartic acid. Given that DNA methylation is generally stable in a wide range of temperatures, it provides a better approach to determining the chronological age even from charred remains.

Fault-Tolerant Control for Quadcopters Under Actuator and Sensor Faults

Fault detection and diagnosis (FDD) methods and fault-tolerant control (FTC) have been the focus of intensive research across various fields to ensure safe operation, reduce costs, and optimize maintenance tasks. Unmanned aerial vehicles (UAVs), particularly quadcopters or quadrotors, are often prone to faults in sensors and actuators due to their complex dynamics and exposure to various external uncertainties. In this context, this work implements different FDD approaches based on the Kalman filter (KF) for fault estimation to achieve FTC of the quadcopter, considering different faults with nonlinear behaviors and the possibility of simultaneous occurrences in actuators and sensors. Three KF approaches are considered in the analysis: linear KF, extended KF (EKF), and unscented KF (UKF), along with three-stage and adaptive variations of the KF. FDD methods, especially the adaptive filter, could enhance fault estimation performance in the scenarios considered. This led to a significant improvement in the safety and reliability of the quadcopter through the FTC architecture, as the system, which previously became unstable in the presence of faults, could maintain stable operation when subjected to uncertainties.

A tactile perception method with flexible grating structural color

Abstract Affordable high-resolution cameras and state-of-the-art computer vision techniques have led to the emergence of various vision-based tactile sensors. However, current vision-based tactile sensors mainly depend on geometric optics or marker tracking for tactile assessments, resulting in limited performance. To solve this dilemma, we introduce optical interference patterns as the visual representation of tactile information for flexible tactile sensors. We propose a novel tactile perception method and its corresponding sensor combining structural colors from flexible blazed gratings with deep learning. The richer structural colors and finer data processing foster the tactile estimation performance. The proposed sensor has an overall normal force magnitude accuracy of 6 mN, a planar resolution of 79 μm, and a contact-depth resolution of 25 μm. This work presents a promising tactile method that combines wave optics, soft materials, and machine learning. It demonstrates well in tactile measurement, and can be expanded into multiple sensing fields.

Research on 3D humanoid robot pose estimation based on HRNet-Epipolar and CRF robot model by multiple view

Purpose This paper aims to present an unmarked method including entire two-dimensional (2D) and three-dimensional (3D) methods to recover absolute 3D humanoid robot poses from multiview images. Design/methodology/approach The method consists of two separate steps: estimating the 2D poses in multiview images and recovering the 3D poses from the multiview 2D heatmaps. The 2D one is conducted by High-Resolution Net with Epipolar (HRNet-Epipolar), and the Conditional Random Fields Humanoid Robot Pictorial Structure Model (CRF Robot Model) is proposed to recover 3D poses. Findings The performance of the algorithm is validated by experiments developed on data sets captured by four RGB cameras in Qualisys system. It illustrates that the algorithm has higher Mean Per Joint Position Error than Direct Linear Transformation and Recursive Pictorial Structure Model algorithms when estimating 14 joints of the humanoid robot. Originality/value A new unmarked method is proposed for 3D humanoid robot pose estimation. Experimental results show enhanced absolute accuracy, which holds important theoretical significance and application value for humanoid robot pose estimation and motion performance testing.

A class of mixed thinning threshold integer-valued autoregressive model for the COVID-19 data

To better capture the features of time series of counts such as the counting of elements of variable character and piecewise phenomenon, this paper proposes a class of mixed-thinning threshold integer-valued autoregressive model where the distribution of the innovation sequence is unknown. Strict stationarity ergodicity property is proved. The unknown parameters in the model are estimated by conditional least squares and modified quasi-likelihood methods, as well as their asymptotic normality, are established for the case that the threshold variable is known. The performances of the estimators are investigated in simulation, which manifests that the modified quasi-likelihood estimation performs better. Finally, a set of COVID-19 data on critical cases imported from outside China is analyzed to illustrate the application of developed model.

RBCKF-Based Vehicle State Estimation by Adaptive Weighted Fusion Strategy Considering Composite-State Tire Model

The acquisition of vehicle driving status information is a key function of vehicle dynamics systems, and research on high-precision and high-reliability estimation of key vehicle states has significant value. To improve the state observation effect, a vehicle sideslip angle estimation method adopting a robust bias compensation Kalman filter and adaptive weight fusion strategy is proposed. On the basis of the extended Kalman filter algorithm, and with the goals of estimation exactitude and robustness, considering the potential signal deviation, a vehicle state robust deviation compensation Kalman filter estimation algorithm considering bias compensation and residual covariance matrix weighting is proposed. Meanwhile, considering the adaptive and dynamic adjustment capabilities of the observation system in complex state-change scenarios, an estimation strategy based on adaptive weight fusion and a model-based estimator is proposed. The results confirm that the robust bias compensation Kalman filter can ensure estimation exactitude and robustness when the vehicle state fluctuates greatly, and the proposed fusion strategy can ensure that the vehicle maintains optimal estimation performance during operating condition switching.

Event-Triggered Transmission of Sensor Measurements Using Twin Hybrid Filters for Renewable Energy Resource Management Systems

Recently, solar and wind power generation have gained attention as pathways to achieving carbon neutrality, and Renewable Energy Resource Management System (RERMS) technology has been developed to monitor and control small-scale, distributed renewable energy resources. In this work, we present an Event-Triggered Transmission (ETT) algorithm for RERMS, which transmits sensor measurements to the base station only when necessary. The ETT algorithm helps prevent congestion in the communication channel between RERMS and the base station, avoiding time delays or packet loss caused by the excessive transmission of sensor measurements. We design a hybrid state estimation algorithm that combines Kalman and Finite Impulse Response (FIR) filters to enhance the estimation performance, and we propose a new ETT algorithm based on this design. We evaluate the performance of the proposed algorithm through experiments that transmit actual sensor measurements from a photovoltaic power generation system to the base station, demonstrating that it outperforms existing algorithms.

Impact of knowledge of HPV positivity on cervical cytology performance in latin america.

Cervical cytology is recommended by WHO as a triage option in HPV-based cervical cancer screening programmes. We assessed the performance of cytology to detect CIN3+ without and with knowledge of HPV positivity. Women were screened with cytology and HPV across ESTAMPA study centres in Latin America. Screen-positives were referred to colposcopy with biopsy and treatment as needed. Cytology was initially interpreted without knowing HPV results. A subset of cytologies from HPV-positive women were re-interpreted at the same laboratories, with knowledge of HPV status, blinded to previous cytology and histological diagnosis. Performance indicators for cytology to detect CIN3+ without and with knowledge of HPV positivity were estimated. A total of 4,087 women were included, of which 490 had histologically confirmed CIN3 + (455 CIN3 and 35 cancers). Cytology sensitivity without knowledge of HPV positivity for CIN3+ was 47.2% (95% CI: 42.5-51.9), whereas with knowledge of HPV positivity, the sensitivity was higher (58.9%, 95% CI: 54.2-63.5), p < .0001. The specificity without knowledge of HPV was 89.4% (95% CI: 88.2-90.5), while with knowledge of HPV positivity was 78.9% (95% CI: 77.4-80.4), p < .0001. Performance estimates varied by study centre for cytology without knowing the HPV positivity, (range from 32.8% to 61.5% for sensitivity; range 80.7% to 98.6% for specificity). Similarly, performance varied with knowledge of HPV positivity (36.1% to 93.4% for sensitivity; 39.6% to 98.6% for specificity). The increase in sensitivity of cytology with HPV knowledge was limited and highly variable, reinforcing the need for alternative triage methods to support cervical cancer elimination goals.

Generalized Path Integral Energy and Heat Capacity Estimators of Quantum Oscillators and Crystals Using Harmonic Mapping.

Imaginary-time path integral (PI) is a rigorous tool to treat nuclear quantum effects in static properties. However, with its high computational demand, it is crucial to devise precise estimators. We introduce generalized PI estimators for the energy and heat capacity that utilize coordinate mapping. While it can reduce to the standard thermodynamic and centroid virial (CVir) estimators, the formulation can also take advantage of harmonic character of quantum oscillators and crystals to construct a coordinate mapping. The method is not applicable to fluids or systems with imaginary modes such as double-well potentials. This yields harmonically mapped averaging (HMA) estimators, with mappings that decouple (HMAc) or couple (HMAq) the centroid and internal modes. The HMAq is constructed with normal mode coordinates (HMAq-NM) with quadratic scaling of cost or harmonic oscillator staging (HMAq-SG) coordinates with linear scaling. The estimator performance is examined for a 1D anharmonic oscillator and a 3D Lennard-Jones crystal using path integral molecular dynamics (PIMD) simulation. The HMA estimators consistently provide more precise estimates compared to CVir, with the best performance obtained by HMAq-NM, followed by HMAq-SG, and then HMAc. We also examine the effect of anharmonicity (for AO), intrinsic quantumness, and Trotter number. The HMA formulation introduced assumes the availability of forces and Hessian matrix; however, an equally efficient finite difference alternative is possible when these derivatives are inaccessible. The remarkable improvement in precision offered by HMAq estimators provides a framework for efficient PI simulation of more challenging systems, such as those based on ab initio calculations.

Noise‐robust structural response estimation method using short‐time Fourier transform and long short‐term memory

AbstractStructural response estimation based on deep learning can suffer from reduced estimation performance owing to discrepancies between the training and test data as the noise level in the test data increases. This study proposes a short‐time Fourier transform‐based long short‐term memory (STFT‐LSTM) model to improve estimation performance in the presence of noise and ensure estimation robustness. This model enables robust estimations in the presence of noise by positioning an STFT layer before feeding the data into the LSTM layer. The output transformed into the time‐frequency domain by the STFT layer is learned by the LSTM model. The robustness of the proposed model was validated using a numerical model with three degrees of freedom at various signal‐to‐noise ratio levels, and its robustness against impulse and periodic noise was verified. Experimental validation assessed the estimation robustness under impact load and verified the robustness against environmental noise in the acquired acceleration response.

Non-Destructive Estimation of Paper Fiber Using Macro Images: A Comparative Evaluation of Network Architectures and Patch Sizes for Patch-Based Classification

Over the years, research in the field of cultural heritage preservation and document analysis has exponentially grown. In this study, we propose an advanced approach for non-destructive estimation of paper fibers using macro images. Expanding on studies that implemented EfficientNet-B0, we explore the effectiveness of six other deep learning networks, including DenseNet-201, DarkNet-53, Inception-v3, Xception, Inception-ResNet-v2, and NASNet-Large, in conjunction with enlarged patch sizes. We experimentally classified three types of paper fibers, namely, kozo, mitsumata, and gampi. During the experiments, patch sizes of 500, 750, and 1000 pixels were evaluated and their impact on classification accuracy was analyzed. The experiments demonstrated that Inception-ResNet-v2 with 1000-pixel patches achieved the highest patch classification accuracy of 82.7%, whereas Xception with 750-pixel patches exhibited the best macro-image-based fiber estimation performance at 84.9%. Additionally, we assessed the efficacy of the method for images containing text, observing consistent improvements in the case of larger patch sizes. However, limitations exist in background patch availability for text-heavy images. This comprehensive evaluation of network architectures and patch sizes can significantly advance the field of non-destructive paper analysis, offering valuable insights into future developments in historical document examination and conservation science.

SMS-Net: Bridging the Gap Between High Accuracy and Low Computational Cost in Pose Estimation

Human pose estimation identifies and classifies key joints of the human body in images or videos. Existing pose estimation methods can precisely capture human movements in real time but require significant computational time and resources, which restricts their usage in specific conditions. Thus, we propose a lightweight pose estimation model—SMS-Net—based on the sequentially stacked structure of the hourglass network. The proposed model uses various lightweight techniques to enable high-speed pose estimation while requiring minimal storage space and computation. Specifically, a shuffle-gated block was introduced to reduce the computational load and number of parameters during the feature extraction process of the encoder composing each hourglass network. A multi-dilation block was used in the decoder to secure the receptive fields of various scales without increasing the computational load. The performance of the proposed model was assessed using the MPII and Common Objects in Context (COCO) datasets used for pose estimation and certain performance metrics and compared with state-of-the-art lightweight pose estimation models. Furthermore, an ablation study was performed to assess the impact of each module on network performance and efficiency. The results demonstrate that the proposed model achieved an improved balance between computational efficiency and performance compared to existing models in human pose estimation. Overall, the study findings can provide a basis for applications in computer vision technology.

Recursive-RARE-based three-dimensional parameter estimation of near-field source considering amplitude attenuation

This paper addresses the issue for near-field (NF) localization considering amplitude attenuation, proposing a recursive rank-reduction (RARE) method for three-dimensional (3-D) parameter estimation of NF sources incident on a symmetrical cross array. The proposed method constructs several one-dimensional (1-D) spectral peak search estimators to obtain two-dimensional angle and range parameters. Initially, using the received data from symmetrical array elements in one axis, a 1-D spectral peak search estimator is constructed. The origins of two types of pseudo peaks within this estimator are analyzed, and then, corresponding pseudo peaks removal methods, namely the initial screening method and the recursive RARE method, are presented to obtain the estimate of the first angle parameter. Subsequently, the estimated results are fed into another 1-D spectral peak search estimator constructed from the original received data to obtain the range parameter. Finally, the same process is applied to the other axis to obtain the second angle and range parameters, followed by a parameter matching operation for 3-D parameters. Compared to existing NF source localization methods, the proposed method more effectively eliminates pseudo peaks, and demonstrates superior parameter estimation performance under conditions of small number of snapshots and low signal-to-noise ratio, as validated by several simulation results.

Neuro-Cognitive Insights Into Engineering Design: Exploring Electroencephalography Predictive Associations With Task Performance

Abstract This paper investigates the relationship between brain activity, measured by electroencephalography (EEG) data, and the performance assessment result of engineering design activities involving different cognitive processes. Employing a novel signal processing pipeline, we analyzed EEG variations of 37 subjects during two design tasks that mostly leverage, respectively, convergent and divergent thinking: the design with morphological table (task and the problem-solving task. The EEG recordings underwent meticulous artifact removal, allowing for a comprehensive investigation into the statistical relationships between frequency bands, channels, and design outcome performance metrics. The developed models linking better design outcomes with brain (de)synchronization demonstrated remarkable accuracy, precision, and recall across performance metrics for both tasks. Notably, the EEG data in theta band measured from the frontal area at both hemispheres and a left parietal/occipital channel were essential for estimating better design performance with brain desynchronization. On the contrary, the model based on brain synchronization produces precise estimations of design performance with alpha band and channels in temporal and parietal areas. These findings highlight EEG variation as a viable proxy for design performance, paving the way for more effective performance prediction models with fewer sensors. Overall, this research contributes to the emerging field of neurocognitive design assessment and underscores the potential for EEG-based predictions in engineering design tasks.