Search Results (16,516)

In computer vision, accurately estimating a 3D human skeleton from a single RGB image remains a challenging task. Inspired by the advantages of multi-view approaches, we propose a method of predicting enhanced 2D skeletons (specifically, predicting the joints’ relative depths) from multiple virtual viewpoints based on a single real-view image. By fusing these virtual-viewpoint skeletons, we can then estimate the final 3D human skeleton more accurately. Our network consists of two stages. The first stage is composed of a two-stream network: the Real-Net stream predicts 2D image coordinates and the relative depth for each joint from the real viewpoint, while the Virtual-Net stream estimates the relative depths in virtual viewpoints for the same joints. Our network’s second stage consists of a depth-denoising module, a cropped-to-original coordinate transform (COCT) module, and a fusion module. The goal of the fusion module is to fuse skeleton information from the real and virtual viewpoints so that it can undergo feature embedding, 2D-to-3D lifting, and regression to an accurate 3D skeleton. The experimental results demonstrate that our single-view method can achieve a performance of 45.7 mm on average per-joint position error, which is superior to that achieved in several other prior studies of the same kind and is comparable to that of other sequence-based methods that accept tens of consecutive frames as the input. Full article

The accurate estimation of flow angles is crucial for enhancing flight performance and aircraft safety. Flow angles of fixed-wing small unmanned aerial vehicles (SUAVs) are more vulnerable due to their low airspeed. Current flow angle measurement devices have not been widely implemented in SUAVs due to their substantial cost and size constraints. Moreover, there are no general estimation methods suitable for SUAVs based on their rudimentary sensor suite. This study presents a generalized optimization-assisted filter estimation (OAFE) method for estimating the relative velocity and flow angles of fixed-wing SUAVs based on a standard sensor suite. This OAFE method mainly consists of a cubature Kalman filter and an optimizer. The filter serves as the main loop with which to generate flow angles in real time by fusing the acceleration, angular rate, attitude, and airspeed. Without flow angle measurements, the optimizer generates approximate aerodynamic derivatives, which serve as pseudo-measurements with which to refine the performance of the filter. The results demonstrate that the estimated angle of attack and side slip angle displayed root mean square errors of around 0.11° and 0.24° in the simulation. The feasibility was also verified in field tests. The OAFE method does not require flow angle measurements, the prior acquisition of aerodynamic parameters, or model training, making it suitable for quick deployment on different SUAVs. Full article

In this study, we combined genomic and gut microbiome data to evaluate 13 economically important growth and feed efficiency traits in 407 Dahen broilers, including body weight (BW) at four, six, nine, and ten weeks of age (BW4, BW6, BW9, and BW10), as well as the average daily gain (ADG6, ADG9, and ADG10), feed conversion ratio (FCR6, FCR9, and FCR10), and residual feed intake (RFI6, RFI9, and RFI10) for the three growing ages. The highest ADG and lowest FCR were observed at nine and six weeks of age, respectively. We obtained 47,872 high-quality genomic single-nucleotide polymorphisms (SNPs) by sequencing the genomes and 702 amplicon sequence variants (ASVs) of the gut microbiome by sequencing the 16S rRNA gene, both of which were used for analyses of linear mixed models. The heritability estimates (± standard error, SE) ranged from 0.103 ± 0.072 to 0.156 ± 0.079 for BW, 0.154 ± 0.074 to 0.276 ± 0.079 for the ADG, 0.311 ± 0.076 to 0.454 ± 0.076 for the FCR, and 0.413 ± 0.077 to 0.609 ± 0.076 for the RFI traits. We consistently observed moderate and low negative genetic correlations between the BW traits and the FCR and RFI traits (r = −0.562 to −0.038), whereas strong positive correlations were observed between the FCR and RFI traits (r = 0.564 to 0.979). For the FCR and RFI traits, strong positive correlations were found between the measures at the three ages. In contrast to the genomic contribution, we did not detect a gut microbial contribution to all of these traits, as the estimated microbiabilities did not confidently deviate from zero. We systematically evaluated the contributions of host genetics and gut microbes to several growth and feed efficiency traits in Dahen broilers, and the results show that only the host genetics had significant effects on the phenotypic variations in a flock. The parameters obtained in this study, based on the combined use of genomic and gut microbiota data, may facilitate the implementation of efficient breeding schemes in Dahen broilers. Full article

Canopy water interception is a key parameter to study the hydrological cycle, water utilization efficiency, and energy balance in terrestrial ecosystems. Especially in sprinkler-irrigated farmlands, the canopy interception further influences field energy distribution and microclimate, then plant transpiration and photosynthesis, and finally crop yield and water productivity. To reduce the field damage and increase measurement accuracy under traditional canopy water interception measurement, UAVs equipped with multispectral cameras were used to extract in situ crop canopy information. Based on the correlation coefficient (r), vegetative indices that are sensitive to canopy interception were screened out and then used to develop canopy interception models using linear regression (LR), random forest (RF), and back propagation neural network (BPNN) methods, and lastly these models were evaluated by root mean square error (RMSE) and mean relative error (MRE). Results show the canopy water interception is first closely related to relative normalized difference vegetation index (R_△NDVI) with r of 0.76. The first seven indices with r from high to low are R_△NDVI, reflectance values of the blue band (Blue), reflectance values of the near-infrared band (Nir), three-band gradient difference vegetation index (TGDVI), difference vegetation index (DVI), normalized difference red edge index (NDRE), and soil-adjusted vegetation index (SAVI) were chosen to develop canopy interception models. All the developed linear regression models based on three indices (R_△NDVI, Blue, and NDRE), the RF model, and the BPNN model performed well in canopy water interception estimation (r: 0.53–0.76, RMSE: 0.18–0.27 mm, MRE: 21–27%) when the interception is less than 1.4 mm. The three methods underestimate the canopy interception by 18–32% when interception is higher than 1.4 mm, which could be due to the saturation of NDVI when leaf area index is higher than 4.0. Because linear regression is easy to perform, then the linear regression method with NDVI is recommended for canopy interception estimation of sprinkler-irrigated winter wheat. The proposed linear regression method and the R_△NDVI index can further be used to estimate the canopy water interception of other plants as well as forest canopy. Full article

The traditional optimization scheduling of distribution networks has often only considered the volatility and randomness of wind and solar output. When estimating the prediction errors of wind and solar output, wind turbines and photovoltaics are typically considered separately, overlooking the correlation between them. Accurate modeling of wind and solar output prediction errors is crucial for enhancing the reliability and economy of distribution network scheduling. To address this, this paper proposes a new modeling method. First, based on the volatility and randomness of wind and solar output, it considers the characteristic that wind and solar outputs in the same region at the same time are correlated. A multivariate nonparametric kernel density estimation is introduced to fit the joint prediction error distribution of wind and solar output using historical data. Next, the impact of joint prediction errors on system scheduling costs is considered by introducing a penalty cost in the economic objective function for the errors caused by wind and solar predictions. Additionally, energy storage devices are integrated into the system to smooth power fluctuations, thereby constructing an economically optimized scheduling model for wind–solar–storage distribution networks based on stochastic correlations. Finally, testing is conducted using an improved IEEE-33 node system. The results indicate that the model considering the correlation between wind and solar output significantly improves the fitting accuracy of prediction errors compared to traditional models that only consider randomness. It also enhances the utilization rate of wind and solar energy and improves the economic performance of the distribution network. Full article

This study investigates the relationship between shipping connectivity, environmental quality, financial development, and economic growth among 14 countries in the Regional Comprehensive Economic Partnership (RCEP) from 2006 to 2019. Using panel-corrected standard error, Dynamic Seemingly Unrelated Regression, and Driscoll–Kraay estimation methods, the analysis reveals that shipping connectivity significantly contributes to financial development and economic growth, while also exerting a negative impact on environmental quality. These findings suggest that the maritime sector can have significant impacts not only on economic growth and financial development but also on environmental sustainability. In countries where maritime shipping has increased, particularly with the growth of trade, positive outcomes are observed in terms of financial development and economic growth, while negative impacts on environmental quality are also evident. This study provides insights for policymakers to develop strategies that maximize economic benefits while reducing environmental harm in order to achieve sustainable development in the maritime sector. Full article

Accident analysis models are crucial tools for understanding and preventing accidents in the maritime industry. Despite the advances in ship technology and regulatory frameworks, human factors remain a leading cause of marine accidents. The complexity of human behavior, influenced by social, technical, and psychological aspects, makes accident analysis challenging. Various methods are used to analyze accidents, but no single approach is universally chosen for use as the most effective. Traditional methods often emphasize human errors, technical failures, and mechanical breakdowns. However, hybrid models, which combine different approaches, are increasingly recognized for providing more accurate predictions by addressing multiple causal factors. In this study, a dynamic hybrid model based on the Human Factors Analysis and Classification System (HFACS) and Bayesian Networks is proposed to predict and estimate accident risks in narrow waterways. The model utilizes past accident data and expert judgment to assess the potential risks ships encounter when navigating these confined areas. Uniquely, this approach enables the prediction of accident probabilities under varying operational conditions, offering practical applications such as real-time risk estimation for vessels before entering the Istanbul Strait. By offering real-time insights, the proposed model supports traffic operators in implementing preventive measures before ships enter high-risk zones. The results of this study can serve as a decision-support system not only for VTS operators, shipmasters, and company representatives but also for national and international stakeholders in the maritime industry, aiding in both accident probability prediction and the development of preventive measures. Full article

This study addresses the challenge of optimizing energy management in the electric vehicle industry, specifically focusing on motorsport. It particularly targets optimizing energy management during an endurance event at the Formula Student competition. The research involves detailed simulation of a complete endurance event, including developing precise track and vehicle models and their application in real-time energy management of our motorsport vehicle. The primary objective is to develop an energy reference profile that optimizes point scoring following the event’s specific rules. The energy reference profile serves as a strategic guideline for energy consumption and its regeneration throughout the endurance event. What sets this study apart is its emphasis on the real-time feedback controller’s implementation in the Formula Student prototype, FST12, specifically during the endurance event. This controller dynamically regulates the inverter’s power output, ensuring the vehicle closely follows the pre-established energy reference profile. This real-time energy management approach enhances overall performance by optimizing energy utilization for maximum scoring potential. The developed distance estimation method presented an error of less than 0.7% compared to experimental measurements. The Formula Student prototype, FST12, underwent experimental validation on a real 20 km closed-loop track. Results showed that the optimized strategy can be implemented with less than 0.5% of error in energy consumption and 6.8% of error in the obtained competing points. Full article

This study contributes to improving the accuracy of temperature measurements with a platinum resistance temperature detector (RTD) by proposing techniques to mitigate the error due to self-heating by the operating current. An assessment of the measurement errors of the platinum RTD was carried out to study ways to improve their accuracy. High accuracy can be achieved by individual calibration using a voltage divider circuit to measure resistance, the substitution method, and the transitional measure. It was shown that each of these approaches offers potential improvements in the accuracy of temperature measurements using RTDs. However, one of the genuine limitations is the error due to heating the RTD by the operating current. To address this, both linear and nonlinear methods for correcting the error due to heating by the operating current were studied. This paper examines how these methods can be applied to mitigate the influence of self-heating on measurement accuracy. Moreover, the residual errors associated with these methods of correction were estimated. The analysis showed that while these methods can reduce the errors significantly, there remain limitations below which it is not possible to mitigate the error. Full article

With the growing demand for industrial robots in the aerospace manufacturing process, the lack of positioning accuracy has become a critical factor limiting their broad application in precision manufacturing. To enhance robot positioning accuracy, one crucial approach is to analyze the distribution patterns of robot errors and leverage spatial similarity for error prediction and compensation. However, existing methods in Cartesian space struggle to achieve accurate error estimation when the robot is loaded or the end-effector orientations are varied. To address these challenges, a novel method for robot error prediction and accuracy compensation within configuration space is proposed. The analysis of robot error distribution reveals that the spatial similarity of robot errors is more pronounced and stable in configuration space compared to Cartesian space, and this property exhibits significant anisotropy across joint dimensions. A spatial-interpolation-based unbiased estimation method with joint weights optimization is proposed for robot errors prediction, and the particle filter method is utilized to search for the optimal joint weights, enhancing the anisotropic characteristics of the prediction model. Based on the robot error prediction model, a cyclic searching method is employed to directly compensate for the joint angles. An experimental system is established using an industrial robot equipped with a 120 kg end-effector and a laser tracker. Eighty sampling points with diverse poses are randomly selected within the task workspace to measure the robot errors before and after compensation. The proposed method achieves an error prediction accuracy of 0.172 mm, reducing the robot error from the original 4.96 mm to 0.28 mm, thus meeting the stringent accuracy requirements for hole machining in robotic aerospace assembly processes. Full article

Human Pose Estimation (HPE) is a computer vision application that utilizes deep learning techniques to precisely locate Key Joint Points (KJPs), enabling the accurate description of a person’s pose. HPE models can be extended to facilitate Range of Motion (ROM) assessment by leveraging patient photographs. This study aims to evaluate and compare the performance of HPE models for assessing upper limbs ROM. A physiotherapist evaluated the degrees of ROM in shoulders (flexion, extension, and abduction) and elbows (flexion and extension) for fifty-two participants using both Universal Goniometer (UG) and five HPE models. Participants were instructed to repeat each movement three times to obtain measurements with the UG, then positioned while photos were captured using the NLMeasurer mobile application. The paired t-test, bias, and error measures were employed to evaluate the difference and agreement between measurement methods. Results indicated that the MoveNet Thunder INT16 model exhibited superior performance. Root Mean Square Errors obtained through this model were <10° in 8 of 10 analyzed movements. HPE models demonstrated better performance in shoulder flexion and abduction movements while exhibiting unsatisfactory performance in elbow flexion. Challenges such as image perspective distortion, environmental lighting conditions, images in monocular view, and complications in the pose may influence the models’ performance. Nevertheless, HPE models show promise in identifying KJPs and facilitating ROM measurements, potentially enhancing convenience and efficiency in assessments. However, their current accuracy for this application is unsatisfactory, highlighting the need for caution when considering automated upper limb ROM measurement with them. The implementation of these models in clinical practice does not diminish the crucial role of examiners in carefully inspecting images and making adjustments to ensure measurement reliability. Full article

Wearable accelerometers are widely used as an ecologically valid and scalable solution for long-term at-home sleep monitoring in both clinical research and care. In this study, we applied a deep learning domain adversarial convolutional neural network (DACNN) model to this task and demonstrated that this new model outperformed existing sleep algorithms in classifying sleep–wake and estimating sleep outcomes based on wrist-worn accelerometry. This model generalized well to another dataset based on different wearable devices and activity counts, achieving an accuracy of 80.1% (sensitivity 84% and specificity 58%). Compared to commonly used sleep algorithms, this model resulted in the smallest error in wake after sleep onset (MAE of 48.7, Cole–Kripke of 86.2, Sadeh of 108.2, z-angle of 57.5) and sleep efficiency (MAE of 11.8, Cole–Kripke of 18.4, Sadeh of 23.3, z-angle of 9.3) outcomes. Despite being around for many years, accelerometer-alone devices continue to be useful due to their low cost, long battery life, and ease of use. Improving the accuracy and generalizability of sleep algorithms for accelerometer wrist devices is of utmost importance. We here demonstrated that domain adversarial convolutional neural networks can improve the overall accuracy, especially the specificity, of sleep–wake classification using wrist-worn accelerometer data, substantiating its use as a scalable and valid approach for sleep outcome assessment in real life. Full article

Indoor positioning systems have become increasingly important due to the rapid expansion of Internet of Things (IoT) technologies, especially for providing precise location-based services in complex environments such as multi-floor campus buildings. This paper presents a WiFi fingerprint indoor localization system based on AdaBoost, combined with a new access point (AP) filtering technique. The system comprises offline and online phases. During the offline phase, a fingerprint database is created using received signal strength (RSS) values for two four-floor campus buildings. In the online phase, the AdaBoost classifier is used to accurately estimate locations. To improve localization accuracy, APs that always appear in the measurement data are selected for applying the AdaBoost algorithm, aiming to eliminate noise from the fingerprint database. The performance of the proposed method is compared with other well-known machine learning-based positioning algorithms in terms of positioning accuracy and error distances. The results indicate that the average positioning accuracy of the proposed scheme reaches 95.55%, which represents an improvement of 5.55% to 16.21% over the other methods. Additionally, the two-dimensional positioning error can be reduced to 0.25 m. Full article

With advancements in the Internet of Things (IoT), diverse and high-resolution data sources, such as environmental sensors and user-generated inputs from mobile devices, have become available to model and estimate citizens’ acoustic comfort in urban environments. These IoT-enabled data sources offer scalable insights in real time into both objective parameters (e.g., noise levels and environmental conditions) and subjective perceptions (e.g., personal comfort and soundscape experiences), which were previously challenging to capture comprehensively by using traditional methods. Despite this, there remains a lack of a clear framework explicitly presenting the role of these diverse inputs in determining acoustic comfort. This paper contributes by (1) exploring the relationship between attributes governing the physical aspect of the built environment (sensory data) and the end-users’ characteristics/inputs/sensations (such as their acoustic comfort level) and how these attributes can correlate/connect; (2) developing a CityGML-based framework that leverages semantic 3D city models to integrate and represent both objective sensory data and subjective social inputs, enhancing data-driven decision making at the city level; and (3) introducing a novel approach to crowdsourcing citizen inputs to assess perceived acoustic comfort indicators, which inform predictive modeling efforts. Our solution is based on CityGML’s capacity to store and explain 3D city-related shapes with their semantic characteristics, which are essential for city-level operations such as spatial data mining and thematic queries. To do so, a crowdsourcing method was used, and 20 perceptive indicators were identified from the existing literature to evaluate people’s perceived acoustic attributes and types of sound sources and their relations to the perceived soundscape comfort. Three regression models—K-Nearest Neighbor (KNN), Support Vector Regression (SVR), and XGBoost—were trained on the collected data to predict acoustic comfort at bus stops in Montréal based on physical and psychological attributes of travellers. In the best-performing scenario, which incorporated psychological attributes and measured noise levels, the models achieved a normalized mean squared error (NMSE) as low as 0.0181, a mean absolute error (MAE) of 0.0890, and a root mean square error (RMSE) of 0.1349. These findings highlight the effectiveness of integrating subjective and objective data sources to accurately predict acoustic comfort in urban environments. Full article

Several stochastic $H_{\infty }$ filters for estimating the attitude of a rigid body from line-of-sight measurements and rate gyro readings are developed. The measurements are corrupted by white noise with unknown variances. Our approach consists of estimating the quaternion while attenuating the transmission gain from the unknown variances and initial errors to the current estimation error. The time-varying $H_{\infty }$ gain is computed by solving algebraic and differential linear matrix inequalities for a given transmission threshold, which is iteratively lowered until feasibility fails. Thanks to the bilinear structure of the quaternion state-space model, the algorithm parameters are independent of the state. The case of a gyro drift is addressed, too. Extensive Monte-Carlo simulations show that the proposed stochastic $H_{\infty }$ quaternion filters perform well for a wide range of noise variances. The actual attenuation, which improves with the noise variance and is worst in the noise-free case, is better than the guaranteed attenuation by one order of magnitude. The proposed stochastic $H_{\infty }$ filter produces smaller biases than nonlinear Kalman or unscented filters and similar standard deviations at large noise levels. An essential advantage of this $H_{\infty }$ filter is that the gains are independent of the quaternion, which makes it insensitive to modeling errors. This desired feature is illustrated by comparing its performances against those of unmatched nonlinear optimal filters. When provided with too high or too low noise variances, the multiplicative Kalman filter and the unscented quaternion filter are outperformed by the $H_{\infty }$ filter, which essentially delivers identical error magnitudes. Full article