Low Error Values Research Articles

Advancing heat transfer modeling through machine learning: A focus on forced convection with nanoparticles

This study underscores the critical role of heat transfer modeling in the design and optimization of heat exchangers, recognizing the challenges posed by traditional numerical methods. To address the need for more efficient alternatives, machine learning emerges as a promising solution, leveraging its capacity to unravel intricate relationships in heat transfer processes. The research focuses on forced convection heat transfer involving nanoparticles (specifically TiO2, Al2O3, and Cu) dispersed in water, employing the Lagrangian–Eulerian approach under turbulent flow conditions with a constant surface heat flux. Machine-learning techniques, namely extreme gradient boosting, support vector regression, and tree regression are employed to predict heat transfer outcomes based on collected data. The achieved results exhibit promising accuracy levels, with eXtreme gradient boosting, support vector regression, and tree regression algorithm models demonstrating impressive accuracies of 91%, 91%, and 94%, respectively. The mean absolute errors for these machine-learning models were recorded as 1.07, 7.24, and 3.74. This research serves as a demonstration of the potential of machine-learning methodologies in modeling complex physical systems, as evidenced by their efficiency in capturing the behavior of nanofluids under various conditions. The obtained accuracy and low mean absolute error values indicate the robustness of these machine-learning models in predicting heat transfer results. The implications of these findings are substantial for the field of heat exchanger design and optimization. The study suggests that machine-learning techniques offer a more efficient and cost-effective approach compared to traditional numerical simulations. By leveraging the capabilities of these models, there is potential for enhanced accuracy and efficiency in the design and optimization processes of heat exchangers, contributing to advancements in thermal engineering.

Study on Imagery Modeling of Electric Recliner Chair: Based on Combined GRA and Kansei Engineering

This study aims to integrate data-driven methodologies with user perception to establish a robust design paradigm. The study consists of five steps: (1) theoretical research—a review of the subject background and applications of Kansei engineering and gray relational analysis (GRA); (2) algorithmic framework research—the discussion delves into the intricate realm of Kansei engineering theory, accompanied by a thorough elucidation of the gray relational analysis (GRA) algorithmic framework, a crucial component in constructing a fuzzy logic model for product image modeling; (3) Kansei data collection—18 groups of perceptual words and six classic samples are selected, and the electric recliner chair samples are scored by the Kansei words; (4) Kansei data analysis—morphological analysis categorizes the electric recliner chair into four variables. followed by the ranking and key consideration areas of each area; (5) GRA fuzzy logic model verification—the GRA fuzzy logic model performs simple–complex (S-C) imagery output on 3D models of three modeling instances. By calculating the RMSE value of the seat image modeling design GRA fuzzy logic model, it is proven that the seat image modeling design GRA fuzzy logic model performs well in predicting S-C imagery. The subsequent experimental study results also show that the GRA fuzzy logic model consistently produces lower root mean square error (RMSE) values. These results indicate the efficacy of the GRA fuzzy logic approach in forecasting the visual representation of the electric recliner chair shape’s 3D model design. In summary, this research underscores the practical utility of the GRA model, harmoniously merged with perceptual engineering, in the realm of image recognition for product design. This synergy could fuel the extensive exploration of product design, examining perceptual engineering nuances in product modeling design.

Accuracy and reproducibility of two-dimensional computed tomography-based positioning of femoral component rotational alignment in preoperative planning for total knee arthroplasty

BackgroundPoor rotation of the femoral component in total knee arthroplasty (TKA) can result in various postoperative complications, underscoring the critical importance of preoperative planning.PurposeTo improve the accuracy of femoral component positioning during TKA, this study compared the accuracy and repeatability of different two-dimensional (2D) computed tomography (CT) measurement methods for measuring the posterior condylar angle (PCA) in preoperative TKA planning.MethodsA retrospective analysis was conducted on 75 patients (150 knees) who underwent bilateral lower extremity computed tomography angiography (CTA) at Fuyang People's Hospital from January 2021 to July 2021. Three different methods were used to measure the PCA based on 2D CT images (axial CT slices) and three-dimensional(3D) models (femoral models reconstructed from CT data) in this study. Method 1: Single-plane 2D CT measurement, measuring PCA in the most obvious single-plane CT slice of the surgical transepicondylar axis (sTEA); Method 2: multi-plane 2D CT measurement, identifying and locating anatomical landmarks in multiple 2D CT slices and measuring PCA; Method 3: 3D model measurement, measuring PCA in the reconstructed femur 3D model. Compare the differences in PCA measurements between the three measurement methods. A positive PCA measurement was recorded when the sTEA was externally rotated relative to the posterior condylar line (PCL). Any difference exceeding 3° between the PCA measurement in the 2D CT and the PCA reference value in the 3D model was classified as an outlier. The intraclass correlation coefficient (ICC) and Bland–Altman method were utilized to assess the intra- and inter-observer reproducibility of the three measurement methods.ResultsThe PCA measurement in the single-plane 2D CT was 1.91 ± 1.94°, with a measurement error of − 1.22 ± 1.32° and 12.7% of outlier values. In the multi-plane 2D CT, the PCA measurement was 2.96 ± 1.68°, with a measurement error of -0.15 ± 0.91° and 6.0% of outlier values. The PCA measurement in the 3D model was 3.12 ± 1.69°. The PCA measurement in single-plane 2D CT was notably smaller than that in multi-plane 2D CT and 3D models, with no significant difference between the latter two. The multi-plane 2D CT showed significantly lower measurement error and outlier values than the single-plane 2D CT. All three PCA measurement methods exhibited high reproducibility (ICC: 0.93 ~ 0.97).ConclusionsUsing of multi-plane 2D CT for measuring PCA in preoperative planning of TKA has high reproducibility and accuracy, with fewer outlier values. We recommend preoperative measurement of PCA using muti-plane 2D CT to improve the accuracy of positioning the femoral component rotational alignment during surgery.

Python-Powered Precision: Unraveling Consumer Price Index Trends in Makassar City through a Duel of Long Short-Term Memory and Gated Recurrent Unit Models

This research aims to carry out a predictive analysis of the Consumer Price Index in the city of Makassar to anticipate possible impacts on inflation and deflation in the future. The Consumer Price Index is an indicator that can be used as a basis for measuring changes in the prices of goods and services purchased by consumers which have an impact on inflation in a region. The CPI is very useful for knowing the level of increase in prices, services, and income, as well as measuring the amount of production costs. This data was obtained through the official website of the Central Statistics Agency (BPS) for the Makassar city area. The methods used in this research are Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results of this research show that based on analysis and testing, the LSTM model has an MAE of 1.0849 and the GRU model has an MAE of 0.9915, which shows that there is no significant difference between the two methods and both methods can work very well, however, The lowest error value was obtained in the GRU model using a 70:30 dataset ratio, 9 number of sequences, 16 neurons in hidden layer 1 and 32 neurons in hidden layer 2, and 1000 number of epochs.

Utilizing an intelligent machine learning strategy for predicting the tensile strength and ductility properties of nitrogen doped CoCrFeMnNi based high entropy alloys

The integration of machine learning (ML) within the realm of artificial intelligence has unveiled remarkable potential for predicting material properties. Particularly, determining critical properties such as yield strength (YS), tensile strength (UTS), and elongation in high entropy alloys (HEAs) has been a formidable challenge due to the extensive composition possibilities. The application of ML methods offers a viable solution for determining the optimal composition and mechanical properties of HEA materials. In this study, six ensemble ML algorithms, including random forest (RF), adaboost, xgboost, gradient boosting, bagging, and extra trees are employed to predict the tensile strength and ductility of nitrogen (N) doped CoCrFeMnNi based HEAs, which includes yield strength, tensile strength, and elongation properties. To explore the correlations between different features in the dataset, both the Pearson correlation and SHAP (SHapley Additive exPlanations) coefficient methods are employed. The gradient boosting ML model, in particular, distinguished itself with remarkable precision, achieving outstanding coefficient of determination (R2) values of approximately 98.25% for YS, 97.39% for UTS, and 94.45% for elongation. Moreover, it demonstrated lower mean absolute error (MAE) values for yield strength (32.62 MPa), tensile strength (37.48 MPa), and elongation (3.40%). This pattern strongly emphasizes its superiority in providing more accurate predictions compared to the other models. Notably, the model's prediction results for all three tensile properties are closely matched with the values obtained through experimental testing. This alignment between predictions and actual results serves as a crucial validation of the model's exceptional accuracy and reliability in precisely predicting these properties. Furthermore, the scrutinizing the impact of both prominent and less influential features on the ML model's performance is analyzed. Thereby, these findings underscore the remarkable effectiveness of the gradient boosting model as a predictive tool, emphasizing its ability to provide highly accurate and reliable predictions for HEAs properties.

A highly effective SERS platform formed by the fabrication of Ag@ZIF-8@Au nanoparticles for rapid detection of acetamiprid in environment

The unreasonable spraying and random migration of acetamiprid may cause pollution of crops, soil and water resources in the environment, resulting in threatening ecosystem and human health. However, the monitoring of acetamiprid using mass spectrum in the environment encounters challenges due to high-cost instruments and complex processing time. Herein, we fabricated a rapid and reliable SERS method based on Ag@ZIF-8@Au platforms for tracing acetamiprid residues in the environment. In this method, a MOF material named ZIF-8 is coated with silver nanoparticles and distributed internally between AgNPs and AuNPs to enhance Raman signal, which can enrich pesticide molecules into the hotspots area provided by noble material and helps avoid the oxidation of silver nanoparticles. High sensitivity (LOD of 9.027 × 10-10 M for acetamiprid, and SERS enhancement factor of 4.3 × 107), excellent reproducibility (6.496% or 7.198% RSD for 30 random points) and superior stability (3.127% RSD for 6 weeks) were achieved using the proposed method. Acetamiprid with concentrations from 10-4 to 10-9 M were successfully detected by SERS method. Furthermore, the linear detection models of acetamiprid in different environment matrices (lake water, tea leaves, tea garden soil, oranges and oranges orchard soil) were established and all the correlation coefficient (R2) were higher than or equal to 95%, indicating the excellent adaptability of Ag@ZIF-8@Au platform in environment. The randomly spiked concentrations of acetamiprid were also tested with good recovery values and low relative error values, further confirming the reliability of the detection method.

Prediction of gross calorific value from coal analysis using decision tree-based bagging and boosting techniques

The calorific value of any fuel is one of the crucial parameters to grade fuel's burning capability. The bomb calorimeter has historically been used to calculate coal's gross calorific value (GCV). However, for many years, engineers and scientists were trying to measure coal's GCV without a bomb calorimeter, using only laboratory-derived ultimate and/or proximate analyses to eliminate tedious and time-consuming laboratory analyses. In this study, Extra trees, Bagging, Decision tree, and Adaptive boosting are developed for the first time in coal's GCV modeling. In addition, the prediction and computational efficiency of previously applied decision tree-based algorithms, such as Random forest, Gradient boosting, and XGBoost are investigated. Well-established empirical models, namely Schuster, Mazumdar, Channiwala and Parikh, Parikh et al. and Central Fuel Research Institute of India are examined to compare their efficiency with newly developed algorithms. Proximate and ultimate analysis parameters are ranked based on their significance in GCV modeling. The studied models are tuned using an exhaustive grid search technique. Statistical indexes, such as explained variance (EV), mean absolute error (MAE), coefficient of determinant (R2), mean squared error (MSE), maximum error, minimum error, and mean absolute percentage error (MAPE) are used to critique these models. To accomplish the goals, 7430 data points containing ten coal features, such as ash, moisture, fixed carbon, volatile matter, hydrogen, carbon, sulfur, nitrogen, oxygen, and GCV are selected from the U.S. Geological Survey Coal Quality (COALQUAL) database. It has been found that, due to simplicity and location-specific constraints, empirical models could not correlate proximate and/or ultimate analyses with GCV. Bagging and boosting techniques tested here performed well with the coefficient of determinant (R2) of over 0.97. The XGBoost model outperforms other tree-based algorithms with the most significant coefficient of determinant (R2 of 0.9974) and lowest error values (MSE of 14703.3, max_error of 1027.2, MAE of 89.2, MAPE of 0.009). The studied models' ranking (highest to lowest) based on their performance are XGBoost, Extra trees, Random forest, Bagging, Gradient boosting, Decision tree, and Adaptive boosting. The correlation heatmap and scatterplots used here clearly indicate that oxygen and carbon are the utmost significant, whereas volatile matter and sulfur are the least essential rank parameters for GCV modeling. The strategy suggested in this research can aid engineers/operators in obtaining a rapid and accurate determination of the GCV with a few coal features, thus lessening complicated, tedious, expensive, and time-consuming laboratory efforts.

Identifying complex causal patterns in students’ performance using machine learning

ABSTRACT Today, in every academic institution as well as the university system assessing students’ performance, identifying the uniqueness of each student and finding solutions to performance problems have become challenging issues. The main purpose of the study is to predict how student performance changes as a result of their behaviours, hobbies, extracurricular activities and different university activities. This study collected data from graduates via the online and supervised machine learning algorithms used to solve the problem. After pre-processing data, classification algorithms were applied, namely Random Forest, Multi-Layer Perceptron, Support Vector Machine, Naïve Bayes and Decision Tree. The results show that the Multi-Layer Perceptron is the best algorithm considering the highest accuracy and lowest error values. An ensemble learning algorithm was then applied by combining those five algorithms. The best results were obtained using it, and according to the final results, ensemble learning increases the accuracy rather than each classifier.

Comparison of the sensitivities and accuracies of optoelectronic transducers for solar irradiance measurement

This paper compares the sensitivities and accuracies of four different optoelectronic transducers in measuring solar irradiance for the fabrication of portable and low-cost pyranometers. Trans-impedance conditioning circuits were designed for two phototransistors (BP103 and SFH3310) and two photodiodes (BPW21 and BPW34). The Arduino Mega 2560 was used as an interface between the analogue signal produced by the conditioning circuits and the digital output ports. The transducers with a standard pyranometer RSRA_05V were arranged on a vero board and exposed to the sun. Statistical analysis of the experimental results produced the least root mean square error value of 6.58794 Wm−2 for phototransistor BP103 during the dry season followed by 13.35216 Wm−2 for phototransistor SFH3310 during the dry season. The correlation coefficients of BPW21, BPW34, BP103, and SFH3310 with the standard pyranometer are 0.9489, 0.9916, 0.9976, and 0.9905, respectively. The experimental results obtained from the phototransistors BP103 and SFH3310 strongly correlated with those of the standard pyranometer coupled with lower root mean square error and mean bias error values than those of the photodiodes. Thus, the phototransistors BP103 and SFH3310 are more accurate and effective for measuring solar irradiance. This study contributes to the development of low-cost and accurate solar radiation meters.

A comparison of CAPM and Fama-French three-factor model under Machine Learning approaching

With the economy experiencing rapid growth in recent years, more individuals have started venturing into the stock market. Precisely forecasting the rate of return can mitigate investment risks for stock investors and significantly enhance their investment returns. The Capital Asset Pricing Model (CAPM) and the 3-factor Fama-French model (FF3) are widely recognized in academic and practical settings. This model comparison provides frameworks to analyze the relationship between portfolio risk and return in inefficient markets. This research utilized the Support Vector Regression (SVR) algorithm to forecast the returns of a diversified portfolio in the Hanoi stock market (HNX) from 2010 to 2022. Subsequently, the explanatory power of the CAPM and FF3 models were compared using the Ordinary Least Squares (OLS) algorithm. Finally, this research incorporated the SVR algorithm within the FF3 framework to develop a predictive model. The research findings demonstrate that the FF3 model provides a superior explanation to the CAPM model. Additionally, the study reveals that the SVR algorithm outperforms the OLS algorithm in terms of efficiency, as it yields lower Root Mean Square Error (RMSE) values. Consequently, the next research direction entails replacing the FF3 model with a more comprehensive multi-factor model, anticipating obtaining an enhanced predictive model.

Rapid parameter identification of three diode photovoltaic systems using the Cheetah optimizer

This study focuses on accurate parameter identification for solar cells and photovoltaic module simulation using experimental data. To tackle the challenge of modelling these highly nonlinear systems, we propose the novel use of the Cheetah Optimizer (CO) algorithm, inspired by cheetah hunting strategies. The CO algorithm employs mathematical models and randomization parameters to balance exploration and exploitation, avoiding local optima by considering energy limitations. We demonstrate the CO algorithm's effectiveness by applying it to the three-diode model in solar photovoltaic systems, specifically the STP6-120/36 and Photowatt-PWP201 PV modules. Impressively, the CO algorithm achieves remarkably low root mean square error values of 0.0145 A and 0.0019 A, outperforming state-of-the-art methods and ensuring high accuracy. Additionally, it delivers the lowest power errors of 0.16054 W and 0.01484 W for the respective modules, highlighting its exceptional performance. The CO algorithm proves to be a promising tool for precise parameter extraction and optimization, leading to improved modelling and performance of solar photovoltaic systems.

A Collaborative Filtering Recommendation Algorithm Model Based on User Feature Transfer

The quality of teaching resources and recommended practices in flipped classrooms determine the advantages and disadvantages of this educational model. However, current teaching resource recommendation platforms suffer from issues such as cold startup and sparse data. In order to address these issues, a collaborative filtering recommendation algorithm based on user feature transfer was proposed and utilized to examine the correlation between students’ preference behavior and the recommendation of teaching resources in flipped classes for tourism management. The aim was to enhance the quality of teaching in current classes. Using this algorithm, a transfer by user feature (TUF) model is constructed. In this model, a soft embedding method is employed to accurately extract user feature information in the auxiliary space. This method addresses the challenge of filling large-scale missing matrices in the auxiliary space. Additionally, singular value decomposition is performed to obtain more precise user features. Finally, an optimized Wiberg algorithm with rapid convergence is designed to solve the constructed model. The performance of this algorithm is measured and compared using two common datasets. Compared to other algorithms, the proposed algorithm demonstrates superior performance and a lower mean absolute error value. In summary, the recommendation algorithm can enhance the quality of resource organization and provide more suitable personalized recommendations for the recommendation platform. This is beneficial for improving the quality of students’ learning.

Point and interval prediction for significant wave height based on LSTM-GRU and KDE

Accurate wave height prediction is significant for wave power generation, maritime traffic, and disaster prevention and reduction. This paper proposes a novel point and interval prediction framework based on deep learning methods for wave height prediction. First, multidimensional and multisource datasets are preprocessed. Subsequently, a feature selection process is executed to remove superfluous features. Third, a hybrid model that combines long short-term memory (LSTM) and a gated recurrent unit (GRU) is used to predict wave height. This model uses multivariate features that are positively correlated with wave height as input data. Finally, kernel density estimation (KDE) is leveraged to estimate the probability density distribution of the prediction errors generated the wave height prediction interval. The proposed LSTM-GRU-KDE forecasting framework is compared with benchmark models to verify its practicability. The LSTM-GRU model with multiple feature inputs has lower root mean square error and mean absolute error values and a higher coefficient of determination in predicting hourly wave height for all buoy stations compared to those of LSTM with multiple feature inputs and LSTM-GRU with a single feature input. Moreover, by the coverage width-based criterion, KDE (box) stands out as a superior choice among interval forecasting methods, offering a higher degree of reliability when constructing prediction intervals.

Smart nano generation of transgenic algae expressing white spot syndrome virus in shrimps for inner ear-oral infection treatments using the spotted hyena optimizer (SHO)-Long short-term memory algorithm

Nanotechnology offers a promising avenue to amplify the effectiveness and precision of using transgenic algae in managing WSSV in shrimp by possibly crafting nano-carriers for targeted therapeutic agent delivery or modifying algae cells at a molecular level. Leveraging the capabilities of nano-scale interventions, this study could explore innovative means to manipulate cellular processes, control biological interactions, and enhance treatment efficacy while minimizing undesirable impacts in aquatic environments. The White Spot Syndrome Virus (WSSV) is a double-stranded DNA virus with a tail and rod form that belongs to theNimaviridaefamily. There is no workable way to manage this illness at the moment. This research proposes a new model based on the Long Short-Term Memory (LSTM) and Spotted Hyena Optimizer (SHO) method to control the inner ear-oral infection, utilizing transgenic algae (Chlamydomonas reinhardtii). It is pretty tricky to modify the weight matrix in LSTM. The output will be more accurate if the weight of the neurons is exact. Histological examinations and nested polymerase chain reaction (PCR) testing were performed on the challenged shrimp every 4 h to assess the degree of white spot disease. The SHO-LSTM has shown the highest accuracy and Roc value (98.12% and 0.93, respectively) and the lowest error values (MSE = 0.182 and MAE = 0.48). The hybrid optimized model improves the overall inner ear-oral linked neurological diseases detection ratio. Additionally, with the slightest technical complexity, it effectively controls the forecast factors required to anticipate the ENT. Algal cells were found to be particularly well-suited for inner ear-oral infections, and shrimps fed a transgenic line had the best survival ratio in WSSV infection studies, with 87% of the shrimp surviving. This shows that using this line would effectively stop the spread of WSSV in shrimp populations.

Multivariable Regression 3D Failure Criteria for In-Situ Rock

Wellbore stability problems increase with the exploration and development of oil and gas reservoirs. A new 3D non-linear failure criterion is proposed as a trigonometric function considering the intermediate principal stress (2) on the triaxial compression test data. Mohr-Coulomb and Hoek-Brown are well-known failure criteria, but they do not consider the influence of (2) on rock strength. This new criterion produces a concave surface on the principal stress space (1,2, 3) with the influence of intermediate principal stress. In this study, sensitivity analysis for the variable is also done to understand the significant influence of parameters on the accuracy of the proposed criterion. Further validation of this non-linear criterion on three principal stresses (1,2, 3) was done compared with linear regression and second-degree polynomial regression results. It has been observed that the new non-linear 3D criterion with five material parameters reveals a good fit compared to linear regression and second-degree polynomial regression, which have four and six material parameters, respectively. The new non-linear criterion was further validated by comparison with existing criteria like the Priest, Drucker-Prager, and Mogi-Coulomb. It has been observed that the new 3D non-linear criterion shows a more accurate result than these existing criteria as certain rock types exhibit coefficient of determination (DC) values near one, precisely 0.95 for inada granite, 0.94 for orikabe monzonite, and 0.91 for KTB amphibolite. In contrast, other rock types have DC values ranging from 0.7 to 0.9. The new 3D non-linear criterion also yields lower root means square error (RMSE) values than the Mogi-Coulomb criterion for seven rock types. Specifically, the RMSE values by the new criterion are as follows: KTB amphibolite - 40.03 MPa, Dunham dolomite - 15.16 MPa, Shirahama sandstone - 9.08 MPa, Manazuru andesite - 22.14 MPa, Inada granite - 35.47 MPa, and Coconino sandstone - 19.047 MPa. This new 3D criterion gave precise predictions of the failure of the formation under in-situ stresses and was further helpful for the simulation of the wellbore in the petroleum industry. The variable in the new 3D criterion should be calculated from triaxial compression test data for each formation rock before applying this criterion to the wellbore stability problem and the sand production problem.

Performance Evaluation of an Immersive Virtual Reality Application for Rehabilitation after Arthroscopic Rotator Cuff Repair.

Few studies have evaluated the effectiveness of shoulder rehabilitation in virtual environments. The objective of this study was to investigate the performance of a custom virtual reality application (VR app) with a stereophotogrammetric system considered the gold standard. A custom VR app was designed considering the recommended rehabilitation exercises following arthroscopic rotator cuff repair. Following the setting of the play space, the user's arm length, and height, five healthy volunteers performed four levels of rehabilitative exercises. Results for the first and second rounds of flexion and abduction displayed low total mean absolute error values and low numbers of unmet conditions. In internal and external rotation, the number of times conditions were not met was slightly higher; this was attributed to a lack of isolated shoulder movement. Data is promising, and volunteers were able to reach goal conditions more often than not. Despite positive results, more literature comparing VR applications with gold-standard clinical parameters is necessary. Nevertheless, results contribute to a body of literature that continues to encourage the application of VR to shoulder rehabilitation programs.

Integrating topographic features and patch matching into point cloud restoration for terrain modelling

ABSTRACTPoint clouds are widely used in Earth surface research but usually exhibit gaps of missing data. Previous point cloud restoration methods used in terrain modelling have not fully considered complex terrain characteristics, which can be summarised as the controlling role of topographic features in shaping terrain surfaces and the inherent similarities observed among these surfaces. This work introduces a novel method that integrates Topographic Features and Patch Matching (TFPM) into point cloud restoration processes for terrain modelling. The method mainly contains three steps. First, identifying gap boundary points. Second, topographic feature points are extracted and subsequently interpolated into the identified gaps. Third, searching other parts of the raw point cloud for patches resembling the gaps, and the identified patches are used as templates to restore the point cloud. The proposed method is benchmarked against three state-of-the-art point cloud restoration methods. The experimental results demonstrate that the TFPM method consistently exhibits superior accuracy in terrain modelling and analysis, as evidenced by low values of the root mean square error, average elevation difference, and average slope difference. This work endeavours to incorporate topographic features into point cloud restoration processes and can benefit future research related to terrain modelling and analysis.

Deep fusible skinning of animation sequences

Animation compression is a key process in replicating and streaming animated 3D models. Linear Blend Skinning (LBS) facilitates the compression of an animated sequence while maintaining the capability of real-time streaming by deriving vertex to proxy bone assignments and per frame bone transformations. We introduce a innovative deep learning approach that learns how to assign vertices to proxy bones with persistent labeling. This is accomplished by learning how to correlate vertex trajectories to bones of fully rigged animated 3D models. Our method uses these pretrained networks on dynamic characteristics (vertex trajectories) of an unseen animation sequence (a sequence of meshes without skeleton or rigging information) to derive an LBS scheme that outperforms most previous competent approaches by offering better approximation of the original animation sequence with fewer bones, therefore offering better compression and smaller bandwidth requirements for streaming. This is substantiated by a thorough comparative performance evaluation using several error metrics, and compression/bandwidth measurements. In this paper, we have also introduced a persistent bone labeling scheme that (i) improves the efficiency of our method in terms of lower error values and better visual outcome and (ii) facilitates the fusion of two (or more) LBS schemes by an innovative algorithm that combines two arbitrary LBS schemes. To demonstrate the usefulness and potential of this fusion process, we have combined the outcome of our deep skinning method with that of Rignet—which is a state-of-the-art method that performs rigging on static meshes—with impressive results.

Simulation of the soil water-carrying capacity of Haloxylon ammodendron plantations in the Alxa Desert, China: Implications for afforestation

In recent years, China has achieved remarkable results in curbing desertification through afforestation. However, the dry soil layer resulting from the long-term water consumption of overloaded perennial plants seriously threatens the sustainability of afforestation, and quantifying the maximum vegetation carrying capacity under certain soil moisture conditions is crucial to the sustainability of afforestation in arid areas. Therefore, we aimed to simulate soil water in Haloxylon ammodendron plantations at different growth stages using the simultaneous heat and water transfer (SHAW) model to determine the vegetation carrying capacity threshold. Field-measured soil and vegetation data for 2021 were used to calibrate the SHAW model. Good consistency in soil water content (SWC) was observed between measurements and simulations in the calibration and validation phases of the model, with considerable linear correlation and low prediction error values. Therefore, the soil water dynamics of H. ammodendron plantations in the study area could be accurately predicted using the SHAW model. The simulation results show that, with increasing forest age, the SWC at 0–400 cm gradually decreases and a dry soil layer starts to form when the forest age reaches 11 years. The dry layer thickness reaches 120 cm by 22 years, thus the optimal growth age of artificial H. ammodendron plantations in the study area should not exceed 22 years, and the maximum biomass soil water carrying capacity of vegetation is 1,650 kg/hm2. A vegetation carrying capacity threshold can be determined in this study for the sustainable management of future afforestation activities.

Ensemble approaches for leveraging machine learning models in load estimation

AbstractHelicopter component load estimation can be achieved through a variety of machine learning techniques and algorithms. A range of ensemble integration techniques were investigated in order to leverage multiple machine learning models to estimate main rotor yoke loads from flight state and control system parameters. The techniques included simple averaging, weighted averaging and forward selection. Performance of the models was evaluated using four metrics: root mean squared error, correlation coefficient and the interquartile ranges of these two metrics. When compared, every ensemble outperformed the best individual model. The ensembles using forward selection achieved the best performance. The resulting output is more robust, more highly correlated and achieves lower error values as compared to the top individual models. While individual model outputs can vary significantly, confidence in their results can be greatly increased through the use of a diverse set of models and ensemble techniques.