Smaller Root Mean Square Error Research Articles

When does adjusting covariate under randomization help? A comparative study on current practices

PurposeWe aim to thoroughly compare past and current methods that leverage baseline covariate information to estimate the average treatment effect (ATE) using data from of randomized clinical trials (RCTs). We especially focus on their performance, efficiency gain, and power.MethodsWe compared 6 different methods using extensive Monte-Carlo simulation studies: the unadjusted estimator, i.e., analysis of variance (ANOVA), the analysis of covariance (ANCOVA), the analysis of heterogeneous covariance (ANHECOVA), the inverse probability weighting (IPW), the augmented inverse probability weighting (AIPW), and the overlap weighting (OW) as well as the augmented overlap weighting (AOW) estimators. The performance of these methods is assessed using the relative bias (RB), the root mean square error (RMSE), the model-based standard error (SE) estimation, the coverage probability (CP), and the statistical power.ResultsEven with a well-executed randomization, adjusting for baseline covariates by an appropriate method can be a good practice. When the outcome model(s) used in a covariate-adjusted method is closer to the correctly specified model(s), the efficiency and power gained can be substantial. We also found that most covariate-adjusted methods can suffer from the high-dimensional curse, i.e., when the number of covariates is relatively high compared to the sample size, they can have poor performance (along with lower efficiency) in estimating ATE. Among the different methods we compared, the OW performs the best overall with smaller RMSEs and smaller model-based SEs, which also result in higher power when the true effect is non-zero. Furthermore, the OW is more robust when dealing with the high-dimensional issue.ConclusionTo effectively use covariate adjustment methods, understanding their nature is important for practical investigators. Our study shows that outcome model misspecification and high-dimension are two main burdens in a covariate adjustment method to gain higher efficiency and power. When these factors are appropriately considered, e.g., performing some variable selections if the data dimension is high before adjusting covariate, these methods are expected to be useful.

Underwater maneuvering target motion analysis using delayed azimuth angles

Accurate position information of an underwater target is the premise of successfully executing underwater missions, and this paper focuses on underwater target motion analysis (TMA) using delayed azimuth angles. Considering that the underwater sound speed (around 1500 m/s) is much smaller than the speed of light (3 × 108 m/s), the underwater TMA needs to adopt the non-stop model considering the effect of the target movement during signal propagation on state estimation, instead of the traditional go-stop model ignoring the target movement during signal propagation. The existing non-stop model is based on a constant-velocity target, and the model mismatch will make the estimated results biased when it is applied to a maneuvering target. In this paper, we focus on the constant-acceleration (CA) target and propose two methods to solve this problem. One is to extend the non-stop model to the case of a constant-acceleration target. We build the corresponding least squares (LS) estimator and derive the expression of the root mean square error (RMSE) of the LS solution. The other is to directly offset the estimation bias of the CA go-stop model and a bias-compensated algorithm is proposed to improve the performance. Simulations prove that the proposed methods can result in a smaller RMSE than the traditional CA go-stop model. Their RMSEs decrease with the number of measurements and observers and increase with random angle errors. When the number of measurements is small, the RMSE of the established CA non-stop model is smaller than that of the bias-compensated algorithm. As the number of measurements increases, their estimation precisions become gradually equal. The running time of the proposed methods increases with the number of measurements and observers. When the number of observers is small, the bias-compensated algorithm has the advantage of needing less running time. In addition, the running time of the bias-compensated algorithm does not approximately change with the random angle errors, while that of the CA non-stop model increases with the random angle errors.

PERAMALAN NILAI TUKAR PETANI PROVINSI ACEH: DITINJAU DENGAN METODE DOUBLE EXPONENTIAL SMOOTHING DAN HOLT WINTER

This research aimed to compare the performance of the Double Exponential Smoothing and Holt-Winter methods in forecasting the Farmer Exchange Rate (NTP) for the Horticulture Farmer Subsector in Aceh Province. Secondary data on the NTP for the Aceh Horticulture Subsector from 2020-2023 was obtained from the Aceh Provincial Central Statistics Agency (BPS) website. The data processing was carried out using the R software. The results showed that the Double Exponential Smoothing method had a Root Mean Squared Error (RMSE) of 3.413201, a Mean Absolute Percentage Error (MAPE) of 2.85835, and a Mean Percentage Error (MPE) of -0.5980113. Meanwhile, the Holt-Winter's Additive method had an RMSE of 4.055652, a MAPE of 3.055992, and an MPE of 0.2534276. The best forecasting method was selected based on the smallest RMSE, MAPE, and MPE values, which was Double Exponential Smoothing. The 12-month forecast using the Double Exponential Smoothing method indicated that the lowest NTP would occur in January 2024 at 106.7195, while the highest NTP would be in December 2024 at 113.6443

Construction of a meteorological application system based on BDS ground-based augmentation network and water vapor products validation

The national Beidou Navigation Satellite System (BDS) ground-based augmentation network (BGAN) of China is constructed with the existing GNSS observation resources of industrial sectors and local governments, based on the concept of joint building and sharing with sustainable development. This study provides a detailed introduction to the design, construction and operation of a meteorological application system based on BGAN, and validation of its water vapor products. BDS and GPS real-time observation of atmospheric water vapor is achieved nationwide in China and multi-GNSS applications. Through the application of multi-GNSS data and validation of the water vapor products from 2018 to 2020, the accuracy of precipitable water vapor (PWV) derived from BDS only is equivalent to that from GPS only. The root mean square error (RMSE) between them is about 2 mm with high correlation coefficient. Based on radiosonde data, the validation is conducted with the products of BDS-PWV, GPS-PWV, and Combined-PWV derived with multi-GNSS of BDS and GPS. The error characteristics of the three products show a consistent trend over the months. The bias is relatively small. The RMSE of the three products is in the range of 2.18–2.73 mm. The BDS-PWV has the largest RMSE, followed by GPS-PWV, and Combined-PWV has the smallest RMSE.

Hyper ensembled extreme gradient boosting techniques via novel triple algorithms to appraise the hardened properties of modern ternary admixed concrete

Mechanical parameters used in many design codes can be achieved by expensive and time-consuming experiments or by non-destructive approaches such as estimative modelling. This investigation proposed Extreme Gradient Boost (XGB) for estimating the slump (SL) and compressive strength (CS) of high-performance concrete (HPC). In addition, to bring the results of the models closer to the experimental data and increase the accuracy, algorithms were combined with the model, including Sunflower Optimizer (SFO) and Jellyfish Search Optimize (JSO). The relevant models have been examined in three frameworks: individual, hybrid, and ensemble-hybrid. For this purpose, several evaluators were provided to determine the errors, compare, and accuracy of the presented models. The XGFJ model has demonstrated exceptional performance, achieving remarkable results in terms of RMSE (Root Mean Square Error) and R2 (R-squared) values. Specifically, it has attained an exceptionally small RMSE value of 1.785 for CS and 5.183 for SL, indicating the model’s high precision in predicting these parameters. Additionally, it has achieved the biggest R2 values of 0.9960 for CS and 0.9949 for SL. Additionally, it is worth noting that the XGSF model closely matches the performance of the ensemble form of XGFJ, as evident from its R2 values of 0.9956 for CS and 0.9934 for SL. Based on the study, it was observed that using machine learning to anticipate the mechanical characteristics of concrete is valuable and efficient and can be considered an alternative method instead of time-consuming laboratory methods. This research addresses challenges in predicting HPC properties fueled by the need to overcome drawbacks in traditional methods. Costly and time-intensive laboratory experiments prompted the exploration of alternatives, leading to the proposal of XGB combined with optimization algorithms (SFO and JSO). The study aims to enhance prediction accuracy while tackling broader concerns such as construction costs, material efficiency, and environmental impact. The resource-intensive nature of conventional methods, along with inaccuracies due to material variations, serves as a primary challenge. The proposed resolution advocates for a paradigm shift to machine learning, exemplified by the XGFJ model, showcasing exceptional precision and efficiency in predicting HPC properties.

Determination of the Acid and Peroxide Values of Vegetable Oils by Raman Spectroscopy with Competitive Adaptive Reweighted Sampling (CARS) and Back Propagation Neural Network (BPNN)

Acid and peroxide values are important indicators to evaluate the hydrolysis or oxidation level of vegetable oil. In order to achieve rapid determination of these parameters by Raman spectroscopy, rapeseed and soybean oil were analyzed, and a competitive adaptive reweighted sampling-back propagation neural network (CARS-BPNN) method was developed. First, the Raman spectrum was preprocessed to reduce noise using moving window smoothing. Next, competitive adaptive reweighted sampling (CARS), successive projections algorithm (SPA), and uninformative variable elimination (UVE) was applied to extract the Raman characteristic information that indicated the acid and peroxide values. Based on the extracted characteristic information, back propagation neural network (BPNN), partial least squares regression (PLSR), and support vector machine (SVM) prediction models were established and compared. The results showed that the best accuracy was obtained using CARS-BPNN. For rapeseed oil, the coefficients of determination (R2) of acid value and peroxide value were 0.9207 and 0.9772. The root mean square error (RMSE) values were 0.0909 and 0.0022, respectively. For soybean oil, the coefficients of determination (R 2) of acid and peroxide values were 0.9381 and 0.9716. The RMSE values were 0.1250 and 0.0027, respectively. A good correlation coefficient and a small RMSE value were obtained. The results indicate that Raman spectroscopy combined with CARS-BPNN accurately evaluated the acid and peroxide values, which provides a reference for the optimization of the Raman spectrum and creates a new approach for the evaluation of vegetable oil quality.

An improved estimate of daily precipitation from the ERA5 reanalysis

AbstractPrecipitation is an essential climate variable and a fundamental part of the global water cycle. Given its importance to society, precipitation is often assessed in climate monitoring activities, such as in those led by the Copernicus Climate Change Service (C3S). To undertake these activities, C3S predominantly uses ERA5 reanalysis precipitation. Research has shown that short‐range forecasts for precipitation made from this reanalysis can provide valuable estimates of the actual (observed) precipitation in extratropical regions but can be less useful in the tropics. While some of these limitations will be reduced with future reanalyses because of the latest advancements, there is potentially a more immediate way to improve the precipitation estimate. This is to use the precipitation modelled in the Four‐Dimensional Variational (4D‐Var) data assimilation window of the reanalysis, and it is the aim of this study to evaluate this approach. Using observed 24‐h precipitation accumulations at 5637 stations from 2001 to 2020, results show that smaller root‐mean‐square errors (RMSEs) and mean absolute errors are generally found by using the ERA5 4D‐Var precipitation. For example, for all available days from 2001 to 2020, 87.5% of stations have smaller RMSEs. These improvements are driven by reduced random errors in the 4D‐Var precipitation because it is better constrained by observations, which are themselves sensitive to or influence precipitation. However, there are regions (e.g., Europe) where larger biases occur, and via the decomposition of the Stable Equitable Error in Probability Space score, this is shown to be because the 4D‐Var precipitation has a wetter bias on ‘dry’ days than the standard ERA5 short‐range forecasts. The findings also highlight that the 4D‐Var precipitation does improve the discrimination of ‘heavy’ observed events. In conclusion, an improved ERA5 precipitation estimate is largely obtainable, and these results could prove useful for C3S activities and for future reanalyses, including ERA6.

Forecasting groundwater levels using machine learning methods: The case of California’s Central Valley

Groundwater, the second largest stock of freshwater on the planet, is an important water source used for municipal water supply, irrigation, or industrial needs. For instance, California’s arid Central Valley relies on groundwater resources to produce a quarter of the United States’ food demand as farmers rely on this precious resource when surface water is scarce. Despite its importance, the nexus between groundwater dynamics and climate drivers remains difficult to quantify, model, and predict because of the lack of a comprehensive observation network. In this study, machine learning techniques were used to predict groundwater levels with a 3-month forecasting horizon for the Sacramento River Basin. For this, publicly available meteorological and hydrological datasets and in-situ well-level measurements were used. Time series, ensemble-based, and deep-learning models including transformers were all tested, with an ensemble-based, XGBoost model, producing the best mean standard deviation percent error (MSPE) of 32.23% and a root mean squared error (RMSE) of 1.05 m (m) when using a 3- month forecasting horizon and when tested using a monthly rolling window over the years 2017–2020. The model proved to be better at predicting into wet months than the dry summer months and was found to be better at extracting seasonality than explaining well-level residuals, with well-specific features, as opposed to exogenous meteorological features specific to the hydrological unit of the well, ranking as the most important features to the model. Though other forecasting horizons were tested, a 3-month look-ahead window resulted in the best balance of precision and accuracy, where smaller forecasting horizons resulted in smaller RMSE but larger MSPE scores and vice-versa for larger forecasting horizons.

CT Number Accuracy and Association With Object Size: A Phantom Study Comparing Energy-Integrating Detector CT and Deep Silicon Photon-Counting Detector CT.

BACKGROUND. Variable beam hardening based on patient size causes variation in CT numbers for energy-integrating detector (EID) CT. Photon-counting detector (PCD) CT more accurately determines effective beam energy, potentially improving CT number reliability. OBJECTIVE. The purpose of the present study was to compare EID CT and deep silicon PCD CT in terms of both the effect of changes in object size on CT number and the overall accuracy of CT numbers. METHODS. A phantom with polyethylene rings of varying sizes (mimicking patient sizes) as well as inserts of different materials was scanned on an EID CT scanner in single-energy (SE) mode (120-kV images) and in rapid-kilovoltage-switching dual-energy (DE) mode (70-keV images) and on a prototype deep silicon PCD CT scanner (70-keV images). ROIs were placed to measure the CT numbers of the materials. Slopes of CT number as a function of object size were computed. Materials' ideal CT number at 70 keV was computed using the National Institute of Standards and Technology XCOM Photon Cross Sections Database. The root mean square error (RMSE) between measured and ideal numbers was calculated across object sizes. RESULTS. Slope (expressed as Hounsfield units per centimeter) was significantly closer to zero (i.e., less variation in CT number as a function of size) for PCD CT than for SE EID CT for air (1.2 vs 2.4 HU/cm), water (-0.3 vs -1.0 HU/cm), iodine (-1.1 vs -4.5 HU/cm), and bone (-2.5 vs -10.1 HU/cm) and for PCD CT than for DE EID CT for air (1.2 vs 2.8 HU/cm), water (-0.3 vs -1.0 HU/cm), polystyrene (-0.2 vs -0.9 HU/cm), iodine (-1.1 vs -1.9 HU/cm), and bone (-2.5 vs -6.2 HU/cm) (p < .05). For all tested materials, PCD CT had the smallest RMSE, indicating CT numbers closest to ideal numbers; specifically, RMSE (expressed as Hounsfield units) for SE EID CT, DE EID CT, and PCD CT was 32, 44, and 17 HU for air; 7, 8, and 3 HU for water; 9, 10, and 4 HU for polystyrene; 31, 37, and 13 HU for iodine; and 69, 81, and 20 HU for bone, respectively. CONCLUSION. For numerous materials, deep silicon PCD CT, in comparison with SE EID CT and DE EID CT, showed lower CT number variability as a function of size and CT numbers closer to ideal numbers. CLINICAL IMPACT. Greater reliability of CT numbers for PCD CT is important given the dependence of diagnostic pathways on CT numbers.

Optimization and prediction of the cotton fabric dyeing process using Taguchi design-integrated machine learning approach

The typical textile dyeing process calls for a wide range of operational parameters, and it has always been difficult to pinpoint which of these qualities is the most important in dyeing performance. Consequently, this research used a combined design of experiments and machine learning prediction models’ method to offer a sustainable and beneficial reactive cotton fabric dyeing process. To be more precise, we built a least square support vector regression (LSSVR) model based on Taguchi's statistical orthogonal design (L27) to predict exhaustion percentage (E%), fixation rate (F%), and total fixation efficiency (T%) and color strength (K/S) in the reactive cotton dyeing process. The model's prediction accuracy was assessed using many measures, including root mean square error (RMSE), mean absolute error (MAE), and the coefficient of determination (R2). Principal component regression (PCR), partial least square regression (PLSR), and fuzzy modelling were some of the other types of regression models used to compare results. Our findings reveal that the LSSVR model greatly outperformed competing models in predicting the E%, F%, T%, and K/S. This is shown by the LSSVR model's much smaller RMSE and MAE values. Overall, it provided the highest possible R2 values, which reached 0.9819.

Performance of two complementary machine-learned potentials in modelling chemically complex systems

Chemically complex multicomponent alloys possess exceptional properties derived from an inexhaustible compositional space. The complexity however makes interatomic potential development challenging. We explore two complementary machine-learned potentials—the moment tensor potential (MTP) and the Gaussian moment neural network (GM-NN)—in simultaneously describing configurational and vibrational degrees of freedom in the Ta-V-Cr-W alloy family. Both models are equally accurate with excellent performance evaluated against density-functional-theory. They achieve root-mean-square-errors (RMSEs) in energies of less than a few meV/atom across 0 K ordered and high-temperature disordered configurations included in the training. Even for compositions not in training, relative energy RMSEs at high temperatures are within a few meV/atom. High-temperature molecular dynamics forces have similarly small RMSEs of about 0.15 eV/Å for the disordered quaternary included in, and ternaries not part of training. MTPs achieve faster convergence with training size; GM-NNs are faster in execution. Active learning is partially beneficial and should be complemented with conventional human-based training set generation.

Regression Analysis for Predicting Soil Strength in Bangladesh

This study focuses on establishing a robust relationship between Standard Penetration Test-N values (SPT-N), geotechnical parameters and unconfined compressive strength (qu) using regression analysis. The proposed relationship offers a reliable method for estimating qu based on SPT-N values. A comprehensive dataset comprising approximately 200 soil samples collected from various boreholes across Dhaka city was utilized. Multiple Linear Regression (MLR), Rando-forest Regression (RFR) and AdaBoost Regression techniques were employed to develop a unified correlation model. Evaluation metrics including R-squared (R2), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), along with Trend-behavior Analysis were employed to assess and compare the performances of the models. Additionally, sensitivity analysis was carried out on the selected model in order to assess the importance of each parameter used to predict qu. Finally, the selected model was compared against the existing empirical models that were published in previous studies. In terms of evaluation metrics and Trend-behavior Analysis, the results showed that the RFR model performed better than the others. Additionally, the selected model outperformed the others, demonstrating the highest R2 score, the smallest RMSE and MAE values and lower residuals compared to the previous models. Hence, the proposed model provides accurate predictions of qu for clayey soil in Bangladesh. Its implementation could ensure more efficient geotechnical designs, specifically adjusted to the geological conditions of the Dhaka region. While previous studies have established regional equations for various parts of the world, our model uniquely has incorporated the Plasticity Index (PI) as a predictor for qu and is specifically calibrated for the geological characteristics of Dhaka city. The findings of this study highlight the effectiveness and applicability of regression analysis in predicting qu for Dhaka's soil properties, thus introducing a valuable tool for enhancing the accuracy and effectiveness of geotechnical assessments and design in the region. KEYWORDS: Unconfined compressive strength, Standard penetration test-N values, Plasticity index, Multiple linear regression, Random-forest regression, AdaBoost regression, Evaluation metrics, Trend-behavior analysis, Sensitivity analysis

Development and validation of the creatinine clearance predictor machine learning models in critically ill adults

BackgroundIn critically ill patients, measured creatinine clearance (CrCl) is the most reliable method to evaluate glomerular filtration rate in routine clinical practice and may vary subsequently on a day-to-day basis. We developed and externally validated models to predict CrCl one day ahead and compared them with a reference reflecting current clinical practice.MethodsA gradient boosting method (GBM) machine-learning algorithm was used to develop the models on data from 2825 patients from the EPaNIC multicenter randomized controlled trial database. We externally validated the models on 9576 patients from the University Hospitals Leuven, included in the M@tric database. Three models were developed: a “Core” model based on demographic, admission diagnosis, and daily laboratory results; a “Core + BGA” model adding blood gas analysis results; and a “Core + BGA + Monitoring” model also including high-resolution monitoring data. Model performance was evaluated against the actual CrCl by mean absolute error (MAE) and root-mean-square error (RMSE).ResultsAll three developed models showed smaller prediction errors than the reference. Assuming the same CrCl of the day of prediction showed 20.6 (95% CI 20.3–20.9) ml/min MAE and 40.1 (95% CI 37.9–42.3) ml/min RMSE in the external validation cohort, while the developed model having the smallest RMSE (the Core + BGA + Monitoring model) had 18.1 (95% CI 17.9–18.3) ml/min MAE and 28.9 (95% CI 28–29.7) ml/min RMSE.ConclusionsPrediction models based on routinely collected clinical data in the ICU were able to accurately predict next-day CrCl. These models could be useful for hydrophilic drug dosage adjustment or stratification of patients at risk.Trial registration. Not applicable.

Respiratory motion management using a single rapid MRI scan for a 0.35 T MRI-Linac system.

MRI has a rapidly growing role in radiation therapy (RT) for treatment planning, real-time image guidance, and beam gating (e.g., MRI-Linac). Free-breathing 4D-MRI is desirable in respiratory motion management for therapy. Moreover, high-quality 3D-MRIs without motion artifacts are needed to delineate lesions. Existing MRI methods require multiple scans with lengthy acquisition times or are limited by low spatial resolution, contrast, and signal-to-noise ratio. We developed a novel method to obtain motion-resolved 4D-MRIs and motion-integrated 3D-MRI reconstruction using a single rapid (35-45 s scan on a 0.35 T MRI-Linac. Golden-angle radial stack-of-stars MRI scans were acquired from a respiratory motion phantom and 12 healthy volunteers (n=12) on a 0.35 T MRI-Linac. A self-navigated method was employed to detect respiratory motion using 2000 (acquisition time=5-7 min) and the first 200 spokes (acquisition time=35-45 s). Multi-coil non-uniform fast Fourier transform (MCNUFFT), compressed sensing (CS), and deep-learning Phase2Phase (P2P) methods were employed to reconstruct motion-resolved 4D-MRI using 2000 spokes (MCNUFFT2000) and 200 spokes (CS200 and P2P200). Deformable motion vector fields (MVFs) were computed from the 4D-MRIs and used to reconstruct motion-corrected 3D-MRIs with the MOtion Transformation Integrated forward-Fourier (MOTIF) method. Image quality was evaluated quantitatively using the structural similarity index measure (SSIM) and the root mean square error (RMSE), and qualitatively in a blinded radiological review. Evaluation using the respiratory motion phantom experiment showed that the proposed method reversed the effects of motion blurring and restored edge sharpness. In the human study, P2P200 had smaller inaccuracy in MVFs estimation than CS200. P2P200 had significantly greater SSIMs (p<0.0001) and smaller RMSEs (p<0.001) than CS200 in motion-resolved 4D-MRI and motion-corrected 3D-MRI. The radiological review found that MOTIF 3D-MRIs using MCNUFFT2000 exhibited the highest image quality (scoring>8 out of 10), followed by P2P200 (scoring>5 out of 10), and then motion-uncorrected (scoring<3 out of 10) in sharpness, contrast, and artifact-freeness. We have successfully demonstrated a method for respiratory motion management for MRI-guided RT. The method integrated self-navigated respiratory motion detection, deep-learning P2P 4D-MRI reconstruction, and a motion integrated reconstruction (MOTIF) for 3D-MRI using a single rapid MRI scan (35-45 s) on a 0.35 T MRI-Linac system.

Prediction of water retention properties of French soils using the in situ volumetric water content at field capacity as single input data

The objective of this study was to investigate the relevance of using the in situ volumetric water content at field capacity (θFC) as a predictor of the water retention properties by comparing the performances of pedotransfer functions (PTFs) established using artificial neural networks (ANN-PTFs) and support vector machines (SVM-PTFs) with much simpler PTFs in the form of simple linear regressions (SLR-PTFs). A dataset comprising 456 horizons collected in soils located in France was used. The available data were: the silt and clay contents (SC), the organic carbon content (OC), the bulk density at field capacity (BDFCm), the in situ gravimetric water content at field capacity (WFCm) related to θFC by using BDFCm, and the volumetric water content at –1, –3.3, –10, –33, –100, –330 and –1500 kPa matric potential. The performances of the PTFs studied were compared by using the root mean squared error (RMSE) and the coefficient of determination (R²). Our results showed the relevance of using θFC, which was proved to be close to the volumetric water content at –10 kPa matric potential, as a predictor of the water retention properties. With ANN-PTFs, the best performances were recorded when both θFC and SC were used as input data (RMSE = 0.027 cm3 cm-3 and R2 = 0.92). With SVM-PTFs, the smallest RMSE was recorded when θFC was used as single input data (RMSE = 0.026 cm3 cm-3). As for R2 of SVM-PTFs, it was the highest with θFC and SC as input data (R2 = 0.84). The SLR-PTFs using θFCas single predictor after stratification by texture performed better (RMSE = 0.031 cm3 cm-3 and R2 = 0.88) than the ANN-PTFs using one or two soil characteristics as input data. Comparison of SLR-PTFs with SVM-PTFs showed that the latter performed slightly better than SLR-PTFs after stratification by texture but R2 was smaller when θFCwas used as the single predictor. Use of a predicted value of the bulk density at field capacity to obtain a value of in situ volumetric water content at field capacity led to poorer performances of the SLR-PTFs but after stratification by texture they remained close to those recorded with ANN-PTFs or SVM-PTFs when they used a single soil characteristic as input data. Finally, our results showed that associating OC to the input data did not increase the perfomances of the ANN-PTFs and SVM-PTFs.

Principal Component Analysis of morphometric traits and body indices in South African Kalahari Red goats

Principal component analysis (PCA) is a vital statistical technique for defining the morphological structure of livestock but has not been used in South African Kalahari Red goats. Thirteen morphometric traits and eleven body indices from two hundred and ninety-six (296) South African Kalahari Red goats (269 does and 27 bucks) aged 2–3 years were used to define morphological structure using PCA. The coefficient of determination (R2), root mean square error (RMSE), Akaike’s information criterion (AIC), Mallows' Cp-statistic (Cp), and coefficient of variation (CV) were used to select the best fit model. Body weight was correlated with all morphometric traits in both sexes. The first two principal components explained 87.31% of the variation in measurements from male goats and 62.32% of the trait variation in the females. The inclusion of head length, body length, canon circumference, rump length, rump width, body condition score, wither height, and rump height increased the accuracy to 98% with smaller RMSE (2.42), AIC (55.35), Cp (10.00), and CV (3.98), and the use of PC1 and PC2 included 94% of the variation (RMSE, 3.62; AIC, 72.26; Cp, 3.00; CV, 5.94 in males). In females, the inclusion of all morphometric traits included 87% of the variation (RMSE, 2.93; AIC, 590.63; Cp, 13.00; CV 5.87). The use of PC1 and PC2 included 82% of the variation (RMSE, 3.41; AIC, 663.60; Cp, 3.00; CV, 6.84). PCA can therefore be used in breeding programs to define the morphological structure of South African Kalahari Red goats with a severe reduction in the number of morphometric traits to be recorded.

Multicenter quantitative 18F-fluorodeoxyglucose positron emission tomography performance harmonization: use of hottest voxels towards more robust quantification.

Harmonization methods reduce variability between different make and models of positron emission tomography (PET) scanners. The study aims to explore harmonization strategies that lead to comparable and robust quantitative metrics in a multicenter setting. NEMA IEC Phantom data acquisition was performed for low and high spheres-to-background ratios (SBR4:1 and 10:1) on six PET/CT (computed tomography) scanners. Different reconstruction sets, including the number of sub-iterations, number of subsets, and full width at half maximum (FWHM) for each scanner, were evaluated towards optimized and harmonized reconstruction settings. Recovery coefficients (RCs) of four quantitative metrics, including standardized uptake value (SUV)max, SUVISO-50 (SUVmean in 50% isocontour), SUVpeak, and mean uptake of 10 highest concentration voxels were evaluated as RCmax, RCISO-50, RCpeak, and RC10V, representing percent difference relative to the static ground truth case as functions of sphere sizes. A set of image reconstruction parameters was proposed for harmonized reconstruction to minimize variability between scanners. The root mean square error (RMSE), curvature, and reproducibility were examined. The proposed reconstruction protocols for harmonization and standard clinical reconstruction settings were compared to each other across all scanners. A significant difference (P value <0.0001) was observed in the aforementioned quantitative metrics between SBR10 and SBR4. Reconstruction parameter sets with the smallest RMSE and RC values within 10% bias were identified as the best candidate for harmonization. The coefficient of variation of the mean value of RCs (CVMRC) shows a remarkable reduction of about 28%, 26%, 32%, and 19% in harmonized reconstruction settings for MRCmax, MRCISO-50, MRCpeak, and MRC10V, respectively. CVMRC for MRC10V in the harmonized reconstruction setting was 5.9% in SBR4, while the smallest value in SBR10 belongs to MRCpeak, with a value of 5.8%. The reproducibility of RC is improved by deriving the value from ten hottest voxels and is equally reproducible with RCpeak. Compared to RCmax and RCISO-50, the variability is reduced by 18% and 22% if ten voxels are pooled. Harmonizing PET/CT systems with and without point spread function/time of flight (PSF/TOF) using various vendor-developed image reconstruction algorithms improves the quantification reproducibility. RC10V, likewise RCpeak, is superior to the rest of the quantitative indices in terms of accuracy and reproducibility and helpful in quantifying lesion volume below 1 mL.

A two-stage method for model parameter identification based on the maximum power matching and improved flow direction algorithm

Parameter identification of the photovoltaic (PV) model is essential to research in the PV field. A two-stage method of model parameter identification based on maximum power matching (MPM) and improved flow direction algorithm (IFDA) is proposed. The two-stage method, i.e., MPM-based rough extraction and IFDA-based precise identification. The quality of I–V data dramatically impacts the PV model’s parameter identification accuracy. At first, the measured I–V curves are preprocessed. The process includes outlier removal, curve fitting, and sparsification of I–V data. Then the MPM is used for the rough extraction of model parameters from the preprocessed I–V data. Finally, the rough extraction results are used as the initial values of the iterations in the precise identification using IFDA. The root mean square error (RMSE) between the measured and calculated currents is used as the fitness function of IFDA. The experimental section compares sixteen methods. IFDA presents the highest accuracy with the smallest RMSE at 0.0024 A. Five methods with outstanding performance are selected for 1000 repetitive experiments. The IFDA is the most stable with RMSE in the range of 0.002 A to 0.003 A.

Modelling of Reference Evapotranspiration using Neural Network and Regression Approaches for Semi-humid Region of Sikkim

This study compared the applicability of multiple linear regression (MLR) and artificial neural network (ANN) approaches for estimating the weekly reference evapotranspiration (ET0) in a semi-humid area of Tadong in Gangtok district of Sikkim state in India. Daily meteorological data (1991 - 2020) were used for developing MLR and ANN model using various combinations of meteorological data. Predicted ET0 values were compared with the FAO-56 Penman Monteith (PM) equation estimated ET0. The coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), and Nash Sutcliffe efficiency (NSE) were used to assess the performance of MLR and ANN models. For ANN model, one hidden layer and four neurons was found as the best ANN architecture. ANN-4 model with inputs parameters of maximum air temperature (Tmax), minimum air temperature (Tmin), maximum relative humidity (RHmax), minimum relative humidity (RHmin), and sunshine hours (SSH) had the smallest RMSE (0.609 mm.day-1 and 0.880 mm.day-1), MAE (0.473 mm.day-1 and 0.551mm.day-1) and the highest R2 (0.752 and 0.657) and NSE (0.782 and 0.696) during training and testing phases, respectively. The MLR-4 model with same combination of input parameters (Tmax, Tmin, RHmax, RHmin, SSH) resulted in smallest RMSE (0.704 mm.day-1 and 0.714 mm.day-1), MAE (0.562 mm.day-1and 0.583 mm.day-1); and the highest R2 (0.679 and 0.602) and NSE (0.708 and 0.597) during training and testing phase, respectively. Study also showed increase in model performance of ANN and MLR models with increase in number of meteorological parameters. All the ANN models gave comparable results, but ANN 4 model resulted in higher prediction accuracy for the sub-humid region of Tadong in Gangtok district of North-east India. The developed ANN-4 model could be helpful for preparing irrigation schedules and planning, and management of water resources in the data scarce northeast region of India and other identical climatic regions.

Classifying and Scoring Major Depressive Disorders by Residual Neural Networks on Specific Frequencies and Brain Regions.

Major Depressive Disorder (MDD) - can be evaluated by advanced neurocomputing and traditional machine learning techniques. This study aims to develop an automatic system based on a Brain-Computer Interface (BCI) to classify and score depressive patients by specific frequency bands and electrodes. In this study, two Residual Neural Networks (ResNets) based on electroencephalogram (EEG) monitoring are presented for classifying depression (classifier) and for scoring depressive severity (regression). Significant frequency bands and specific brain regions are selected to improve the performance of the ResNets. The algorithm, which is estimated by 10-fold cross-validation, attained an average accuracy rate ranging from 0.371 to 0.571 and achieved average Root-Mean-Square Error (RMSE) from 7.25 to 8.41. After using the beta frequency band and 16 specific EEG channels, we obtained the best-classifying accuracy at 0.871 and the smallest RMSE at 2.80. It was discovered that signals extracted from the beta band are more distinctive in depression classification, and these selected channels tend to perform better on scoring depressive severity. Our study also uncovered the different brain architectural connections by relying on phase coherence analysis. Increased delta deactivation accompanied by strong beta activation is the main feature of depression when the depression symptom is becoming more severe. We can therefore conclude that the model developed here is acceptable for classifying depression and for scoring depressive severity. Our model can offer physicians a model that consists of topological dependency, quantified semantic depressive symptoms and clinical features by using EEG signals. These selected brain regions and significant beta frequency bands can improve the performance of the BCI system for detecting depression and scoring depressive severity.