scholarly journals Next Generation Network Real-Time Kinematic Interpolation Segment to Improve the User Accuracy

2015 ◽  
Vol 2015 ◽  
pp. 1-15 ◽  
Author(s):  
Mohammed Ouassou ◽  
Anna B. O. Jensen ◽  
Jon G. O. Gjevestad ◽  
Oddgeir Kristiansen
Keyword(s):  
Real Time ◽  
Mean Square Error ◽  
Thin Plate ◽  
Goodness Of Fit ◽  
Spline Interpolation ◽  
Computation Time ◽  
Absolute Error ◽  
Kriging Interpolation ◽  
Mean Square ◽  
Real Time Kinematic

This paper demonstrates that automatic selection of the right interpolation/smoothing method in a GNSS-based network real-time kinematic (NRTK) interpolation segment can improve the accuracy of the rover position estimates and also the processing time in the NRTK processing center. The methods discussed and investigated are inverse distance weighting (IDW); bilinear and bicubic spline interpolation; kriging interpolation; thin-plate splines; and numerical approximation methods for spatial processes. The methods are implemented and tested using GNSS data from reference stations in the Norwegian network RTK service called CPOS. Data sets with an average baseline between reference stations of 60–70 km were selected. 12 prediction locations were used to analyze the performance of the interpolation methods by computing and comparing different measures of the goodness of fit such as the root mean square error (RMSE), mean square error, and mean absolute error, and also the computation time was compared. Results of the tests show that ordinary kriging with the Matérn covariance function clearly provides the best results. The thin-plate spline provides the second best results of the methods selected and with the test data used.

Investigation of the spatial variation of sediments heavy metals along the Nun River using kriging interpolation technique

2021 ◽  
Vol 4 (2) ◽  
pp. 108-118
Author(s):  
I. R. Ilaboya ◽  
J. O. Ehiorobo ◽  
N. Onwo
Keyword(s):  
Heavy Metals ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Goodness Of Fit ◽  
Critical Parameters ◽  
Kriging Interpolation ◽  
Suitable Model ◽  
Mean Square ◽  
High Concentration ◽  
Cadmium Lead

This study employs geospatial statistical technique to assess the spatial distribution of heavy metals along the Nun River. Core sediment samples were collected from relatively undisturbed areas (twenty-five different stations) using Uwitec Triple sediment cutter. The rectangular coordinates of the sediment sample location were determined with the aid of Germin handheld GPS receiver. The concentrations of cadmium, lead chromium and zinc present in the sediments was determined with the aid of an atomic absorption spectrophotometer. For geospatial analysis, five semi-variogram models (stable, circular, spherical, exponential and K-Bessel) were fitted for each of the four critical parameters (heavy metals). In addition, four goodness-of-fit statistics (mean square error, root mean square error, root mean square standardized error and average standard error) were utilized to decide the most suitable model used to develop the final prediction map for each parameter. From the results obtained, it was observed that; regions with red color codes signify higher concentrations of cadmium, lead, chromium and zinc. Further assessment of the results showed that Otuan, Obeleli, Angiama, Odobio, Kasama, Akedda and Akele experienced high concentration of cadmium while Tombia, Ewoi, Abilabio, Agudama and Yenikpa experienced high concentration of lead.

scholarly journals Application of Novel Machine Learning Techniques for Predicting the Surface Chloride Concentration in Concrete Containing Waste Material

Materials ◽  
2021 ◽  
Vol 14 (9) ◽  
pp. 2297
Author(s):  
Ayaz Ahmad ◽  
Furqan Farooq ◽  
Krzysztof Adam Ostrowski ◽  
Klaudia Śliwa-Wieczorek ◽  
Slawomir Czarnecki
Keyword(s):  
Machine Learning ◽  
Mean Square Error ◽  
Gene Expression Programming ◽  
Chloride Concentration ◽  
Absolute Error ◽  
Chloride Ions ◽  
Machine Learning Techniques ◽  
Extensive Literature ◽  
Mean Square ◽  
Chloride Concentrations

Structures located on the coast are subjected to the long-term influence of chloride ions, which cause the corrosion of steel reinforcements in concrete elements. This corrosion severely affects the performance of the elements and may shorten the lifespan of an entire structure. Even though experimental activities in laboratories might be a solution, they may also be problematic due to time and costs. Thus, the application of individual machine learning (ML) techniques has been investigated to predict surface chloride concentrations (Cc) in marine structures. For this purpose, the values of Cc in tidal, splash, and submerged zones were collected from an extensive literature survey and incorporated into the article. Gene expression programming (GEP), the decision tree (DT), and an artificial neural network (ANN) were used to predict the surface chloride concentrations, and the most accurate algorithm was then selected. The GEP model was the most accurate when compared to ANN and DT, which was confirmed by the high accuracy level of the K-fold cross-validation and linear correlation coefficient (R2), mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) parameters. As is shown in the article, the proposed method is an effective and accurate way to predict the surface chloride concentration without the inconveniences of laboratory tests.

Designing an efficient predictor model using PSNN and crow search based optimization technique for gold price prediction

2021 ◽  
pp. 1-9
Author(s):  
Rajashree Dash ◽  
Anuradha Routray ◽  
Rasmita Dash ◽  
Rasmita Rautray
Keyword(s):  
Mean Square Error ◽  
Optimization Technique ◽  
Absolute Error ◽  
Time Frame ◽  
Gold Price ◽  
Future Price ◽  
Mean Square ◽  
Learning Speed ◽  
Predictor Model ◽  
Hidden Layer

Predicting future price of Gold has always been an intriguing field of investigation for researchers as well as investors who desire to invest in present and gain profit in the future. Since ancient time, Gold is being arbitrated as a leading asset in monetary business. As the worth of gold changes within confined boundaries, reducing the effect of inflation, so it is a beneficial property favoured by many stakeholders. Hence, there is always an urge of a more authenticate model for forecasting the gold price based upon the changes in it in a previous time frame. This study focuses on designing an efficient predictor model using a Pi-Sigma Neural Network (PSNN) for forecasting future gold. The underlying motivation of using PSNN is its quick learning and easy implementation compared to other neural networks. The fixed unit weights used in between hidden and output layer of PSNN helps it in achieving faster learning speed compared to other similar types of networks. But estimating the unknown weights used in between the input and hidden layer is still a major challenge in its design phase. As final outcome of the network is highly influenced by its weight, so a novel Crow Search based nature inspired optimization algorithm (CSA) is proposed to estimate these adjustable weights of the network. The proposed model is also compared with Particle Swarm Optimization (PSO) and Differential Evolution (DE) based learning of PSNN. The model is validated over two historical datasets such as Gold/INR and Gold/AED by considering three statistical errors such as Mean Square Error (MSE), Root Mean Square Error (RMSE) and Mean Absolute Error (MAE). Empirical observations clearly show that, the developed CSA-PSNN predictor model is providing better prediction results compared to PSO-PSNN and DE-PSNN model.

scholarly journals Indian COVID-19 dynamics: Prediction using autoregressive integrated moving average modelling

2021 ◽  
Vol 52 (1) ◽  
pp. 6-14
Author(s):  
Amit Tak ◽  
Sunita Dia ◽  
Mahendra Dia ◽  
Todd Wehner
Keyword(s):  
Root Mean Square Error ◽  
Real Time ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Moving Average ◽  
Information Criteria ◽  
Evidence Based ◽  
Mean Square ◽  
Autoregressive Integrated Moving Average ◽  
Akaike Information Criteria

Background: The forecasting of Coronavirus Disease-19 (COVID-19) dynamics is a centrepiece in evidence-based disease management. Numerous approaches that use mathematical modelling have been used to predict the outcome of the pandemic, including data-driven models, empirical and hybrid models. This study was aimed at prediction of COVID-19 evolution in India using a model based on autoregressive integrated moving average (ARIMA). Material and Methods: Real-time Indian data of cumulative cases and deaths of COVID-19 was retrieved from the Johns Hopkins dashboard. The dataset from 11 March 2020 to 25 June 2020 (n = 107 time points) was used to fit the autoregressive integrated moving average model. The model with minimum Akaike Information Criteria was used for forecasting. The predicted root mean square error (PredRMSE) and base root mean square error (BaseRMSE) were used to validate the model. Results: The ARIMA (1,3,2) and ARIMA (3,3,1) model fit best for cumulative cases and deaths, respectively, with minimum Akaike Information Criteria. The prediction of cumulative cases and deaths for next 10 days from 26 June 2020 to 5 July 2020 showed a trend toward continuous increment. The PredRMSE and BaseRMSE of ARIMA (1,3,2) model were 21,137 and 166,330, respectively. Similarly, PredRMSE and BaseRMSE of ARIMA (3,3,1) model were 668.7 and 5,431, respectively. Conclusion: It is proposed that data on COVID-19 be collected continuously, and that forecasting continue in real time. The COVID-19 forecast assist government in resource optimisation and evidence-based decision making for a subsequent state of affairs.

scholarly journals Artificial Neural Network (FFBP-ANN) Based Grey Relational Analysis for Modeling Dyestuff Solubility in Supercritical CO2 with Ethanol as the Co-Solvent

2021 ◽  
Author(s):  
FNU SRINIDHI
Keyword(s):  
Carbon Dioxide ◽  
Supercritical Carbon Dioxide ◽  
Mean Square Error ◽  
Supercritical Co2 ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Mean Square ◽  
Relational Analysis ◽  
Grey Relational ◽  
Supercritical Carbon

The research on dye solubility modeling in supercritical carbon dioxide is gaining prominence over the past few decades. A simple and ubiquitous model that is capable of accurately predicting the solubility in supercritical carbon dioxide would be invaluable for industrial and research applications. In this study, we present such a model for predicting dye solubility in supercritical carbon dioxide with ethanol as the co-solvent for a qualitatively diverse sample of eight dyes. A feed forward back propagation - artificial neural network model based on Levenberg-Marquardt algorithm was constructed with seven input parameters for solubility prediction, the network architecture was optimized to be [7-7-1] with mean absolute error, mean square error, root mean square error and Nash-Sutcliffe coefficient to be 0.026, 0.0016, 0.04 and 0.9588 respectively. Further, Pearson-product moment correlation analysis was performed to assess the relative importance of the parameters considered in the ANN model. A total of twelve prevalent semiempirical equations were also studied to analyze their efficiency in correlating to the solubility of the prepared sample. Mendez-Teja model was found to be relatively efficient with root mean square error and mean absolute error to be 0.094 and 0.0088 respectively. Furthermore, Grey relational analysis was performed and the optimum regime of temperature and pressure were identified with dye solubility as the higher the better performance characteristic. Finally, the dye specific crossover ranges were identified by analysis of isotherms and a strategy for class specific selective dye extraction using supercritical CO2 extraction process is proposed.

Metabolic Rate in Adolescent Athletes: The Development and Validation of New Equations, and Comparison to Previous Models

2020 ◽  
Vol 30 (4) ◽  
pp. 249-257
Author(s):  
Reid J. Reale ◽  
Timothy J. Roberts ◽  
Khalil A. Lee ◽  
Justina L. Bonsignore ◽  
Melissa L. Anderson
Keyword(s):  
Root Mean Square Error ◽  
Metabolic Rate ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Mean Absolute Error ◽  
Compartment Model ◽  
Absolute Error ◽  
Mean Square ◽  
Adolescent Athletes ◽  
Two Compartment Model

We sought to assess the accuracy of current or developing new prediction equations for resting metabolic rate (RMR) in adolescent athletes. RMR was assessed via indirect calorimetry, alongside known predictors (body composition via dual-energy X-ray absorptiometry, height, age, and sex) and hypothesized predictors (race and maturation status assessed via years to peak height velocity), in a diverse cohort of adolescent athletes (n = 126, 77% male, body mass = 72.8 ± 16.6 kg, height = 176.2 ± 10.5 cm, age = 16.5 ± 1.4 years). Predictive equations were produced and cross-validated using repeated k-fold cross-validation by stepwise multiple linear regression (10 folds, 100 repeats). Performance of the developed equations was compared with several published equations. Seven of the eight published equations examined performed poorly, underestimating RMR in >75% to >90% of cases. Root mean square error of the six equations ranged from 176 to 373, mean absolute error ranged from 115 to 373 kcal, and mean absolute error SD ranged from 103 to 185 kcal. Only the Schofield equation performed reasonably well, underestimating RMR in 51% of cases. A one- and two-compartment model were developed, both r2 of .83, root mean square error of 147, and mean absolute error of 114 ± 26 and 117 ± 25 kcal for the one- and two-compartment model, respectively. Based on the models’ performance, as well as visual inspection of residual plots, the following model predicts RMR in adolescent athletes with better precision than previous models; RMR = 11.1 × body mass (kg) + 8.4 × height (cm) − (340 male or 537 female).

scholarly journals Electrical Energy Prediction in Residential Buildings for Short-Term Horizons Using Hybrid Deep Learning Strategy

2020 ◽  
Vol 10 (23) ◽  
pp. 8634
Author(s):  
Zulfiqar Ahmad Khan ◽  
Amin Ullah ◽  
Waseem Ullah ◽  
Seungmin Rho ◽  
Miyoung Lee ◽  
...  
Keyword(s):  
Mean Square Error ◽  
Learning Strategy ◽  
Residential Buildings ◽  
Electricity Consumption ◽  
Absolute Error ◽  
Management Policy ◽  
Mean Square ◽  
Load Prediction ◽  
Energy Prediction ◽  
Proposed Model

Smart grid technology based on renewable energy and energy storage systems are attracting considerable attention towards energy crises. Accurate and reliable model for electricity prediction is considered a key factor for a suitable energy management policy. Currently, electricity consumption is rapidly increasing due to the rise in human population and technology development. Therefore, in this study, we established a two-step methodology for residential building load prediction, which comprises two stages: in the first stage, the raw data of electricity consumption are refined for effective training; and the second step includes a hybrid model with the integration of convolutional neural network (CNN) and multilayer bidirectional gated recurrent unit (MB-GRU). The CNN layers are incorporated into the model as a feature extractor, while MB-GRU learns the sequences between electricity consumption data. The proposed model is evaluated using the root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) metrics. Finally, our model is assessed over benchmark datasets that exhibited an extensive drop in the error rate in comparison to other techniques. The results indicated that the proposed model reduced errors over the individual household electricity consumption prediction (IHEPC) dataset (i.e., RMSE (5%), MSE (4%), and MAE (4%)), and for the appliances load prediction (AEP) dataset (i.e., RMSE (2%), and MAE (1%)).

scholarly journals Estimating Maximum Daily Precipitation in the Upper Vistula Basin, Poland

Atmosphere ◽  
2019 ◽  
Vol 10 (2) ◽  
pp. 43 ◽  
Author(s):  
Dariusz Młyński ◽  
Andrzej Wałęga ◽  
Andrea Petroselli ◽  
Flavia Tauro ◽  
Marta Cebulska
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Goodness Of Fit ◽  
Daily Precipitation ◽  
Probability Distributions ◽  
Random Variables ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Probability Of Exceedance

The aim of this study was to determine the best probability distributions for calculating the maximum annual daily precipitation with the specific probability of exceedance (Pmaxp%). The novelty of this study lies in using the peak-weighted root mean square error (PWRMSE), the root mean square error (RMSE), and the coefficient of determination (R2) for assessing the fit of empirical and theoretical distributions. The input data included maximum daily precipitation records collected in the years 1971–2014 at 51 rainfall stations from the Upper Vistula Basin, Southern Poland. The value of Pmaxp% was determined based on the following probability distributions of random variables: Pearson’s type III (PIII), Weibull’s (W), log-normal, generalized extreme value (GEV), and Gumbel’s (G). Our outcomes showed a lack of significant trends in the observation series of the investigated random variables for a majority of the rainfall stations in the Upper Vistula Basin. We found that the peak-weighted root mean square error (PWRMSE) method, a commonly used metric for quality assessment of rainfall-runoff models, is useful for identifying the statistical distributions of the best fit. In fact, our findings demonstrated the consistency of this approach with the RMSE goodness-of-fit metrics. We also identified the GEV distribution as recommended for calculating the maximum daily precipitation with the specific probability of exceedance in the catchments of the Upper Vistula Basin.

scholarly journals Global Mean Sea Surface Height Estimated from Spaceborne Cyclone-GNSS Reflectometry

2020 ◽  
Vol 12 (3) ◽  
pp. 356 ◽  
Author(s):  
Hui Qiu ◽  
Shuanggen Jin
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Correlation Coefficient ◽  
Root Mean Square ◽  
Absolute Error ◽  
Satellite System ◽  
Sea Surface Height ◽  
Sea Surface ◽  
Mean Square ◽  
Mean Sea Surface

Mean sea surface height (MSSH) is an important parameter, which plays an important role in the analysis of the geoid gap and the prediction of ocean dynamics. Traditional measurement methods, such as the buoy and ship survey, have a small cover area, sparse data, and high cost. Recently, the Global Navigation Satellite System-Reflectometry (GNSS-R) and the spaceborne Cyclone Global Navigation Satellite System (CYGNSS) mission, which were launched on 15 December 2016, have provided a new opportunity to estimate MSSH with all-weather, global coverage, high spatial-temporal resolution, rich signal sources, and strong concealability. In this paper, the global MSSH was estimated by using the relationship between the waveform characteristics of the delay waveform (DM) obtained by the delay Doppler map (DDM) of CYGNSS data, which was validated by satellite altimetry. Compared with the altimetry CNES_CLS2015 product provided by AVISO, the mean absolute error was 1.33 m, the root mean square error was 2.26 m, and the correlation coefficient was 0.97. Compared with the sea surface height model DTU10, the mean absolute error was 1.20 m, the root mean square error was 2.15 m, and the correlation coefficient was 0.97. Furthermore, the sea surface height obtained from CYGNSS was consistent with Jason-2′s results by the average absolute error of 2.63 m, a root mean square error ( RMSE ) of 3.56 m and, a correlation coefficient ( R ) of 0.95.

Sign in / Sign up

Export Citation Format

Share Document