Terms Of Correlation Research Articles

A machine learning aided interpretable model for rupture strength prediction in Fe-based martensitic and austenitic alloys

The class of 9–12% Cr ferritic-martensitic alloys (FMA) and austenitic stainless steels have received considerable attention due to their numerous applications in high temperature power generation industries. To design high strength steels with prolonged service life requires a thorough understanding of the long-term properties, e.g., creep rupture strength, rupture life, etc., as a function of the chemical composition and processing parameters that govern the microstructural characteristics. In this article, the creep rupture strength of both 9–12% Cr FMA and austenitic stainless steel has been parameterized using curated experimental datasets with a gradient boosting machine. The trained model has been cross validated against unseen test data and achieved high predictive performance in terms of correlation coefficient (R^{2} > 0.98 for 9–12% Cr FMA and R^{2} > 0.95 for austenitic stainless steel) thus bypassing the need for additional comprehensive tensile test campaigns or physical theoretical calculations. Furthermore, the feature importance has been computed using the Shapley value analysis to understand the complex interplay of different features.

Approaches for Optimizing the Performance of Adaptive Neuro-Fuzzy Inference System and Least-Squares Support Vector Machine in Precipitation Modeling

This study employs two heuristic algorithms, including the genetic algorithm (GA) and ant colony optimization for continuous domains (ACOR), for optimizing the parameters of two soft computing models, namely adaptive neuro-fuzzy inference system (ANFIS) and least-squares support vector machine (LSSVM), which were used for modeling monthly precipitation for all 12 months of the year. Data from 40 meteorological stations situated in different parts of Iran were used. The effectiveness of input data was determined by internal correlation-coefficient and nonlinear sensitivity analysis. Selected input data were further evaluated by another sensitivity analysis method, cosine amplitude (CA). Considering different evaluation months, LSSVM was more accurate and reliable than ANFIS. It was also found that both algorithms improved the performance of models for most months of the year. ACOR was better and more reliable than was GA in optimizing the models. ACOR produced the best results in autumn that led to the improvement of performance of ANFIS in terms of correlation coefficient (R) and root-mean square error (RMSE) by 35% and 0.40 mm for October; 42% and 0.99 mm for November; and 31% and 0.74 mm for December. The performance of LSSVM was enhanced by 6% and 0.28 mm for October; 22% and 0.20 mm for November; and 4% and 0.10 mm for December, respectively. For July and August, the suggested algorithms could not improve the performance of ANFIS. The algorithms did optimize LSSVM in all months, so the RMSE and mean absolute error were improved by 0.15 and 0.28 mm for July and 0.28 and 0.56 mm for August, respectively.

A Characterization of Hot Flow Behaviors of Invar36 Alloy by an Artificial Neural Network with Back-Propagation Algorithm

In order to investigate the hot deformation behaviors of Invar36 alloy, isothermal compressive tests were conducted on a Gleeble 1500 thermo-mechanical simulator at the temperatures of 873, 948, 1023, 1098 and 1173 K and the strain rates of 0.01, 0.1, 1 and 10 s−1. The effects of strain, temperature and strain rate on flow stress were analyzed, and a dynamic recrystallization type softening characteristic with unimodal flow behavior is determined. An artificial neural network based on back-propagation algorithm was proposed to handle the complex deformation behavior characteristics. The ANN model was evaluated in terms of correlation coefficient and average absolute relative error. A comparative study was performed on ANN model and constitutive equation by regression method for Invar36 alloy. Finally, the ANN model was applied to the finite element simulation, and an experimental study on trial hot forming of a V-shaped part was conducted to demonstrate the precision of the finite element simulation based on predicted flow stress data by ANN model. The results have sufficiently showed that the well-trained ANN model with BP algorithm is able to deal with the complex flow behaviors of Invar36 alloy and has great application potentiality in hot deformation.

Application of Various Machine Learning Techniques in Predicting Total Organic Carbon from Well Logs.

Unconventional resources have recently gained a lot of attention, and as a consequence, there has been an increase in research interest in predicting total organic carbon (TOC) as a crucial quality indicator. TOC is commonly measured experimentally; however, due to sampling restrictions, obtaining continuous data on TOC is difficult. Therefore, different empirical correlations for TOC have been presented. However, there are concerns about the generalization and accuracy of these correlations. In this paper, different machine learning (ML) techniques were utilized to develop models that predict TOC from well logs, including formation resistivity (FR), spontaneous potential (SP), sonic transit time (Δt), bulk density (RHOB), neutron porosity (CNP), gamma ray (GR), and spectrum logs of thorium (Th), uranium (Ur), and potassium (K). Over 1250 data points from the Devonian Duvernay shale were utilized to create and validate the model. These datasets were obtained from three wells; the first was used to train the models, while the data sets from the other two wells were utilized to test and validate them. Support vector machine (SVM), random forest (RF), and decision tree (DT) were the ML approaches tested, and their predictions were contrasted with three empirical correlations. Various AI methods' parameters were tested to assure the best possible accuracy in terms of correlation coefficient (R) and average absolute percentage error (AAPE) between the actual and predicted TOC. The three ML methods yielded good matches; however, the RF-based model has the best performance. The RF model was able to predict the TOC for the different datasets with R values range between 0.93 and 0.99 and AAPE values less than 14%. In terms of average error, the ML-based models outperformed the other three empirical correlations. This study shows the capability and robustness of ML models to predict the total organic carbon from readily available logging data without the need for core analysis or additional well interventions.

Identification of genetic diversity among Juglans regia L. genotypes using molecular, morphological, and fatty acid data

In this study, 40 walnut (Juglans regia L.) samples including international cultivars, national cultivars and local genotypes were analyzed in terms of detailed morphological traits, molecular characteristics, and biochemical (fatty acids) features. The results showed high morphological diversity among the genotypes, and the kernel ratio was found to have major contribution for the principal component analysis (PCA). Molecular results showed that the 19 SRAP primer combinations produced, on average, 171 bands in the accessions examined, of which 156 (90.6%) were polymorphic and DICE’s similarity coefficient ranged from 0.49 to 0.94 indicating high genetic diversity. The polymorphism ratio of 11 primers was 100% while the lowest polymorphism was 66.7%. There were no significant differences in terms of correlation coefficient between the similarity matrices of the morphological traits and SRAP (r = 0.03). The main fatty acids of walnut kernel oils were found to be linoleic acid (C18:2) followed by oleic acid (C18:1) and linolenic acid (C18:3). The polyunsaturated fatty acids constitute the main group of fatty acids in walnut kernel oils, and these ratios varied between 85.99–92.19%. It has been determined that the morphological and biochemical data may be insufficient alone in identification of genetic diversity and relativeness in walnut because they should be supported by molecular data.

Prediction of Polymer Flow Length by Coupling Finite Element Simulation with Artificial Neural Network

In this study, computer-aided engineering (CAE) simulation software and the design of experiments (DOE) method were used to simulate the injection molding process in terms of the melt flow length, using a spiral part. Process parameters such as melt temperature, mold temperature, injection pressure and mold cavity thickness were considered as injection molding variables. A predictive model for the flow length was created using a three-layer artificial neural network (ANN). The ANN model was trained with both simulation and experimental data, and the predictive performances were compared in terms of correlation coefficient, root mean square error and mean relative error. The cavity thickness and melt temperature were found to be the most significant factors for both the simulation and the experiment, while the injection pressure and the mold temperature had little effect on the flow length. The ANN model trained with Moldex3D data shows a significantly higher prediction capacity than the ANN model trained with experimental data. However, the melt flow lengths predicted by the ANN model for both Moldex3D and Moldflow simulation data are statistically significant, indicating that the proposed prediction methodology, which combines the ANN model, DOE method and the CAE simulation technology, can effectively predict the flow length of injection molded parts, with a small number of data.

Modelling and prediction of water current using artificial neural networks: A case study of the commodore channel

Water current modelling and prediction techniques along coastal inlets have attracted growing concern in recent years. This is largely so because water current component continues to be a major contributor to movement of sediments, tracers and pollutants, and to a whole range of offshore applications in engineering, environmental observations, exploration and oceanography. However, most research works are lacking adequate methods for developing precise prediction models along the commodore channel in Lagos State. This research work presents water current prediction using Artificial Neural Networks (ANNs). The Back Propagation (BP) technique with feed forward architecture and optimized training algorithm known as Levenbergq-Marquardt was used to develop a Neural Network Water Current Prediction model-(NNWLM) in a MATLAB programming environment. It was passed through model sensitivity analysis and afterwards tested with data from the Commodore channel (Lagos Lagoon). The result revealed prediction accuracy ranging from 0.012 to 0.045 in terms of Mean Square Error (MSE) and 0.80 to 0.83 in terms of correlation coefficient (R-value). With this high performance, the Neural network developed in this work can be used as a veritable tool for water current prediction along the Commodore channel and in extension a wide variety of coastal engineering and development, covering sediment management program: dredging, sand bypassing, beach-contingency plans, and protection of beaches vulnerable to storm erosion and monitoring and prediction of long-term water current variations in coastal inlets.
 Keywords: Artificial Neural Network, Commodore Channel, Coastal Inlet, Water Current, Back Propagation.

Radar Sea Clutter Reconstruction Based on Statistical Singularity Power Spectrum and Instantaneous Singularity Exponents Distribution

The modeling and reconstruction of radar sea clutter (RSC) based on fractal theory is studied in this article. With theoretical derivation and quantitative analysis, the radar clutter reconstruction model based on singularity power spectrum (SPS) and instantaneous singularity exponent (ISE) distribution is proposed. The proposed ISE–SPS model consists of two coupling channels: power measure channel and dimension measure channel. The former is controlled by SPS to characterize the power distribution of signals in the SE domain, while the latter is determined by ISE function to characterize the statistical distribution of ISE. The multiscale wavelet coefficients are estimated based on the coupling of the two channels to reconstruct the RSC. The proposed ISE–SPS method is tested on RSC data in different sea state, from the ice multiparameter imaging X-band (IPIX) radar. Experimental and simulation based on the IPIX radar data set indicates that the proposed method performs better than the $N$ -partitioned random multiplicative model (NRMM) method and SPS-multifractal spectrum (MFS) method, and exceeds the traditional methods by nearly 35% in terms of correlation coefficient and normalized mean square error of MFS and SPS.

Statistics of thickness and strength of first-year ice along the Northern Sea Route

In this paper, statistics of ice thickness and ice strength of first-year sea ice along the Northern Sea Route (NSR) is studied to provide useful information for the design and operation of Arctic ships. Specifically, ice thickness, ice strength and other physical parameters of the sea ice are estimated. Four representative sites are selected to study the ice environment and ice strength in different sea areas along the NSR during the ice growth season. Besides that, a good knowledge of the co-variation relationships between these ice parameters in a particular region would promote the estimation of ice loads acting on structures located in this region. In this work, a novel probabilistic model is introduced to describe the probability distribution of the ice flexural strength. The co-variation relationships between ice thickness and ice strength are quantified in terms of correlation coefficients. The influence of air temperature on ice properties is also investigated and discussed.

A two-step fusion framework for quality improvement of a remotely sensed soil moisture product: A case study for the ECV product over the Tibetan Plateau

High quality remotely sensed soil moisture (SM) with high temporal coverage, high variation capturing ability and high accuracy, is very important to agricultural, hydrological and environmental applications. The Essential Climate Variable (ECV) SM dataset is the first product attempting to address the continuity and reliability issues of individual SM sensors by using multi-satellite observations, but limitations in quality still persist. This study proposes a two-step fusion framework to obtain high temporal coverage, high variation capturing ability and high accuracy remotely sensed SM. The first step aims to improve the temporal coverage by filling the gaps of remotely sensed SM with a machine learning method. The second step aims to improve the variation capturing ability and accuracy of the high temporal coverage SM from first step using a cumulative distribution function (CDF) matching based fusion method. We chose the ECV and Fengyun (FY) SM products as an algorithm test to improve the quality of ECV SM over the Tibetan Plateau (TP). Results suggest that the two-step SM fusion framework improved the original ECV SM temporal coverage from 30.84% to 78.12% for the entire TP. The variation capturing ability, here expressed in terms of correlation coefficient (R), was also improved by 6% and 49% at Naqu and Maqu, respectively, compared with the high temporal coverage ECV SM. The accuracy, measured in terms of unbiased root mean square error (ubRMSE), was also improved. Hence, the fusion framework and the FY SM could effectively improve the quality of ECV SM. The high quality fused SM is expected to help us better understand the role of SM in the water and energy cycles under global change.

심층신경망을 이용한 중국의 쌀 수확량 예측 실험

Global warming due to the increase of greenhouse gases may significantly affect various aspects of the Earth’s environment and human life. In particular, the impacts of climate change on agriculture would be severe, leading to damages to crop yields. This paper examines the experimental prediction of rice yield in China using DNN (deep neural network) and climate model data for the period between 1979 and 2009. The DNN model built through the process of hyperparameter optimization can mitigate an overfitting problem and cope with outlier cases. Our model showed approximately 38.7% improved accuracy than the MLR (multiple linear regression) model, in terms of correlation coefficient with the yield statistics. We found that the diurnal temperature range and potential evapotranspiration were the critical factors for rice yield prediction. Our DNN model was also robust to extreme conditions such as drought in 2006 and 2007 in China, which showed its applicability to the future simulation of crop yields under climate change.

Forecasting techniques in construction industry: earned value indicators and performance models

Machine Learning Regression Techniques (MLRT) as a shrewd method can be utilized in this study being exceptionally fruitful in demonstrating non-linear and the interrelationships among them in problems of construction projects such as the earned value indexes for tall buildings projects in Republic of Iraq. Three forecasting models were developed to foresee Schedule Performance Index (SPI) as first model, Cost Performance Index (CPI) as a second model, and the third model is To Complete Cost Performance Indicator (TCPI) in Bismayah New City was chosen as a case study. The methodology is mainly impacted by the deciding various components (variables) which impact on the earned value analysis, six free factors (X1: BAC, Budget at Completion; X2: AC, Actual Cost; X3: A%, Actual Percentage; X4: EV, Earned Value; X5: P%, Planning Percentage, and X6: PV, Planning Value) were self-assertively assigned and agreeably depicted for per tall buildings projects. It was found that the MLRT showed good results of estimation in terms of correlation coefficient (R) generated by MLR models for SPI and CPI and TCPI where the R were 85.5%, 89.2%, and 86.3% respectively. At long last, a result tends to be presumed that these models show a brilliant concurrence with the genuine estimations.

Spatio-temporal undersampling: Recovering ultrasonic guided wavefields from incomplete data with compressive sensing

Many non-destructive evaluation techniques are based on the study and assessment of guided wavefields. Yet, the extent of the sensing region and the span of time over which wavefield data is acquired can be tremendous, resulting in an enormous amount of spatio-temporal data. As a result, reducing the burden of data acquisition and storage from undersampled data could be highly advantageous. To achieve this end, various signal processing methodologies have been proposed in the literature, many of which make use of compressive sensing. In prior work, such methodologies for effective wavefield reconstruction from incomplete data in space and in time (separately) have been demonstrated. In this paper, we combine these approaches. We present a compressive sensing based guided wave retrieval method with a two-dimensional ultrasonic guided wave model, which enables us to reconstruct wavefields that are undersampled in both the temporal and spatial domains. Results from implementing this method on a dataset consisting of experimental guided wave propagation indicate its potential for accurate wave reconstruction in the presence of spatio-temporal undersampling. We compare results for a variety of subsampling strategies and study the impact of sparsity on the reconstruction performance. Our results indicate that the proposed methodology in this paper is capable of achieving an accuracy of more than 80 percent (in terms of correlation coefficient) at a spatio-temporal undersampling ratio of about 40 percent using random sampling in space and time.

Comparative Evaluation of the GPM IMERG Early, Late, and Final Hourly Precipitation Products Using the CMPA Data over Sichuan Basin of China

The Global Precipitation Measurement (GPM) mission has generated global precipitation products of improved accuracy and coverage that are promising for advanced hydrological and meteorological studies. This study evaluates three Integrated Multi-satellitE Retrievals for GPM (IMERG) Hourly products, including the Early-, Late-, and Final-run products (IMERG-HE, IMERG-HL, and IMERG-HF, respectively), over Sichuan Basin of China. This highly complex terrain of the steep mountainous region offers further scrutiny on the quality and applicability of the data. The China Meteorological Precipitation Analysis (CMPA) data from January 2016 to December 2018 are used as the reference for the evaluation. Results show that: (1) At grid scale, IMERG-HL and IMERG-HF outperform IMERG-HE in terms of correlation coefficient (CC) and root-mean-square error (RMSE), but IMERG-HL has smaller relative bias (RB) than that of the IMERG-HF (by 21.16%). IMERG-HF presents the highest probability of detection (POD = 0.52) and critical success index (CSI = 0.32), except for high false alarm ratio (FAR) for light precipitation. (2) At regional scale, IMERG-HF outperforms IMERG-HE and IMERG-HL in annual evaluation in all the metrics except for the serious overestimation as shown in RB (20.18%, 3.84%, and 4.97%, respectively). Its accumulative precipitation deviation mainly comes from moderate precipitation events (1–10 mm/h), while better detection capability is seen in light precipitation (<1 mm/h). Seasonally, IMERG-HF performs the best in winter, while IMERG-HL performs the best in the other seasons. (3) IMERG-HF captures the peak precipitation more accurately in all seasons. In reproducing the diurnal cycle, IMERG-HF performs better in winter, while IMERG-HL performs better in summer and autumn, and IMERG-HE in spring. However, all three products overestimate the early morning precipitation (01:00–08:00 local standard time) of the diurnal cycle in spring, summer, and autumn.

Face Identification Using HAAR Wavelet Transform

Face identification is the process of matching one or more people by analyzing and comparing the patterns of their faces. Algorithms for face identification typically extract facial features and compare them to a database to find the best match. The Haar wavelet transform has been mainly used for image processing and pattern identification due to its low computing requirements and quality to conserve and to compact the energy of a signal. In discrete wavelet transform, an image signal can be analyzed by passing it through an analysis filter bank followed by a decimation operation. Face identification has been performed in terms of correlation coefficient, Euclidean distance and sum of absolute difference.

Face Identification Using HAAR Wavelet Transform

Face identification is the process of matching one or more people by analyzing and comparing the patterns of their faces. Algorithms for face identification typically extract facial features and compare them to a database to find the best match. The Haar wavelet transform has been mainly used for image processing and pattern identification due to its low computing requirements and quality to conserve and to compact the energy of a signal. In discrete wavelet transform, an image signal can be analyzed by passing it through an analysis filter bank followed by a decimation operation. Face identification has been performed in terms of correlation coefficient, Euclidean distance and sum of absolute difference.

Investigation of the accuracy of linear and nonlinear time series models in modeling and forecasting of pan evaporation in IRAN

Water evaporation process is one of the main components of the hydrological cycle, according to which the correct estimation of this phenomenon plays an important role in irrigation management and river flow forecasting. Statistical and random models in the form of time series analysis are commonly used methods of estimation and forecasting. In this study, ARMA (autoregressive moving average), ARIMA (autoregressive integrated moving average), PARMA (periodic autoregressive moving average), and BL (bilinear) time series models (TSMs) are used to predict the annual and monthly pan evaporation values from the evaporation stations in several provinces of Iran in a 20-year statistical period. Results showed that PARMA model’s accuracy in term of correlation coefficient and Nash–Sutcliffe efficiency for almost all 31 stations had a precise forecasting among other proposed TSMs. For PARMA model, the forecasting accuracy in term of NSE indicated that PARMA model almost was the promising model among other linear and nonlinear TSMs in prediction of Epan for all stations, except Arak (NSE = 0.94) and Qom (NSE = 0.93). The ARIMA model for Khorramabad and Bandar Abbas with NSE = 0.52 had the unreliable prediction for Epan compared with other stations. In addition, Arak station in term of RMSE had the least error, 23.79 mm/day and 10.90 mm/day, respectively, for training and testing stages among the other stations.

Over-the-Air Performance Evaluation in Indoor and Outdoor Multipath Propagation Channels of Antenna Diversity Systems inside Anechoic Chamber

With the ever-growing requirement for higher data rates, terminals supporting multiple-input multiple-output (MIMO) technologies are being developed for next-generation. As for wireless device manufacturers, a radio performance evaluation of multi-antenna terminals in desired environments is mandatory before product release. This paper discusses the Over the Air (OTA) performance evaluation of antenna diversity systems in Indoor and Outdoor multi-path propagation channel models inside anechoic chamber, in terms of correlation coefficients and diversity gain (DG). These channel models have been emulated in terms of angles of arrivals (AoA) and cross-polarization ratio (XPR) with Rayleigh fading. For this purpose, SATIMO SG24 measurement system has been used. However, the actual configuration of this system is not able to emulate desired realistic environments. Therefore, an innovative methodology based on the SG24 probes control has been developed. The obtained results in simulations and measurements have shown a good agreement.

Estimation of the Microbiological Quality of Meat Using Rapid and Non-Invasive Spectroscopic Sensors

Spectroscopic methods in tandem with machine learning methodologies have attracted considerable research interest for the estimation of food quality. The objective of this study was the evaluation of Fourier transform infrared (FTIR) spectroscopy and multispectral imaging (MSI) coupled with appropriate machine learning regression algorithms for assessing meat microbiological quality. For this purpose, minced pork patties were stored aerobically and under modified atmosphere packaging (MAP) conditions, at isothermal and dynamic temperature conditions. At regular time intervals during storage, samples were subjected to (i) microbiological analysis, (ii) FTIR measurements and (iii) MSI acquisition. The collected FTIR data were processed by feature extraction methods to reduce dimensionality, and subsequently Support Vector Machines (SVM) regression models were trained using spectral features (FTIR and MSI) to estimate microbiological quality of meat (microbial population). The regression models were evaluated with different experimental replicates using distinct meat batches. The performance of the models was evaluated in terms of correlation coefficient (r), root mean square error (RMSE), mean absolute error (MAE) and residual prediction deviation (RPD). The RMSE values for the microbial population estimation models using FTIR were 1.268 and 1.024 for aerobic and MAP storage, respectively. The performance in terms of RMSE for the MSI-based models was 1.144 for aerobic and 0.923 for MAP storage, while the combination of FTIR and MSI spectra resulted in models with RMSE equal to 1.146 for aerobic and 0.886 for MAP storage. The experimental results demonstrated the potential of estimating the microbiological quality of minced pork meat from spectroscopic data.

Validating INSAT-3D atmospheric temperature retrievals over india using radiosonde measurements and other satellite observations

Atmospheric temperature profiles retrieved from a geostationary INSAT-3D (Indian National Satellite System) sounder level-2 physical retrieval data are evaluated with respect to radiosonde observations, Atmospheric Infrared Sounder (AIRS), and National Centers for Environmental Prediction and Department of Energy (NCEP-DOE) reanalysis-2 data sets over India and adjoining area. This evolution was carried out in the terms of correlation coefficients, bias, and root-mean-square error (RMSE) at each pressure level from surface 1000 to 100 hPa during a one year period in 2016.The initial validation of INSAT-3D temperature profiles with AIRS and NCEP-DOE reanalysis-2 data were taken as reference and computed for the spatial distribution of correlation coefficient, bias, and RMSE at each pressure level over the Indian region. In addition to that, we also compared the INSAT-3D temperature retrievals with 12 selected IMD (India Meteorological Department) radiosonde observations at different geographical features over the Indian subcontinent during the one year period in 2016. In this analysis, for each station at all pressure levels, the correlation coefficients, biases and their corresponding root-mean-square errors (RMSEs) were carried out between INSAT-3D and radiosonde observations. The results of the inter-comparison reveal that temperature retrievals from the INSAT-3D are a good agreement with AIRS and NCEP-DOE reanalysis-2 over the land region and a slight degradation performance over the ocean- and coastal regions of Arabian Sea and Bay of Bengal below 850 hPa. The degradation performance over the ocean- and coastal areas associated with maybe possibility of undetected clouds and uncertainty in surface emissivity and also it might be attributed to improper bias correction coefficients used for brightness temperature of clear-sky pixels before physical retrievals in INSAT-3D algorithm or inherent deficiency in the retrieval algorithm which mainly depends on initial guess field from NWP models. Furthermore, an evaluation of INSAT-3D with 12 IMD radiosonde observation results reveals that temperature retrievals for each station shows very good agreement at all pressure levels, except slight degradation in performance over the coastal regions (GOA, MDS) and island (AMN, PBL) stations possibly the same reason as that of AIRS/NCEP. Overall, the results show that INSAT-3D temperature retrievals over land are a good agreement with AIRS/NCEP and RSRW then over the ocean- and coastal regions which need to be analyzed.