Absolute Coefficients Research Articles

Research on Oil Well Production Prediction Based on GRU-KAN Model Optimized by PSO

Accurately predicting oil well production volume is of great significance in oilfield production. To overcome the shortcomings in the current study of oil well production prediction, we propose a hybrid model (GRU-KAN) with the gated recurrent unit (GRU) and Kolmogorov–Arnold network (KAN). The GRU-KAN model utilizes GRU to extract temporal features and KAN to capture complex nonlinear relationships. First, the MissForest algorithm is employed to handle anomalous data, improving data quality. The Pearson correlation coefficient is used to select the most significant features. These selected features are used as input to the GRU-KAN model to establish the oil well production prediction model. Then, the Particle Swarm Optimization (PSO) algorithm is used to enhance the predictive performance. Finally, the model is evaluated on the test set. The validity of the model was verified on two oil wells and the results on well F14 show that the proposed GRU-KAN model achieves a Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (R2) values of 11.90, 9.18, 6.0% and 0.95, respectively. Compared to popular single and hybrid models, the GRU-KAN model achieves higher production-prediction accuracy and higher computational efficiency. The model can be applied to the formulation of oilfield-development plans, which is of great theoretical and practical significance to the advancement of oilfield technology levels.

Communication—Prediction of Area Specific Resistance of Solid Oxide Cell Stacks from Electrochemical Impedance Spectra

A support vector regression model was trained to predict the area specific resistance of solid oxide cell stacks from electrochemical impedance spectroscopy measurements. In particular, the minimum necessary frequency range required for accurate predictions was investigated. Therefore, 711 pairs of DC polarization and electrochemical impedance spectroscopy measurements, conducted at the same stage of stack degradation and under similar measurement conditions, were evaluated. Prediction accuracies of less than 8% mean absolute percentage error and coefficients of determination greater than 93% were achieved. The 101–102 Hz range is sufficient for accurate predictions, allowing an efficient and non-destructive etimation of DC polarization measurements.

Evaluation of Clustering Techniques for Solar Irradiance Prediction for Optimal Design of Microgrids in Rural Communities

Abstract The electrification of rural communities is crucial from both social and economic perspectives, aligned with Sustainable Development Goal 7: “Affordable and Clean Energy”. This study presents a comprehensive comparison of clustering techniques, including k-means, Gaussian Mixture Models (GMM), Hierarchical Clustering, Density-based Spatial Clustering of Applications with Noise (DBSCAN), and Agglomerative Clustering, aimed at enhancing solar irradiance prediction. Leveraging historical climate data from a rural community in the coastal region of Ecuador, each technique is evaluated using error metrics such as Mean Absolute Error (MAE) and Coefficient of Determination R2. This assessment identifies the most effective clustering technique in this specific context. In order to delve deeper into these comparisons, simulations are conducted in AMPL to validate and refine the selection of techniques. In this process, it is considered the sizing and design of a microgrid within the Barcelona community, Ecuador, which integrates various energy sources, including solar. Additionally, a penalty system is introduced for unmet energy demands during less critical periods, thereby optimizing efficiency and enhancing energy availability within the community. In conclusion, this paper introduces a scalable methodology to improve solar irradiance prediction, emphasizing the significance of comparing clustering techniques as its main contribution. This advancement in prediction accuracy has the potential to enhance the feasibility and efficiency of renewable energy systems for rural communities, thereby fostering sustainable economic growth and bolstering efforts in climate change mitigation and adaptation.

Unraveling the Associations Between Voice Pitch and Major Depressive Disorder: A Multisite Genetic Study.

Major depressive disorder (MDD) often goes undiagnosed due to the absence of clear biomarkers. We sought to identify voice biomarkers for MDD and separate biomarkers indicative of MDD predisposition from biomarkers reflecting current depressive symptoms. Using a two-stage meta-analytic design to remove confounds, we tested the association between features representing vocal pitch and MDD in a multisite case-control cohort study of Chinese women with recurrent depression. Sixteen features were replicated in an independent cohort, with absolute association coefficients (beta values) from the combined analysis ranging from 0.24 to 1.07, indicating moderate to large effects. The statistical significance of these associations remained robust, with P-values ranging from 7.2 × 10-6 to 6.8 × 10-58. Eleven features were significantly associated with current depressive symptoms. Using genotype data, we found that this association was driven in part by a genetic correlation with MDD. Significant voice features, reflecting a slower pitch change and a lower pitch, achieved an AUC-ROC of 0.90 (sensitivity of 0.85 and specificity of 0.81) in MDD classification. Our results return vocal features to a more central position in clinical and research work on MDD.

Battery state of charge estimation for electric vehicle using Kolmogorov-Arnold networks

Accurate estimation of the state of charge (SoC) in electric vehicle (EV) batteries is essential for effective battery management and optimal performance. This study investigates the application of Kolmogorov-Arnold Networks (KAN) for SoC estimation, comparing its performance against Artificial Neural Networks (ANN) and a hybrid Barnacles Mating Optimizer-deep learning model (BMO-DL). The dataset, derived from simulations involving a lithium polymer cell model (ePLB C020) in an electric car similar to Nissan Leaf EV, encompasses 68,741 instances, divided into training and testing sets. Three KAN models were developed and evaluated based on root mean square error (RMSE), mean absolute error (MAE), maximum error (MAX), and coefficient of determination (R2). Residual analysis indicates that KAN-Model 1 performs the best, with residuals closely clustered around zero and no significant patterns, suggesting reliable and unbiased predictions. KAN-Model 2 also performs well but exhibits some nonlinear trends in the residuals. ANN and BMO-DL models show larger deviations and less consistent performance. These findings highlight the potential of KAN for enhancing SoC estimation accuracy in EV applications.

Predicting Marshall stability and flow parameters in asphalt pavements using explainable machine-learning models

The traditional method for determining the Marshall stability (MS) and Marshall flow (MF) of asphalt pavements is laborious, time consuming, and costly. This study aims to predict these parameters using explainable machine-learning techniques. A comprehensive database comprising 721 hot mix asphalt (HMA) data points was established, including variables such as aggregate percentage, asphalt content, and specific gravity. Models were constructed using the PyCaret Python library, and their performance was assessed using metrics such as the mean absolute error (MAE) and coefficient of determination (R²). The CatBoost regression model outperformed the other models, achieving R² values of 0.835 and 0.845 for MS and MF, respectively. Additionally, Shapley values were used to quantify the variable effects on the predictions. This approach enables the efficient preselection of design variables, reducing the need for extensive laboratory testing and promoting sustainable construction practices.

Worst-case analysis of restarted primal-dual hybrid gradient on totally unimodular linear programs

We analyze restarted PDHG on totally unimodular linear programs. In particular, we show that restarted PDHG finds an ϵ-optimal solution in O(Hm12.5nnz(A)log⁡(Hm2/ϵ)) matrix-vector multiplies where m1 is the number of constraints, m2 the number of variables, nnz(A) is the number of nonzeros in the constraint matrix, H is the largest absolute coefficient in the right hand side or objective vector, and ϵ is the distance to optimality of the outputted solution.

Optimization of Machining Parameters for Nimonic PE16 Using Machine Learning Models

Machining high-temperature alloys such as Nimonic PE16 demands precise control of machining parameters to achieve desired outcomes while minimizing tool wear and optimizing surface finish. In this study, we propose using machine learning regression models combined with synthetic data and response surface methodology strategies to optimize machining parameters for PE16. We aim to develop a predictive model that accurately estimates optimal cutting speeds and feed rates based on key output parameters, including cutting forces and surface roughness. Our methodology involves collecting experimental data from controlled machining tests conducted on PE16 samples under varying conditions. We used the datasets to train and validate regression models to establish correlations between input parameters and machining outcomes. The performance of each model is evaluated based on metrics such as mean absolute error and coefficient of determination. These metrics show relationships within the data and can determine a model’s success. The proposed machine learning framework offers a data-driven approach to optimize machining processes for PE16, facilitating enhanced efficiency, productivity, and quality in nuclear and other high-performance applications. Our findings contribute to understanding machining dynamics in challenging materials and provide valuable insights for intelligent machining systems.

Role of diffusion-weighted imaging in the diagnosis of pituitary region tumors.

This study aimed to assess the role of Diffusion-Weighted Imaging (DWI) in routine pituitary Magnetic Resonance Imaging (MRI) protocols for distinguishing sellar and parasellar tumors, addressing the lack of clear guidelines in contemporary literature. A retrospective analysis of 242 pituitary MRI scans with DWI sequences was conducted in a single-center study using a 1.5T scanner and standard DWI sequence parameters. Measurements of both absolute and relative mean apparent diffusion coefficient (ADC) values, along with minimal ADC values within tumors, were performed. The adopted region of interest (ROI) based method used for these measurements was validated. Invasive pituitary adenomas exhibited significantly lower min ADC and min rADC than meningiomas, with optimal cut-off points of 0.64 (sensitivity 73%, specificity 82%) and 0.78 (sensitivity 73%, specificity 89%), respectively. Post-hemorrhagic pituitary adenomas demonstrated lower ADC values than adamantinomatous craniopharyngiomas, with an AUC of 0.893 for min rADC = 1.07, and Rathke's Cleft Cysts with mucous content, AUC 0.8 for min rADC = 1.01. Specific differentiation with high sensitivity and specificity based on diffusion parameters was observed for these tumor groups. Cystic pituitary non-functional adenomas obtained significantly lower ADC values compared to the adamantinomatous type of craniopharyngiomas and serous Rathke's Cleft Cysts (AUC up to 0.942). The study concludes that integrating DWI into routine pituitary MRI protocols enhances diagnostic accuracy in distinguishing sellar and parasellar tumors. The short scan time of one minute makes DWI a valuable and precise tool, supporting its recommendation as a standard component of pituitary MRI examinations.

Regression prediction of critical exhaust volumetric flow rate in tunnel fire with two-point extraction ventilation based on neural network method

In this study, a Genetic Algorithm-Backpropagation Neural Network (GA-BPNN) model was developed to predict critical exhaust volumetric flow rate in tunnel fires with two-point extraction ventilation system. Seven influencing factors served as inputs for the model, while the critical exhaust volumetric flow rate was the output. Experimental data from two reduced-scale tunnels were utilized to both train and validate the GA-BPNN model. The results demonstrate a satisfactory prediction performance, with key metrics such as Mean Absolute Percentage Error (MAPE), Relation Coefficient (R2), and Root Mean Square Error (RMSE) achieving values of 0.0384, 0.9989, and 3.5258, respectively. Importantly, the model maintains a maximum Absolute Percentage Error (APE) below 10 %. In contrast, the traditional BPNN model exhibited an APE of approximately 18.9 %. Moreover, the predictive results of the GA-BPNN model were compared with those of a previously semi-empirical formula. It was observed that the semi-empirical predictions exhibited APE exceeding 20 % for certain data points. This further underscores the superiority of the GA-BPNN model in predicting critical exhaust volumetric flow rates in tunnel fires with two-point ventilation system. These findings affirm the feasibility and effectiveness of GA-BPNN regression model as a reliable method for predicting critical exhaust volumetric flow rates under multiple factors.

A discussion on estimating small bodies taxonomies using phase curves results

Upcoming large multiwavelength photometric surveys will provide a leap in our understanding of small body populations, among other fields of modern astrophysics. Serendipitous observations of small bodies in different orbital locations allow us to study diverse phenomena related to how their surfaces scatter solar light.In particular, multiple observations of the same object in different epochs permit us to construct their phase curves to obtain absolute magnitudes and phase coefficients. In this work, we tackle a series of long-used relationships associating these phase coefficients with the taxa of small bodies and suggest that some may need to be revised in the light of large-number statistics.

Scrutiny of pseudoplastic nanofluid flow under the influence of magnetic hydrodynamics with chemical reaction across the cylinder with slip boundary condition

Buoyantly induced flows possess diversified utilizations in numerous engineering processes for instance, reactor cooling through passive strategy, LED lights, pipes manufacturing, ship funnel and many more. Galvanized sheets sticked to form a hollow cylinder is used for fast cooling in naval ship and chimney of steam power plant. In view of such mesmerizing significance of flow and thermal attributes of fluid over vertical cylinder, current effort is articulated. For this purpose, Williamson fluid model is accounted and nanoparticles are also induced to envision advanced thermal features in the flow over vertically oriented cylinder. Physical effectiveness of magnetic field implications and chemical reactive species are entertained to notice change in hydrothermal and mass fields. Slip boundary constraint along with stagnant flow at the surface of cylinder is considered to inspect behavior in free stream region. The fundamental governing equations of problem are attained in the sense of PDEs by utilizing the concept of boundary layer approximation and converted into coupled nonlinear ODEs by substituting specific similar variables. Numerically the resulting ODEs are resolved by making the use of bvp4c built in MATLAB routine, the outcomes are attained and arranged in graphical and tabular manner. The influence of pertinent flow parameters such as (0.1 ≤ We ≤ 1.0), (1.0 ≤ M ≤ 3.0), (1.0 ≤ Pr ≤ 11), thermophoresis parameter (0.5 ≤ Tp ≤ 4.5), (1.0 ≤ Bp ≤ 5.0), (0.05 ≤ Nr ≤ 0.7), and (0.5 ≤ Kc ≤ 5.0) are examined on the momentum, thermal and concentration distributions. It is manifested that the velocity distribution depreciates by uplifting magnetic field strength. Increment in magnitude of wall drag and convective heat transfer is perceived by enhancing Prandtl number. It is inferred that friction coefficient in absolute sense and heat flux coefficient tends to exceed against elevation in (We). From comprehensive analysis, declination in velocity and thermal field is depicted versus Reynold number whereas, contrary aspects are visualized in concentration. Enhancement in the value of surface drag and thermal flux is revealed versus (Re).

Wind speed prediction in some major cities in Africa using Linear Regression and Random Forest algorithms

Globally, wind energy if properly harnessed, could serve as a source of energy generation in Africa. This study compared the performance of two Machine Learning (ML) algorithms (Linear regression and Random Forest) in predicting wind speed in five major cities in Africa (Yaoundé, Pretoria, Nairobi, Cairo and Abuja). Wind data were collected between January 1, 2000, and December 31, 2022, using the Solar Radiation Data Archive. The data preprocessing was carried out with 80% of the data used for training and 20% for validation. The performance of these ML algorithms was evaluated using Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and coefficient of determination (R2). The result shows that Nairobi (3.814795 m/s) closely followed by Cairo (3.606453 m/s) has the highest mean wind speed while Yaoundé (1.090512 m/s) has the lowest. Based on the performance metrics used, the two Machine Learning algorithms were competitive. Still, the Linear Regression (LR) algorithm outperformed the Random Forest Algorithm in predicting wind speed in all the selected major African cities. In Yaoundé (RMSE = 0.3892, MAE= 0.3001, MAPE =0.5030), Pretoria (RMSE=1.2339, MAE=0.9480, MAPE=0.7450) Nairobi (RMSE= 0.4223, MAE =0.6499, MAPE =0.1872), Nairobi (RMSE=0.6499, MAE=0.5171, MAPE =0.1872), Cairo (RMSE =1.0909, MAE =0.8544, MAPE =0.3541) and Abuja (RMSE = 0.70245, MAE =0.5441, MAPE= 0.4515) the Linear regression algorithms was found to outperformed Random Forest Regression. Therefore, the Linear regression algorithm is more reliable in predicting wind speed compared with the Random Forest regression.

Accuracy of goodness-of-fit criteria for nonlinear regression: a study via Monte Carlo simulation

Nonlinear regression models are widespread in the literature, and one of their main applications is in the study of sigmoidal growth curves. There are several models for this purpose, and the most used are the logistic, Gompertz, von Bertalanffy, and Brody models. Each one of them has its own characteristics and is more suitable for a given curve shape. There are several criteria in the literature for selecting the most appropriate model, but there is no consensus on the best criteria. Thus, the present study aims to evaluate the accuracy of the main selection criteria via Monte Carlo simulation, considering the logistic, Gompertz, von Bertalanffy, and Brody nonlinear regression models. Four simulation scenarios are used, each simulated with ideal curves of the logistic, Gompertz, von Bertalanffy and Brody models. Next, the 4 models are adjusted for each of the scenarios, and the main quality criteria found in the literature are calculated to assess the ability of the criteria to identify the most appropriate model for each scenario. The results show that the criteria asymptotic index, mean absolute error and coefficient of determination choose the correct model more often than the other criteria studied. Although the measures of the Battes and Watts curvature and box bias are important for the evaluation of the goodness-of-fit of the models, they are not indicated for the selection of the best model.

Valvular and perivalvular thrombosis following self-expandable aortic valve replacement: analysis of 100 multi-detector computed tomography scans

Abstract Aims Subclinical thrombosis may represent an early stage of prosthesis structural disease. Most of the available evidence on the incidence, location, predictors, and consequences of thrombosis comes from studies that have employed balloon-expandable valves. We aimed to describe the different localisations of valvular and perivalvular thrombosis and analyse prosthesis-host multi-detector computed tomography predictors in the context of self-expandable prosthesis. Additionally, we aimed to assess the impact of valvular and perivalvular thrombosis on prosthesis performance and subsequent clinical outcomes. Methods and results This analysis includes 100 consecutive patients with normal renal function who underwent transcatheter aortic valve replacement using Evolut R and received multi-detector computed tomography and transthoracic bi-dimensional echocardiography at the 6 month follow-up. Leaflet thrombosis was detected in 18 (18%) patients; 6 (6%) had at least one leaflet with severe thrombosis. Thrombosis of the anatomic sinus was detected in 24 patients (24%) and was more prevalent in the non-coronary sinus. Subvalvular thrombosis with partial or complete circumferential involvement of the prosthesis inner skirt was diagnosed in 23 patients (23%). Bicuspid valve was the predictor with highest association with hypoattenuated lesions [least absolute shrinkage and selection operator coefficient 0.35, 95%, confidence interval (CI) 0.21–0.68]. There was no difference in terms of haemodynamic structural valve dysfunction, neurological events, and re-hospitalisation between the groups with and without thrombosis (hazard ratio: 0.86, 95% CI: 0.24–3.06, P = 0.82). Conclusion This study showed that in a relatively low-risk population, valvular and perivalvular thrombosis were not rare phenomena following transcatheter aortic valve replacement at early follow-up. Bicuspid valve showed the strongest association with post-implant thrombosis.

A novel-approach for identifying sources of fluvial DOM using fluorescence spectroscopy and machine learning model

Rivers are well known as one of the most threatened aquatic environments, whose structure and water quality can be deeply impacted by intensive anthropogenic activities. Despite the fact that anthropogenic influences on river ecosystems could indeed be deduced from the composition and chemistry of fluvial dissolved organic matter (DOM), sources of anthropogenic loading to DOM are still poorly explored. Here, by uniting fluorescence excitation-emission matrices (EEM) and principal component absolute coefficient, four sources of DOM from seventeen rivers in major drainage basins of China could be identified, i.e., originating from municipal sewage, domestic wastewater, livestock wastewater, and natural origins, and thus being defined as MS-DOM, DW-DOM, LW-DOM, NO-DOM, respectively. Based on the random forest model, special nodes in EEM could be traced from four sources, respectively. According to parallel factor analysis, DOM mainly contained protein-like, microbial humic-like, and fulvic-like fluorescence substances, among which protein-like was dominant in MS-DOM and DW-DOM, microbial humic-like in LW-DOM, and fulvic-like in NO-DOM. Based on key peaks and essential nodes in EEM, the identifying source indices were first proposed, which could be introduced to simply distinguish the different anthropogenic-derived sources of fluvial DOM. It was associated with intensity ratios of the key peaks and the essential nodes of EEM spectra from four sources, i.e., municipal sewage (MS-SI: Ex/Em = 280/(335, 410) nm), domestic wastewater (DW-SI: Ex/Em = 280/(340, 410) nm), livestock wastewater (LW-SI: Ex/Em = 235/(345, 380) nm), and natural origins (NO-SI: Ex/Em = 260/(380, 430) nm). By statistical analysis, the high identifying source indices of municipal sewage (>0.5) and natural origins (>0.4) values could be related to MS-DOM and NO-DOM, respectively. The identifying source indices of domestic wastewater with 0.1–0.3 might be linked to DW-DOM and the identifying source indices of livestock wastewater with 0.3–0.4 to LW-DOM. Compared with conventional optical indices, the novel identifying source indices showed remarkable discrimination for the sources of fluvial DOM with different forms of anthropogenic disturbances. Hence the innovative approach could be relatively convenient and accurate to evaluate water quality or pollution risk in river ecosystems.

Influence of Grip Width on the Load-Velocity Relationship and 1 Repetition Maximum Value in the Bench Press Exercise: A Comparative and Reliability Analysis of Mean Velocity Vs. Mean Propulsive Velocity Vs. Peak Velocity.

Herrera-Bermudo, JC, Puente-Alcaraz, C, Díaz-Sánchez, P, González-Badillo, JJ, and Rodríguez-Rosell, D. Influence of grip width on the load-velocity relationship and 1 repetition maximum value in the bench press exercise: a comparative and reliability analysis of mean velocity vs. mean propulsive velocity vs. peak velocity. J Strength Cond Res XX(X): 000-000, 2024-This study aimed to analyze the reliability and compare the load (percentage of 1 repetition maximum [%1RM])-velocity relationship, bar displacement (DIS), the 1RM, and the velocity attained against the 1RM value (V1RM) in the bench press exercise using 3 different bar grip widths: narrow (120% of the biacromial distance [BD]), medium (160%), and wide (200%). A group of 54 healthy, physically active men randomly performed a total of 6 incremental tests (1 week apart) up to 1RM (2 with each bar grip width) on a Smith machine. The mean velocity (MV), mean propulsive velocity (MPV), peak velocity, and DIS were recorded for the subsequent analysis. The 3 velocity variables showed high relative (intraclass correlation coefficient: 0.90-0.97) and absolute (coefficient of variation: 2.21-9.38%) reliability in all grip widths against all relative loads. The 1RM value and the V1RM present high absolute and relative reliability in all grip widths. There are no significant differences in the value of 1RM and V1RM between grip widths. High relationships were observed between the relative load (%1RM) and velocity variables, with MPV showing the best fit. Significant greater values in MPV, MV, and DIS associated with each %1RM were observed for narrow and medium compared with wide grip width. In conclusion, our results suggest that the 3 velocity variables were highly reliable at the different grip widths used against all relative loads. In addition, there was a tendency to reach higher MV, MPV, and DIS values as the grip width decreased. Therefore, this factor should be considered for the assessment and design of training.

Fat-signal suppression in breast diffusion-weighted imaging: the Good, the Bad, and the Ugly.

Fat-signal suppression is essential for breast diffusion magnetic resonance imaging (or diffusion-weighted MRI, DWI) as the very low diffusion coefficient of fat tends to decrease absolute diffusion coefficient (ADC) values. Among several methods, the STIR (short-tau inversion recovery) method is a popular approach, but signal suppression/attenuation is not specific to fat contrary to other methods such as SPAIR (spectral adiabatic (or attenuated) inversion recovery). This article focuses on those two techniques to illustrate the importance of appropriate fat suppression in breast DWI, briefly presenting the pros and cons of both approaches. We show here through simulation and data acquired in a dedicated breast DWI phantom made of vials with water and various concentrations of polyvinylpyrrolidone (PVP) how ADC values obtained with STIR DWI may be biased toward tissue componentswith the longest T1 values: ADC values obtained with STIR fat suppression may be over/underestimated depending on the T1 and ADC profile within tissues. This bias is also illustrated in twoclinical examples. Fat-specific methods should be preferred over STIR for fat-signal suppression in breast DWI, such as SPAIR which also provides a higher sensitivity than STIR for lesion detection. One should remain aware, however, that efficient fat-signal suppression with SPAIR requires good B0 shimming to avoid ADC underestimation from residual fat contamination. The spectral adiabatic (or attenuated) inversion recovery (SPAIR) method should be preferred over short-tau inversion recovery (STIR) for fat suppression in breast DWI. Fat-signal suppression is essential for breast DWI; the SPAIR method is recommended. Short-tau inversion recovery (STIR)is not specific to fat; as a result, SNR is decreased and ADC values may be over- or underestimated. The STIR fat-suppression method must not be used after the injection of gadolinium-based contrast agents.

Hybrid noise reduction-based data-driven modeling of relative humidity in Khulna, Bangladesh

In this study, a hybrid Machine Learning (ML) approach is proposed for Relative Humidity (RH) prediction with a combination of Empirical Mode Decomposition (EMD) to improve the prediction accuracy over the traditional prediction technique using a Machine Learning (ML) algorithm called Support Vector Machine (SVM). The main objective of proposing this hybrid technique is to deal with the extremely nonlinear and noisy humidity pattern in Khulna, Bangladesh, which is experiencing rapid urbanization and environmental change. To develop the model, data on temperature, relative humidity, rainfall, and wind speed were collected from the Bangladesh Meteorological Department (BMD), and the data was divided into three phases: 70 % of the historical dataset as training data for the model, 15 % of the data set as the validation phase, and the remaining 15 % of the data set as the test phase of the model. Employing the Particle Swarm Optimization (PSO) algorithm, the SVM model determines its best hypermeters within this research. In the present research, performance analysis is carried out utilizing the Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE) and Coefficient of Determination (R2). Results show that the increase in R2 values resulting from the EMD-based approach is significant: 21.05 % in H1(Traditional model), 19.48 % in H2 (Traditional model), 76.92 % in H3 (Traditional model), 55.93 % in H4 (Traditional model), and 64.29 % in H5 (Traditional model) and H6 (Traditional model). The analytical results show that the proposed EMD-based technique efficiently filters and processes noisy, highly nonlinear humidity data during prediction in the Khulna region. It is recommended that this technique could be applied to other geological areas.

Pareto optimization of SPECT acquisition and reconstruction settings for 177Lu activity quantification

BackgroundThe aim was to investigate the noise and bias properties of quantitative 177Lu-SPECT with respect to the number of projection angles, and the number of subsets and iterations in the OS-EM reconstruction, for different total acquisition times.MethodsExperimental SPECT acquisition of six spheres in a NEMA body phantom filled with 177Lu was performed, using medium-energy collimators and 120 projections with 180 s per projection. Bootstrapping was applied to generate data sets representing acquisitions with 20 to 120 projections for 10 min, 20 min, and 40 min, with 32 noise realizations per setting. Monte Carlo simulations were performed of 177Lu-DOTA-TATE in an anthropomorphic computer phantom with three tumours (2.8 mL to 40.0 mL). Projections representing 24 h and 168 h post administration were simulated, each with 32 noise realizations. Images were reconstructed using OS-EM with compensation for attenuation, scatter, and distance-dependent resolution. The number of subsets and iterations were varied within a constrained range of the product number of iterations ×\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\ imes$$\\end{document} number of projections ≤2400\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\le 2400$$\\end{document}. Volumes-of-interest were defined following the physical size of the spheres and tumours, the mean activity-concentrations estimated, and the absolute mean relative error and coefficient of variation (CV) over noise realizations calculated. Pareto fronts were established by analysis of CV versus mean relative error.ResultsPoints at the Pareto fronts with low CV and high mean error resulted from using a low number of subsets, whilst points at the Pareto fronts associated with high CV but low mean error resulted from reconstructions with a high number of subsets. The number of projection angles had limited impact.ConclusionsFor accurate estimation of the 177Lu activity-concentration from SPECT images, the number of projection angles has limited importance, whilst the total acquisition time and the number of subsets and iterations are parameters of importance.