High Error Values Research Articles

Forecasting geothermal temperature in western Yemen with Bayesian-optimized machine learning regression models

Geothermal energy is a sustainable resource for power generation, particularly in Yemen. Efficient utilization necessitates accurate forecasting of subsurface temperatures, which is challenging with conventional methods. This research leverages machine learning (ML) to optimize geothermal temperature forecasting in Yemen’s western region. The data set, collected from 108 geothermal wells, was divided into two sets: set 1 with 1402 data points and set 2 with 995 data points. Feature engineering prepared the data for model training. We evaluated a suite of machine learning regression models, from simple linear regression (SLR) to multi-layer perceptron (MLP). Hyperparameter tuning using Bayesian optimization (BO) was selected as the optimization process to boost model accuracy and performance. The MLP model outperformed others, achieving high R2 values and low error values across all metrics after BO. Specifically, MLP achieved R2 of 0.999, with MAE of 0.218, RMSE of 0.285, RAE of 4.071%, and RRSE of 4.011%. BO significantly upgraded the Gaussian process model, achieving an R2 of 0.996, a minimum MAE of 0.283, RMSE of 0.575, RAE of 5.453%, and RRSE of 8.717%. The models demonstrated robust generalization capabilities with high R2 values and low error metrics (MAE and RMSE) across all sets. This study highlights the potential of enhanced ML techniques and the novel BO in optimizing geothermal energy resource exploitation, contributing significantly to renewable energy research and development.

ESTIMATION OF PATIENT RADIATION DOSE WITH SIZE SPECIFIC DOSE ESTIMATE (SSDE) METHOD IN ABDOMEN CT-SCAN EXAMINATION AT SEMEN GRESIK HOSPITAL

CT-Scan abdomen is an examination to see the anatomy and pathology of the abdominal organs, and the scanning image results are in the form of three-dimensional axial images of the body. The radiation dose released from the CT-Scan examination is more significant than other radiology modalities. Therefore, it is very important to estimate the patient's dose accurately. Computed Tomography Dose Index (CTDIvol) and Dose Length Product (DLP) are dose parameters used in CT-Scan to describe the dose value received by the patient. However, these parameters are the output of the CT-Scan, not as the dose received by the patient. The Size Specific Dose Estimate (SSDE) method based on AAPM Report No. 204 is used to determine the estimated dose received by the CT-Scan Abdomen patient. Calculations are done manually and with IndoseCT software. The data used are secondary data of 60 patients, namely 21 females and 39 males, who were on the CT-Scan Abdomen examination without contrast from the Instalasi Radiologi Rumah Sakit Semen Gresik. The SSDE value is obtained from the multiplication between the conversion factor and CTDIvol, where the conversion factor is an effective diameter function. The analysis examined the error value in manual calculations and IndoseCT software in men and women, the relationship between effective diameter and scanning radiation output (CTDIvol), and dose estimation estimates (SSDE). The difference in SSDE values between manual calculations and IndoseCT software was insignificant. The highest error value in women was 3% and 3.2% in men. Meanwhile, the relationship between effective diameter (Deff) and scanning radiation output (CTDIvol) and dose estimation estimates (SSDE) showed that the correlation between effective diameter (Deff) and CTDIvol showed a stronger correlation, namely with R2 around 0.7 in women and men, compared to the correlation between effective diameter (Deff) and SSDE with R2 around 0.03 in women and 0.2 in men. Keywords: CT-Scan, Abdomen, Size Specific Dose Estimate (SSDE).

Grey-box solution for predicting thermo-mechanical response of rocks

Evaluating the thermo-mechanical response of rocks under high temperature treatments is crucial for various engineering geology projects. Current predictions of rock thermo-mechanical response rely on simplistic mathematical fittings treating temperature as a reduction factor, while existing machine learning algorithms often present practical challenges due to their black-box solutions. In this study, highly practical grey-box solutions, utilizing gene expression programming (GEP) are proposed for forecasting rock strength following high-temperature treatments. The dataset, comprising temperature, rock type, rock density, sample size, crack damage stress, confining pressure, and elastic modulus, serves as input parameters, with rock strength from triaxial compression tests as the output. Three grey-box solutions (mathematical formulations) based on distinct input parameter sets are proposed, all demonstrating excellent accuracy with high R2-values (R2 > 0.95) and low error values across both the training and testing phases. Feature importance analysis highlights crack damage stress, confining pressure, and elastic modulus as statistically significant parameters influencing the strength of rocks subjected to high temperatures. External validation of the proposed models indicates strong generalization capabilities, underscoring their ability to perform well beyond the training data. Furthermore, a monotonicity study demonstrates that the proposed models align with the expected physical processes. The proposed formulations offer valuable field implications, effectively addressing the limitations of labor-intensive and costly laboratory processes for evaluating rock thermo-mechanical responses.

Assessing the compressive strength of eco-friendly concrete made with rice husk ash: A hybrid artificial intelligence-aided technique

Providing an eco-friendly replacement for cement in cementitious materials mitigates not only its consumption but also the environmental effects such as extraction of natural resources and greenhouse gas emissions resulting from its production. In light of this, the utilization of rice husk as a by-product of rice fields in the form of rice husk ash (RHA) as a partial substitute for cement, in addition to solving the problem of its disposal due to its silica content and high pozzolanic reaction, has been considered in the construction of sustainable concretes. This study seeks to move from the traditional laboratory-based methods for the examination of compressive strength (fc′) of concretes containing RHA towards artificial intelligence-based techniques by developing a novel hybrid model by integrating biogeography-based optimization (BBO) technique with artificial neural network (ANN). Besides, the performance of the hybrid ANN-BBO model was assessed with the single ANN model. To this end, the models were developed on an extensive dataset including 1276 data records collected from the literature. The efficiency of the models was evaluated by performance criteria and error histogram, and also cross-validation was utilized to avoid overfitting problems and generalize the models. Results demonstrated that the hybrid ANN-BBO model outperformed the single ANN model with high accuracy and minimum error values. Error histograms revealed that over 90 % of errors in the ANN-BBO model occurred in the range (−4 MPa, 4 MPa], while this range for the ANN model fell within (−6 MPa, 6 MPa]. Analyzing the influence of input parameters showed that more than 70 % of the contribution rate in the fc′ of RHA concrete belonged to four influential parameters of specimen age, cement, rice husk ash, and water, respectively. Eventually, to validate the proposed ANN-BBO model, a comparison was made with recent studies, in which the performance criteria revealed that the proposed model based on a more extensive dataset outperformed the models in previous studies.

Integration and Optimization of a Waste Heat Driven Organic Rankine Cycle for Power Generation in Wastewater Treatment Plants

The study focuses on achieving energy self-sufficiency in Wastewater Treatment Plants by proposing a comprehensive model for integrating, sizing, and optimizing an Organic Rankine Cycle system. The Organic Rankine Cycle system is designed to utilize waste heat from the gensets at As Samra Wastewater Treatment Plant in Jordan, where it will contribute to the overall electrical energy supply of the plant. Real data from As Samra Wastewater Treatment Plant is used to model and calculate the available waste heat using TRNSYS® software. The Organic Rankine Cycle model is then developed using ASPEN PLUS® software to explore the impact of operational parameters and determine their optimal values for maximizing the plant's energy profile. An economic analysis is conducted to assess the feasibility of the proposed model, considering system components, installation, operation, and maintenance costs. To optimize the Organic Rankine Cycle system, the study employs the Multi-Output Support Vector Regression technique to capture nonlinear relationships between independent variables (fluid type, turbine inlet pressure, turbine inlet temperature, turbine outlet pressure, and mass flow rate) and dependent variables (pump power input, waste heat input, and turbine specific work). The Osprey optimization algorithm is used to address the multi-objective optimization problem, with the proposed Pareto-based Osprey Optimization Algorithm and the Multi-Objective Particle Swarm Optimization technique being employed to evaluate critical performance and economic parameters such as system thermal efficiency, net power output, and the levelized cost of electricity. The results of the optimization strategies indicate that the M-SVR model's prediction accuracy is significantly improved after parameter optimization, with the model returning high R2 and low Mean Square Error values of 0.991 and 0.00216, respectively. The Pareto-Based Osprey Optimization Algorithm optimizer identifies the best working fluid as Isobutane/Isopentane in a ratio of 66:34, with optimal turbine inlet pressure and temperature of 15 bars and 218 °C, respectively. The Organic Rankine Cycle model at these optimal conditions achieves a cycle efficiency of 19.93 % and an Levelized Cost of Electricity value of 0.0353 USD/kWh.

Design of drought early warning system based on standardized precipitation index prediction using hybrid ARIMA-MLP in Banten province

Drought Early Warning System (DEWS) is an effort to disseminate early warning information based on climate and hydrology aspects. The DEWS design uses ARIMA, MLP, and hybrid ARIMA-MLP models to predict drought based on SPI for 1, 3, and 6 months. Predictions were made using ERA5 monthly rainfall data from 1981-2022 corrected based on observation data on 9 grids of observation rain gauges in Banten Province. The design of the ARIMA model is determined by selecting the combination of p and q parameters with the lowest AIC value, while the MLP architecture is determined by referring to the study literature and by trial and error testing. ARIMA models and hybrid models are not able to follow actual data fluctuations and have high error values in both SPI1, SPI3, and SPI6, so they are not recommended in this study. The MLP model has the best prediction ability, namely in SPI6 prediction with NSE value reaching >0.5 and RMSE value.

Evaluation of five gridded precipitation products for estimating precipitation and drought over Yobe, Nigeria

ABSTRACT Ground observations are often considered as the most reliable and precise source of precipitation data. However, long-term precipitation data from ground observations are lacking in many parts of the world. Gridded precipitation products (GPPs) therefore have emerged as crucial alternatives to ground observations, but it is essential to assess their capability to accurately replicate precipitation patterns. This study aims to evaluate the performance of five GPPs, NASA POWER, TerraClimate, Climate Hazards Group Infrared Precipitation with Climate Data (CHIRPS), GPCC, and Climate Research Unit (CRU), in capturing precipitation and drought patterns from 1981 to 2021 in Yobe, Nigeria. The results indicate that GPCC had good performance at both monthly and annual scales, with high correlation coefficients and low error values. However, it tends to underestimate precipitation amounts in certain areas. Other products also exhibit satisfactory performance with moderate correlations with ground observations. Drought analysis indicates that GPCC outperforms other products in standardised precipitation index-6 calculations, while NASA POWER demonstrates inconsistencies with ground observations, particularly during the early 1980s and mid-2000s. In conclusion, GPCC is the most preferable GPP for precipitation and drought analysis in the Yobe State in Nigeria.

A computer vision system for apple fruit sizing by means of low-cost depth camera and neural network application

AbstractFruit size is crucial for growers as it influences consumer willingness to buy and the price of the fruit. Fruit size and growth along the seasons are two parameters that can lead to more precise orchard management favoring production sustainability. In this study, a Python-based computer vision system (CVS) for sizing apples directly on the tree was developed to ease fruit sizing tasks. The system is made of a consumer-grade depth camera and was tested at two distances among 17 timings throughout the season, in a Fuji apple orchard. The CVS exploited a specifically trained YOLOv5 detection algorithm, a circle detection algorithm, and a trigonometric approach based on depth information to size the fruits. Comparisons with standard-trained YOLOv5 models and with spherical objects were carried out. The algorithm showed good fruit detection and circle detection performance, with a sizing rate of 92%. Good correlations (r > 0.8) between estimated and actual fruit size were found. The sizing performance showed an overall mean error (mE) and RMSE of + 5.7 mm (9%) and 10 mm (15%). The best results of mE were always found at 1.0 m, compared to 1.5 m. Key factors for the presented methodology were: the fruit detectors customization; the HoughCircle parameters adaptability to object size, camera distance, and color; and the issue of field natural illumination. The study also highlighted the uncertainty of human operators in the reference data collection (5–6%) and the effect of random subsampling on the statistical analysis of fruit size estimation. Despite the high error values, the CVS shows potential for fruit sizing at the orchard scale. Future research will focus on improving and testing the CVS on a large scale, as well as investigating other image analysis methods and the ability to estimate fruit growth.

Tuberculosis Chest X-Ray Image Retrieval System Using Deep Learning Based Biomarker Predictions.

The world health organization's global tuberculosis (TB) report for 2022 identifies TB, with an estimated 1.6 million, as a leading cause of death. The number of new cases has risen since 2020, particularly the number of new drug-resistant cases, estimated at 450,000 in 2021. This is concerning, as treatment of patients with drug resistant TB is complex and may not always be successful. The NIAID TB Portals program is an international consortium with a primary focus on patient centric data collection and analysis for drug resistant TB. The data includes images, their associated radiological findings, clinical records, and socioeconomic information. This work describes a TB Portals' Chest X-ray based image retrieval system which enables precision medicine. An input image is used to retrieve similar images and the associated patient specific information, thus facilitating inspection of outcomes and treatment regimens from comparable patients. Image similarity is defined using clinically relevant biomarkers: gender, age, body mass index (BMI), and the percentage of lung affected per sextant. The biomarkers are predicted using variations of the DenseNet169 convolutional neural network. A multi-task approach is used to predict gender, age and BMI incorporating transfer learning from an initial training on the NIH Clinical Center CXR dataset to the TB portals dataset. The resulting gender AUC, age and BMI mean absolute errors were 0.9854, 4.03years and . For the percentage of sextant affected by lesions the mean absolute errors ranged between 7% to 12% with higher error values in the middle and upper sextants which exhibit more variability than the lower sextants. The retrieval system is currently available from https://rap.tbportals.niaid.nih.gov/find_similar_cxr.

Effect of microwave pretreatment on truffle solar drying from an energetic perspective

AbstractDrying, an age‐old method of food preservation, involves the concurrent exchange of heat and mass, resulting in reduced moisture content. The current study is based on experimental approach to evaluate the impact of combined microwave and solar drying on the drying kinetics and the energy efficiency of truffle drying. This study explores the impact of a 4‐min microwave pretreatment on the solar drying of truffle slices. The findings demonstrate that microwave treatment significantly reduces the time required for solar drying. When compared to solar drying without pretreatment, microwave treatment leads to a reduction in drying time ranging from 23.07% to 70.37% at temperatures between 50 and 80°C. The Midilli–Kucuk model is employed to elucidate the experimental results, revealing strong fits with high correlation coefficients and low standard error values. Microwave pretreatment enhances the drying rate of truffle slices, resulting in a higher effective moisture diffusivity compared to untreated slices. The activation energy for drying also decreases from 76.37 to 25.25 kJ/mol after microwave pretreatment. An energy analysis of the drying process underscores that elevating the drying air temperature reduces energy consumption. Furthermore, the proposed microwave pretreatment influences the energy efficiency of the drying process.

Assessing the Efficacy of UV-C Light for the Inactivation of Phytopythium and Phytophthora Species in Water: A Mathematical Modeling Approach Using an Ultraviolet Light-Emitting-Diode System

The use of untreated, recirculated irrigation water is a profitable practice, but it can harbor plant pathogens such as Phytophthora ( Pt) cinnamomi, Pt. nicotianae, Phytopythium ( Pp) vexans, and Pp. helicoides, posing disease risks in crop production. UV-C (240 to 290 nm) light-emitting diode (LED) irradiation was evaluated for inactivating the zoospores of oomycetes in water, providing potential for effective treatment. Zoospore suspensions were exposed to quantifiable UV-C doses under dynamic stirring, calculated by multiplying fluence rate (mW cm−2) and exposure time(s). UV-C irradiation effectively inactivated the tested pathogens following linear (logarithmic linear [ Pt. cinnamomi and Pt. nicotianae]) and nonlinear (Weibull and Weibull + tail [ Pp. vexans and Pp. helicoides]) kinetics as identified by parameters of goodness of model fit: high R2 and low root mean square error (RMSE) values. D10 values of Pt. cinnamomi and Pt. nicotianae calculated from the rate constants ( Kmax) of the log-linear models were 5.05 ± 0.38 mJ cm−2 ( R2 = 0.95, RMSE = 0.091, Kmax = 0.49 ± 0.03) and 4.73 ± 0.33 mJ cm−2 ( R2 = 0.96, RMSE = 0.091, Kmax = 0.49 ± 0.03), respectively. The Weibull + tail model best described the inactivation of Pp. vexans ( R2 = 0.97, RMSE = 0.099) and Pp. helicoides ( R2 = 0.96, RMSE = 0.083), and the δ and Nres values were determined to be 9.88 ± 0.12 and 2.06 ± 0.06 and 11.47 ± 0.38 and 2.45 ± 0.05, respectively. These study findings can be applied to develop water disinfection systems, either alone or in combination with other methods, for effective control of pathogens in irrigation systems. [Formula: see text] Copyright © 2024 The Author(s). This is an open access article distributed under the CC BY-NC-ND 4.0 International license .

Study of color degradation in package prints: Analyzing kinetics with principal component analysis

AbstractColor degradation is a pressing issue in various fields like food and medicine packaging, as well as printed materials, leading to a loss or distortion of vital information. Therefore, understanding how the color of package prints evolves over time is essential for product quality assessment and effective product life cycle management. This study focuses on investigating color changes in prints on blister foils, widely used in the medicine and packaging industries. To assess fading characteristics, samples printed via the gravure process have been exposed to a Xenon Test Chamber (B‐SUN). Spectrophotometric measurements of the prints have been conducted using a spectroradiometer, and the data have been analyzed using principal component analysis (PCA). The fading nature of cyan and black prints aligns with Type IV, while magenta and yellow prints correspond to Type II, as described by Giles. Notably, cyan and black inks demonstrated resistance toward fading at the end of the exposure, with a minor exception. The investigation involved curve fitting, revealing a consistent first‐order kinetic model governing fading rates throughout the exposure time. High R2 values (0.96–0.99) and low root means square error values (0.02–0.08) are observed across all cases. While color fading involves diverse kinetics, the fading rate consistently adheres to a singular first‐order kinetic path. The study highlights that yellow ink is most sensitive to light, followed by magenta ink. These findings offer valuable insights for optimizing packaging materials and ensuring product quality in industries reliant on printed materials. By mitigating color degradation, manufacturers can enhance the longevity and appeal of their products, reinforcing consumer trust and satisfaction. Furthermore, the effective utilization of PCA as a data analysis tool offers a valuable approach for future investigations in color science and related fields.

Accuracy and temporal analysis of non-Newtonian models of blood in the computational FFR – Numerical implementation

Non-invasive assessment of stenosed coronary is a goal for clinical applications. Thus, engineering aligned with medicine has been the solution to solve this problem. This work, serving as a proof of concept, has the main goal to predict the non-invasive fractional flow reserve (FFR) in an atherosclerotic coronary artery. A 3-element Windkessel and Womersley models were used to model boundary conditions of the patient-specific coronary arteries: the pressure at the outlets of the artery and the velocity at the inlet, respectively. Apart from implementing the previous conditions in the numerical code, the novelty of this work is to implement and use, in numerical simulations, Newtonian and non-Newtonian models for blood such as Carreau, Carreau-Yasuda, Casson and Simplified Phan-Thien/Tanner to analyse the accuracy of the computed FFR and the computational time of the simulations. Results indicate that the non-Newtonian viscoelastic model, Simplified Phan-Thien/Tanner, took the longest time but produced the most accurate results - 8h and 2.7% relative error between invasive and non-invasive FFR. The shear-thinning non-Newtonian models required lower computational times but returned a higher average error (3.9h; 7.6% error) which is considered significant. The Newtonian model required the least time but had the highest error value (2.9h; 7.8% error). Thus, although the computational time considering the non-Newtonian viscoelastic model is the highest, this model must be considered in the numerical simulations to obtain the FFR since it is the most accurate for this patient case. This research is a step forward to numerically quantify the non-invasive FFR of a patient.

Predicting sulfanilamide solubility in the binary mixtures using a reference solvent approach.

Solubility is a fundamental physicochemical property of active pharmaceutical ingredients. The optimization of a dissolution medium aims not only to increase solubility and other aspects are to be included such as environmental impact, toxicity degree, availability, and costs. Obtaining comprehensive solubility characteristics of chemical compounds is a non-trivial and demanding process. Therefore, support from theoretical approaches is of practical importance. This study aims to examine the accuracy of the reference solubility approach in the case of sulfanilamide dissolution in a variety of binary solvents. This pharmaceutically active substance has been extensively studied, and a substantial amount of solubility data is available. Unfortunately, using this set of data directly for theoretical modeling is impeded by noticeable inconsistencies in the published solubility data. Hence, this aspect is addressed by data curation using theoretical and experimental confirmations. In the experimental part of our study, the popular shake-flask method combined with ultraviolet (UV) spectrophotometric measurements was applied for solubility determination. The computational phase utilized the conductor-like screening model for real solvents (COSMO-RS) approach. The analysis of the results of solubility calculations for sulfonamide in binary solvents revealed abnormally high error values for acetone-ethyl acetate mixtures, which were further confirmed with experimental measurements. Additional confirmation was obtained by extending the solubility measurements to a series of homologous acetate esters. Our study addresses the crucial issue of coherence of solubility data used for many theoretical inquiries, including parameter fitting of semi-empirical models, in-depth thermodynamic interpretations and application of machine learning protocols. The effectiveness of the proposed methodology for dataset curation was demonstrated for sulfanilamide solubility in binary mixtures. This approach enabled not only the formulation of a consistent dataset of sulfanilamide solubility binary solvent mixtures, but also its implementation as a qualitative tool guiding rationale solvent selection for experimental solubility screening.

Slow Pyrolysis of Waste Cow Bone for Biochar Production and Its Application in Copper Removal From Acidic Solutions

This study presents a comprehensive analysis of bone char derived from cow bones, focusing on its characterization and potential applications in wastewater treatment. Cow bones, which are normally regarded as biowaste, were heated slowly to 300°C, 400°C, and 500°C, with a one‐hour residence period and a heating rate of 10°C per minute, to produce biochar. The resultant cow bone char underwent extensive analyses to determine its physical and chemical properties. Elemental analysis revealed that the biochar is primarily composed of carbon. Nitrogen adsorption and desorption isotherms were employed to measure the specific surface area, pore size, and pore volume, with the highest specific surface area observed at 500°C, measuring approximately 77.31 m2·g−1, and an average pore diameter of 13.53 nm, indicating a predominantly mesoporous structure and exhibiting Type III isotherms. Functional group analysis identified the presence of various functional groups, including carboxylic acids, alkanes, and amines, which are effective for the removal of heavy metals from aqueous solutions. The adsorption capacity of the bone char for synthetic heavy metal copper in aqueous solutions was evaluated, revealing that the experimental data indicated the best fitting of the FL‐PFO kinetic model and the Toth isotherm model, both demonstrating high correlation coefficients and minimal error values. These findings indicate that cow bone char has significant potential as an effective adsorbent for removing heavy metals from wastewater, offering a sustainable solution for managing biowaste and treating water pollutants.

Machine Learning Techniques for Sugarcane Yield Prediction Using Weather Variables

Weather has a profound influence on crop growth, development and yield. The present study deals with the use of weather parameters for sugarcane yield forecasting. Machine learning techniques like K- Nearest Neighbors (KNN) and Random Forest model have been used for sugarcane yield forecasting. Weather parameters namely maximum temperature and minimum temperature, rainfall, relative humidity in the morning and evening, sunshine hours, evaporation along with sugarcane yield have been used as inputs variables. The performance metrics like R2, Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) have been used to select the best model for predicting the yield of the crop. Among the models, Random Forest algorithm is selected as the best fit based on the high R2 and minimum error values. The results indicate that among the weather variables, rainfall and relative humidity in the evening have significant influence on sugarcane yield.

Baby Incubator with Room Temperature and Skin Temperature Monitoring Via IoT-Based WIFI Network

Newborns require special attention to the labor process, this affects the health of the baby itself. Similarly, with premature babies who have a high level of sensitivity to the surrounding environment, one of the biggest causes of death in premature babies is hypothermia, therefore adjustments are needed starting from room temperature and skin in the baby incubator. The purpose of this study is to develop a monitoring system that will facilitate the performance of nurses in monitoring the parameters of the baby incubator. Related to this, an incubator device is needed that can be monitored remotely. This module uses a wifi network system for data transmission. Using the ESP32 module assembled into a module for monitoring and control which will then be displayed on the LCD and in the blynk as a monitoring display. Data transmission will be communicated using an external WIFI network and the monitoring results of each sensor will be displayed on Blynk. The highest error values were 1.24% for incubator room temperature parameters and 1.15% for skin temperature parameters. The results showed that there were still inaccuracies in some parameter readings, one of the factors that read inaccurate parameters was sensor sensitivity. This research is expected to help medical personnel to facilitate monitoring the condition of premature babies in baby incubators.

Using adaptive neuro-fuzzy inference system for predicting thermal conductivity of silica -MWCNT-alumina/water hybrid nanofluid

In this study, the thermal conductivity (knf) of Silicon Oxide-MWCNT-Alumina/Water hybrid nanofluid (HNF) is predicted versus solid volume fraction (SVF) and temperature. For this reason, various combinations of SVF and temperature are considered from SVF= 0.1–0.5% and 20–60 (°C) respectively. Then, an adaptive neuro-fuzzy inference system (ANFIS) has been effectively used to model the knf of HNF as one of the effective machine learning techniques. Various shapes of membership functions are considered and the generalized bell shape membership function showed to have acceptable accuracy for knf prediction using an ANFIS-based model. Moreover, the outcomes reveal that the effect of SVF is higher than temperature influence on the knf of HNF. Specifically, when the SVF is increased from 0.1% to 0.5%, there is an approximate 25% increase in knf. Conversely, an increase in temperature leads to a smaller ratio of knf increment. When the temperature rises from 20° to 60°C, knf only increases by less than 10%. The highest error value is found at φ = 0.2% and T = 60 °C, amounting to 0.01128 W/mK.

Exploring organo-bentonite adsorption properties for biphenyl removal from organic-aqueous media: kinetic study and industrial perspective

Biphenyl, a frequently encountered and resilient compound in wastewater, proves resistant to conventional treatment methods because of its enduring nature. It forms the structural basis for persistent organic pollutants such as PCBs. In this study, we explored the adsorption of biphenyl in an organo-aqueous medium using both natural (Bent) and organomodified (CTAB-Bent) bentonite clay. Our objective was to highlight its potential for biphenyl wastewater treatment. We analyzed the physicochemical and textural properties of these clays through FTIR, XRF, XRD, SEM, BET method, and Zeta potential measurements. Impressively, these materials exhibited remarkable biphenyl adsorption capacity under acidic conditions, with Bent achieving 60% removal and CTAB-Bent an impressive 91%. We investigated the adsorption kinetics using first-order and pseudo-second-order models and assessed isotherm data with the Langmuir, Freundlich, and Langmuir-Freundlich (sips) equations. The Langmuir model, at pH 3, proved optimal, with high accuracy (R²) and minimal error (RMSE) values (0.997 and 1.20, respectively). Clay nature significantly influenced pollutant uptake efficiency, confirming the efficacy of the selected bio-based clay. We propose a protocol adaptable for industrial-scale applications.

Enhancing compressive strength prediction in self-compacting concrete using machine learning and deep learning techniques with incorporation of rice husk ash and marble powder

Focusing on sustainable development, the demand for alternative materials in concrete, especially for Self-Compacting Concrete (SCC), has risen due to excessive cement usage and resulting CO2 emissions. As Compressive Strength (CS) is dominant among concrete properties, this research concentrates on developing SCC by incorporating Rice Husk Ash (RHA) and Marble Powder (MP) as cement and filler replacements, respectively, while applying Machine Learning (ML) and Deep Learning (DL) techniques to forecast the CS of RHA/MP-based SCC. The research further evaluates material characteristics, with a strong emphasis on ML and DL for CS prediction. Concrete samples with various mixed ratios were cast and examined after 91 days to collect data for model application. In the experimental technique, 133 samples were gathered, and CS was predicted using seven input factors (cement, RHA, MP, superplasticizer, coarse aggregate, fine aggregate, and water) in an 80:20 ratio. Various ML algorithms, including linear regression, ridge regression, lasso regression, K-nearest neighbors (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), and boosting methods such as gradient boost (GB), XG boost (XGB), and adaptive boosting (ADB) are employed, along with the DL technique of backpropagation neural network (BPNN) with different optimizer algorithms (Adam, SGD, RMSprop) to predict CS in RHA/MP-based SCC. The predicted data is further validated using evaluation parameters such as R-squared (R2), mean squared error (MSE), normalized root mean squared error (NRMSE), mean absolute error (MAE), and mean absolute percentage error (MAPE). Comparatively, ML ensemble algorithms and BPNN using Adam and RMSprop optimizers demonstrate high accuracy in predicting CS outcomes, indicated by their high coefficient correlation R2 values and low error values.