Lower Root Mean Square Research Articles

Evaluating the dry matter content of raw yams using hyperspectral imaging spectroscopy and machine learning

Yams (Dioscorea spp.) are important food and commercial crops in West African countries. They contribute significantly to global food production and provide dietary energy. The quality of yam food products depends on specific internal and external parameters, such as the DMC and other biochemical traits. However, measuring these traits can be challenging, particularly when analyzing many genotypes. This study aimed to evaluate the feasibility of using near-infrared (NIR) hyperspectral imaging (932–1721 nm) along with machine learning to rapidly measure the dry matter content (DMC) of fresh, intact yam tubers. Hyperspectral images were acquired across the yam tuber’s cross-sections, and the resulting spectra from the images were averaged and preprocessed. Partial least square regression (PLSR) combined with successive progressions algorithms (SPA), Competitive Adaptive Reweighted Sampling (CARS), Artificial Neural network (ANN) and Boruta algorithms (BA) were used to select the important wavelengths for developing a prediction model for DMC (g/100 g). The PLSR-SPA-CARS model showed the most accurate prediction performances with a coefficient of determinations in calibration (R2cal) and prediction (R2pred) of 0.974 and 0.958, respectively, and low root mean square error (RMSEP) of 0.898 g/100 g. The distribution of DMC was visually represented by projecting the developed model to generate color chemical maps. This study resolves that NIR hyperspectral imaging can rapidly assess the DMC of fresh, intact yam tubers.

Utilizing multiple inputs autoregressive models for bearing remaining useful life prediction

Accurate prediction of the remaining useful life (RUL) of rolling bearings is crucial in industrial production, yet existing models often struggle with limited generalization capabilities due to their inability to fully process all vibration signal patterns. We introduce a novel multi-input autoregressive model to address this challenge in RUL prediction for bearings. Our approach uniquely integrates vibration signals with previously predicted RUL values, employing feature fusion to output current window RUL values. Through autoregressive iterations, the model attains a global receptive field, effectively overcoming the limitations in generalization. Furthermore, we innovatively incorporate a segmentation method and multiple training iterations to mitigate error accumulation in autoregressive models. Empirical evaluation on the PMH2012 dataset demonstrates that our model, compared to other backbone networks using similar autoregressive approaches, achieves significantly lower root mean square error (RMSE) and Score. Notably, it outperforms traditional autoregressive models that use label values as inputs and non-autoregressive networks, showing superior generalization abilities with a marked lead in RMSE and Score metrics.

An ultrasound multiparametric method to quantify liver fat using magnetic resonance as standard reference.

There is an unmet need for a reliable and reproducible non-invasive measure of fatty liver content (FLC) for monitoring steatotic liver disease in clinical practice. Sonographic FLC assessment is qualitative and operator-dependent, and the dynamic quantification range of algorithms based on a single ultrasound (US) parameter is unsatisfactory. This study aims to develop and validate a new multiparametric algorithm based on B-mode images to quantify FLC using Magnetic Resonance (MR) values as standard reference. Patients with elevated liver enzymes and/or bright liver at US (N = 195) underwent FLC evaluation by MR and by US. Five US-derived quantitative features [attenuation rate(AR), hepatic renal-ratio(HR), diaphragm visualization(DV), hepatic-portal-vein-ratio(HPV), portal-vein-wall(PVW)] were combined by mixed linear/exponential regression in a multiparametric model (Steatoscore2.0). One hundred and thirty-four subjects were used for training and 61 for independent validations; score-computation underwent an inter-operator reproducibility analysis. The model is based on a mixed linear/exponential combination of 3 US parameters (AR, HR, DV), modelled by 2 equations according to AR values. The computation of FLC by Steatoscore2.0 (mean ± std, 7.91% ± 8.69) and MR (mean ± std, 8.10% ± 10.31) is highly correlated with a low root mean square error in both training/validation cohorts, respectively (R = 0.92/0.86 and RMSE = 5.15/4.62, p < .001). Steatoscore2.0 identified patients with MR-FLC≥5%/≥10% with sensitivity = 93.2%/89.4%, specificity = 86.1%/95.8%, AUROC = 0.958/0.975, respectively and correlated with MR (R = 0.92) significantly (p < .001) better than CAP (R = 0.73). Multiparametric Steatoscore2.0 measures FLC providing values highly comparable with MR. It is reliable, inexpensive, easy to use with any US equipment and qualifies to be tested in larger, prospective studies as new tool for the non-invasive screening and monitoring of FLC.

Development and validation of accelerated failure time model for cause-specific survival and prognostication of oral squamous cell carcinoma: SEER data analysis.

Oral Squamous Cell Carcinoma is the most prevalent malignancies affecting the oral cavity. Despite progress in studies and treatment options its outlook remains grim with survival prospects greatly affected by demographic and clinical factors. Precisely predicting survival rates and prognosis plays a role in making treatment choices for the best achievable overall health outcomes. To develop and validate an accelerated failure time model as a predictive model for cause-specific survival and prognosis of Oral Squamous Cell Carcinoma patients and compare its results to the traditional Cox proportional hazard model. We screened Oral cancer patients diagnosed with Squamous Cell Carcinoma from the Surveillance Epidemiology and End Results (SEER) database between 2010 and 2020. An accelerated failure time model using the Type I generalized half logistic distribution was used to determine independent prognostic factors affecting the survival time of patients with oral squamous carcinoma. In addition, accelerated factors were estimated to assess how some variables influence the survival times of the patients. We used the Akaike Information Criterion, Bayesian Information Criterion to evaluate the model fit, the area under the curve for discriminability, Concordance Index (C-index) and Root Mean Square Error and calibration curve for predictability, to compare the type I generalized half logistic survival model to other common classical survival models. All tests are conducted at a 0.05 level of significance. The accelerated failure time models demonstrated superior effectiveness in modeling (fit and predictive accuracy) the cause-specific survival (CSS) of oral squamous cell carcinoma compared to the Cox model. Among the accelerated failure time models considered, the Type I generalized half logistic distribution exhibited the most robust model fit, as evidenced by the lowest Akaike Information Criterion (AIC = 27370) and Bayesian Information Criterion (BIC = 27415) values. This outperformed other parametric models and the Cox Model (AIC = 47019, BIC = 47177). The TIGHLD displayed an AUC of 0.642 for discrimination, surpassing the Cox model (AUC = 0.544). In terms of predictive accuracy, the model achieved the highest concordance index (C-index = 0.780) and the lowest root mean square error (RMSE = 1.209), a notable performance over the Cox model (C-index = 0.336, RMSE = 6.482). All variables under consideration in this study demonstrated significance at the 0.05 level for CSS, except for race and the time span from diagnosis to treatment, in the TIGHLD AFT model. However, differences emerged regarding the significant variations in survival times among subgroups. Finally, the results derived from the model revealed that all significant variables except chemotherapy, all TNM stages and patients with Grade II and III tumor presentations contributed to the deceleration of time to cause-specific deaths. The accelerated failure time model provides a relatively accurate method to predict the prognosis of oral squamous cell carcinoma patients and is recommended over the Cox PH model for its superior predictive capabilities. This study also underscores the importance of using advanced statistical models to improve survival predictions and outcomes for cancer patients.

Enhancing arsenate removal through interpretable machine learning guiding the modular design of metal–organic frameworks

The modular design of metal–organic frameworks (MOFs) for enhancing arsenate (As(V)) adsorption remains a challenge. We have developed twelve interpretable machine learning prediction models by integrating six decision tree-based algorithms with two molecular fingerprints, Morgan and MACCS. The optimal XGBoost-Morgan model, with its high determination coefficient of 0.97 and low root mean square error of 11.78, not only demonstrates excellent prediction and generalization capabilities in As(V) adsorption capacity, but also validates the feasibility of modeling concepts by feature engineering adopted in this work. Our comprehensive model interpretation initiates with the molecular fragment composition of the organic linkers, the secondary building units, and the topological nets, that constitute MOFs, and structure parameters. It culminates in the proposal of a reticular chemistry design scheme specifically tailored for the adsorption of As(V) by MOFs. Furthermore, it delineates the optimal environmental conditions conducive to effective As(V) adsorption. We anticipate that our MOF design strategy will be extensively applicable to the target removal of pollutants.

Holistic in silico developability assessment of novel classes of small proteins using publicly available sequence-based predictors.

The development of novel therapeutic proteins is a lengthy and costly process, with an average attrition rate of 91% (Thomas et al. Clinical Development Success Rates and Contributing Factors 2011-2020, 2021). To increase the probability of success and ensure robust drug supply beyond approval, it is essential to assess the developability profile of new potential drug candidates as early and broadly as possible in development (Jain et al. MAbs, 2023. https://doi.org/10.1016/j.copbio.2011.06.002 ). Predicting these properties in silico is expected to be the next leap in innovation as it would enable significantly reduced development timelines combined with broader screens at lower costs. However, developing predictive algorithms typically requires substantial datasets generated under very defined conditions, a limiting factor especially for new classes of therapeutic proteins that hold immense clinical promise. Here we describe a strategy for assessing the developability of a novel class of small therapeutic Anticalin® proteins using machine learning in conjunction with a knowledge-driven approach. The knowledge-driven approach considers developability attributes such as aggregation propensity, charge variants, immunogenicity, specificity, thermal stability, hydrophobicity, and potential post-translational modifications, to calculate a holistic developability score. Based on sequence-derived descriptors as input parameters we established novel statistical models designed to predict the developability scores for Anticalin proteins. The best models yielded low root mean square errors across the entire dataset and were further validated by removing input data from individual screening campaigns and predicting developability scores for those drug candidates. The adoption of the described workflow will enable significantly streamlined preclinical development of Anticalin drug candidates and could potentially be applied to other therapeutic protein scaffolds.

Accelerating the design of catalysts for CO2 electroreduction to HCOOH: A data-driven DFT-ML screening of dual atom catalysts

Dual-atom catalysts (DACs) have emerged as potential catalysts for effective electroreduction of CO2 due to their high atom utilization efficiency and multiple active sites. However, the screening of DACs remains a challenge due to the large number of possible combinations, making exhaustive experimental or computational screening a daunting task. In this study, a density functional theory (DFT)-based machine learning (ML)-accelerated (DFT-ML) hybrid approach was developed to test a set of 406 dual transition metal catalysts on N-doped graphene (NG) for the electroreduction of CO2 to HCOOH. The results showed that the ML algorithms can successfully capture the relationship between the descriptors of the DACs (inputs) and the limiting potential for HCOOH generation (output). Of the four ML algorithms studied in this work, the feedforward neural network model achieved the highest prediction accuracy (the highest correlation coefficient (R2) of 0.960 and the lowest root mean square error (RMSE) of 0.319 eV on the test set) and the predicted results were verified by DFT calculations with an average absolute error of 0.14 eV. The DFT-ML approach identified Co-Co-NG and Ir-Fe-NG as the most active and stable electrocatalysts for the electrochemical reduction of CO2 to HCOOH. The DFT-ML hybrid approach exhibits exceptional prediction accuracy while enabling a significant reduction in screening time by an impressive 64% compared to conventional DFT-only calculations. These results demonstrate the immense potential of using ML methods to accelerate the screening and rational design of efficient catalysts for various energy and environmental applications.

Forecasting and unveiling the impeded factors of total export of Bangladesh using nonlinear autoregressive distributed lag and machine learning algorithms

Rising global oil prices are a major challenge for an emerging oil-importing nation such as Bangladesh. The majority of prior research on the economic effects of an oil price shock has concentrated on developed countries, with emerging economies receiving comparatively less attention. Bangladesh is vulnerable to price shocks due to its rising oil consumption over the past decade. This study aims to investigate how changes in oil prices would affect Bangladesh's total export earnings and to forecast the overall export volume. This study utilized a nonlinear autoregressive distributed lag (NARDL) approach to account for the asymmetric behavior of oil prices from 1991 to 2021. To assess the accuracy of predictions, the study employed the Prophet forecasting model and the Long Short-Term Memory (LSTM) method. Additionally, the symmetry test revealed a nonlinear relationship between export volume and oil price but a linear relationship between inflation and export volume. According to the NARDL assessment, both positive and negative oil shocks increase export earnings over the long run. The short run summary clarifies that both positive and negative changes in oil prices exert a significant negative effect on exports. Also, Inflation influences export earnings negatively in the short run but positively over the long term. Moreover, using machine learning methods, it was found that the LSTM method outperforms the prophet model in prediction performance with a low root mean square error (RMSE) of 1.88. Also, the analysis revealed policymakers that the export sector requires diversification to reduce its exposure to oil price shocks.

AI-based non-linear models for mechanical and toughness properties of sustainable fiber-reinforced geopolymer concrete (FRGPC)

The incorporation of fibers into geopolymer concrete (GPC) produces FRGPC which mitigates brittle failure and restrains macro crack propagation; however, research on predicting the mechanical and toughness properties of FRGPC remains limited. This study addresses this gap by developing prediction models for compressive strength (CS), flexural strength (FS), flexural toughness (FT), and fracture toughness (FR). A dataset of 600 data points was compiled from the published literature, encompassing various constituent proportions, fiber shapes, fiber dosages, aspect ratios, and curing conditions. Employing an artificial neural network (ANN) methodology, 10 independent variables (g1, g2, …., g10) were utilized to predict four dependent variables (CS, FS, FT, and FR), resulting in the development of eight non-linear ANN models for both straight fibers (SFs) and hooked fibers (HFs). Each model has shown a higher R 2 value and lower root mean square error (RMSE) for training (70%), testing (15%), and validation (15%) datasets. The prediction model for the CS of FRGPC with HFs (CS-HF) and SF (CS-SF) showed R 2 values of 0.983 and 0.973, and RMSE of 2.088 and 2.435 MPa highlighting the accuracy of the ANN models. Similarly, the comparative analysis for FR models exhibited R 2 values of 0.997 and 0.987, and RMSE values of 0.045 Mpa √m and 0.032 Mpa √m for FR-HF and FR-SF, highlighting that fiber addition strongly impacts improving toughness properties. To identify the most influential independent variable(s), sensitivity analysis revealed g10, g1, g8, and g9 as the most influential parameters for mechanical and toughness properties with SFs. For HFs, g1, g2, and g3 were most influential for mechanical properties, and g8, g9, and g10 for toughness. This study also presented the mathematical formulation of the developed models for better interpretability and to facilitate optimal and economical FRGPC mix design selection, highlighting the potential of AI-based models in advancing sustainable construction materials.

Examining optimized machine learning models for accurate multi-month drought forecasting: A representative case study in the USA.

TheColorado River has experienced a significant streamflow reduction in recent decades due to climate change, resulting in pronounced hydrological droughts that pose challenges to the environment and human activities. However, current models struggle to accurately capture complex drought patterns, and their accuracy decreases as the lead time increases. Thus, determining the reliability of drought forecasting for specific months ahead presents a challenging task. This study introduces a robust approach that utilizes the Beluga Whale Optimization (BWO) algorithm to train and optimize the parameters of the Regularized Extreme Learning Machine (RELM) and Random Forest (RF) models. The applied models are validated against a KNN benchmark model forforecasting drought from one- tosix-month ahead across four hydrological stationsdistributed over the Colorado River. The achieved results demonstrate that RELM-BWO outperforms RF-BWO and KNN models, achieving the lowest root-mean square error (0.2795), uncertainty (U95 = 0.1077), mean absolute error (0.2104), and highest correlation coefficient (0.9135). Also, the current study uses Global Multi-Criteria Decision Analysis (GMCDA) as an evaluation metric to assess the reliability of the forecasting. The GMCDA results indicate that RELM-BWO provides reliable forecasts up to four months ahead. Overall, the research methodology is valuable for drought assessment and forecasting, enabling advanced early warning systems and effective drought countermeasures.

Off-Axis Integral Cavity Carbon Dioxide Gas Sensor Based on Machine-Learning-Based Optimization.

Accurately detecting atmospheric carbon dioxide is a vital part of responding to the global greenhouse effect. Conventional off-axis integral cavity detection systems are computationally intensive and susceptible to environmental factors. This study deploys an Extreme Learning Machine model incorporating a cascaded integrator comb (CIC) filter into the off-axis integrating cavity. It is shown that appropriate parameters can effectively improve the performance of the instrument in terms of lower detection limit, accuracy, and root mean square deviation. The proposed method is incorporated successfully into a monitoring station situated near an industrial area for detecting atmospheric carbon dioxide (CO2) concentration daily.

Better representation of vegetation phenology improves estimations of annual gross primary productivity

Carbon uptake by vegetation plays a vital role in the global carbon cycle. Annual gross primary productivity (AGPP) represents the total amount of carbon compounds produced by vegetation photosynthesis over a year and is a crucial metric for quantifying vegetation carbon uptake. Although some theories have been developed to explain the spatiotemporal variation in AGPP, they often overlook the seasonal differences in photosynthesis across vegetation phenological periods. This gap highlights the need for a more reasonable representation of vegetation phenology in AGPP modelling. Therefore, we developed a novel theoretical AGPP model that decomposes AGPP into detailed vegetation phenological periods (green-up, maturation, and senescence) and investigated the effects of climatic factors on the seasonal components of AGPP. Compared with existing models, our model considers the length of the multiple vegetation phenological periods, rather than just the length of the carbon uptake period. When evaluated against flux tower data, our model outperformed the comparative model, with a higher determination coefficient and lower root mean square error. The analysis also demonstrated that the developed model can reproduce spatial and temporal variations in satellite-based global AGPP. In addition, we identified distinct differences in the responses of AGPP's seasonal components to climatic factors: shortwave radiation predominantly affected the seasonal component of AGPP during senescence, air temperature during green-up, and vapor pressure deficit during maturation. Our study proposes a potential mechanism for AGPP estimation and highlights the importance of accurately representing vegetation phenology in AGPP modelling.

A hierarchical estimation of road grade based on tire force observation

Road grade is important for autonomous vehicles, but it is difficult to measure directly. To address this issue, a hierarchical estimation of road grade is suggested based on the observation of tire forces. First, a 7-degree-of-freedom (DOF) dynamics model, including vehicle longitudinal, lateral, and yaw motions together with wheel rotations, is developed while considering the road grade. Subsequently, a dual-layer road grade estimation strategy is proposed based on an unscented Kalman filter (UKF). The lower-layer UKF estimates the longitudinal and lateral tire forces for road grade observation, and the upper-layer UKF is employed to estimate the road grade by considering the vehicle’s lateral acceleration and yaw rate. Finally, CarSim and MATLAB joint simulations and road tests are performed under different conditions to validate the correctness and effectiveness of the proposed estimation method. The results show that the proposed tire force observation-based estimator exhibits a lower mean absolute error and root mean square error on sloping roads and combined curved and sloping roads, and presents a better overall estimation performance on road grade compared with the widely used kinematics and dynamics model-based estimators.

Validation of a novel AI-based automated multimodal image registration of CBCT and intraoral scan aiding presurgical implant planning.

The objective of this study is to assess accuracy, time-efficiency and consistency of a novel artificial intelligence (AI)-driven automated tool for cone-beam computed tomography (CBCT) and intraoral scan (IOS) registration compared with manual and semi-automated approaches. A dataset of 31 intraoral scans (IOSs) and CBCT scans was used to validate automated IOS-CBCT registration (AR) when compared with manual (MR) and semi-automated registration (SR). CBCT scans were conducted by placing cotton rolls between the cheeks and teeth to facilitate gingival delineation. The time taken to perform multimodal registration was recorded in seconds. A qualitative analysis was carried out to assess the correspondence between hard and soft tissue anatomy on IOS and CBCT. In addition, a quantitative analysis was conducted by measuring median surface deviation (MSD) and root mean square (RMS) differences between registered IOSs. AR was the most time-efficient, taking 51.4 ± 17.2 s, compared with MR (840 ± 168.9 s) and SR approaches (274.7 ± 100.7 s). Both AR and SR resulted in significantly higher qualitative scores, favoring perfect IOS-CBCT registration, compared with MR (p = .001). Additionally, AR demonstrated significantly superior quantitative performance compared with SR, as indicated by low MSD (0.04 ± 0.07 mm) and RMS (0.19 ± 0.31 mm). In contrast, MR exhibited a significantly higher discrepancy compared with both AR (MSD = 0.13 ± 0.20 mm; RMS = 0.32 ± 0.14 mm) and SR (MSD = 0.11 ± 0.15 mm; RMS = 0.40 ± 0.30 mm). The novel AI-driven method provided an accurate, time-efficient, and consistent multimodal IOS-CBCT registration, encompassing both soft and hard tissues. This approach stands as a valuable alternative to manual and semi-automated registration approaches in the presurgical implant planning workflow.

Tumor spheroid elasticity estimation using mechano-microscopy combined with a conditional generative adversarial network

Background and ObjectivesTechniques for imaging the mechanical properties of cells are needed to study how cell mechanics influence cell function and disease progression. Mechano-microscopy (a high-resolution variant of compression optical coherence elastography) generates elasticity images of a sample undergoing compression from the phase difference between optical coherence microscopy (OCM) B-scans. However, the existing mechano-microscopy signal processing chain (referred to as the algebraic method) assumes the sample stress is uniaxial and axially uniform, such that violation of these assumptions reduces the accuracy and precision of elasticity images. Furthermore, it does not account for prior information regarding the sample geometry or mechanical property distribution. In this study, we investigate the feasibility of training a conditional generative adversarial network (cGAN) to generate elasticity images from phase difference images of samples containing a cell spheroid embedded in a hydrogel. MethodsTo construct the cGAN training and simulated test sets, we generated 30,000 artificial elasticity images using a parametric model and computed the corresponding phase difference images using finite element analysis to simulate compression applied to the artificial samples. We also imaged real MCF7 breast tumor spheroids embedded in hydrogel using mechano-microscopy to construct the experimental test set and evaluated the cGAN using the algebraic elasticity images and co-registered OCM and confocal fluorescence microscopy (CFM) images. ResultsComparison with the simulated test set ground truth elasticity images shows the cGAN produces a lower root mean square error (median: 3.47 kPa, 95 % confidence interval (CI) [3.41, 3.52]) than the algebraic method (median: 4.91 kPa, 95 % CI [4.85, 4.97]). For the experimental test set, the cGAN elasticity images contain features resembling stiff nuclei at locations corresponding to nuclei seen in the algebraic elasticity, OCM, and CFM images. Furthermore, the cGAN elasticity images are higher resolution and more robust to noise than the algebraic elasticity images. ConclusionsThe cGAN elasticity images exhibit better accuracy, spatial resolution, sensitivity, and robustness to noise than the algebraic elasticity images for both simulated and real experimental data.

An improved autoencoder for denoising acoustic emission signals in rock fracturing

ABSTRACT Rock fracture acoustic emission (AE) signals are commonly used non-destructive testing data in geological exploration, resource exploitation, and engineering fields. However, these signals are often accompanied by noise interference caused by environmental factors. In this study, we propose an enhanced model for denoising rock fracture AE signals, called simplified fully convolutional denoising autoencoder (SFCDAE). This model is based on the denoising autoencoder principle in the field of deep learning neural networks. The SFCDAE model consists of only seven layers, with minimal preprocessing of data input. By comparing denoising performance evaluation indicators, higher peak signal-to-noise ratio (PSNR) and lower root mean square error (RMSE) were achieved. On average, PSNR increased by 5.575% and RMSE decreased by 22.225%. Using simulated environmental noise to validate the model, it was found that the model has good robustness and can remove artefacts from sudden noise. The practical application value of the LSTM classification model was validated using data containing real experimental noise, resulting in a higher classification accuracy of 80.083%. These results indicate that the proposed model has better denoising performance compared to existing intelligent models and has certain practical value.

Advancing Reservoir Evaluation: Machine Learning Approaches for Predicting Porosity Curves

Porosity assessment is a vital component for reservoir evaluation in the oil and gas sector, and with technological advancement, reliance on conventional methods has decreased. In this regard, this research aims to reduce reliance on well logging, purposing successive machine learning (ML) techniques for precise porosity measurement. So, this research examines the prediction of the porosity curves in the Sui main and Sui upper limestone reservoir, utilizing ML approaches such as an artificial neural networks (ANN) and fuzzy logic (FL). Thus, the input dataset of this research includes gamma ray (GR), neutron porosity (NPHI), density (RHOB), and sonic (DT) logs amongst five drilled wells located in the Qadirpur gas field. The ANN model was trained using the backpropagation algorithm. For the FL model, ten bins were utilized, and Gaussian-shaped membership functions were chosen for ideal correspondence with the geophysical log dataset. The closeness of fit (C-fit) values for the ANN ranged from 91% to 98%, while the FL model exhibited variability from 90% to 95% throughout the wells. In addition, a similar dataset was used to evaluate multiple linear regression (MLR) for comparative analysis. The ANN and FL models achieved robust performance as compared to MLR, with R2 values of 0.955 (FL) and 0.988 (ANN) compared to 0.94 (MLR). The outcomes indicate that FL and ANN exceed MLR in predicting the porosity curve. Moreover, the significant R2 values and lowest root mean square error (RMSE) values support the potency of these advanced approaches. This research emphasizes the authenticity of FL and ANN in predicting the porosity curve. Thus, these techniques not only enhance natural resource exploitation within the region but also hold broader potential for worldwide applications in reservoir assessment.

Metaheuristic optimization algorithms-based prediction modeling for titanium dioxide-Assisted photocatalytic degradation of air contaminants

Airborne contaminants pose significant environmental and health challenges. Titanium dioxide (TiO2) has emerged as a leading photocatalyst in the degradation of air contaminants compared to other photocatalysts due to its inherent inertness, cost-effectiveness, and photostability. To assess its effectiveness, laboratory examinations are frequently employed to measure the photocatalytic degradation rate of TiO2. However, this approach involves time-consuming requirements, labor-intensive tasks, and high costs. In literature, ensemble or standalone models are commonly used for assessing the performance of TiO2 photocatalytic degradation of water and air contaminants. Nonetheless, the application of metaheuristic hybrid models has the potential to be more effective in predictive accuracy and efficiency. Accordingly, this research utilized hybrid machine learning (ML) algorithms to estimate the photo-degradation rate constants of organic air pollutants using TiO2 nanoparticles and exposure to ultraviolet light. Six metaheuristics optimization algorithms, namely, nuclear reaction optimization (NRO), differential evolution algorithm (DEA), human felicity algorithm (HFA), lightning search algorithm (LSA), Harris hawks algorithm (HHA), and tunicate swarm algorithm (TSA) were combined with random forest (RF) technique to establish the hybrid models. A database of 200 data points was acquired from experimental studies for model training and testing. Furthermore, multiple statistical indicators and 10-fold cross-validation were employed to examine the established hybrid model's accuracy and robustness. The TSA-RF model demonstrated superior prediction accuracy among the six suggested models, achieving an impressive correlation (R) of 0.90 and a lower root mean square error (RMSE) of 0.25. In contrast, the HFA-RF, HHA-RF, and NRO-RF models exhibited a slightly lower R-value of 0.88, with RMSE scores of 0.32. The DEA-RF and LSA-RF models, while effective, showed a marginally lower R-value of 0.85, with RMSE values of 0.45 and 0.44, respectively. Moreover, the SHapley Additive exPlanation (SHAP) results indicated that the degradation rates of air contaminants through photocatalysis were most notably influenced by factors such as the reactor sizes, photocatalyst dosage, humidity, and intensity.

Determination of oil quality during crispy pork rind frying: Near infrared spectra and color values as predictors

This study provides a comprehensive analysis of oil degradation during the frying of various semi-finished pork rinds, including high-fat (HF), non-fat (NF), streaky (SK), and thin (TN) types. By quantitatively assessing parameters such as peroxide, acid, anisidine, and Totox values, we sought to elucidate the complex interactions and effects on oil quality during the frying process. The oil samples underwent evaluation utilizing a near-infrared (NIR) spectrometer and the color variations in the frying oil during the process. The resulting data highlighted significant correlations between color parameters and oil quality. The NIR models exhibited an impressive and robust predictive proficiency with high correlation coefficients values (R > 0.9 for all measured parameters) and low root mean square errors of cross-validation (RMSECVs). They promise rapid, non-destructive, and accurate evaluation of oil quality during frying processes. Additionally, the study identified oil color as a viable, low-cost alternative for predicting oil quality parameters where sophisticated spectroscopic equipment is unavailable.

Integrating machine learning and the finite element method for assessing stiffness degradation in photovoltaic modules

This study introduces a novel machine learning (ML) method utilizing a stacked auto-encoder network to predict stiffness degradation in photovoltaic (PV) modules with pre-existing cracks. The input data for the training process was derived from numerical simulations, ensuring a comprehensive representation of module behavior under various conditions. The findings highlight the robust predictive capability of the model, as evidenced by its impressive R2 value of 0.961 and notably low root mean square error (RMSE) of 4.02%. These metrics significantly outperform those of other conventional methods, including the artificial neural network with R2 of 0.905 and RMSE of 9.43%, the space vector machine with R2 of 0.827 and RMSE of 17.93%, and the random forest (RF) with R2 of 0.899 and RMSE of 11.02%. Moreover, the findings suggest that the predictive dynamics of degradation are affected by the varying weight functions of different input parameters, such as climate temperature (CT), grain size (GS), material effort, and pre-crack size, as the degradation level changes. Furthermore, a geometric analysis reveals model deficiencies where significant overestimations correlate with thicker glass components, while pronounced underestimations are predominantly associated with thinner layers of polycrystalline silicon wafer and Ethylene Vinyl Acetate in the module. As a case study, it demonstrated that to maintain a constant degradation level between 1.30 and 1.32 in a PV module with components featuring consistent geometric attributes, the input parameters must be kept within specific ranges: CT ranging from 33 °C to 57 °C, GS ranging from 36 to 81 μm, material effort ranging from 0.74 to 0.81, and pre-crack size ranging from 24 to 32 μm. Therefore, this underscores that the ML model not only predicts degradation but also delineates the parameter space required to achieve a consistent output value.