Search Results (370)

Crop monitoring can promptly reflect the growth status of crops. However, conventional methods of growth monitoring, although simple and direct, have limitations such as destructive sampling, reliance on human experience, and slow detection speed. This study estimated the fresh weight of lettuce (Lactuca sativa L.) in a plant factory with artificial light based on three-dimensional (3D) reconstruction technology. Data from different growth stages of lettuce were collected as the training dataset, while data from different plant forms of lettuce were used as the validation dataset. The partial least squares regression (PLSR) method was utilized for modeling, and K-fold cross-validation was performed to evaluate the model. The testing dataset of this model achieved a coefficient of determination (R²) of 0.9693, with root mean square error (RMSE) and mean absolute error (MAE) values of 3.3599 and 2.5232, respectively. Based on the performance of the validation set, an adaptation was made to develop a fresh weight estimation model for lettuce under far-red light conditions. To simplify the estimation model, reduce estimation costs, enhance estimation efficiency, and improve the lettuce growth monitoring method in plant factories, the plant height and canopy width data of lettuce were extracted to estimate the fresh weight of lettuce in addition. The testing dataset of the new model achieved an R² value of 0.8970, with RMSE and MAE values of 3.1206 and 2.4576. Full article

In industrial applications, hydraulic presses maintain workloads by controlling the hydraulic cylinder to extend and retract, ensuring optimum tracking performance in terms of position and force. Dealing with nonlinear and multinode systems, such as hydraulic systems, often requires an advanced approach that frequently includes machine learning and artificial intelligence methods. Introducing an adaptive control system to significantly improve the response of hydraulic presses is a challenge. Therefore, a polynomial regression model predictive control (PR-MPC) mechanism is proposed in this paper to compensate for external disturbances such as the forming processes and friction dynamics. Using polynomial regression modeling and least squares optimization, the approach produces highly accurate data-driven models with an R² value of 0.948 to 0.999. The simplicity of polynomial regression facilitates the integration of smart algorithms into an expert system with additional decision-making rules. Remote adaptive control integrated within a 5G network is based on I 4.0 distributed system guidelines that provide insights into the behavior of the hydraulic press. The results of real-time experiments have shown that the PR-MPC mechanism integrated into the expert system reduces the absolute response error of the hydraulic press by up to 98.7% compared to the initial control system with a PID regulation. Full article

This study accurately inverts key growth parameters of rice, including Leaf Area Index (LAI), chlorophyll content (SPAD) value, and height, by integrating multisource remote sensing data (including MODIS and ERA5 imagery) and deep learning models. Dehui City in Jilin Province, China, was selected as the case study area, where multidimensional data including vegetation indices, ecological function parameters, and environmental variables were collected, covering seven key growth stages of rice. Data analysis and parameter prediction were conducted using a variety of machine learning and deep learning models including Partial Least Squares (PLSs), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory Networks (LSTM), among which the LSTM model demonstrated superior performance, particularly at multiple critical time points. The results show that the LSTM performed best in inverting the three parameters, with the LAI inversion accuracy on 21 August reaching a coefficient of determination (R²) of 0.72, root mean square error (RMSE) of 0.34, and mean absolute error (MAE) of 0.27. The SPAD inversion accuracy on the same date achieved an R² of 0.69, RMSE of 1.45, and MAE of 1.16. The height inversion accuracy on 25 July reached an R² of 0.74, RMSE of 2.30, and MAE of 2.08. This study not only verifies the effectiveness of combining multisource data and advanced algorithms but also provides a scientific basis for the precision management and decision-making of rice cultivation. Full article

Lung cancer remains the leading cause of cancer-related mortality globally, with a poor prognosis primarily due to late diagnosis and limited treatment options. This research highlights the critical demand for advanced prognostic tools by creating a model centered on aging-related genes (ARGs) to improve prediction and treatment strategies for lung adenocarcinoma (LUAD). By leveraging datasets from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO), we developed a prognostic model that integrates 14 ARGs using the least absolute shrinkage and selection operator (LASSO) alongside Cox regression analyses. The model exhibited strong predictive performance, achieving area under the curve (AUC) values greater than 0.8 for one-year survival in both internal and external validation cohorts. The risk scores generated by our model were significantly correlated with critical features of the tumor microenvironment, including the presence of cancer-associated fibroblasts (CAFs) and markers of immune evasion, such as T-cell dysfunction and exclusion. Higher risk scores correlated with a more tumor-promoting microenvironment and increased immune suppression, highlighting the model’s relevance in understanding LUAD progression. Additionally, XRCC6, a protein involved in DNA repair and cellular senescence, was found to be upregulated in LUAD. Functional assays demonstrated that the knockdown of XRCC6 led to decreased cell proliferation, whereas its overexpression alleviated DNA damage, highlighting its significance in tumor biology and its potential therapeutic applications. This study provides a novel ARG-based prognostic model for LUAD, offering valuable insights into tumor dynamics and the tumor microenvironment, which may guide the development of targeted therapies and improve patient outcomes. Full article

In the last decade, the size and complexity of datasets have expanded significantly, necessitating more sophisticated predictive methods. Despite this growth, limited research has been conducted on the effects of autocorrelation within widely used regression methods. This study addresses this gap by investigating how autocorrelation impacts the predictive accuracy and efficiency of six regression approaches: Artificial Neural Network (ANN), Ordinary Least Squares (OLS), Cochrane–Orcutt (CO), Prais–Winsten (PW), Maximum Likelihood Estimation (MLE), and Restricted Maximum Likelihood Estimation (RMLE). The study evaluates each method’s performance on three datasets characterized by autocorrelation, comparing their predictive accuracy and variability. The analysis is structured into three phases: the first phase examines predictive accuracy across methods using Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE); the second phase evaluates the efficiency of parameter estimation based on standard errors across methods; and the final phase visually assesses the closeness of predicted values to actual values through scatter plots. The results indicate that the ANN consistently provides the most accurate predictions, particularly in large sample sizes with extensive training data. For GDP data, the ANN achieved an MSE of 1.05 × 10⁹, an MAE of 23,344.64, and an MAPE of 81.66%, demonstrating up to a 90% reduction in the MSE compared to OLS. These findings underscore the advantages of the ANN for predictive tasks involving autocorrelated data, highlighting its robustness and suitability for complex, large-scale datasets. This study provides practical guidance for selecting optimal prediction techniques in the presence of autocorrelation, recommending the ANN as the preferred method due to its superior performance. Full article

This paper investigates the design and stability of Traub–Steffensen-type iteration schemes with and without memory for solving nonlinear equations. Steffensen’s method overcomes the drawback of the derivative evaluation of Newton’s scheme, but it has, in general, smaller sets of initial guesses that converge to the desired root. Despite this drawback of Steffensen’s method, several researchers have developed higher-order iterative methods based on Steffensen’s scheme. Traub introduced a free parameter in Steffensen’s scheme to obtain the first parametric iteration method, which provides larger basins of attraction for specific values of the parameter. In this paper, we introduce a two-step derivative free fourth-order optimal iteration scheme based on Traub’s method by employing three free parameters and a weight function. We further extend it into a two-step eighth-order iteration scheme by means of memory with the help of suitable approximations of the involved parameters using Newton’s interpolation. The convergence analysis demonstrates that the proposed iteration scheme without memory has an order of convergence of 4, while its memory-based extension achieves an order of convergence of at least $7.993$, attaining the efficiency index $7.{993}^{1/3}\approx 2$. Two special cases of the proposed iteration scheme are also presented. Notably, the proposed methods compete with any optimal j-point method without memory. We affirm the superiority of the proposed iteration schemes in terms of efficiency index, absolute error, computational order of convergence, basins of attraction, and CPU time using comparisons with several existing iterative methods of similar kinds across diverse nonlinear equations. In general, for the comparison of iterative schemes, the basins of iteration are investigated on simple polynomials of the form $z^n-1$ in the complex plane. However, we investigate the stability and regions of convergence of the proposed iteration methods in comparison with some existing methods on a variety of nonlinear equations in terms of fractals of basins of attraction. The proposed iteration schemes generate the basins of attraction in less time with simple fractals and wider regions of convergence, confirming their stability and superiority in comparison with the existing methods. Full article

This article introduces a novel approach to detecting honey adulteration by combining ultra-fast gas chromatography (UF-GC) with advanced machine learning techniques. Machine learning models, particularly support vector regression (SVR) and least absolute shrinkage and selection operator (LASSO), were applied to predict adulteration in orange blossom (OB) and sunflower (SF) honeys. The SVR model achieved R² values above 0.90 for combined honey types. Treating OB and SF honeys separately resulted in a significant accuracy improvement, with R² values exceeding 0.99. LASSO proved especially effective when honey types were treated individually. The integration of UF-GC with machine learning not only provides a reliable method for detecting honey adulteration, but also sets a precedent for future research in the application of this technique to other food products, potentially enhancing food authenticity across the industry. Full article

This study used the Gleeble 3800 thermomechanical simulator to examine the hot deformation characteristics of AISI 8822H steel. The main goal was to understand the alloy’s behaviour under various thermomechanical settings, emphasising temperature ranges between 1173 K and 1323 K and strain rates from 0.01 s⁻¹ to 10 s⁻¹. This study aimed to enhance the alloy’s manufacturing process by offering a thorough understanding of the material’s response to these conditions. Four various constitutive models—Arrhenius-type, Johnson–Cook, modified Johnson–Cook, and Trimble—were used in a comprehensive technique to forecast flow stress values in order to meet the study’s goals. The accuracy of each model in forecasting the behaviour of the material under the given circumstances was assessed. A thorough comparison investigation revealed that the Trimble model was the most accurate model allowing prediction of material behaviour, with the maximum correlation factor (R = 0.99) and at least average absolute relative error (1.7%). On the other hand, the Johnson–Cook model had the least correlation factor (R = 0.92) and the maximum average absolute relative error (32.2%), indicating that it was the least accurate because it could not account for all softening effects. Full article

Composite robots often encounter difficulties due to changes in illumination, external disturbances, reflective surface effects, and cumulative errors. These challenges significantly hinder their capabilities in environmental perception and the accuracy and reliability of pose estimation. We propose a nonlinear optimization approach to overcome these issues to develop an integrated localization and navigation framework, IIVL-LM (IMU, Infrared, Vision, and LiDAR Fusion for Localization and Mapping). This framework achieves tightly coupled integration at the data level using inputs from an IMU (Inertial Measurement Unit), an infrared camera, an RGB (Red, Green and Blue) camera, and LiDAR. We propose a real-time luminance calculation model and verify its conversion accuracy. Additionally, we designed a fast approximation method for the nonlinear weighted fusion of features from infrared and RGB frames based on luminance values. Finally, we optimize the VIO (Visual-Inertial Odometry) module in the R3LIVE++ (Robust, Real-time, Radiance Reconstruction with LiDAR-Inertial-Visual state Estimation) framework based on the infrared camera’s capability to acquire depth information. In a controlled study, using a simulated indoor rescue scenario dataset, the IIVL-LM system demonstrated significant performance enhancements in challenging luminance conditions, particularly in low-light environments. Specifically, the average RMSE ATE (Root Mean Square Error of absolute trajectory Error) improved by 23% to 39%, with reductions from 0.006 to 0.013. At the same time, we conducted comparative experiments using the publicly available TUM-VI (Technical University of Munich Visual-Inertial Dataset) without the infrared image input. It was found that no leading results were achieved, which verifies the importance of infrared image fusion. By maintaining the active engagement of at least three sensors at all times, the IIVL-LM system significantly boosts its robustness in both unknown and expansive environments while ensuring high precision. This enhancement is particularly critical for applications in complex environments, such as indoor rescue operations. Full article

Open-grown trees in cities can improve environmental conditions by providing sustainable ecosystem services. Reliable data are necessary for assessing the functions of urban trees. The diameter at breast height (DBH), diameter increment, and annual ring measurements are the main parameters in the development of reliable models. To model periodic mean diameter increments calculated for different time periods (5, 10, 15, 20, and 25 years), a total of 43 open-grown stone pines (Pinus pinea L.) of different diameter classes were sampled in several urban parks in Istanbul, Türkiye. The DBH was measured, and increment cores were extracted from each tree at 1.30 m stem height using an increment borer. Tree age at breast height was determined by counting annual rings, and periodic mean diameter increments were calculated for different periods based on the measured tree-ring widths. The periodic mean increments of different periods were related to the inside-bark diameter at breast height and tree age. Since there was no significant relationship between tree age and periodic mean increments for each period’s length, as shown in the correlation analysis, models used to estimate the periodic mean increments of inside-bark DBH were developed using the least squares regression and quantile regression (QR) techniques. As the period length increased, the estimation success of the diameter increment models increased while the mean absolute percentage error (MAE) values decreased from 40 to 32%. The best model was the one used for the last 25-year period with the quantile value q = 0.50 which estimated the diameter increment with an RMSE = 1.391 mm/year and MAE = 32.27%. Full article

Accurate electricity demand forecasting is crucial for ensuring the sustainability and reliability of power systems. Least square support vector machines (LSSVM) are well suited to handle complex non-linear power load series. However, the less optimal regularization parameter and the Gaussian kernel function in the LSSVM model have contributed to flawed forecasting accuracy and random generalization ability. Thus, these parameters of LSSVM need to be chosen appropriately using intelligent optimization algorithms. This study proposes a new hybrid model based on the LSSVM optimized by the improved bacterial foraging optimization algorithm (IBFOA) for forecasting the short-term daily electricity load in Peninsular Malaysia. The IBFOA based on the sine cosine equation addresses the limitations of fixed chemotaxis constants in the original bacterial foraging optimization algorithm (BFOA), enhancing its exploration and exploitation capabilities. Finally, the load forecasting model based on LSSVM-IBFOA is constructed using mean absolute percentage error (MAPE) as the objective function. The comparative analysis demonstrates the model, achieving the highest determination coefficient (R²) of 0.9880 and significantly reducing the average MAPE value by 28.36%, 27.72%, and 5.47% compared to the deep neural network (DNN), LSSVM, and LSSVM-BFOA, respectively. Additionally, IBFOA exhibits faster convergence times compared to BFOA, highlighting the practicality of LSSVM-IBFOA for short-term load forecasting. Full article

The Holy See is an absolute monarchy, both as a political and as a spiritual entity. The Second Vatican Council indicated, retrieving biblical terms and metaphors, a new way of giving value to the whole people of God, the laity (laos theou), constituted by baptism. Rather than a societas perfecta in a pyramidal system, the intention was to declericalise and in this sense democratise the church and its decision-making, not least seeking to secure its witness in an ever more secular world. Even if a sacramental and ontological difference is maintained, this indicates clergy are no longer a first class of believers against which the laity would be a second class; rather, they are rooted and stand with and within the whole people of God with their specific vocation and ordination. The notion of the royal and universal priesthood of believers, taken from 1 Peter 2:9 and emphasised by Luther and other reformers as they distributed power between ordained and not ordained leaders, was visible in the Second Vatican Council and finds new enactment in the synodality process which culminated in the Ordinary Synod in Rome, in October 2024. Based on his own theology of the people of God, developed during the dictatorship and economic oppression in Argentina, with strong cultural and religious connotations, Pope Francis seeks to further major involvement of the laity and especially of women in the church’s administration and transformation processes. Not surprisingly, this process has been receiving criticism both from those who find it is not going far enough and from those who believe the process has already gone far too far. Based on bibliographical and documental research, the intention of this article is to describe and analyse the notion of the people of God as proposed by Pope Francis and its forms of concretisation including its deficiencies, as well as, in dialogue with ongoing debates on populism, highlight the precariousness of any “people” as a concept and as a reality. A dynamic notion of “people” and a theological accountability of the people and the clergy towards each other, towards God and towards the world can do justice to both the ambiguities and the irreplaceability of the people as citizens of the church as well as the world. Full article

The ability to quickly and accurately estimate the state of charge (SOC) of lithium batteries is a key function of the battery management system (BMS). To enhance the accuracy of SOC estimation for lithium batteries, we propose a method that combines the dynamic factor recursive least squares (DFFRLS) algorithm and the strong tracking H-infinity filtering (STF-HIF) algorithm. To address the issue of fixed forgetting factors in recursive least squares (RLS) that struggle to maintain both fast convergence and stability in battery parameter identification, we introduce dynamic forgetting factors. This approach adjusts the forgetting factor based on the residuals between the model’s estimated and actual values. To improve the H-infinity filtering (HIF) algorithm’s poor performance in tracking sudden state changes, we propose a combined STF-HIF algorithm, integrating HIF with strong tracking filtering (STF). Simulation experiments indicate that, compared to the HIF algorithm, the STF-HIF algorithm achieves a maximum absolute SOC estimation error (MaxAE) of 0.69%, 0.72%, and 1.22%, with mean absolute errors (MAE) of 0.27%, 0.25%, and 0.38%, and root mean square errors (RMSE) of 0.33%, 0.30%, and 0.46% under dynamic stress testing (DST), federal urban driving schedules (FUDS), and Beijing dynamic stress testing (BJDST) conditions, respectively. Full article

To develop agricultural risk management strategies, the early identification of water deficits during the growing cycle is critical. This research proposes a deep learning hybrid approach for multi-step soil moisture forecasting in the Bundaberg region in Queensland, Australia, with predictions made for 1-day, 14-day, and 30-day, intervals. The model integrates Geospatial Interactive Online Visualization and Analysis Infrastructure (Giovanni) satellite data with ground observations. Due to the periodicity, transience, and trends in soil moisture of the top layer, time series datasets were complex. Hence, the Maximum Overlap Discrete Wavelet Transform (moDWT) method was adopted for data decomposition to identify the best correlated wavelet and scaling coefficients of the predictor variables with the target top layer moisture. The proposed 3-phase hybrid moDWT-Lasso-LSTM model used the Least Absolute Shrinkage and Selection Operator (Lasso) method for feature selection. Optimal hyperparameters were identified using the Hyperopt algorithm with deep learning LSTM method. This proposed model’s performances were compared with benchmarked machine learning (ML) models. In total, nine models were developed, including three standalone models (e.g., LSTM), three integrated feature selection models (e.g., Lasso-LSTM), and three hybrid models incorporating wavelet decomposition and feature selection (e.g., moDWT-Lasso-LSTM). Compared to alternative models, the hybrid deep moDWT-Lasso-LSTM produced the superior predictive model across statistical performance metrics. For example, at 1-day forecast, The moDWT-Lasso-LSTM model exhibits the highest accuracy with the highest $R^2\approx 0.92469$ and the lowest RMSE $\approx 0.97808$, MAE $\approx 0.76623$, and SMAPE $\approx 4.39700$%, outperforming other models. The moDWT-Lasso-DNN model follows closely, while the Lasso-ANN and Lasso-DNN models show lower accuracy with higher RMSE and MAE values. The ANN and DNN models have the lowest performance, with higher error metrics and lower R2 values compared to the deep learning models incorporating moDWT and Lasso techniques. This research emphasizes the utility of the advanced complementary ML model, such as the developed moDWT-Lasso-LSTM 3-phase hybrid model, as a robust data-driven tool for early forecasting of soil moisture. Full article

To address the limitations in the prediction accuracy of the remaining useful life (RUL) of lithium-ion batteries, stemming from model accuracy, particle degradation, and insufficient diversity in the particle filter (PF) algorithm, this paper proposes a battery RUL prediction method utilizing a randomly perturbed unscented particle filter (RP-UPF) algorithm, based on the constructed battery capacity degradation model. The method utilizes evaluation metrics adjusted R-squared (R_adj²) and the Akaike Information Criterion (AIC) to select the battery capacity decline model C₅ with a higher goodness of fit. The initial values for constructing the C₅ model are obtained using the relevance vector machine (RVM) and nonlinear least squares methods. Based on the constructed battery capacity decline model C₅, the RP-UPF algorithm is employed to estimate the posterior parameters and iteratively approach the true battery capacity decline curve, thereby predicting the battery’s RUL. The research results indicate that, using battery B0005 as an example and starting the prediction from the 50th cycle, the RUL prediction results obtained with the RP-UPF algorithm demonstrate reductions in absolute error, relative error, and probability density function (PDF) width of 2%, 2.71%, and 10%, respectively, compared to the PF algorithm. Similar conclusions were drawn for batteries B0006 and B0018. Under the constructed battery capacity degradation model C₅, the RP-UPF algorithm shows higher prediction accuracy for battery RUL and a narrower PDF range compared to the PF algorithm. This approach effectively addresses the issue of particle weight degradation in the PF algorithm, providing a more valuable reference for battery RUL prediction. Full article