Root Mean Square Error Research Articles

Study of Five-Hundred-Meter Aperture Spherical Telescope Feed Cabin Time-Series Prediction Studies Based on Long Short-Term Memory–Self-Attention

The Five-hundred-meter Aperture Spherical Telescope (FAST), as the world’s most sensitive single-dish radio telescope, necessitates highly accurate positioning of its feed cabin to utilize its full observational potential. Traditional positioning methods that rely on GNSS and IMU, integrated with TS devices, but the GNSS and TS devices are vulnerable to other signal and environmental disruptions, which can significantly diminish position accuracy and even cause observation to stop. To address these challenges, this study introduces a novel time-series prediction model that integrates Long Short-Term Memory (LSTM) networks with a Self-Attention mechanism. This model can hold the precision of feed cabin positioning when the measure devices fail. Experimental results show that our LSTM-Self-Attention model achieves a Mean Absolute Error (MAE) of less than 10 mm and a Root Mean Square Error (RMSE) of approximately 12 mm, with the errors across different axes following a near-normal distribution. This performance meets the FAST measurement precision requirement of 15 mm, a standard derived from engineering practices where measurement accuracy is set at one-third of the control accuracy, which is around 48 mm (according to the accuracy form the official threshold analysis on the focus cabin of FAST). This result not only compensates for the shortcomings of traditional methods in consistently solving feed cabin positioning, but also demonstrates the model’s ability to handle complex time-series data under specific conditions, such as sensor failures, thus providing a reliable tool for the stable operation of highly sensitive astronomical observations.

Runoff simulation of the Kaidu River Basin based on the GR4J-6 and GR4J-6-LSTM models

Study regionThe Kaidu River Basin originates from the southern slope of the Tienshan Mountains in the Xinjiang Uygur Autonomous Region, China. Study focusAccurate runoff simulation and prediction significantly affect flood control, drought resilience, and water resource allocation decisions. This study establishes the GR4J-6 model (modèle du Génie Rural à 4 paramètres Journalier-6, including a snowmelt module) and integrates it with the LSTM (Long Short-Term Memory) model to construct the hybrid GR4J-6-LSTM model and enhance the simulation accuracy of snowmelt runoff. A case study is conducted in the Kaidu River Basin to demonstrate the applicability of these models in cold and arid regions. The accuracy of the GR4J-6, LSTM, and GR4J-6-LSTM models is evaluated using Nash-Sutcliffe efficiency (NSE), Kling-Gupta Efficiency (KGE), and Root Mean Squared Error (RMSE) metrics. In addition, the contributions of each feature variable in the models are analyzed using the SHapley Additive exPlanations (SHAP) method to enhance the reliability of the results. New hydrological insights for the regionThe GR4J-6 model demonstrated good applicability in the Kaidu River Basin, with NSE, KGE, and RMSE values of 0.69, 0.79, and 39.39 m3/s during the validation period, respectively. The hybrid model GR4J-6-LSTM exhibited the highest comprehensive accuracy among all the models, with NSE, KGE, and RMSE values of 0.84, 0.87, and 28.79 m3/s, respectively. In the LSTM model, temperature and precipitation were found to significantly influence the simulated runoff, indicating that higher temperature and precipitation lead to increased runoff. In the GR4J-6-LSTM model, Tmin (minimum temperature) and the hydrological feature variable Qsim exhibited a strong positive correlation with simulated runoff, as Tmin and Qsim increased, they promoted stronger flow production. This study provides a framework for runoff simulation in snowmelt river basins, offering a reference for projecting extreme hydrological events under climate change.

Predictive modeling of compressive strength in silica fume‐modified self‐compacted concrete: A soft computing approach

AbstractSelf‐compacting concrete (SCC) is a specialized type of concrete that features excellent fresh properties, enabling it to flow uniformly and compact under its weight without vibration. SCC has been one of the most significant advancements in concrete technology over the past two decades. In efforts to reduce the environmental impact of cement production, a major source of CO2 emissions, silica fume (SF) is often used as a partial replacement for cement. SF‐modified SCC has become a common choice in construction. This study explores the effectiveness of soft computing models in predicting the compressive strength (CS) of SCC modified with varying amounts of silica fume. To achieve this, a comprehensive database was compiled from previous experimental studies, containing 240 data points related to CS. The compressive strength values in the database range from 21.1 to 106.6 MPa. The database includes seven independent variables: cement content (359.0–600.0 kg/m3), water‐to‐binder ratio (0.22–0.51), silica fume content (0.0–150.0 kg/m3), fine aggregate content (680.0–1166.0 kg/m3), coarse aggregate content (595.0–1000.0 kg/m3), superplasticizer content (1.5–15.0 kg/m3), and curing time (1–180 days). Four predictive models were developed based on this database: linear regression (LR), multi‐linear regression (MLR), full‐quadratic (FQ), and M5P‐tree models. The data were split, with two‐thirds used for training (160 data points) and one‐third for testing (80 data points). The performance of each model was evaluated using various statistical metrics, including the coefficient of determination (R2), root mean square error (RMSE), mean absolute error (MAE), objective value (OBJ), scatter index (SI), and a‐20 index. The results revealed that the M5P‐tree model was the most accurate and reliable in predicting the compressive strength of SF‐based SCC across a wide range of strength values. Additionally, sensitivity analysis indicated that curing time had the most significant impact on the mixture's properties.

Prediction of Carbon Dioxide Concentrations in Strawberry Greenhouse by Using Time Series Models

Carbon dioxide (CO2) concentrations play an important role in plant production, as they have a direct impact on both plant growth and yield. Therefore, the objectives of this study were to predict CO2 concentrations in the greenhouse by applying time series models using five datasets. To estimate the CO2 concentrations, this study was conducted over a four-month period from 1 December 2023 to 31 March 2024, in a strawberry-cultivating greenhouse. Fifteen sensors (MCH-383SD, Lutron, Taiwan) were installed inside the greenhouse to measure CO2 concentration at 1-min intervals. Finally, the dataset was transformed into intervals of 1, 5, 10, 30, and 60 min. The time-series data were analyzed using the autoregressive integrated moving average (ARIMA) and the Prophet Forecasting Model (PFM), with performance assessed through root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2). The evaluation indicated that the best model performance was achieved with data collected at 1-min intervals, while model performance declined with longer intervals, with the lowest performance observed at 60-min intervals. Specifically, the ARIMA model outperformed across all data collection intervals while comparing with the PFM. The ARIMA model, with data collected at 1-min intervals, achieved an R2 of 0.928, RMSE of 7.359, and MAE of 2.832. However, both ARIMA and PFM exhibited poorer performances as the interval of data collection increased, with the lowest performance at 60-min intervals where ARIMA had an R2 of 0.762, RMSE of 19.469, and MAE of 11.48. This research underscores the importance of frequent data collection for precise environmental control in greenhouse agriculture, emphasizing the critical role of short-interval data collection for accurate predictive modeling.

Cross-material battery capacity estimation using hybrid-model fusion transfer learning

Evaluating battery health involves navigating the intricate interplay of physical, chemical, and electrochemical processes across multiple scales—a task that becomes even more complex with the introduction of new battery materials. This necessitates substantial development, modeling, and recalibration of boundary conditions. Our study introduces a hybrid fusion model that combines convolutional neural networks (CNNs) with self-attention mechanisms to enhance battery health assessments. In total, three datasets are involved—covering 77 LFP, 20 NMC, and 18 NCA batteries—encompassing over 170,000 cycles across a broad spectrum of battery materials and operational conditions for pre-training the base model and for transfer learning. Our findings reveal that, when transferring aging knowledge from LFP to ternary batteries (NMC and NCA) under diverse chemistries, temperatures, and operational strategies, the model achieved root mean square errors (RMSEs) of 7.47 mAh and 12.4 mAh, mean absolute percentage errors (MAPEs) of 0.67 % and 1.14 %, and coefficients of determination (R2) of 0.922 and 0.918, respectively. These results demonstrate the effectiveness of our hybrid fusion model, which uses deep transfer learning and combines CNNs with self-attention mechanisms to accurately diagnose battery capacity across various types by analyzing short cycle sequences and integrating insights throughout the cell operational history.

Personalized movie recommendation in IoT-enhanced systems using graph convolutional network and multi-layer perceptron

Exploring the optimization of communication strategies for animation films in the context of cross-cultural communication, this research integrates the Internet of Things (IoT) and convolutional networks. The research constructs a collaborative filtering (CF) movie recommendation model based on a graph convolutional neural network (GCN) and investigates its application in cross-cultural communication. The fusion of IoT and convolutional networks in movie communication is also analyzed, and the effectiveness of the proposed GCN-CF model is validated through comparative experiments. The results indicate that, compared to other models, the GCN-CF model achieves the lowest Root Mean Square Error (RMSE) on the MovieLens 100 K and MovieLens 1 M datasets, with values of 0.8762 and 0.8275, respectively. Compared to traditional models, the GCN-CF model exhibits significantly superior performance in terms of RMSE, with reductions ranging from 0.6 to 5.2%, highlighting its heightened detection accuracy and overall performance. Moreover, the performance of the GCN-CF model is enhanced after introducing attention mechanisms and auxiliary information on both datasets, showing an improvement of 0.4% compared to the scenario without these additions. This data demonstrates the effectiveness of attention mechanisms and auxiliary information. Finally, the research presents an animation film communication strategy based on IoT and convolutional networks, offering novel insights for film production and communication, along with positive implications for cultural exchange and the advancement of the global media industry.

Modeling rate of penetration using hybridization of Artificial Neural Network and Artificial Fish Swarm algorithm

This study aims to develop a robust and efficient approach for predicting the Rate of Penetration (ROP) by integrating the Artificial Fish Swarm Algorithm (AFSA) with the Back Propagation (BP) algorithm in an Artificial Neural Network (ANN). The integration of AFSA with Back Propagation is the primary novelty of this work, as it seeks to achieve optimal weight and bias values for the ANN, thereby enhancing prediction accuracy. A dataset of 1944 data points from a vertical well in southern Algeria was utilized. The performance of the developed models was evaluated using correlation coefficient and root mean square error (RMSE). The results demonstrated that the AFSA-ANN model significantly outperforms conventional ANN, Support Vector Regression (SVR), Random Forest regressor (RFR), and Bourgoyne and Young’s model in terms of accuracy. Additionally, the application of leverage method revealed that only 0.98% of the data falls outside the model’s applicability domain, indicating that the data and the model are statistically valid and reliable. The findings of this study have significant implications for the oil and gas field, providing a more accurate and reliable method for predicting ROP, which can lead to more efficient drilling operations and reduced costs.

Research on the Feasibility of Machine Learning Methods in Stock Price Prediction

Abstract: Stock price prediction has always been an important topic in financial research. Accurate price prediction can not only help investors make informed investment decisions but also enhance market stability and reduce systemic risk. In recent years, with advancements in computing technology and data science, machine learning methods have been increasingly applied in the financial field. Compared to traditional methods, machine learning methods can better handle high-dimensional, nonlinear, and large datasets, thus demonstrating higher prediction accuracy and applicability in stock price prediction.This paper reviews relevant literature and selects five models for empirical research: Support Vector Machine (SVM), Long Short-Term Memory network (LSTM), LightGBM, a combination of LSTM and LightGBM, and Convolutional Neural Network (CNN). The effectiveness of these models in predicting the stock price of Meituan-W (3690) was analyzed and compared in detail. The experimental results show that the LightGBM model performs best in terms of Mean Squared Error (MSE), Mean Absolute Error (MAE), and Root Mean Squared Error (RMSE), proving its significant advantages in handling large-scale, high-dimensional, and nonlinear data. By comparing the prediction results of different models, this paper explores the strengths and weaknesses of each model and their feasibility and effectiveness in practical applications. Machine learning methods have significant potential in stock price prediction, model selection needs to comprehensively consider data characteristics, computational resources, and practical application scenarios.

Mapping the Normalized Difference Vegetation Index for the Contiguous U.S. Since 1850 Using 391 Tree-Ring Plots

The forests and grasslands in the U.S. are vulnerable to global warming and extreme weather events. Current satellites do not provide historical vegetation density images over the long term (more than 50 years), which has restricted the documentation of key ecological processes and their resultant responses over decades due to the absence of large-scale and long-term monitoring studies. We performed point-by-point regression and collected data from 391 tree-ring plots to reconstruct the annual normalized difference vegetation index (NDVI) time-series maps for the contiguous U.S. from 1850 to 2010. Among three machine learning approaches for regressions—Support Vector Machine (SVM), General Regression Neural Network (GRNN), and Random Forest (RF)—we chose GRNN regression to simulate the annual NDVI with lowest Root Mean Square Error (RMSE) and highest adjusted R2. From the Little Ice Age to the present, the NDVI increased by 6.73% across the contiguous U.S., except during some extreme events such as the Dust Bowl drought, during which the averaged NDVI decreased, particularly in New Mexico. The NDVI trend was positive in the Northern Forest, Tropical Humid Forest, Northern West Forest Mountains, Marin West Coast Forests, and Mediterranean California, while other ecoregions showed a negative trend. At the state level, Washington and Louisiana had significantly positive correlations with temperature (p < 0.05). Washington had a significantly negative correlation with precipitation (p < 0.05), whereas Oklahoma had a significantly positive correlation (p < 0.05) with precipitation. This study provides insights into the spatial distribution of paleo-vegetation and its climate drivers. This study is the first to attempt a national-scale reconstruction of the NDVI over such a long period (151 years) using tree rings and machine learning.

Advanced hybrid neural network techniques for minimizing gas turbine emissions

Purpose Emissions have significant environmental impacts. Hence, minimizing emissions is essential. This study aims to use a hybrid neural network model to predict carbon monoxide (CO) and nitrogen oxide (NOx) emissions from gas turbines (GTs) to enhance emission prediction for GTs in predictive emissions monitoring systems (PEMS). Design/methodology/approach The hybrid model architecture combines convolutional neural networks (CNN) and bidirectional long-short-term memory (Bi-LSTM) networks called CNN-BiLSTM with modified extrinsic attention regression. Over five years, data from a GT power plant was uploaded to Google Colab, split into training and testing sets (80:20), and evaluated using test matrices. The model’s performance was benchmarked against state-of-the-art emissions prediction methodologies. Findings The model showed promising results for GT CO and NOx emissions. CO predictions had a slight underestimation bias of −0.01, with root mean-squared error (RMSE) of 0.064, mean absolute error (MAE) of 0.04 and R2 of 0.82. NOx predictions had an RMSE of 0.051, MAE of 0.036, R2 of 0.887 and a slight overestimation bias of +0.01. Research limitations/implications While the model demonstrates relative accuracy in CO emission predictions, there is potential for further improvement in future research. Practical implications Implementing the model in real-time PEMS and establishing a continuous feedback loop will ensure accuracy in real-world applications, enhance GT functioning and reduce emissions, fuel consumption and running costs. Social implications Accurate GT emissions predictions support stricter emission standards, promote sustainable development goals and ensure a healthier societal environment. Originality/value This paper presents a novel approach that integrates CNN and Bi-LSTM networks. It considers both spatial and temporal data to mitigate previous prediction shortcomings.

A Comprehensive Investigation on Catalytic Behavior of Anaerobic Jar Gassing Systems and Design of an Enhanced Cultivation System

The rapid and reliable diagnosis of anaerobic bacteria constitutes one of the key procedures in clinical microbiology. Automatic jar gassing systems are commonly used laboratory instruments for this purpose. The most critical factors affecting the cultivation performance of these systems are the level of residual oxygen remaining in the anaerobic jar and the reaction rate determined by the Pd/Al2O3 catalyst. The main objective of the presented study is to design and manufacture an enhanced jar gassing system equipped with an extremum seeking-based estimation algorithm that combines real-time data and a reaction model of the Pd/Al2O3 catalyst. The microkinetic behavior of the palladium catalyst was modeled through a learning-from-experiment methodology. The majority of microkinetic model parameters were derived from material characterization analysis. A comparative validation test of the designed cultivation system was conducted using conventional gas pouches via six different bacterial strains. The results demonstrated high cell viability, with colony counts ranging from 1.26 × 105 to 2.17 × 105 CFU mL−1. The favorable catalyst facets for water formation on Pd surfaces and the crystal structure of Pd/Al2O3 pellets were identified by X-ray diffraction analysis (XRD). The doping ratio of the noble metal (Pd) and the support material (Al2O3) was validated via energy-dispersive spectroscopy (EDS) measurements as 0.68% and 99.32%, respectively. The porous structure of the catalyst was also analyzed by scanning electron microscopy (SEM). During the reference clinical trial, the estimation algorithm was terminated after 878 iterations, having reached its predetermined termination value. The measured and modelled reaction rates were found to converge with a root-mean-squared error (RMSE) of less than 10−4, and the Arrhenius parameters of ongoing catalytic reaction were obtained. Additionally, our research offers a comprehensive analysis of anaerobic jar gassing systems from an engineering perspective, providing novel insights that are absent from the existing literature.

Validity of wearable sensors for total knee arthroplasty (TKA) rehabilitation: A study in younger and older healthy participants

BackgroundWith 100,000 total knee arthroplasty (TKA) procedures taking place in the United Kingdom annually, the demand on rehabilitation services is high. Most regimes are home-based. Without clinician-patient interaction, detection of rehabilitation concerns can be delayed, reducing the chance of successful early intervention. Wearable technologies, such as MotionSenseTM (Stryker, US), may offer a solution to this problem by remotely supporting post-operative TKA rehabilitation through the provision of personalised rehabilitation and tracking of home exercises, enabling healthcare professionals to continuously monitor rehabilitation progress remotely. Validation of such devices against a known kinematic model in activities of daily living is important for confident interpretation of resulting clinical data. The aim of this study therefore was to validate the accuracy of MotionSenseTM against a clinical motion capture standard. MethodsTwenty younger and 14 older healthy, able-bodied adults attended one testing session (Younger: 24 ± 4 years old; Older: 71 ± 5 years old). Movement was tracked using Vicon motion analysis and a Plug-In-Gait lower body model was applied to all participants. Three activities were performed – walking, stair ascent, stair descent. The knee flexion angle root mean square error (RMSE) between the technologies was determined. ResultsFor both groups the knee flexion RMSE remained below 3° for all activities. The combined RMSE for all adults was 2.4° for walking, 2.7° for stair ascent, and 2.6° for stair descent. The signed error increased during the swing phase of gait. ConclusionMotionSenseTM was found to accurately estimate knee flexion angles during several common activities compared to Vicon motion capture.

Comparison of Prior Distributions for the Heterogeneity Parameter in a Rare Events Meta-Analysis of a Few Studies.

Bayesian meta-analysis is a promising approach for rare events meta-analysis. However, the inference of the overall effect in rare events meta-analysis is sensitive to the choice of prior distribution for the heterogeneity parameter. Therefore, it is crucial to assign a convincing prior specification and ensure that it is both plausible and transparent. Various priors for the heterogeneity parameter have been proposed; however, the comparative performance of alternative prior specifications in rare events meta-analysis is poorly understood. Based on a binomial-normal hierarchical model, we conducted a comprehensive simulation study to compare seven heterogeneity prior specifications for binary outcomes, using the odds ratio as the metric. We compared their performance in terms of coverage, median percentage bias, width of the 95% credible interval, and root mean square error (RMSE). We illustrate the results with two recently published rare events meta-analyses of a few studies. The results show that the half-normal prior (with a scale of 0.5), the prior proposed by Turner etal. for the general healthcare setting (without restriction to a specific type of outcome) and for the adverse event setting perform well when the degree of heterogeneity is not relatively high, yielding smaller bias and shorter interval widths with similar coverage and RMSE in most cases compared to other prior specifications. None of the priors performed better when the heterogeneity between-studies were significantly extreme.

A satellite-derived bathymetry method combining depth invariant index and adaptive logarithmic ratio: A case study in the Xisha Islands without in-situ measurements

Accurate bathymetric data is crucial for various aspects such as marine resource exploitation and marine ecological conservation. Currently, satellite-derived bathymetry (SDB) based on empirical and physical models has been widely utilized in constructing underwater terrain in shallow seas. However, the application of such SDB models is limited in remote island reef areas lacking in-situ measurement data. To overcome this issue, the manuscript proposes an unconstrained SDB optimization method without in-situ measurement data, utilizing satellite multispectral imagery (Geoeye-1) and spaceborne LiDAR data (ICESat-2). By classifying the seafloor substrate in coral reef areas into sandy and coral, based on the depth invariant index (DII), we employ an adaptive logarithmic ratio model for unconstrained SDB. The ICESat-2 LiDAR data are then used to correct the SDB results, achieving bathymetry optimization in the coral reef area of the Xisha Islands. Additionally, the proposed method is applied to Yuanzhi Island of the Xisha Islands, and the accuracy of the bathymetric results is evaluated against ALB (Airborne LiDAR Bathymetry) data. The findings demonstrate that compared to conventional methods, our method can improve the accuracy of SDB results with good adaptability. In the Yuanzhi Island area, the proposed method yields SDB results with an R2 of 0.93, an MAE (Mean Absolute Error) of 0.94, and an RMSE (Root Mean Square Error) of 1.12 m, compared to ALB data. The average error is less than 10 % of the maximum depth, essentially meeting the requirements of the International Hydrographic Organization (IHO) standards for depth measurement error when depth is <20 m. This study can offer a novel approach for enhancing bathymetric accuracy around offshore and remote islands, where gathering underwater terrain data is challenging.

A Modified Johnson Cook Model-Based Kalman Filter Method to Determine the Hot Flow Behavior of Sustainable AA6082 Al Alloy

AA6082 alloys play a significant role in advancing sustainable development goals (SDGs) by contributing to environmental sustainability, economic growth, and social well-being. These alloys are highly recyclable and align with SDG 12 by promoting resource efficiency and reducing waste. Their application in lightweight vehicles and improving energy efficiency in construction supports SDG 9 and SDG 11, as they help reduce carbon emissions and enhance the sustainability of urban environments. While AA6082 alloys offer significant advantages, their use has limitations that can hinder their industrial applications. One key challenge is their lower formability, particularly at room temperature. Elevated-temperature deformation is frequently employed to enhance the formability of these alloys and address their limitations. Thus, a deep understanding of the constitutive analysis of these alloys under a wide range of T and ε is essential for manufacturing sound components from these alloys. Thus, this study aims to propose a new modification for the JC model (PJCM) and compare its reliability to predict the warm/hot flow behavior of AA6082 alloys with that of the original JC model (OJCM) and the modified JC model by Lin et al. (LMJCM). By comparing the experimental results with these model results and confirming the determining correlation coefficient (R), average absolute relative error (AARE), and root mean square error (RMSE) values, it is concluded that the stresses predicted by the PMJCM closely match the experimental stresses of the LMJCM and OJCM because of the interaction between ε, ε, and T, which might be a reason for the complex nonlinear behavior of AA6082 alloys during hot deformation.

Enhanced Collaborative Filtering: Combining Autoencoder and Opposite User Inference to Solve Sparsity and Gray Sheep Issues

In recent years, the study of recommendation systems has become crucial, capturing the interest of scientists and academics worldwide. Music, books, movies, news, conferences, courses, and learning materials are some examples of using the recommender system. Among the various strategies employed, collaborative filtering stands out as one of the most common and effective approaches. This method identifies similar active users to make item recommendations. However, collaborative filtering has two major challenges: sparsity and gray sheep. Inspired by the remarkable success of deep learning across a multitude of application areas, we have integrated deep learning techniques into our proposed method to effectively address the aforementioned challenges. In this paper, we present a new method called Enriched_AE, focused on autoencoder, a well-regarded unsupervised deep learning technique renowned for its superior ability in data dimensionality reduction, feature extraction, and data reconstruction, with an augmented rating matrix. This matrix not only includes real users but also incorporates virtual users inferred from opposing ratings given by real users. By doing so, we aim to enhance the accuracy of predictions, thus enabling more effective recommendation generation. Through experimental analysis of the MovieLens 100K dataset, we observe that our method achieves notable reductions in both RMSE (Root Mean Squared Error) and MAE (Mean Absolute Error), underscoring its superiority over the state-of-the-art collaborative filtering models.

Predicting interfacial tension in brine-hydrogen/cushion gas systems under subsurface conditions: Implications for hydrogen geo-storage

Underground hydrogen storage (UHS) critically relies on cushion gas to maintain pressure balance during injection and withdrawal cycles, prevent excessive water inflow, and expand storage capacity. Interfacial tension (IFT) between brine and hydrogen/cushion gas mixtures is a key factor affecting fluid dynamics in porous media. This study develops four machine learning models— Decision Trees (DT), Random Forests (RF), Support Vector Machines (SVM), and Multi-Layer Perceptrons (MLP)—to predict IFT under geo-storage conditions. These models incorporate variables such as pressure, temperature, molality, overall gas density, and gas composition to evaluate the impact of different cushion gases. A group-based data splitting method enhances the realism of our tests by preventing information leakage between training and testing datasets. Shapley Additive Explanations (SHAP) reveal that while the MLP model prioritizes gas composition, the RF model focuses more on operational parameters like pressure and temperature, showing distinct predictive dynamics. The MLP model excels, achieving coefficients of determination (R2) of 0.96, root mean square error (RMSE) of 2.10 mN/m, and average absolute relative deviation (AARD) of 3.25%. This robustness positions the MLP model as a reliable tool for predicting IFT values between brine and hydrogen/cushion gas (es) mixtures beyond the confines of the studied dataset. The findings of this study present a promising approach to optimizing hydrogen geo-storage through accurate predictions of IFTs, offering significant implications for the advancement of energy storage technologies.

Experimental and numerical evaluation of soil water and salt dynamics in a corn field with shallow saline groundwater and crop-season drip and autumn post-harvest irrigations

In areas with shallow saline groundwater, soil salts inevitably accumulate in the root zone during the growth period due to irrigation and upward movement of salts from the groundwater. In Northern China, autumn irrigation (AIR) with large amounts of water is commonly employed post-harvest to mitigate soil salt stress on crop growth in the subsequent year. Optimizing the total irrigation depth during both crop-growth and non-growth periods is challenging because of the movement of soil salts, which is influenced by their two-dimensional distribution around drippers and the impact of the winter freeze-thaw cycles, significantly affecting water flow and solute transport during winter. In this study, the HYDRUS-1D and HYDRUS-2D models were integrated and calibrated using experimental data collected from 2021 to 2023 in China's Ordos south bank irrigation area. This model integration was conducted to assess soil water and salt dynamics during the non-growth and corn-growth periods under different irrigation strategies: a) AIR with high (AH) and low (AL) irrigation depths, and b) drip irrigation (DIR) with high (DH), medium (DM), and low (DL) irrigation depths. The results indicated that HYDRUS effectively modeled the electrical conductivity of the saturation paste extract (ECe) across different irrigation strategies, yielding an average coefficient of determination (R2) and the root mean square errors (RMSE) of 0.87 and 0.53 dS m−1, respectively. Generally, ECe increased during the growth period with DIR and decreased during the non-growth period with AIR. For the 0–40 cm soil layer, ECe decreased by 5.7 % and 12 % for every 100 mm increase in the AIR and DIR depths, respectively. Compared with the AHDM and AHDL treatments, reducing an AIR depth and increasing a DIR depth resulted in lower ECe in the 0–40 cm layer during the growth period and higher crop yield (CY) and irrigation water productivity (WPI). Specifically, the average ECe in the 0–40 cm layer decreased by 4.8 % during the growth period in the ALDH treatment compared to the AHDM treatment, and CY and WPI increased by 7.2 % and 10.3 %, respectively. Additionally, the irrigation strategy was the most effective in reducing ECe when AIR accounted for 35 % of the total irrigation. This study suggested that combining low AIR and high DIR could enhance water and field productivity.

Automating cancer diagnosis using advanced deep learning techniques for multi-cancer image classification

Cancer detection poses a significant challenge for researchers and clinical experts due to its status as the leading cause of global mortality. Early detection is crucial, but traditional cancer detection methods often rely on invasive procedures and time-consuming analyses, creating a demand for more efficient and accurate solutions. This paper addresses these challenges by utilizing automated cancer detection through AI-based techniques, specifically focusing on deep learning models. Convolutional Neural Networks (CNNs), including DenseNet121, DenseNet201, Xception, InceptionV3, MobileNetV2, NASNetLarge, NASNetMobile, InceptionResNetV2, VGG19, and ResNet152V2, are evaluated on image datasets for seven types of cancer: brain, oral, breast, kidney, Acute Lymphocytic Leukemia, lung and colon, and cervical cancer. Initially, images undergo segmentation techniques, proceeded by contour feature extraction where parameters such as perimeter, area, and epsilon are computed. The models are rigorously evaluated, with DenseNet121 achieving the highest validation accuracy as 99.94%, 0.0017 as loss, and the lowest Root Mean Square Error (RMSE) values as 0.036056 for training and 0.045826 for validation. These results revealed the capability of AI-based techniques in improving cancer detection accuracy, with DenseNet121 emerging as the most effective model in this study.

Hysteresis Compensation and Trajectory Tracking Control Model for Pneumatic Artificial Muscles

The optimum performance position control of pneumatic artificial muscles (PAM) is restricted by their in-built hysteresis and nonlinearity. The hysteresis is usually depicted by a phenomenological model, while the model mentioned above always only describes the hysteresis phenomenon under certain conditions. Thus, the universality of the compensator is due to its weakness in handling disparate outside conditions. Our research employs the FN–QUPI (feedforward neural network–quadratic unparallel Prandtl–Ishlinskii) model to depict the phenomenon of pressure-displacement hysteresis in PAMs. This model has high-precision expression and generalization ability for the PAM hysteresis phenomenon. According to this, an inverse model of the QUPI operator is established as a feedforward control while combining with the feedback control of incremental PID-type iterative learning. The results show that due to the hysteresis of PAM, the compound control of feedforward control and iterative learning has better tracking performance than the ordinary PID compound control in terms of convergence rate and stability. According to the mean absolute error (MAE) and root mean square error (RMSE) of the tracking process, it can be seen that the control model can achieve accurate nonlinear compensation, and the control system shows excellent robustness to different input signals.