Search

Present report demonstrates the application of Sb 0.3 Sn 0.7 Se 2 single crystal as a paper based flexible photodetector. Direct vapour transport grown bulk crystals of Sb 0.3 Sn 0.7 Se 2 has been converted to nanosheets by chemical assisted exfoliation process. The paper-based photodetector is fabricated and the switching action is studied. Tuning of photodetector has been carried out by 670 nm laser illumination for different bias voltages. Temporal photo-response is also studied under polychromatic light with different intensities in vacuum and open environment. The low temperature stability of photodetector has been studied for temperature range 300 K–180 K. Experimental results are obtained in terms of time resolved photocurrent under different illumination and atmospheric conditions. The flexibility and stability are also examined in detail for fabricated detector. Overall, the results suggest the application of Sb 0.3 Sn 0.7 Se 2 as a versatile flexible photodetector. Additionally, the machine learning (ML) model is trained and tested using an experimental photocurrent dataset that has a complex material design with variations in time, bias voltage, intensity, and temperature. The k-nearest neighbor algorithm exhibited outstanding performance, achieving the highest R2 value of 0.9986 when applied to a temperature dataset, with a test size of 0.4. Performance metrics such as mean absolute error and root mean squared error of various test sizes ranging from 0.4 to 0.6 are used to assess the model's accuracy and robustness in changing conditions. This comprehensive analysis not only establishes a platform for future experimental optimization of photodetector materials but also underscores the efficacy of ML regression techniques in developing high-performance photodetectors. [Display omitted] • Chemical assisted exfoliation process were used for the synthesis of SbSnSe2 nanosheets. • Synthesized nanosheets were decorated on paper for the fabrication of flexible photo-detector. • The photodetection application was demonstrated for different atmospheric conditions and different illuminations. • Low temperature stability of the detector was also studied. • KNN Machine learning model were applied to the experimental data for the prediction of photodetection behavior. [ABSTRACT FROM AUTHOR]

Tool condition monitoring technology is an indispensable part of intelligent manufacturing. Most current research focuses on complex signal processing techniques or advanced deep learning algorithms to improve prediction performance without fully leveraging the end-to-end advantages of deep learning. The challenge lies in transforming multi-sensor raw data into input data suitable for direct model feeding, all while minimizing data scale and preserving sufficient temporal interpretation of tool wear. However, there is no clear reference standard for this so far. In light of this, this paper innovatively explores the processing methods that transform raw data into input data for deep learning models, a process known as an input paradigm. This paper introduces three new input paradigms: the downsampling paradigm, the periodic paradigm, and the subsequence paradigm. Then an improved hybrid model that combines a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) was employed to validate the model's performance. The subsequence paradigm demonstrated considerable superiority in prediction results based on the PHM2010 dataset, as the newly generated time series maintained the integrity of the raw data. Further investigation revealed that, with 120 subsequences and the temporal indicator being the maximum value, the model's mean absolute error (MAE) and root mean square error (RMSE) were the lowest after threefold cross-validation, outperforming several classical and contemporary methods. The methods explored in this paper provide references for designing input data for deep learning models, helping to enhance the end-to-end potential of deep learning models, and promoting the industrial deployment and practical application of tool condition monitoring systems. [ABSTRACT FROM AUTHOR]

The maturity grading of walnuts during harvesting relies on experience. In this paper, walnut images in a natural environment were collected to construct a dataset, and deep learning algorithms were utilized to combine walnut internal physical and chemical indicators to carry out research on walnut maturity detection methods and further research on walnut oil content prediction by combining walnut images with walnut oil content indicators. The main contents of this paper include collecting walnut images in a natural environment, constructing datasets, and using deep learning algorithms combined with internal physical and chemical indexes of walnuts to study walnut maturity detection and oil content prediction methods. First, two walnut image acquisition schemes were designed, and a total of 9504 images were collected from 23 August to 21 September 2021. The dataset was expanded to 18,504 images through data preprocessing and image enhancement. A self-supervised Gaussian attention network (GATCluster) walnut ripeness detection method based on image clustering is proposed to develop ripeness criteria through unsupervised clustering, and the accuracy of the criteria is verified by analysis of variance (ANOVA). The maturity detection accuracy of the test set of 1500 images is 88.33%. Secondly, a walnut oil content prediction method based on improved ResNet34 is proposed. The feature extraction capability is improved by introducing the Squeeze-and-Excitation Networks (SENet) channel attention mechanism and the convolutional self-attention module. The prediction results on 50 images show that the root mean square error, average absolute percentage error, and regression coefficient are 2.96, 0.103, and 0.8822, respectively. The experiments show that the method performs well in predicting the oil content of walnuts at different maturity levels. [ABSTRACT FROM AUTHOR]

The expeditious and precise prediction of stress variations in nonlinear boom structures is paramount for ensuring the safe, dependable, and effective operation of pump trucks. Nonetheless, balancing prediction accuracy and efficiency by constructing a suitable machine-learning model remains a challenge in engineering practice. To this end, this paper introduces an interpretable fusion model named RS–XGBoost–RF (Random Search–Extreme Gradient Boosting Tree–Random Forest) and develops an intelligent algorithm for the stress prediction of the nonlinear boom structure of concrete pump trucks. Firstly, an information acquisition system is deployed to collect relevant data from the boom systems of ZLJ5440THBBF 56X-6RZ concrete pump trucks during its operational phase. Data pre-processing is conducted on the 2.4 million sets of acquired data. Then, a sample dataset of typical working conditions is obtained. Secondly, the RS algorithm, RF model, and XGBoost model are selected based on their complementary strengths to construct the fusion model. The model fusion condition is established with a focus on prediction efficiency. By leveraging the synergy between search and prediction mechanisms, the RS–XGBoost model is constructed for the prediction of the master hyperparameters of the RF model. This model uses the random search (RS) process to obtain the mapping between the loss function and the hyperparameters. This mapping relationship is then learned using the XGBoost model, and the hyperparameter value with the smallest loss value is predicted. Finally, the RS–XGBoost–RF model with optimized hyperparameters is employed to achieve rapid stress prediction at various detection points of the nonlinear boom structure. The findings demonstrate that, within the acceptable prediction efficiency for engineering practice, the fitting accuracy (R2) of the RS–XGBoost–RF model consistently exceeds 0.955 across all measurement points, with only a few exceptions. Concerning the stress magnitudes themselves, the mean absolute error (MAE) and root mean square error (RMSE) are maintained within the ranges of 2.22% to 3.91% and 4.79% to 7.85%, respectively. In comparison with RS–RF–RF, RS–RF–XGBoost, and RS–XGBoost–XGBoost, the proposed model exhibits the optimal prediction performance. The method delineated in this paper offers valuable insights for expeditious structural stress prediction in the realm of inherent safety within construction machinery. [ABSTRACT FROM AUTHOR]

Accurate prediction of taxiing time is important in ensuring efficient and safe operations on the airport surface. It helps improve ground operation efficiency, reduce fuel waste, and improve carbon emissions at the airport. In actual operations, taxiing time is influenced by various factors, including a large number of categorical features. However, few previous studies have focused on selecting such features. Additionally, traditional taxiing time prediction methods are often black-box models that only provide a single prediction result; they fail to provide effective practical references for controllers. Therefore, this paper analyses the features that affect taxiing time from different data types and forms a taxi feature set consisting of nine key features. We also propose a taxiing time prediction method based on adaptive scenario matching rules. This process classifies the scenarios into multiple typical historical scenario sets and adaptively matches the current target scenario to a typical scenario set based on quantified rules. Then, based on the matching results, a pre-trained model obtained from the corresponding scenario set is used to predict the taxiing time of an aircraft in the target scenario, aiming to mitigate the impact of data heterogeneity on prediction results. Experimental results show that compared to baseline methods, the mean absolute error and root mean square error of the proposed method decreased by 4.8% and 12.6%, respectively. This method significantly reduces the fluctuations in results caused by sample heterogeneity and enhances controllers' acceptance of prediction results from the model. It can be used to further improve auxiliary decision making systems and enhance the precise control capabilities of airport surface operations. [ABSTRACT FROM AUTHOR]

Conventional aquaponics conserve water used in aquaponics whereas the literature suggests a certain level of freshwater replenishment or freshwater exchange for good water quality, fish and plant wellbeing, and the overall productivity of the system. This paper deals with the determination of an optimal freshwater replenishment rate for a standard aquaponics system. IoT devices and sensors were used for this project data collection. This paper used linear regressions and ensemble methods to determine the optimal rate of periodic water replenishment to maintain the water quality parameters that determine the yield and productivity of aquaponics systems. Cubic spline and Lagrange interpolation were applied to raw and simulated data. Results were evaluated and compared using statistical error estimation approaches. The bestmodel amongst the investigated machine learning models was gradient boost with an optimal replenishment rate of 19L per week and a water quality of 4.86 for an aquaponic tank of 100 L capacity. The error estimations were a Mean Squared Error of 0.0224, Mean Absolute Error of 0.1137, Root Mean Squared Error of 0.1499, and R2 of 0.7208. This was within 1% of the value obtained fromraw and interpolated data using a polynomial regression. These findings suggest that the water quality of an aquaponics system can be maintained at the desired optimal level with a weekly 19% water replenishment, thereby contributing to the improvement of productivity and resource efficiency. [ABSTRACT FROM AUTHOR]

This paper addresses a notable gap in the field of photovoltaic system forecasting by introducing the Machine Learning-based PV Prediction and Fault Analysis System (ML-PVPFAS). This framework is designed to optimize the decomposition of variational systems automatically, using a multi-objective intelligent optimization method to establish its weight. The paper evaluates a range of Machine Learning (ML) and Ensemble Learning (EL) techniques for diagnosing faults in PV arrays, with a primary focus on identifying and categorizing complex faults that could affect these arrays. These faults encompass multiple anomalies and defects with similar current-voltage curves, which have not been previously examined. The analysis of prediction scores reveals that the ML-PVPFAS approach outperforms other methods, with the lowest Mean Absolute Percentage Error (MAPE) at 4.93, Root Mean Squared Error (RMSE) at 4.64, high Accuracy at 90.31%, Precision at 93.60%, a strong Pearson Correlation Coefficient of 0.90, and a fast Computation Time of 77.64 milliseconds. The results suggest that ML-PVPFAS is a dependable and practical algorithm for predicting the power output of PV solar systems, making it a valuable contribution to the field of predictive modeling. [ABSTRACT FROM AUTHOR]

In shallow water, Sentinel-2 multispectral imagery has only four visible bands and limited quantization levels, which easily leads to the occurrence of the same spectral profile but different depth (SSPBDD) phenomenon, resulting in a one-to-many relationship between water depth and spectral profile. Investigating the impact of this relationship on water depth inversion models is the main objective of this paper. The Stumpf model and three machine learning models (Random Forest, Support Vector Machine, and Mixture Density Network) are employed, and the performance of these models is analysed based on the spatial distribution of the training dataset and the input information composition of these models. The results show that the root mean square errors (RMSEs) of the depth inversion of Random Forest and Support Vector Machine are significantly affected by the spatial distribution of the training dataset, while minimal effects are observed for the Stumpf model and the Mixture Density Network model. The SSPBDD phenomenon is widespread in Sentinel-2 images at all depths, particularly between 5 m and 15 m, with most of the depth maximum difference of the SSPBDD pixels ranging from 0 to 5 m. The SSPBDDs phenomenon can significantly reduce the inversion accuracy of any model. The number and the depth maximum difference of the SSPBDDs pixels are the main influencing factors. However, by increasing the visible spectral information and the spatial neighbourhood information in the input layer of machine learning models, the inversion accuracy and stability of the models can be improved to a certain extent. Among the models, the Mixture Density Network achieves the best inversion accuracy and stability. [ABSTRACT FROM AUTHOR]

As the demand for electricity, electrification, and renewable energy rises, accurate forecasting and flexible energy management become imperative. Distribution network operators face capacity limits set by regional grids, risking economic penalties if exceeded. This study examined data-driven approaches of load forecasting to address these challenges on a city scale through a use case study of Eskilstuna, Sweden. Multiple Linear Regression was used to model electric load data, identifying key calendar and meteorological variables through a rolling origin validation process, using three years of historical data. Despite its low cost, Multiple Linear Regression outperforms the more expensive non-linear Light Gradient Boosting Machine, and both outperform the "weekly Naïve" benchmark with a relative Root Mean Square Errors of 32–34% and 39–40%, respectively. Best-practice hyperparameter settings were derived, and they emphasize frequent re-training, maximizing the training data size, and setting a lag size larger than or equal to the forecast horizon for improved accuracy. Combining both models into an ensemble could the enhance accuracy. This paper demonstrates that robust load forecasts can be achieved by leveraging domain knowledge and statistical analysis, utilizing readily available machine learning libraries. The methodology for achieving this is presented within the paper. These models have the potential for economic optimization and load-shifting strategies, offering valuable insights into sustainable energy management. [ABSTRACT FROM AUTHOR]

Purpose: This paper explores different machine learning (ML) algorithms for analyzing diffusion nuclear magnetic resonance imaging (dMRI) models when analytical fitting shows restrictions. It reviews various ML techniques for dMRI analysis and evaluates their performance on different b-values range datasets, comparing them with analytical methods. Materials and Methods: After standard fitting for reference, four sets of diffusion-weighted nuclear magnetic resonance images were used to train/test various ML algorithms for prediction of diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion fraction (f), and kurtosis (K). ML classification algorithms, including extra-tree classifier (ETC), logistic regression, C-support vector, extra-gradient boost, and multilayer perceptron (MLP), were used to determine the existence of diffusion parameters (D, D*, f, and K) within single voxels. Regression algorithms, including linear regression, polynomial regression, ridge, lasso, random forest (RF), elastic-net, and support-vector machines, were used to estimate the value of the diffusion parameters. Performance was evaluated using accuracy (ACC), area under the curve (AUC) tests, and cross-validation root mean square error (RMSECV). Computational timing was also assessed. Results: ETC and MLP were the best classifiers, with 94.1% and 91.7%, respectively, for the ACC test and 98.7% and 96.3% for the AUC test. For parameter estimation, RF algorithm yielded the most accurate results The RMSECV percentages were: 8.39% for D, 3.57% for D*, 4.52% for f, and 3.53% for K. After the training phase, the ML methods demonstrated a substantial decrease in computational time, being approximately 232 times faster than the conventional methods. Conclusions: The findings suggest that ML algorithms can enhance the efficiency of dMRI model analysis and offer new perspectives on the microstructural and functional organization of biological tissues. This paper also discusses the limitations and future directions of ML-based dMRI analysis. [ABSTRACT FROM AUTHOR]

Despite the complexity of thermodynamic models in predicting wax precipitation, they have not shown satisfactory results in the literature. This paper proposes the least-squares support vector machine optimized by the genetic algorithm to forecast wax precipitation based on the mole fractions, specific gravity, and temperature of crude oil samples. The genetic algorithm was used to prevent sticking in local optima in optimizing the parameters of the predictive model. A dataset of 88 experimental wax precipitation samples was used to evaluate the performance of the proposed method. The results revealed that the suggested algorithm could predict wax precipitation with an accuracy of 0.939 and 0.997 before and after sensitivity analysis, respectively. Furthermore, sensitivity analysis improved the Coefficient of Determination, Mean Squared Error, and Root Mean Squared Error from 0.939, 0.768, and 0.877 to 0.997, 0.041, and 0.202, respectively. The results were compared with the results of previous data-driven and mathematical models that showed the outperformance of the proposed method. The contribution of this paper can be summarized as demonstrating the ability of intelligent models to predict wax precipitation without a need for complex thermodynamic models. Also, it was shown that a proper feature selection could improve the model's performance. [ABSTRACT FROM AUTHOR]

Quantitative analysis of rock samples using laser-induced breakdown spectroscopy (LIBS) is a challenging task due to the significant differences in spectra between pressed pellet samples and rock samples, with pressed pellet samples usually exhibiting stronger spectral lines. The predictive ability of LIBS quantitative analysis models for rock samples is poorer compared to that for pressed pellet samples, and quantitative analysis models constructed using pressed pellet samples cannot be directly applied to predict the composition of rock samples. To address the issue, a quantitative analysis method for raw rocks based on feature transfer learning using transfer component analysis (TCA) is proposed in this paper. By establishing a feature mapping relationship between pressed pellet samples and rock samples, the differences between data features are reduced, thus enabling the training of a more quantitative analysis model. The transfer learning was introduced into a multivariate regression machine learning model for training using pressed pellet samples, which successfully addresses the problem of prediction accuracy of rock sample element contents. In this model, all data were mapped to a high-dimensional reproducing kernel Hilbert space, and a subset of the most similar features was selected to train the quantitative analysis model. Upon testing the model with independent rock samples, the difference between the predicted and true values was significantly reduced. The model yielded a root mean square error of prediction (RMSEP) of 3.7131, 1.0185, 0.2985, 13.0439, and 1.5450 for Si, Al, Fe, Ca, and Mg in rock samples, respectively. These results indicate that LIBS coupled with the transfer learning algorithm can effectively eliminate the differences between the spectra of the pressed pellet and the raw rock and provide another idea for in situ LIBS detection. [ABSTRACT FROM AUTHOR]

Fake social media profiles are responsible for various cyber-attacks, spreading fake news, identity theft, business and payment fraud, abuse, and more. This paper aims to explore the potential of Machine Learning in detecting fake social media profiles by employing various Machine Learning algorithms, including the Dummy Classifier, Support Vector Classifier (SVC), Support Vector Classifier (SVC) kernels, Random Forest classifier, Random Forest Regressor, Decision Tree Classifier, Decision Tree Regressor, MultiLayer Perceptron classifier (MLP), MultiLayer Perceptron (MLP) Regressor, Naïve Bayes classifier, and Logistic Regression. For a comprehensive evaluation of the performance and accuracy of different models in detecting fake social media profiles, it is essential to consider confusion matrices, sampling techniques, and various metric calculations. Additionally, incorporating extended computations such as root mean squared error, mean absolute error, mean squared error and cross-validation accuracy can further enhance the overall performance of the models. [ABSTRACT FROM AUTHOR]

Electric vehicles (EVs) are expected to be vital in transitioning to a low-carbon energy system. However, integrating EVs into the power grid poses significant challenges for grid operators and energy suppliers, especially regarding the uncertainty and variability of EV charging demand. Accurate forecasting of EV charging demand is essential for optimal power system integration, yet previous studies have often only considered point predictions that are inadequate for risk assessment. Therefore, this paper compares different probabilistic forecasting models for the short-term prediction of EV charging demand at various aggregation levels, using a large and novel dataset of over 350,000 charging processes at more than 500 locations across Germany. The performance of both machine learning and deep learning methods is evaluated against a naïve benchmark model, and the impact of data availability on the forecasting models is investigated. Further, the paper examines the effects of forecast accuracy on energy procurement, which has so far received minor attention in the literature. The results show that machine learning methods such as Ada Boosting and Random Forest yield robust results with a normalized root mean square error of 0.42 and 0.41 and a mean absolute scaled error of 0.36 and 0.34 at the highest aggregation level. Furthermore, the results show the influence of different site compositions on the forecast quality and how many charging points are likely to yield a robust forecast. Energy and fleet managers can use the described method to reliably predict the required energy quantities for fleets of sufficient size and procure them at low risk. [ABSTRACT FROM AUTHOR]

The preparation process and composition design of heavy-section ductile iron are the key factors affecting its fracture toughness. These factors are challenging to address due to the long casting cycle, high cost and complex influencing factors of this type of iron. In this paper, 18 cubic physical simulation test blocks with 400 mm wall thickness were prepared by adjusting the C, Si and Mn contents in heavy-section ductile iron using a homemade physical simulation casting system. Four locations with different cooling rates were selected for each specimen, and 72 specimens with different compositions and cooling times of the heavy-section ductile iron were prepared. Six machine learning-based heavy-section ductile iron fracture toughness predictive models were constructed based on measured data with the C content, Si content, Mn content and cooling rate as input data and the fracture toughness as the output data. The experimental results showed that the constructed bagging model has high accuracy in predicting the fracture toughness of heavy-section ductile iron, with a coefficient of coefficient (R2) of 0.9990 and a root mean square error (RMSE) of 0.2373. [ABSTRACT FROM AUTHOR]

This paper presents a multi-algorithm fusion model (StackingGroup) based on the Stacking ensemble learning framework to address the variable selection problem in high-dimensional group structure data. The proposed algorithm takes into account the differences in data observation and training principles of different algorithms. It leverages the strengths of each model and incorporates Stacking ensemble learning with multiple group structure regularization methods. The main approach involves dividing the data set into K parts on average, using more than 10 algorithms as basic learning models, and selecting the base learner based on low correlation, strong prediction ability, and small model error. Finally, we selected the grSubset + grLasso, grLasso, and grSCAD algorithms as the base learners for the Stacking algorithm. The Lasso algorithm was used as the meta-learner to create a comprehensive algorithm called StackingGroup. This algorithm is designed to handle high-dimensional group structure data. Simulation experiments showed that the proposed method outperformed other R2, RMSE, and MAE prediction methods. Lastly, we applied the proposed algorithm to investigate the risk factors of low birth weight in infants and young children. The final results demonstrate that the proposed method achieves a mean absolute error (MAE) of 0.508 and a root mean square error (RMSE) of 0.668. The obtained values are smaller compared to those obtained from a single model, indicating that the proposed method surpasses other algorithms in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

In practice, time series data obtained is usually small and missing, which poses a great challenge to data analysis in different domains, such as increasing the bias of model predictions, reducing the accuracy of model classification, and affecting the analysis data. This paper aims to address the problem of missing data imputation and classification of small sample time series data. By exploring and implementing efficient data interpolation strategies to improve classification accuracy, the robustness and accuracy of classification models in the face of incomplete data. To achieve this, we propose a new model that can effectively classify time series data with missing values. Our model utilizes a bi-directional long short-term memory network combined with an extreme learning machine for the imputation task, which can recover the missing time series values. For the classification task, we employ a self-attentional Inception Time network, which is regularized by a classification loss to effectively mitigate network overfitting. To improve the performance of the model on small sample time series datasets, we use a gradient penalty adversarial training approach. Our model integrates the advantages of multiple network modules, the gradient penalty adversarial multi-task model achieves optimal imputation and robust classification of missing small sample time series data. To evaluate the overall performance of our model, we selected forty datasets from the UCR time series datasets, and selected the German emotional speech datasets and the EEG epilepsy datasets, with the plant electrical signal datasets obtained from real measurements. A series of experiments were conducted to evaluate the effectiveness of our method compared to other methods, the datasets were set up with multiple missing rates, with root mean square error and coefficient of determination to assess the accuracy of imputation, and with accuracy to assess the performance of the classification task. The results show that our proposed method outperforms existing methods in terms of imputation accuracy and classification performance. To better understand the deep learning model, we used the Grad-CAM + + method to enhance the reliability and credibility of the model by visualizing the important features of the temporal data when the plant electrical signal datasets was tested. In summary, this paper presents a model framework for the imputation and classification of missing small sample time series data, and the experimental results show that our model provides an effective solution for dealing with the analysis of missing small sample time series data. [ABSTRACT FROM AUTHOR]

Addressing the contemporary complexity inherent in anomaly detection within heterogeneous systems is paramount. This paper presents a novel methodology tailored to pinpoint appliance anomalies within the framework of Internet of Things (IoT) technology. By amalgamating the capabilities of IoT and Machine Learning (ML), this approach not only heightens the precision and dependability of anomaly detection but also serves as a practical solution for industrial applications. To better align with the current industrial landscape, we emphasize the practical implications of our work. Our methodology is designed to cater specifically to industrial needs, offering a solution that can be seamlessly integrated into existing systems, thereby enhancing operational efficiency and reliability. The core of our approach lies in employing a hybrid method, utilizing both the Facebook Prophet and Isolation Forest ML algorithms for robust and intelligent anomaly detection. This dual-layered strategy, integrating forecasting and classification objectives, ensures a comprehensive approach to anomaly detection tailored for industrial settings. Evaluation of our methodology involves rigorous testing against real-time and emulated datasets, as well as comparison with existing methods. MSE has also been calculated using DT, RF, SVM, NB and Logistic supervised regressor. The Facebook Prophet model's accuracy, assessed using Root Mean Squared Error (RMSE), demonstrates its proficiency in forecasting values closely aligned with reference data points. Meanwhile, the IForest Unsupervised ML model excels in identifying anomalies, achieving high accuracy rates across various contamination levels. Through meticulous cross-validation, our proposed method exhibits significant accuracy, with rates of 93.60% and 95.72% on real-time and emulated datasets, respectively. The hybrid model (Fbprophet + iforest) has an average accuracy of 96.35% on (real-time + emulated). These results underscore the efficacy and reliability of our approach in industrial anomaly detection scenarios. In summary, by addressing the present-day challenges in anomaly detection and offering a tailored solution for industrial applications, our methodology stands poised to significantly enhance the efficiency and reliability of systems operating in diverse industrial contexts. [ABSTRACT FROM AUTHOR]

In late 2023, the United Nations conference on climate change (COP28), which was held in Dubai, encouraged a quick move from fossil fuels to renewable energy. Solar energy is one of the most promising forms of energy that is both sustainable and renewable. Generally, photovoltaic systems transform solar irradiance into electricity. Unfortunately, instability and intermittency in solar radiation can lead to interruptions in electricity production. The accurate forecasting of solar irradiance guarantees sustainable power production even when solar irradiance is not present. Batteries can store solar energy to be used during periods of solar absence. Additionally, deterministic models take into account the specification of technical PV systems and may be not accurate for low solar irradiance. This paper presents a comparative study for the most common Deep Learning (DL) and Machine Learning (ML) algorithms employed for short-term solar irradiance forecasting. The dataset was gathered in Islamabad during a five-year period, from 2015 to 2019, at hourly intervals with accurate meteorological sensors. Furthermore, the Grid Search Cross Validation (GSCV) with five folds is introduced to ML and DL models for optimizing the hyperparameters of these models. Several performance metrics are used to assess the algorithms, such as the Adjusted R2 score, Normalized Root Mean Square Error (NRMSE), Mean Absolute Deviation (MAD), Mean Absolute Error (MAE) and Mean Square Error (MSE). The statistical analysis shows that CNN-LSTM outperforms its counterparts of nine well-known DL models with Adjusted R2 score value of 0.984. For ML algorithms, gradient boosting regression is an effective forecasting method with Adjusted R2 score value of 0.962, beating its rivals of six ML models. Furthermore, SHAP and LIME are examples of explainable Artificial Intelligence (XAI) utilized for understanding the reasons behind the obtained results. [ABSTRACT FROM AUTHOR]

The real-time monitoring of corn yield by a combine harvester is a critical data source for constructing the yield histogram, which significantly benefits precision management and decision-making in modern precision agriculture. While widely used, the current photoelectric sensor-based yield monitoring method has limitations. It detects the corn height on each scraper and calculates the yield through a geometric formula. However, it neglects the noticeable difference in the corn stacking patterns affected by factors such as feeding volume, terrain, and driving speed. This oversight often results in low accuracy and poor stability in the prediction of corn yield, highlighting the need for a more advanced approach. To resolve this, we employ EDEM discrete element simulation to demonstrate the large difference of corn stacking patterns on the scraper of the elevator corresponding to feeding volume. Then, we develop a real-time monitoring system on our selfdeveloped double elevator testing rig for carrying out a composite dataset for training three machine learning algorithm-based models, namely Deep Neural Networks (DNN), Gradient Boosting Machine (GBM), and Random Forest (RF). Importantly, these models have undergone rigorous validation under various feeding volumes, ensuring their robustness and reliability. The auxiliary elevator speed is meticulously set at 150r/min, 225r/min, and 450r/min, providing a comprehensive performance assessment. The results denote that the DNN model performs best and is stable, with a coefficient of determination (R²) of 0.998, root mean square error (RMSE) of 0.526, and mean absolute error (MAE) of 0.425. The paper also performs field experiments to test the proposed three prediction models and the system. The results also denote the DNN-based prediction model's best performance for the lowest relative error of 2.29% and the highest average accuracy of 97.85%. Consequently, the proposed real-time corn yield monitoring system achieves high accuracy and reliability for the combine harvester applications. [ABSTRACT FROM AUTHOR]

In this paper, a new method is designed to effectively determine the parameters of proton exchange membrane fuel cells (PEMFCs), i.e., ξ 1 , ξ 2 , ξ 3 , ξ 4 , R C , λ , and b . The fuel cells (FCs) involve multiple variable quantities with complex non-linear behaviours, demanding accurate modelling to ensure optimal operation. An accurate model of these FCs is essential to evaluate their performance accurately. Furthermore, the design of the FCs significantly impacts simulation studies, which are crucial for various technological applications. This study proposed an improved parameter estimation procedure for PEMFCs by using the GOOSE algorithm, which was inspired by the adaptive behaviours found in geese during their relaxing and foraging times. The orthogonal learning mechanism improves the performance of the original GOOSE algorithm. This FC model uses the root mean squared error as the objective function for optimizing the unknown parameters. In order to validate the proposed algorithm, a number of experiments using various datasets were conducted and compared the outcomes with different state-of-the-art algorithms. The outcomes indicate that the proposed GOOSE algorithm not only produced promising results but also exhibited superior performance in comparison to other similar algorithms. This approach demonstrates the ability of the GOOSE algorithm to simulate complex systems and enhances the robustness and adaptability of the simulation tool by integrating essential behaviours into the computational framework. The proposed strategy facilitates the development of more accurate and effective advancements in the utilization of FCs. [ABSTRACT FROM AUTHOR]

In this paper, hybrid feed-forward deep neural network and ANFIS framework is developed to control an active suspension system of half vehicle. The dataset were generated from previous literature that studies driver comfort on different road profiles. The deep neural network aims to learn intricate relationships within dataset between features and output. The deep neural network was trained using back propagation algorithm and automated search method was implemented to obtain optimum network structure. The paper starts generating various road roughness profiles according to ISO 8608. Then, through comprehensive examination of rear and front body displacements and pitch angle accelerations, the study highlights system's significant contributions to ride comfort and vehicle dynamics. The proposed framework outperforms other controllers like proportional-integral-derivative (PID), demonstrating its robustness across different road profiles. The results demonstrated effectiveness of proposed control to minimize peak overshooting and settling times which improves ride comfort and stability significantly. Also, the proposed model has small root mean square error (RMSE) values which indicate smoother and less energetic responses, which are typically preferred for passenger comfort. Furthermore, the adaptive neural fuzzy inference system-deep neural network (ANFIS-DNN) has minimum crest factor (CF) which indicates that the signal has fewer peaks relative to its average. [ABSTRACT FROM AUTHOR]

Since the outbreak of the novel coronavirus, Covid-19 has continuously spread across the globe briskly. Countries have undertaken different types of measures to blunt this spread varying from lockdowns to curfews to social distancing to compulsory wearing of protective kits, which has been sporadically fruitful. However, despite these stringent measures, which have their own pitfalls, scientists across the globe have been struggling to develop a suitable mathematical model that could depict the existing disease spreading pattern and also predict a trend of numbers in the forthcoming months or years. In this paper, popularly used mathematical models including Polynomial Regression, Auto Regressive Integrated Moving Average (ARIMA) and Deep learning techniques such as Recurrent Neural Network (RNN) have been explored for 5 countries badly affected by this virus. The models were tested from 16th May, 2020 till 22nd May, 2020 and used for predicting future cases and deaths from 23rd May, 2020 to 30th June, 2020. The current research primarily focuses on forecasting the behaviour of total confirmed cases and deaths in each country and further analysing the performance parameters such as Mean Squared Error, Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). It has been observed that the polynomial regression model provides a best fit solution at par with actual numbers of confirmed and death cases for India by producing minimum RMSE and MAPE. For South Korea and Italy, the ARIMA and RNN models have shown fidelity with actual numbers. RNN model has shown conformity with US numbers while ARIMA model has found closeness to United Kingdom data. The purpose to perform data analysis is to measure the performance metrics by using different techniques and depict the pattern for each country. Furthermore, the paper also highlights the future predictions for every country to control the spread of disease, save lives, avoid health systems breakdowns and benefit the researchers in this field. [ABSTRACT FROM AUTHOR]

This paper presents a method to invert the sea surface wind field from Sentinel‐1 synthetic aperture radar (SAR) interferometric wide swath (IW) band mode ground range detected (GRD) vertical polarization (VV) data based on the deep residual network (ResNet). Compared with the traditional algorithm (i.e., using geophysical model functions (GMFs)), the wind field inversion based on the ResNet deep learning method solves the problem of separate wind direction and wind speed inversion. The ResNet model is developed based on the results of 212 VV polarized IW images and cross calibrated multiplatform (CCMP) data collected in 2021 in the offshore waters of China. The root mean square error, standard deviation, and bias of the inverse wind direction of the ResNet model are 12.5°, 9.8°, and 7.4°, respectively, and the root mean square error, standard deviation, and bias of the inverse wind speed are 2.33, 1.495, and −1.375. The ResNet is better than the conventional local gradient and C‐band model models, further confirming the advantages shown by the deep learning algorithm in nonlinear fitting and its potential application in sea surface wind field inversion. [ABSTRACT FROM AUTHOR]

Sea surface gage height (SSGH) data are commonly measured at sparsely deployed tidal stations while coastal resources management requires spatially distributed SSGH data. This paper presents three different machine learning models, including a Random Forest (RF) model, an Extreme Gradient Boosting (XGBoost) model, and an Artificial Neural Network (ANN) model, for retrieving and mapping spatially distributed SSGH. The models were originally developed and independently validated using 10 years of VIIRS satellite remote sensing data and corresponding in-situ gage height (GH) data within the MATLAB ANN toolbox and RStudio. The paper made two major new contributions to the determination of SSGH, including a scientific contribution and a technical contribution. Scientifically, this paper has provided new insights into important factors affecting SSGH. The SSGH varies significantly with the location (GPS coordinates) and Julian Day with both factors affecting the tide and thus SSGH. SSGH is also affected by sea surface waves that affect the reflectance of light from different wavelengths of satellite sensors, which are described with the VIIRS remote sensing reflectance (Rrs) bands including Rrs 410, 443, 486, 551, and 671. Technically, the machine learning models, particularly the ANN model, are capable of providing the most accurate and spatially distributed SSGH data particularly for coastal waters, as characterized by the model performance metrics including the correlation coefficient R value of 0.94 for training, 0.94 for validation, and 0.93 for testing and the low root mean square error (RMSE) value of 0.113 m for training, 0.113 m for validation, and 0.118 m for testing. [ABSTRACT FROM AUTHOR]

Traditional leaf chlorophyll estimation using Soil Plant Analysis Development (SPAD) devices and spectrophotometers is a high-cost mechanism in agriculture. Recently, research on chlorophyll estimation using leaf camera images and machine learning has been seen. However, these techniques use self-defined image color combinations where the system performance varies, and the potential utility has not been well explored. This paper proposes a new method that combines an improved contact imaging technique, the images' original color parameters, and a 1-D Convolutional Neural Network (CNN) specifically for tea leaves' chlorophyll estimation. This method utilizes a smartphone and flashlight to capture tea leaf contact images at multiple locations on the front and backside of the leaves. It extracts 12 different original color features, such as the mean of RGB, the standard deviation of RGB and HSV, kurtosis, skewness, and variance from images for 1-D CNN input. We captured 15,000 contact images of tea leaves, collected from different tea gardens across Assam, India to create a dataset. SPAD chlorophyll measurements of the leaves are included as true values. Other models based on Linear Regression (LR), Artificial Neural Networks (ANN), Support Vector Regression (SVR), and K-Nearest Neighbor (KNN) were also trained, evaluated, and tested. The 1-D CNN outperformed them with a Mean Absolute Error (MAE) of 2.96, Mean Square Error (MSE) of 15.4, Root Mean Square Error (RMSE) of 3.92, and Coefficient of Regression ( R 2 ) of 0.82. These results show that the method is a digital replication of the traditional method, while also being non-destructive, affordable, less prone to performance variations, and simple to utilize for sustainable agriculture. [ABSTRACT FROM AUTHOR]

IoT applications have greatly improved the convenience of our lives, generating large amounts of IoT data. How to efficiently use these data to feed IoT applications has become a significant research problem, and many studies have used machine learning methods for advanced IoT data analytics. However, the prediction models of these studies generally suffer from the problem of easy overfitting, and insufficient work done on the analysis and selection of features. In terms of prediction models, this paper proposes a second-order hybrid fusion weight–median (W–M) algorithm, which first ensures the sensitivity of the data by weighted average fusion and then reduces the impact of extreme values on the data by median fusion. In terms of feature analysis and selection, this study constructed feature crosses by studying time and weather factors and proposes a second-order feature selection, recursive feature elimination-cross validation-Pearson correlation coefficient (RFECV-PCC) algorithm, which combines the RFECV method and Pearson correlation coefficient for feature selections. Experiments were conducted to evaluate the prediction results using root mean square logarithmic error (RMSLE) and comparison of the simulation results of the dataset, which the real-time data measurement showed that the W–M algorithm has the strongest RMSLE generalization ability, further improving the prediction accuracy after feature selection by the RFECV-PCC algorithm. [ABSTRACT FROM AUTHOR]

Machine learning-based prediction of the output characteristics of a negative capacitance (NC) double gate (DG) Tunnel FET (TFET) (NC DG TFET) has been demonstrated in this paper. On current (ION), OFF current (IOFF) and sub-threshold slope (SS) have been predicted for different values of the body thickness (TSi), oxide thickness (TOX) and channel length (LCh) and the work function (WF). Random Forest Regression (RFR) model is used in the ML framework to explore the device characteristics. A total of 5444 simulated data has been generated by using the SILVACO ATLAS tool. After pre-processing the data, RFR-ML has been applied to obtain maximum accuracy. Root means square error (RMSE) (~0.34), R2 score (~0.965) and accuracy (~98.51%) parameter have been used as the figures of merit (FOM) to judge the efficiency of the proposed model with respect to the state-of-the-art literature. Besides, with higher accuracy, the model is capable of predicting the data within a few seconds compared to the few hundred hours using TCAD tools. This fast and accurate design strategy will surely be efficacious for the present VLSI industries. [ABSTRACT FROM AUTHOR]

Geomagnetic storms induce ionospheric disturbances, affecting short‐wave radio communication systems. Accurate ionospheric total electron content (TEC) prediction is vital for accurately describing the short‐wave radio environment of the ionosphere. We use the Multi‐Step Auxiliary Prediction (MSAP) model, a deep learning algorithm, to forecast TEC during geomagnetic storms. The MSAP model integrates Bi‐LSTM networks, an auxiliary model, and convolutional processes for spatiotemporal modeling. Our validation shows the MSAP model outperforms the IRI‐2016 model in predicting global TEC for the next 6 days in the test set. We assess its performance during 116 geomagnetic storm events, considering storm intensity, solar activity, month, and Universal Time (UT). The MSAP model exhibits a weak correlation with storm intensity and a strong correlation with solar activity. Monthly variation displays similar strong correlations in root mean square error (RMSE) and R2 for both models. For UT variation, the other metrics exhibit a weak correlation with the number of Global Navigation Satellite System stations, except for the RMSE of the MSAP and IRI‐2016 models. Plain Language Summary: Total electron content (TEC) is an important parameter to describe the ionosphere. The prediction of TEC is crucial for short‐wave communication systems. Geomagnetic storms disturb the ionosphere, thereby affecting the prediction of TEC. In this paper, the existing multi‐step auxiliary prediction model is used to predict the TEC during geomagnetic storms. Using the International Reference Ionosphere‐2016 model as the reference, the storm‐time performance and time‐varying characteristics of Multi‐Step Auxiliary Prediction (MSAP) are studied. It is found that the MSAP model captures variations with solar activity, month, and Universal Time during geomagnetic storms. Key Points: The MSAP model can predict total electron content (TEC) with high accuracy and stabilityThe MSAP model perform differently in different phases of geomagnetic storms [ABSTRACT FROM AUTHOR]

Air pollution is a significant global environmental challenge that can cause health problems affecting everyone on the planet without any geographical boundary. It has a substantial impact directly or indirectly not only on human health but on social and economic activities as well. Researchers worldwide are working to evaluate and predict the air quality index using advanced computational models. These models have drastically altered how we think about and approach API prediction (Air Pollution Index). The primary intent of this paper is to highlight the suitable machine learning models on remotely sensed Sentinel-5P sensor data in assessing and predicting air pollution before, during, and after the lockdown enforced due to the COVID-19 pandemic. This work includes the assessment and prediction of API using four air-polluting parameters- Nitrogen Dioxide, Ozone, Carbon Monoxide, and Sulphur Dioxide in four metropolitan cities of India - Kolkata, Mumbai, Delhi, and Chennai. The paper used Markov Chain as an operator for predicting the AQI state and verified it using ground-level and satellite data. The model's accuracy was estimated using the predicted dataset RMSE (Root Mean Square Error). The outcome of the prediction model was also validated with actual data, which substantiates the finding that during this lockdown period of the COVID-19 pandemic, NO 2 concentration was reduced significantly due to less traffic and energy production from industries. [ABSTRACT FROM AUTHOR]

In this paper, we apply the Fourier neural operator (FNO) paradigm to ocean circulation and prediction problems. We aim to show that the complicated nonlinear dynamics of an ocean circulation can be captured by a flexible, efficient, and expressive structure of the FNO networks. The machine learning model (FNO3D and the recurrent FNO2D networks) trained by simulated data as well as real data takes spatiotemporal input and predicts future ocean states (sea surface current and sea surface height). For this, the double gyre ocean circulation model driven by stochastic wind stress is considered to represent an ideal ocean circulation. In order to generate the training and test data that exhibits rich spatiotemporal variability, the initial states are perturbed by Gaussian random fields. Experimental results confirm that the trained models yield satisfactory prediction accuracy for both types of FNO models in this case. Second, as the training set, we used the HYCOM reanalysis data in a regional ocean. FNO2D experiments demonstrated that the 5-day input to 5-day prediction yields the averaged root mean square errors (RMSEs) of 5.0 cm/s, 6.7 cm/s, 7.9 cm/s, 8.9 cm/s, and 9.4 cm/s in surface current, calculated consecutively for each day, in a regional ocean circulation of the East/Japan Sea. Similarly, the RMSEs for sea surface height were 2.3 cm, 3.5 cm, 4.2 cm, 4.6 cm, and 4.9 cm, for each day. We also trained the model with 15-day input and 10-day prediction, resulting in comparable performance. Extensive numerical tests show that, once learned, the resolution-free FNO model instantly forecasts the ocean states and can be used as an alternative fast solver in various inference algorithms. [ABSTRACT FROM AUTHOR]

The leaf area index (LAI) is a crucial physiological indicator of crop growth. This paper introduces a new spectral index to overcome angle effects in estimating the LAI of crops. This study quantitatively analyzes the relationship between LAI and multi-angle hyperspectral reflectance from the canopy of winter oilseed rape (Brassica napus L.) at various growth stages, nitrogen application levels and coverage methods. The angular stability of 16 traditional vegetation indices (VIs) for monitoring the LAI was tested under nine view zenith angles (VZAs). These multi-angle VIs were input into machine learning models including support vector machine (SVM), eXtreme gradient boosting (XGBoost), and Random Forest (RF) to determine the optimal monitoring strategy. The results indicated that the back-scattering direction outperformed the vertical and forward-scattering direction in terms of monitoring the LAI. In the solar principal plane (SPP), EVI-1 and REP showed angle stability and high accuracy in monitoring the LAI. Nevertheless, this relationship was influenced by experimental conditions and growth stages. Compared with traditional VIs, the observation perspective insensitivity vegetation index (OPIVI) had the highest correlation with the LAI (r = 0.77–0.85). The linear regression model based on single-angle OPIVI was most accurate at −15° (R2 = 0.71). The LAI monitoring achieved using a multi-angle OPIVI-RF model had the higher accuracy, with an R2 of 0.77 and with a root mean square error (RMSE) of 0.38 cm2·cm−2. This study provides valuable insights for selecting VIs that overcome the angle effect in future drone and satellite applications. [ABSTRACT FROM AUTHOR]

The accurate prediction of global horizontal irradiance (GHI) is crucial for optimizing solar power generation systems, particularly in mountainous areas with complex topography and unique microclimates. These regions face significant challenges due to limited reliable data and the dynamic nature of local weather conditions, which complicate accurate GHI measurement. The scarcity of precise data impedes the development of reliable solar energy prediction models, impacting both economic and environmental outcomes. To address these data scarcity challenges in solar energy prediction, this paper focuses on various locations in Europe and Asia Minor, predominantly in mountainous regions. Advanced machine learning techniques, including random forest (RF) and extreme gradient boosting (XGBoost) regressors, are employed to effectively predict GHI. Additionally, optimizing training data distribution based on cloud opacity values and integrating synthetic data significantly enhance predictive accuracy, with R2 scores ranging from 0.91 to 0.97 across multiple locations. Furthermore, substantial reductions in root mean square error (RMSE), mean absolute error (MAE), and mean bias error (MBE) underscore the improved reliability of the predictions. Future research should refine synthetic data generation, optimize additional meteorological and environmental parameter integration, extend methodology to new regions, and test for predicting global tilted irradiance (GTI). The studies should expand training data considerations beyond cloud opacity, incorporating sky cover and sunshine duration to enhance prediction accuracy and reliability. [ABSTRACT FROM AUTHOR]

A network, whose nodes are genes and whose directed edges represent positive or negative influences of a regulatory gene and its targets, is often used as a representation of causality. To infer a network, researchers often develop a machine learning model and then evaluate the model based on its match with experimentally verified "gold standard" edges. The desired result of such a model is a network that may extend the gold standard edges. Since networks are a form of visual representation, one can compare their utility with architectural or machine blueprints. Blueprints are clearly useful because they provide precise guidance to builders in construction. If the primary role of gene regulatory networks is to characterize causality, then such networks should be good tools of prediction because prediction is the actionable benefit of knowing causality. But are they? In this paper, we compare prediction quality based on "gold standard" regulatory edges from previous experimental work with nonlinear models inferred from time series data across four different species. We show that the same non-linear machine learning models have better predictive performance, with improvements from 5.3% to 25.3% in terms of the reduction in the root mean square error (RMSE) compared with the same models based on the gold standard edges. Having established that networks fail to characterize causality properly, we suggest that causality research should focus on four goals: (i) predictive accuracy; (ii) a parsimonious enumeration of predictive regulatory genes for each target gene g; (iii) the identification of disjoint sets of predictive regulatory genes for each target g of roughly equal accuracy; and (iv) the construction of a bipartite network (whose node types are genes and models) representation of causality. We provide algorithms for all goals. [ABSTRACT FROM AUTHOR]

Parkinson's disease (PD) is a neurodegenerative disorder that influence brain's neurological, behavioral, and physiological functions and includes motor and nonmotor manifestations. Although there have been several PD diagnosis systems with supervised machine learning techniques, there are more efforts that need to enhance the accurate detection of PD in its early stage. The current paper developed a novel approach by integrating Least Squares Support Vector Regression (LS-SVR) and Fuzzy Clustering for Unified Parkinson's Disease Rating Scale (UPDRS) diagnosis. This paper used feature selection and Principal Component Analysis (PCA) to overcome the multicollinearity issues in data. This paper used a large medical dataset including Motor- and Total-UPDRS to demonstrate how the proposed method can improve prediction performance via extensive evaluations and comparisons with existing methods. Compared to other prediction methods, the experimental results demonstrate that the proposed method provided the best accuracy for Total-UPDRS (Root Mean Squared Error = 0.7348; R 2 = 0.9169) and Motor-UPDRS (Root Mean Squared Error = 0.8321; R 2 = 0.8756) predictions. [ABSTRACT FROM AUTHOR]

The global COVID-19 pandemic has had a great impact on transportation across the United States. However, there is a lack of studies investigating the pandemic's impact on vehicular traffic at the later stage of the pandemic. Therefore, this paper studies the change of freeway traffic patterns in two metropolitan counties in the State of Utah at the latter stage of the pandemic. We found that with the relaxation of travel restriction and the COVID vaccine, vehicular traffic has recovered to equaling, if not exceeding, pre-pandemic levels. Truck traffic is higher than the pre-pandemic level due to the growth of online shopping and on-demand delivery. To help responsive agencies to prepare for the near-future traffic pattern, a traffic prediction model based on an innovative approach integrating machine learning with graph theory is proposed. The evaluation shows that the proposed prediction model has a desirable performance. The mean absolute percentage prediction error is between 0.38% and 1.74% for different jurisdictions. On average, the modal outperforms the traditional long short-term memory model by 31.20% in terms of root mean squared prediction error. [ABSTRACT FROM AUTHOR]

This paper presents a gesture-controlled robotic arm system designed for agricultural harvesting, utilizing a data glove equipped with bending sensors and OptiTrack systems. The system aims to address the challenges of labor-intensive fruit harvesting by providing a user-friendly and efficient solution. The data glove captures hand gestures and movements using bending sensors and reflective markers, while the OptiTrack system ensures high-precision spatial tracking. Machine learning algorithms, specifically a CNN+BiLSTM model, are employed to accurately recognize hand gestures and control the robotic arm. Experimental results demonstrate the system's high precision in replicating hand movements, with a Euclidean Distance of 0.0131 m and a Root Mean Square Error (RMSE) of 0.0095 m, in addition to robust gesture recognition accuracy, with an overall accuracy of 96.43%. This hybrid approach combines the adaptability and speed of semi-automated systems with the precision and usability of fully automated systems, offering a promising solution for sustainable and labor-efficient agricultural practices. [ABSTRACT FROM AUTHOR]

Accurate estimation of forest canopy height is crucial for biomass inversion, carbon storage assessment, and forestry management. However, deep learning methods are underutilized compared to machine learning. This paper introduces the convolutional neural network–bidirectional long short-term memory (CNN-BiLSTM) model and proposes a Convolutional Neural network–spatial channel attention–bidirectional long short-term memory (CNN-SCA-BiLSTM) model, incorporating dual attention mechanisms for richer feature extraction. A dataset comprising vegetation indices and canopy height data from forest regions in Luoyang, specifically within the 8–20 m range, is used for a comparative analysis of multiple models, with accuracy evaluated based on the mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). The results demonstrate that (1) the CNN-BiLSTM model exhibits strong potential (MAE = 1.6554 m, RMSE = 2.2393 m, R2 = 0.9115) and (2) the CNN-SCA-BiLSTM model, while slightly less efficient (<1%), demonstrates improved performance. It reduces the MAE by 0.3047 m, the RMSE by 0.6420 m, and increases the R2 value by 0.0495. Furthermore, the model is utilized to generate a canopy height map (MAE = 5.2332 m, RMSE = 7.0426 m) for Henan in the Yellow River Basin for the year 2022. The canopy height is primarily distributed around 5–20 m, approaching the accuracy levels of global maps (MAE = 4.0 m, RMSE = 6.0 m). [ABSTRACT FROM AUTHOR]

Financial markets are increasingly interlinked. Therefore, this study explores the complex relationships between the Tadawul All Share Index (TASI), West Texas Intermediate (WTI) crude oil prices, and Bitcoin (BTC) returns, which are pivotal to informed investment and risk-management decisions. Using copula-based models, this study identified Student's t copula as the most appropriate one for encapsulating the dependencies between TASI and BTC and between TASI and WTI prices, highlighting significant tail dependencies. For the BTC–WTI relationship, the Frank copula was found to have the best fit, indicating nonlinear correlation without tail dependence. The predictive power of the identified copulas were compared to that of Long Short-Term Memory (LSTM) networks. The LSTM models demonstrated markedly lower Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean Absolute Scaled Error (MASE) across all assets, indicating higher predictive accuracy. The empirical findings of this research provide valuable insights for financial market participants and contribute to the literature on asset relationship modeling. By revealing the most effective copulas for different asset pairs and establishing the robust forecasting capabilities of LSTM networks, this paper sets the stage for future investigations of the predictive modeling of financial time-series data. The study highlights the potential of integrating machine-learning techniques with traditional econometric models to improve investment strategies and risk-management practices. [ABSTRACT FROM AUTHOR]

The terminal settling velocity of microplastics plays a vital role in the physical behavior of microplastics, and is related to the migration and fate of these microplastics in the ocean. At present, the terminal settling velocity is mostly calculated by formulae, which also leads to a fewer studies on the use of machine-learning models to predict its settling velocity in this field. This study fills this gap by studying the prediction of the settling velocity by machine-learning models and compares it with the traditional formula calculation method. This study evaluates three machine-learning models, namely, random forest, linear regression, and the back propagation neural network. The results of this study show that the prediction results of the three machine-learning models are more accurate than those of traditional formula calculations, with an accuracy increase of 12.79% (random forest), 9.3% (linear regression), and 13.92% (back propagation neural network), respectively. At the same time, according to the results of this study, random forest is better than the other models in the mean absolute error and root mean square error evaluation indicators, which are only 0.0036 and 0.0047. This paper proposes three machine-learning methods to prove that the prediction effect of machine learning is much better than traditional formula calculations, thereby improving the shortcomings in this field. At the same time, it also provides reliable data support for studying the migration behavior of microplastics in water bodies. [ABSTRACT FROM AUTHOR]

The cognitive state of a person can be categorized using the circumplex model of emotional states, a continuous model of two dimensions: arousal and valence. The purpose of this research is to select a machine learning model(s) to be integrated into a virtual reality (VR) system that runs cognitive remediation exercises for people with mental health disorders. As such, the prediction of emotional states is essential to customize treatments for those individuals. We exploit the Remote Collaborative and Affective Interactions (RECOLA) database to predict arousal and valence values using machine learning techniques. RECOLA includes audio, video, and physiological recordings of interactions between human participants. To allow learners to focus on the most relevant data, features are extracted from raw data. Such features can be predesigned, learned, or extracted implicitly using deep learners. Our previous work on video recordings focused on predesigned and learned visual features. In this paper, we extend our work onto deep visual features. Our deep visual features are extracted using the MobileNet-v2 convolutional neural network (CNN) that we previously trained on RECOLA's video frames of full/half faces. As the final purpose of our work is to integrate our solution into a practical VR application using head-mounted displays, we experimented with half faces as a proof of concept. The extracted deep features were then used to predict arousal and valence values via optimizable ensemble regression. We also fused the extracted visual features with the predesigned visual features and predicted arousal and valence values using the combined feature set. In an attempt to enhance our prediction performance, we further fused the predictions of the optimizable ensemble model with the predictions of the MobileNet-v2 model. After decision fusion, we achieved a root mean squared error (RMSE) of 0.1140, a Pearson's correlation coefficient (PCC) of 0.8000, and a concordance correlation coefficient (CCC) of 0.7868 on arousal predictions. We achieved an RMSE of 0.0790, a PCC of 0.7904, and a CCC of 0.7645 on valence predictions. [ABSTRACT FROM AUTHOR]

Accurate estimation of surface evapotranspiration (ET) in the Heihe River Basin using remote sensing data is crucial for understanding water dynamics in arid regions. In this paper, by coupling physical constraints and machine learning for hybrid modeling, we develop a hybrid model based on surface conductance optimization. A hybrid modeling algorithm, two physical process-based ET algorithms (Penman–Monteith-based and Priestley–Taylor-based ET algorithms), and three pure machine learning algorithms (Random Forest, Extreme Gradient Boosting, and K Nearest Neighbors) are comparatively analyzed for estimating the ET. The results showed that, in general, the machine learning model optimized by parameters was able to better predict the surface conductance of the hybrid model. Driver analyses showed that radiation, normalized difference vegetation index (NDVI), and air temperature had high correlations with ET. The hybrid model had a better prediction performance for ET than the other five models, and it improved the R2 of the two physical process-based algorithms to 0.9, reduced the root mean square error (RMSE) to 0.5 mm/day, reduced the BIAS to 0.2 mm/day, and improved the Kling–Gupta efficiency (KGE) to 0.9. The hybrid model outperformed the others across different time scales, displaying lower BIAS, RMSE, and higher KGE. Spatially, its ET patterns aligned with regional vegetation changes, with superior accuracy in annual ET estimation compared to the other models. Comparison with other ET products shows that the estimation results based on the hybrid model have better performance. This approach not only improves the accuracy of ET estimation but also improves the understanding of the physical mechanism of ET estimation by pure machine learning models. This study can provide important support for understanding ET and hydrological processes under different climatic and biotic vegetation in other arid and semi-arid regions. [ABSTRACT FROM AUTHOR]

Background: Cesarean section-induced postpartum hemorrhage (PPH) potentially causes anemia and hypovolemic shock in pregnant women. Hence, it is helpful for obstetricians and anesthesiologists to prepare pre-emptive prevention when predicting PPH occurrence in advance. However, current works on PPH prediction focus on whether PPH occurs rather than assessing PPH amount. To this end, this work studies quantitative PPH prediction with machine learning (ML). Methods: The study cohort in this paper was selected from individuals with PPH who were hospitalized at Shijiazhuang Obstetrics and Gynecology Hospital from 2020 to 2022. In this study cohort, we built a dataset with 6,144 subjects covering clinical parameters, anesthesia operation records, laboratory examination results, and other information in the electronic medical record system. Based on our built dataset, we exploit six different ML models, including logistic regression, linear regression, gradient boosting, XGBoost, multilayer perceptron, and random forest, to automatically predict the amount of bleeding during cesarean section. Eighty percent of the dataset was used as model training, and 20 % was used for verification. Those ML models are constantly verified and improved by root mean squared error(RMSE) and mean absolute error(MAE). Moreover, we also leverage the importance of permutation and partial dependence plot (PDP) to discuss their feasibility. Result: The experiment results show that random forest obtains the highest accuracy for PPH amount prediction compared to other ML methods. Random forest reaches the mean absolute error of 21.7, less than 5.4 % prediction error. It also gains the root mean squared error of 33.75, less than 9.3 % prediction error. On the other hand, the experimental results also disclose indicators that contributed most to PPH prediction, including Ca, hemoglobin, white blood cells, platelets, Na, and K. Conclusion: It effectively predicts the amount of PPH during a cesarean section by ML methods, especially random forest. With the above insight, ML predicting PPH amounts provides early warning for clinicians, thus reducing complications and improving cesarean sections' safety. Furthermore, the importance of ML and permutation, complemented by incorporating PDP, promises to provide clinicians with a transparent indication of individual risk prediction. [ABSTRACT FROM AUTHOR]

Over the past decades, the software industry has expanded to include all industries. Since stakeholders tend to use it to get their work done, software houses seek to estimate the cost of the software, which includes calculating the effort, time, and resources required. Although many researchers have worked to estimate it, the prediction accuracy results are still inaccurate and unstable. Estimating it requires a lot of effort. Therefore, there is an urgent need for modern techniques that contribute to cost estimation. This paper seeks to present a model based on deep learning and machine learning techniques by combining convolutional neural networks (CNN) and the particle swarm algorithm (PSO) in the context of time series forecasting, which enables feature extraction and automatic tuning of hyperparameters, which reduces the manual effort of selecting parameters and contributes to fine-tuning. The use of PSO also enhances the robustness and generalization ability of the CNN model and its iterative nature allows for efficient discovery of hyperparameter similarity. The model was trained and tested on 13 different benchmark datasets and evaluated through six metrics: mean absolute error (MAE), mean square error (MSE), mean magnitude relative error (MMRE), root mean square error (RMSE), median magnitude relative error (MdMRE), and prediction accuracy (PRED). Comparative results reveal that the performance of the proposed model is better than other methods for all datasets and evaluation criteria. The results were very promising for predicting software cost estimation. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Anemia, generally termed as deficiency of hemoglobin or red blood cells in the blood is significant global health concern for the population in underdeveloped as well as in developing nations specially, for children and young women in rural areas. This paper proposes a quantitative approach for anemia detection by regression analysis technique which predicts hemoglobin level in the blood. To achieve this, the image dataset of microscopic blood sample is collected from 70 individuals. The data collection requires proper procedure as it plays vital part in system implementation. The statistical feature utilizing mean pixel intensity values from the red, green, and blue color planes of the images are given as input to the regression model. For the proposed system, we have employed multiple regression analysis model using machine learning approach with both three and four regression coefficients to establish relation between features obtained from blood samples and the hemoglobin level in the blood to achieve the specified task of anemia detection in an individual. Performance analysis show promising results for the proposed system with coefficient of determination (R²) and root mean square error (RMSE) found out be 0.923 and 1.682 respectively. Overall, this paper presents valuable system for anemia detection based on hemoglobin estimation which can be implemented in areas with limited medical resources and gives another supportive technological solution for current healthcare problems. [ABSTRACT FROM AUTHOR]

In this paper, a novel machine-learning based models are presented to predict the effect of notch depth on elastic new strain-concentration factor of rectangular bars with single edge U-notch under combined loading of static tension and pure bending. Regarding the importance of this study, the database with 162 samples is utilized to develop the new methodology of machine learning based models. The database includes the notch radius, the Poisson's ratio, and the thick ratio that represent the influential inputs. The predicted key feature is the elastic new strain-concentration factor under combined loading of static tension and pure bending. These samples were tested with high precision and the predicted values of SNCF were obtained. For comparison, adaptive neural fuzzy inference system, artificial neural network, fine tree, ensemble boosted tree, and ensemble optimized bagged tree were designed and developed in this study. To evaluate and compare the performance of the models, four statistical indices of MAE, MSE, root mean square error (RMSE)and determination coefficient (R) were utilized. Based on the results, all models can predict the SNCF appropriately. However, the Ensemble optimized Bagged tree model had a better performance than other models and it had a significant priority in term of prediction accuracy. Finally, the results indicated that the elastic SNCF increased with increasing notch depth from 0.2 ≤ ho/Ho ≤ 0.7 and sharply decreases with increasing notch depth for shallow notches (0.8 ≤ ho/Ho ≤ 0.95). [ABSTRACT FROM AUTHOR]

The conventional technique of materials design and discovery relies on experimentation and complex computational methods. The sheer number of materials present makes testing each one for specific properties and application makes the entire process time and resource intensive. This has resulted into Machine Learning (ML) to gain popularity in the domain of materials science to revolutionise and accelerate the entire process. Data-driven approaches such as these can be applied to narrow down the number of materials on which we apply the tradition methods, thus cutting down both the cost and time for development of new materials. This paper demonstrates how data-driven approach can be incorporated in materials science taking the use of band gap prediction of different materials using different machine ML algorithms. Using Random Forest Regressor, the highest R squared (r2) score of 0.685 and least root mean squared error (RMSE) of 0.87 eV were achieved. [ABSTRACT FROM AUTHOR]

The ever-increasing demand for electricity has presented a grave threat to traditional energy sources, which are finite, rapidly depleting, and have a detrimental environmental impact. These shortcomings of conventional energy resources have caused the globe to switch from traditional to renewable energy sources. Wind power significantly contributes to carbon-free energy because it is widely accessible, inexpensive, and produces no harmful emissions. Better and more efficient renewable wind power production relies on accurate wind speed predictions. Accurate short-term wind speed forecasting is essential for effectively handling unsteady wind power generation and ensuring that wind turbines operate safely. The significant stochastic nature of the wind speed and its dynamic unpredictability makes it difficult to forecast. This paper develops a hybrid model, L-LG-S, for precise short-term wind speed forecasting to address problems in wind speed forecasting. In this research, state-of-the-art machine learning and deep learning algorithms employed in wind speed forecasting are compared with the proposed approach. The effectiveness of the proposed hybrid model is tested using real-world wind speed data from a wind turbine located in the city of Karachi, Pakistan. Moreover, the mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) are used as accuracy evaluation indices. Experimental results show that the proposed model outperforms the state-of-the-art legacy models in terms of accuracy for short-term wind speed in training, validation and test predictions by 98% respectively. [ABSTRACT FROM AUTHOR]