Low Error Values Research Articles

Investigation of optimized machine learning models with PSO for forecasting the shear capacity of steel fiber-reinforced SCC beams with/out stirrups

This article presents a comprehensive investigation of the applicability of optimized machine learning (ML) models with particle swarm optimization (PSO) for forecasting the shear strength of steel fiber-reinforced self-compacting concrete (SFR-SCC) beams with/without stirrups in engineering applications. Firstly, a database containing the results of 101 specimens with nine input features is adopted to train the models. As ML models such as random forest (RF), adaptive boosting regression (AdaBoost), extreme gradient boosting (XGBoost), support vector regression (SVR), and K-nearest neighbors regression (KNN) are considered, whereas the hyper-parameters of these models are set as default by the sklearn module. On the other hand, PSO-ML models (PSO-RF, PSO-AdaBoost, PSO-XGBoost, PSO-SVR, and PSO–KNN) are constructed using particle swarm optimization to find the optimal combination of the hyper-parameters of these default ML models. Afterwards, the forecasting ability of each model is extensively assessed using various performance metrics, error analysis, and score analysis, and the model with the best forecasting ability is determined and compared with existing empirical models. Moreover, Shapley additive explanation (SHAP) analysis is also utilized to ensure the interpretability of the forecasting models and to overcome the “black box” problem of ML methods. Lastly, based on the best forecasting model developed in this study, a graphical user interface (GUI) has been developed to easily forecast the shear strength of SFR-SCC beams in practical applications. The results of the study clearly illustrate that PSO-ML models exhibit better forecasting capabilities than default models. It can be emphasized from here that the PSO algorithm can be an effective tool to improve the performance of ML models. It should also be pointed out that the use of PSO in simpler algorithms instead of tree-based models can further improve forecasting efficiency. On the other hand, the PSO-RF model has the best performance, with a lower error value and a high final score. And this makes it a more reliable option for predicting the shear strength of the SFR-SCC beams compared to empirical equations. In addition, according to the results of SHAP feature importance analysis, the most important input parameters affecting the shear strength of SFR-SCC beams are stirrup rebar ratio (ρv), stirrup yield strength (fyv) and longitudinal rebar ratio (ρt). This information can assist engineers in paying special attention to these features in their design and assessment processes.

Construction and Evaluation of an Immersive Physical Education Teaching Environment Combining Augmented Reality Technology

Abstract Augmented reality technology is a cutting-edge technology of current social development, and its development promotes the development and change of people’s social production and lifestyle. In this paper, combining the key aspects of sports teaching, training, and actual combat confrontation, the construction of a VR-based immersive sports teaching environment is realized from the aspects of sports teaching materials and sports action and tactical training. Subsequently, using the bit position registration algorithm that integrates complementary filtering (CF) and untraceable Kalman filtering (UKF), as well as the TDOA localization algorithm, a VR sports-assisted training system was designed, and the performance and application effects of the system were empirically analyzed. The login page time of the system is within 3.30s, and the corresponding CPU utilization rate is 43%~50%, which is in line with the expected effect, indicating that it has good usability performance. Fusion filtering on posture angle has a lower error value than CF and UKF, which suggests higher accuracy and is suitable for posture registration in VR sports-assisted training. The TDOA localization algorithm has an error range of [0.127m, 0.389m] and a 50% error below 0.292m, which can be utilized for motion tracking in VR sports-assisted training. The experimental group using the VR sports teaching environment is significantly better than the control group using traditional teaching methods in both visual-sensory perception and technical assessment, which indicates that the VR immersive sports teaching environment constructed in this paper has practical feasibility, and provides a model reference and experience for realizing the practical application of AR technology in sports.

Selecting optimal software code descriptors-The case of Java.

Over the last 25 years, a considerable proliferation of software metrics and a plethora of tools have emerged to extract them. While this is indeed positive concerning the previous situations of limited data, it still leads to a significant problem arising both from a theoretical and a practical standpoint. From a theoretical perspective, several metrics are likely to result in collinearity, overfitting, etc. From a practical perspective, such a set of metrics is difficult to manage and companies, especially small ones, may feel overwhelmed and unable to select a viable subset of them. Still, so far it has not been fully understood what is a viable subset of metrics suitable to properly manage software projects and products. In this paper, we attempt to address this issue. We focus on the case of programs written in Java and we consider classes and methods. We use Sammon error as a measure of the similarity of metrics. Utilizing both Particle Swarm Optimization and Genetic Algorithm, we adapted a method for the identification of a viable subset of such metrics that could solve the mentioned problem. Furthermore, we experiment with our approach on 800 projects coming from GitHub and validate the results on 200 projects. With the proposed method we got optimal subsets of software engineering metrics. These subsets gave us low values of Sammon error at more than 70% at class and method levels on a validation dataset.

Application of Fuzzy Mamdani Model for Biogas Yield Prediction in Anaerobic Co-Digestion of Decomposable Wastes

Accurate prediction of biogas yield is crucial for optimizing waste-to-energy conversion systems in anaerobic co-digestion processes. In this study, a double input and single output (DISO) fuzzy mamdani model (FMM) was developed for the prediction of biogas yield in a pilot scale of 105-L mesophilic anaerobic sludge bio-digester. The input variables considered are the combination of cow dung and pig waste and the retention time (RT), while the output variable is the experimental biogas yield. Triangular Fuzzy Membership Functions (TFMF) were utilized to define the input and output datasets, and rules were derived from de-fuzzification. Comparative analysis between the FMM's predicted results and experimental values showcased its effectiveness in forecasting biogas yield during the anaerobic co-digestion of the hybrid wastes. Significantly, the FMM consistently produced results with low error values for the sample dataset, underscoring its accuracy even under stochastic conditions. This study emphasizes the FMM's ability to generate predictions with minimal deviations, offering superior results. As a prospect for future research, the implementation of hybrid algorithms may further enhance biogas yield prediction accuracy within waste-to-energy systems.

Leveraging transfer learning with deep learning for crime prediction.

Crime remains a crucial concern regarding ensuring a safe and secure environment for the public. Numerous efforts have been made to predict crime, emphasizing the importance of employing deep learning approaches for precise predictions. However, sufficient crime data and resources for training state-of-the-art deep learning-based crime prediction systems pose a challenge. To address this issue, this study adopts the transfer learning paradigm. Moreover, this study fine-tunes state-of-the-art statistical and deep learning methods, including Simple Moving Averages (SMA), Weighted Moving Averages (WMA), Exponential Moving Averages (EMA), Long Short Term Memory (LSTM), Bi-directional Long Short Term Memory (BiLSTMs), and Convolutional Neural Networks and Long Short Term Memory (CNN-LSTM) for crime prediction. Primarily, this study proposed a BiLSTM based transfer learning architecture due to its high accuracy in predicting weekly and monthly crime trends. The transfer learning paradigm leverages the fine-tuned BiLSTM model to transfer crime knowledge from one neighbourhood to another. The proposed method is evaluated on Chicago, New York, and Lahore crime datasets. Experimental results demonstrate the superiority of transfer learning with BiLSTM, achieving low error values and reduced execution time. These prediction results can significantly enhance the efficiency of law enforcement agencies in controlling and preventing crime.

Proposing a Hybrid Method (Artificial Neural Networks – ARIMA) to Predict Temperatures in the City of Baghdad

Statistical methods and artificial intelligence play an important role in building models that can predict time series and thus help in developing strategic plans. The study aimed to propose a hybrid model (ARIMA and artificial neural networks) to predict the temperature in the city of Baghdad and compare it with the AA and N models based on the temperatures in the city of Baghdad for the period from January 2017 to December 2021. By comparing these models using forecast accuracy measures MAE, MSE, and MAPE, it was found that the hybrid method gives lower error values than ARIMA models and artificial neural networks, as it addresses the problem of non-linearity in the data, so it was relied upon to predict temperatures in the city of Baghdad for the next six months.

Forecasting of Electricity Demand in Malaysia with Seasonal Highly Volatile Characteristics using SARIMA – GARCH Model

Developing an accurate forecasting model for electricity demand plays a vital role in maximising the efficiency of the planning process in the power generation industries. The time series data of electricity demand in Malaysia is highly volatile with seasonal characteristics. This study aims to evaluate the forecasting performance of the seasonal autoregressive integrated moving average (SARIMA) model with GARCH for weekly maximum electricity demand. The weekly maximum electricity demand data (in megawatt, MW) from 2005 to 2016 has been used for this study. The results show that SARIMA(1, 1, 0)(0, 1, 0)52−GARCH(1, 2) with generalized error distribution (GED) is the most appropriate model for forecasting electricity demand due to its parsimonious characteristic with low values of root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE) which are 644.1828, 523.8380 and 3.13%, respectively. The MAPE value of the proposed model which is less than 5% indicates that the SARIMA − GARCH model is relatively good in forecasting electricity demand for the case of Malaysia data. In conclusion, the proposed model of SARIMA with GARCH has great potential and provides a promising performance in forecasting electricity demand with seasonal highly volatile characteristics.

Analysis of cohesive particles mixing behavior in a twin-paddle blender: DEM and machine learning applications

This research paper presents a comprehensive discrete element method (DEM) examination of the mixing behaviors exhibited by cohesive particles within a twin-paddle blender. A comparative analysis between the simulation and experimental results revealed a relative error of 3.47%, demonstrating a strong agreement between the results from the experimental tests and the DEM simulation. The main focus centers on systematically exploring how operational parameters, such as impeller rotational speed, blender's fill level, and particle mass ratio, influence the process. The investigation also illustrates the significant influence of the mixing time on the mixing quality. To gain a deeper understanding of the DEM simulation findings, an analytical tool called multivariate polynomial regression in machine learning is employed. This method uncovers significant connections between the DEM results and the operational parameters, providing a more comprehensive insight into their interrelationships. The multivariate polynomial regression model exhibited robust predictive performance, with a mean absolute percentage error of less than 3% for both the training and validation sets, indicating a slight deviation from actual values. The model's precision was confirmed by low mean absolute error values of 0.0144 (80% of the dataset in the training set) and 0.0183 (20% of the dataset in the validation set). The study offers valuable insights into granular mixing behaviors, with implications for enhancing the efficiency and predictability of the mixing processes in various industrial applications.

Advancing heat transfer modeling through machine learning: A focus on forced convection with nanoparticles

This study underscores the critical role of heat transfer modeling in the design and optimization of heat exchangers, recognizing the challenges posed by traditional numerical methods. To address the need for more efficient alternatives, machine learning emerges as a promising solution, leveraging its capacity to unravel intricate relationships in heat transfer processes. The research focuses on forced convection heat transfer involving nanoparticles (specifically TiO2, Al2O3, and Cu) dispersed in water, employing the Lagrangian–Eulerian approach under turbulent flow conditions with a constant surface heat flux. Machine-learning techniques, namely extreme gradient boosting, support vector regression, and tree regression are employed to predict heat transfer outcomes based on collected data. The achieved results exhibit promising accuracy levels, with eXtreme gradient boosting, support vector regression, and tree regression algorithm models demonstrating impressive accuracies of 91%, 91%, and 94%, respectively. The mean absolute errors for these machine-learning models were recorded as 1.07, 7.24, and 3.74. This research serves as a demonstration of the potential of machine-learning methodologies in modeling complex physical systems, as evidenced by their efficiency in capturing the behavior of nanofluids under various conditions. The obtained accuracy and low mean absolute error values indicate the robustness of these machine-learning models in predicting heat transfer results. The implications of these findings are substantial for the field of heat exchanger design and optimization. The study suggests that machine-learning techniques offer a more efficient and cost-effective approach compared to traditional numerical simulations. By leveraging the capabilities of these models, there is potential for enhanced accuracy and efficiency in the design and optimization processes of heat exchangers, contributing to advancements in thermal engineering.

Study on Imagery Modeling of Electric Recliner Chair: Based on Combined GRA and Kansei Engineering

This study aims to integrate data-driven methodologies with user perception to establish a robust design paradigm. The study consists of five steps: (1) theoretical research—a review of the subject background and applications of Kansei engineering and gray relational analysis (GRA); (2) algorithmic framework research—the discussion delves into the intricate realm of Kansei engineering theory, accompanied by a thorough elucidation of the gray relational analysis (GRA) algorithmic framework, a crucial component in constructing a fuzzy logic model for product image modeling; (3) Kansei data collection—18 groups of perceptual words and six classic samples are selected, and the electric recliner chair samples are scored by the Kansei words; (4) Kansei data analysis—morphological analysis categorizes the electric recliner chair into four variables. followed by the ranking and key consideration areas of each area; (5) GRA fuzzy logic model verification—the GRA fuzzy logic model performs simple–complex (S-C) imagery output on 3D models of three modeling instances. By calculating the RMSE value of the seat image modeling design GRA fuzzy logic model, it is proven that the seat image modeling design GRA fuzzy logic model performs well in predicting S-C imagery. The subsequent experimental study results also show that the GRA fuzzy logic model consistently produces lower root mean square error (RMSE) values. These results indicate the efficacy of the GRA fuzzy logic approach in forecasting the visual representation of the electric recliner chair shape’s 3D model design. In summary, this research underscores the practical utility of the GRA model, harmoniously merged with perceptual engineering, in the realm of image recognition for product design. This synergy could fuel the extensive exploration of product design, examining perceptual engineering nuances in product modeling design.

Accuracy and reproducibility of two-dimensional computed tomography-based positioning of femoral component rotational alignment in preoperative planning for total knee arthroplasty

BackgroundPoor rotation of the femoral component in total knee arthroplasty (TKA) can result in various postoperative complications, underscoring the critical importance of preoperative planning.PurposeTo improve the accuracy of femoral component positioning during TKA, this study compared the accuracy and repeatability of different two-dimensional (2D) computed tomography (CT) measurement methods for measuring the posterior condylar angle (PCA) in preoperative TKA planning.MethodsA retrospective analysis was conducted on 75 patients (150 knees) who underwent bilateral lower extremity computed tomography angiography (CTA) at Fuyang People's Hospital from January 2021 to July 2021. Three different methods were used to measure the PCA based on 2D CT images (axial CT slices) and three-dimensional(3D) models (femoral models reconstructed from CT data) in this study. Method 1: Single-plane 2D CT measurement, measuring PCA in the most obvious single-plane CT slice of the surgical transepicondylar axis (sTEA); Method 2: multi-plane 2D CT measurement, identifying and locating anatomical landmarks in multiple 2D CT slices and measuring PCA; Method 3: 3D model measurement, measuring PCA in the reconstructed femur 3D model. Compare the differences in PCA measurements between the three measurement methods. A positive PCA measurement was recorded when the sTEA was externally rotated relative to the posterior condylar line (PCL). Any difference exceeding 3° between the PCA measurement in the 2D CT and the PCA reference value in the 3D model was classified as an outlier. The intraclass correlation coefficient (ICC) and Bland–Altman method were utilized to assess the intra- and inter-observer reproducibility of the three measurement methods.ResultsThe PCA measurement in the single-plane 2D CT was 1.91 ± 1.94°, with a measurement error of − 1.22 ± 1.32° and 12.7% of outlier values. In the multi-plane 2D CT, the PCA measurement was 2.96 ± 1.68°, with a measurement error of -0.15 ± 0.91° and 6.0% of outlier values. The PCA measurement in the 3D model was 3.12 ± 1.69°. The PCA measurement in single-plane 2D CT was notably smaller than that in multi-plane 2D CT and 3D models, with no significant difference between the latter two. The multi-plane 2D CT showed significantly lower measurement error and outlier values than the single-plane 2D CT. All three PCA measurement methods exhibited high reproducibility (ICC: 0.93 ~ 0.97).ConclusionsUsing of multi-plane 2D CT for measuring PCA in preoperative planning of TKA has high reproducibility and accuracy, with fewer outlier values. We recommend preoperative measurement of PCA using muti-plane 2D CT to improve the accuracy of positioning the femoral component rotational alignment during surgery.

Python-Powered Precision: Unraveling Consumer Price Index Trends in Makassar City through a Duel of Long Short-Term Memory and Gated Recurrent Unit Models

This research aims to carry out a predictive analysis of the Consumer Price Index in the city of Makassar to anticipate possible impacts on inflation and deflation in the future. The Consumer Price Index is an indicator that can be used as a basis for measuring changes in the prices of goods and services purchased by consumers which have an impact on inflation in a region. The CPI is very useful for knowing the level of increase in prices, services, and income, as well as measuring the amount of production costs. This data was obtained through the official website of the Central Statistics Agency (BPS) for the Makassar city area. The methods used in this research are Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results of this research show that based on analysis and testing, the LSTM model has an MAE of 1.0849 and the GRU model has an MAE of 0.9915, which shows that there is no significant difference between the two methods and both methods can work very well, however, The lowest error value was obtained in the GRU model using a 70:30 dataset ratio, 9 number of sequences, 16 neurons in hidden layer 1 and 32 neurons in hidden layer 2, and 1000 number of epochs.

Utilizing an intelligent machine learning strategy for predicting the tensile strength and ductility properties of nitrogen doped CoCrFeMnNi based high entropy alloys

The integration of machine learning (ML) within the realm of artificial intelligence has unveiled remarkable potential for predicting material properties. Particularly, determining critical properties such as yield strength (YS), tensile strength (UTS), and elongation in high entropy alloys (HEAs) has been a formidable challenge due to the extensive composition possibilities. The application of ML methods offers a viable solution for determining the optimal composition and mechanical properties of HEA materials. In this study, six ensemble ML algorithms, including random forest (RF), adaboost, xgboost, gradient boosting, bagging, and extra trees are employed to predict the tensile strength and ductility of nitrogen (N) doped CoCrFeMnNi based HEAs, which includes yield strength, tensile strength, and elongation properties. To explore the correlations between different features in the dataset, both the Pearson correlation and SHAP (SHapley Additive exPlanations) coefficient methods are employed. The gradient boosting ML model, in particular, distinguished itself with remarkable precision, achieving outstanding coefficient of determination (R2) values of approximately 98.25% for YS, 97.39% for UTS, and 94.45% for elongation. Moreover, it demonstrated lower mean absolute error (MAE) values for yield strength (32.62 MPa), tensile strength (37.48 MPa), and elongation (3.40%). This pattern strongly emphasizes its superiority in providing more accurate predictions compared to the other models. Notably, the model's prediction results for all three tensile properties are closely matched with the values obtained through experimental testing. This alignment between predictions and actual results serves as a crucial validation of the model's exceptional accuracy and reliability in precisely predicting these properties. Furthermore, the scrutinizing the impact of both prominent and less influential features on the ML model's performance is analyzed. Thereby, these findings underscore the remarkable effectiveness of the gradient boosting model as a predictive tool, emphasizing its ability to provide highly accurate and reliable predictions for HEAs properties.

A highly effective SERS platform formed by the fabrication of Ag@ZIF-8@Au nanoparticles for rapid detection of acetamiprid in environment

The unreasonable spraying and random migration of acetamiprid may cause pollution of crops, soil and water resources in the environment, resulting in threatening ecosystem and human health. However, the monitoring of acetamiprid using mass spectrum in the environment encounters challenges due to high-cost instruments and complex processing time. Herein, we fabricated a rapid and reliable SERS method based on Ag@ZIF-8@Au platforms for tracing acetamiprid residues in the environment. In this method, a MOF material named ZIF-8 is coated with silver nanoparticles and distributed internally between AgNPs and AuNPs to enhance Raman signal, which can enrich pesticide molecules into the hotspots area provided by noble material and helps avoid the oxidation of silver nanoparticles. High sensitivity (LOD of 9.027 × 10-10 M for acetamiprid, and SERS enhancement factor of 4.3 × 107), excellent reproducibility (6.496% or 7.198% RSD for 30 random points) and superior stability (3.127% RSD for 6 weeks) were achieved using the proposed method. Acetamiprid with concentrations from 10-4 to 10-9 M were successfully detected by SERS method. Furthermore, the linear detection models of acetamiprid in different environment matrices (lake water, tea leaves, tea garden soil, oranges and oranges orchard soil) were established and all the correlation coefficient (R2) were higher than or equal to 95%, indicating the excellent adaptability of Ag@ZIF-8@Au platform in environment. The randomly spiked concentrations of acetamiprid were also tested with good recovery values and low relative error values, further confirming the reliability of the detection method.

Prediction of gross calorific value from coal analysis using decision tree-based bagging and boosting techniques

The calorific value of any fuel is one of the crucial parameters to grade fuel's burning capability. The bomb calorimeter has historically been used to calculate coal's gross calorific value (GCV). However, for many years, engineers and scientists were trying to measure coal's GCV without a bomb calorimeter, using only laboratory-derived ultimate and/or proximate analyses to eliminate tedious and time-consuming laboratory analyses. In this study, Extra trees, Bagging, Decision tree, and Adaptive boosting are developed for the first time in coal's GCV modeling. In addition, the prediction and computational efficiency of previously applied decision tree-based algorithms, such as Random forest, Gradient boosting, and XGBoost are investigated. Well-established empirical models, namely Schuster, Mazumdar, Channiwala and Parikh, Parikh et al. and Central Fuel Research Institute of India are examined to compare their efficiency with newly developed algorithms. Proximate and ultimate analysis parameters are ranked based on their significance in GCV modeling. The studied models are tuned using an exhaustive grid search technique. Statistical indexes, such as explained variance (EV), mean absolute error (MAE), coefficient of determinant (R2), mean squared error (MSE), maximum error, minimum error, and mean absolute percentage error (MAPE) are used to critique these models. To accomplish the goals, 7430 data points containing ten coal features, such as ash, moisture, fixed carbon, volatile matter, hydrogen, carbon, sulfur, nitrogen, oxygen, and GCV are selected from the U.S. Geological Survey Coal Quality (COALQUAL) database. It has been found that, due to simplicity and location-specific constraints, empirical models could not correlate proximate and/or ultimate analyses with GCV. Bagging and boosting techniques tested here performed well with the coefficient of determinant (R2) of over 0.97. The XGBoost model outperforms other tree-based algorithms with the most significant coefficient of determinant (R2 of 0.9974) and lowest error values (MSE of 14703.3, max_error of 1027.2, MAE of 89.2, MAPE of 0.009). The studied models' ranking (highest to lowest) based on their performance are XGBoost, Extra trees, Random forest, Bagging, Gradient boosting, Decision tree, and Adaptive boosting. The correlation heatmap and scatterplots used here clearly indicate that oxygen and carbon are the utmost significant, whereas volatile matter and sulfur are the least essential rank parameters for GCV modeling. The strategy suggested in this research can aid engineers/operators in obtaining a rapid and accurate determination of the GCV with a few coal features, thus lessening complicated, tedious, expensive, and time-consuming laboratory efforts.

Identifying complex causal patterns in students’ performance using machine learning

ABSTRACT Today, in every academic institution as well as the university system assessing students’ performance, identifying the uniqueness of each student and finding solutions to performance problems have become challenging issues. The main purpose of the study is to predict how student performance changes as a result of their behaviours, hobbies, extracurricular activities and different university activities. This study collected data from graduates via the online and supervised machine learning algorithms used to solve the problem. After pre-processing data, classification algorithms were applied, namely Random Forest, Multi-Layer Perceptron, Support Vector Machine, Naïve Bayes and Decision Tree. The results show that the Multi-Layer Perceptron is the best algorithm considering the highest accuracy and lowest error values. An ensemble learning algorithm was then applied by combining those five algorithms. The best results were obtained using it, and according to the final results, ensemble learning increases the accuracy rather than each classifier.

Comparison of the sensitivities and accuracies of optoelectronic transducers for solar irradiance measurement

This paper compares the sensitivities and accuracies of four different optoelectronic transducers in measuring solar irradiance for the fabrication of portable and low-cost pyranometers. Trans-impedance conditioning circuits were designed for two phototransistors (BP103 and SFH3310) and two photodiodes (BPW21 and BPW34). The Arduino Mega 2560 was used as an interface between the analogue signal produced by the conditioning circuits and the digital output ports. The transducers with a standard pyranometer RSRA_05V were arranged on a vero board and exposed to the sun. Statistical analysis of the experimental results produced the least root mean square error value of 6.58794 Wm−2 for phototransistor BP103 during the dry season followed by 13.35216 Wm−2 for phototransistor SFH3310 during the dry season. The correlation coefficients of BPW21, BPW34, BP103, and SFH3310 with the standard pyranometer are 0.9489, 0.9916, 0.9976, and 0.9905, respectively. The experimental results obtained from the phototransistors BP103 and SFH3310 strongly correlated with those of the standard pyranometer coupled with lower root mean square error and mean bias error values than those of the photodiodes. Thus, the phototransistors BP103 and SFH3310 are more accurate and effective for measuring solar irradiance. This study contributes to the development of low-cost and accurate solar radiation meters.

A comparison of CAPM and Fama-French three-factor model under Machine Learning approaching

With the economy experiencing rapid growth in recent years, more individuals have started venturing into the stock market. Precisely forecasting the rate of return can mitigate investment risks for stock investors and significantly enhance their investment returns. The Capital Asset Pricing Model (CAPM) and the 3-factor Fama-French model (FF3) are widely recognized in academic and practical settings. This model comparison provides frameworks to analyze the relationship between portfolio risk and return in inefficient markets. This research utilized the Support Vector Regression (SVR) algorithm to forecast the returns of a diversified portfolio in the Hanoi stock market (HNX) from 2010 to 2022. Subsequently, the explanatory power of the CAPM and FF3 models were compared using the Ordinary Least Squares (OLS) algorithm. Finally, this research incorporated the SVR algorithm within the FF3 framework to develop a predictive model. The research findings demonstrate that the FF3 model provides a superior explanation to the CAPM model. Additionally, the study reveals that the SVR algorithm outperforms the OLS algorithm in terms of efficiency, as it yields lower Root Mean Square Error (RMSE) values. Consequently, the next research direction entails replacing the FF3 model with a more comprehensive multi-factor model, anticipating obtaining an enhanced predictive model.

Rapid parameter identification of three diode photovoltaic systems using the Cheetah optimizer

This study focuses on accurate parameter identification for solar cells and photovoltaic module simulation using experimental data. To tackle the challenge of modelling these highly nonlinear systems, we propose the novel use of the Cheetah Optimizer (CO) algorithm, inspired by cheetah hunting strategies. The CO algorithm employs mathematical models and randomization parameters to balance exploration and exploitation, avoiding local optima by considering energy limitations. We demonstrate the CO algorithm's effectiveness by applying it to the three-diode model in solar photovoltaic systems, specifically the STP6-120/36 and Photowatt-PWP201 PV modules. Impressively, the CO algorithm achieves remarkably low root mean square error values of 0.0145 A and 0.0019 A, outperforming state-of-the-art methods and ensuring high accuracy. Additionally, it delivers the lowest power errors of 0.16054 W and 0.01484 W for the respective modules, highlighting its exceptional performance. The CO algorithm proves to be a promising tool for precise parameter extraction and optimization, leading to improved modelling and performance of solar photovoltaic systems.

A Collaborative Filtering Recommendation Algorithm Model Based on User Feature Transfer

The quality of teaching resources and recommended practices in flipped classrooms determine the advantages and disadvantages of this educational model. However, current teaching resource recommendation platforms suffer from issues such as cold startup and sparse data. In order to address these issues, a collaborative filtering recommendation algorithm based on user feature transfer was proposed and utilized to examine the correlation between students’ preference behavior and the recommendation of teaching resources in flipped classes for tourism management. The aim was to enhance the quality of teaching in current classes. Using this algorithm, a transfer by user feature (TUF) model is constructed. In this model, a soft embedding method is employed to accurately extract user feature information in the auxiliary space. This method addresses the challenge of filling large-scale missing matrices in the auxiliary space. Additionally, singular value decomposition is performed to obtain more precise user features. Finally, an optimized Wiberg algorithm with rapid convergence is designed to solve the constructed model. The performance of this algorithm is measured and compared using two common datasets. Compared to other algorithms, the proposed algorithm demonstrates superior performance and a lower mean absolute error value. In summary, the recommendation algorithm can enhance the quality of resource organization and provide more suitable personalized recommendations for the recommendation platform. This is beneficial for improving the quality of students’ learning.