MSE Values Research Articles

Construction of low-carbon economic enterprise management mode based on grey digital model

Since the proposal of the low-carbon economy plan, all countries have deeply realized that the economic model of high energy and high emission poses a threat to human life. Therefore, in order to enable the economy to have a longer-term development and comply with international low-carbon policies, enterprises need to speed up the transformation from a high-carbon to a low-carbon economy. Unfortunately, due to the massive volume of data, developing a low-carbon economic enterprise management model might be challenging, and there is no way to get more precise forecast data. This study tackles the challenge of developing a low-carbon enterprise management mode based on the grey digital paradigm, with the aim of finding solutions to these issues. This paper adopts the method of grey digital model, analyzes the strategy of the enterprise to build the model, and makes a comparative experiment on the accuracy and performance of the model in this paper. The results show that the values of MAPE, MSE and MAE of the model in this paper are the lowest. And the r^2 of the model in this paper is also the highest. The MAPE value of the model in this paper is 0.275, the MSE is 0.001, and the MAE is 0.003. These three indicators are much lower than other models, indicating that the model has high prediction accuracy. r^2 is 0.9997, which is much higher than other models, indicating that the performance of this model is superior. With the support of this model, the efficiency of building an enterprise model has been effectively improved. As a result, developing an enterprise management model for the low-carbon economy based on the gray numerical model can offer businesses new perspectives into how to quicken the shift to the low-carbon economy.

Design of a Novel Fractional Whale Optimization-Enhanced Support Vector Regression (FWOA-SVR) Model for Accurate Solar Energy Forecasting

This study presents a novel Fractional Whale Optimization Algorithm-Enhanced Support Vector Regression (FWOA-SVR) framework for solar energy forecasting, addressing the limitations of traditional SVR in modeling complex relationships within data. The proposed framework incorporates fractional calculus in the Whale Optimization Algorithm (WOA) to improve the balance between exploration and exploitation during hyperparameter tuning. The FWOA-SVR model is comprehensively evaluated against traditional SVR, Long Short-Term Memory (LSTM), and Backpropagation Neural Network (BPNN) models using training, validation, and testing datasets. Experimental results show that FWOA-SVR achieves superior performance with the lowest MSE values (0.036311, 0.03942, and 0.03825), RMSE values (0.19213, 0.19856, and 0.19577), and the highest R2 values (0.96392, 0.96104, and 0.96192) for training, validation, and testing, respectively. These results highlight the significant improvements of FWOA-SVR in prediction accuracy and efficiency, surpassing benchmark models in capturing complex patterns within the data. The findings highlight the effectiveness of integrating fractional optimization techniques into machine learning frameworks for advancing solar energy forecasting solutions.

Anchorage of ZnO quantum dots and CuO on graphene for sonophotocatalytic treatment of pharmaceutical effluent: From experimental data and prediction by advanced machine learning algorithms

Quantum dots (QDs) have recently received much attention as photocatalysts due to their unique properties. Despite the advantages reported for QDs as photocatalysts in literature, their sonophotocatalytic/photocatalytic activity is still hindered by a series of barriers, which limit them to operate after several successive cycles efficiently. The main aim of this work is to fabricate an efficient and recyclable sonophotocatalyst/photocatalyst using ZnO quantum dots (ZQDs), tenorite (CuO), and graphene (G). In this regard, different amounts of ZQDs (ZQDs(x)/G, x= 10, 20, 30, 40, and 50mg) were immobilized on graphene by hydrothermal method and various weight percent of CuO was impregnated on ZQDs(40)/G. The PXRD patterns and Raman spectra confirmed the wurtzite and monoclinic crystal structure for ZQDs and CuO, respectively. Also, FESEM, AFM, and PXRD showed that the mean crystal size of ZQDs increased after immobilization on graphene and impregnation by CuO. PL and Mott–Schottky analyses showed that the presence of GO and CuO in CuO(0.5)/ZQDs(40)/G reduced the recombination of excitons and formed p-n heterogeneous junctions between CuO and ZnO. The VB and CB potential and bandgap energy were obtained using DRS and Mott–Schottky analyses, and the mechanism of tetracycline (TC) degradation was proposed according to active species trapping and H2O2 paper testes. The apparent rate constant (kapp) was 0.030 and 0.060min-1 for photocatalytic and sonophotocatalytic degradation of TC in the presence of CuO(0.5)/ZQDs(40)/G, respectively. The treated effluent of TC showed acceptable performance in growing wheat seeds. The electricity cost estimation showed that (CuO(0.5)/ZQDs(40)/G) consumed less electricity in sonophotocatalytic/photocatalytic TC degradation and could also be used in several successive cycles. Finally, two RF and AdaBoost models based on ML algorithms were developed to predict photocatalytic/sonophotocatalytic degradation. The results showed that the values of statistical metrics, including SAE, MAE, MSE, and RMSE, for the AdaBoost model were relatively lower than those for the RF model, indicating better prediction performance in train and test datasets.

Relationship between body weight and dorsal area in female buffaloes

Background: Body weight (BW) has been reported as important information in the decision-making process; therefore, it is necessary to determine if body measurements obtained from the dorsal view of the animal are related to BW, considering that we are currently living in the era of the so-called "livestock 4.0". Objective: The objective of the present study was to evaluate the relationship between BW and dorsal area (DA) in water buffaloes (Bubalus bubalis) reared in southeastern Mexico. Methods: The BW (340 ± 161.68 kg), hip width (BW), thorax width (TW) and body length (BL) were measured in 215 female Murrah buffaloes aged between 3 months and 5 years. The DA (m2) was calculated using the mathematical formulae for calculating the area of a trapezoid, considering the HW, TW, and BL in the calculation. The relationship between BW and DA was assessed using correlation and regression models. Results: The correlation coefficient between BW and AD was 0.96 (P<0.001). The linear equation demonstrates the highest determination coefficient value (R2 = 0.94) along with the lowest mean square error (MSE = 1716.86), root MSE (RMSE = 41.43), Akaike Information Criterion (AIC = 1603.36), and Bayesian Information Criterion (BIC = 1610.10). Conversely, the allometric equation exhibits the highest values of MSE, RMSE, AIC, and BIC. The quality of fit using the k-folds technique allowed us to identify that the three proposed equations showed consistent adjustments, with an accuracy above 90% (R2 = 0.92). Among them, the quadratic equation exhibited lower values of mean squared prediction error and mean absolute error. Conclusions: The DA can be a good predictor of BW in buffaloes, especially when incorporated into first and second-degree linear equations.

Application of Ensemble Machine Learning for Infectious Diseases with Vaccine Intervention: A Global COVID-19 Case Study

The COVID-19 pandemic has posed significant challenges worldwide, especially in controlling the spread of the disease through vaccination and active case monitoring. This study aims to evaluate the effectiveness of various ensemble machine-learning models in predicting the number of daily vaccinations and the number of active cases of COVID-19 based on global data. The models used include Random Forest, Bagging, Gradient Boosting Machine (GBM), AdaBoost, and XGBoost. The evaluation results show that Random Forest provides the best performance in predicting both the number of daily vaccinations and active COVID-19 cases, with a MSE value of 4.7e+09, MAE of 16,971.1, and RMSE of 68,557.2 for daily vaccinations, as well as an R² Score of 0.989, indicating a high ability to explain data variability. The Bagging model also showed excellent results with MSE of 4.78e+09 and MAE of 17,039.8. In contrast, the AdaBoost model performed the worst in predicting both variables, with an MSE of 5.54e+10 and an MAE of 106,228.6. These findings suggest that Random Forest and Bagging are superior models for predicting the number of daily vaccinations and active COVID-19 cases. This study provides important insights into using machine learning to predict vaccination effectiveness and active case dynamics, aiding decision-making in global pandemic control efforts.

Enhanced Brain Tumor Classification Through Optimized Semantic Preserved Generative Adversarial Networks.

Brain tumor is a most dangerous disease and requires accurate diagnosis in a short period to ensure the best treatment. Traditional methods for brain tumor classification (BTC) are quite effective, even though usually resulting in clinical manual analysis, which takes more time and prone to errors. Initially, the input image is collected from Brain Tumor dataset. The gathered image is given to preprocessing. In preprocessing stage, trust-based distributed set-membership filtering (TDSF) is used to remove the noise. The preprocessed output is fed to the quaternion offset linear canonical transform (QOLCT) for Grayscale statistic and Haralick texture features extraction. Then the extracted features are fed to the Semantic-Preserved Generative Adversarial Network (SPGAN) for classifying the brain tumor into Glioma, Meningioma and Pituitary. Finally, Hunger Games Search Optimization (HGSO) is used to enhance the weight parameters of SPGAN. The proposed BTC-SPGAN-HGSO method attains the accuracies of 99.72% for Glioma, 99.65% for Meningioma, 99.52% for Pituitary and lowest MSE values across all tumor types, with 0.45% for Glioma, 0.39% for Meningioma, and 0.5% for Pituitary, which performs better than existing models. The simulation results highlight the effectiveness of the proposed BTC-SPGAN-HGSO approach in improving the accuracy of BTC and assist neurologists and physicians make exact decisions of diagnostic.

MACHINE LEARNING FOR COST ESTIMATION AND FORECASTING IN BANKING: A COMPARATIVE ANALYSIS OF ALGORITHMS

Accurate cost estimation and forecasting are critical for effective decision-making in the banking sector. This study evaluates the performance of machine learning algorithms, including Linear Regression, Ridge Regression, Random Forest, Gradient Boosting Machine (GBM), and Long Short-Term Memory (LSTM) networks, for cost prediction using a robust dataset comprising operational, transactional, and macroeconomic features. Our results demonstrate that while simpler models like Linear and Ridge Regression offer computational efficiency, their predictive accuracy is limited in handling complex data. Tree-based methods, particularly Random Forest and GBM, significantly enhance performance by capturing intricate patterns, albeit at a higher computational cost. The LSTM network outperformed all models, achieving the highest R² score and the lowest MAE and MSE values, highlighting its superiority in capturing temporal dependencies. This research provides actionable insights for banking institutions, emphasizing the trade-offs between accuracy, efficiency, and model complexity. The findings pave the way for optimized ML adoption in financial forecasting, enhancing operational resilience and strategic planning.

Genomic predictors of drug sensitivity in cancer: Integrating genomic data for personalized medicine in the USA

Despite applying conventional predictive methodologies to obtain genomic insights, predicting drug sensitivity for healthcare organizations in the USA remains a daunting challenge. Cancer is a highly dynamic, adaptive disease tumor cells have repeatedly shown the capability to evolve mechanisms whereby therapeutic interventions can be evaded. Besides, one genomic alteration seldom predicts drug sensitivity. This research project aimed to address the challenges of predicting drug sensitivity by leveraging the GDSC dataset, an extensive resource connecting genomic profiles of cancer cell lines with their sensitivity to a wide range of anti-cancer drugs. This research's key focus was identifying robust genomic markers, including any specific mutations, gene expression patterns, or epigenetic modifications associated with drug sensitivity or resistance. Advanced machine learning and statistical methods were utilized by the predictive models to analyze complex relations that may exist between different genomic alterations and their drug sensitivity. The dataset used for this research project was derived from the Kaggle website. This dataset was compiled by the research project Genomics of Drug Sensitivity in Cancer collaboration between the Sanger Institute in the United Kingdom and the Massachusetts General Hospital Cancer Center in the United States. In their investigation, there was a massive screening of human cancer cell lines with a wide range of anti-cancer drugs. Data collection was performed by large-scale screening of diverse anti-cancer drugs against human cancer cell lines of various types. Cell viability was measured using the Cell-Titer-Glo assay following 72 hours of drug treatment. Several machine learning models were deployed, namely, Random Forest, Linear Regression, and XG-Boost, which exhibited specific strengths. Specific performance metrics used included MSE, RMSE, MAE, and R². As the statistics indicate, among the three models, Random Forest stands out and performs the best on this dataset across all metrics. A smaller value of MAE, MSE, and RMSE signifies that it provided the best forecast for the target variable. It also gave the highest R-squared value. Application of drug sensitivity prediction analysis in cancer can provide an overview of the mechanisms that underlie both tumor response and resistance by investigating the model predictions. The proposed predictive models have the potential to make significant impacts on clinical decision-making in cancer therapy. Predictive models derive informed decisions regarding a patient's risk of recurrence of disease, their response to certain therapies, and their prognosis based on complex clinical and genomic data. Keywords: Genomic Predictors; Drug Sensitivity; Genomic Markers; Personalized medicine; Machine Learning; Random Forest Algorithm.

Implementation of Supervised Learning Algorithm to Predict Climate Factors in Pangkalpinang

Abstract Currently, the world is experiencing erratic climate conditions, characterized by an increase in frequency and intensity of extreme weather, as well as significant climate changes such as an increase in global temperatures. Pangkalpinang city is one of cities with the highest population density in Bangka Belitung Islands. This population density contributes to climate change through increased greenhouse gas emissions from transportation activities, industry, and high energy consumption. Conversely, climate change also has an impact on environmental conditions and the quality of life, making it important to predict climate factors to effectively manage their impact. The purpose of this research is to determine the prediction of climate factors in Pangkalpinang City. In this research, three Supervised Learning algorithm research methods were used, including Linear Regression, ANN (Artificial Neural Network), and XGBoost Regressor (Extreme Gradient Boosting Regressor). Based on the results of the research that has been conducted, it shows that the XGBoost Regressor model provides the best performance with an MSE value of 79.304 and the smallest MAPE value of 16.912. Beside it, the R-squared value is 0.654. This model shows a good ability to predict climate variables compared to other methods. This finding can be the basis for more appropriate policy making in anticipating and managing the impacts of climate change in Pangkalpinang.

Residual Pix2Pix networks: streamlining PET/CT imaging process by eliminating CT energy conversion.

Objective
Attenuation correction of PET data is commonly conducted through the utilization of a secondary imaging technique to produce attenuation maps. The customary approach to attenuation correction, which entails the employment of CT images, necessitates energy conversion. However, the present study introduces a novel deep learning-based method that obviates the requirement for CT images and energy conversion.
Methods
This study employs a residual Pix2Pix network to generate attenuation-corrected PET images using the 4033 2D PET images of 37 healthy adult brains for train and test. The model, implemented in TensorFlow and Keras, was evaluated by comparing image similarity, intensity correlation, and distribution against CT-AC images using metrics such as PSNR and SSIM for image similarity, while a 2D histogram plotted pixel intensities. Differences in standardized uptake values (SUV) demonstrated the model's efficiency compared to the CTAC method.
Results
The residual Pix2Pix demonstrated strong agreement with the CT-based attenuation correction, the proposed network yielding MAE, MSE, PSNR, and MS-SSIM values of 3×10-3, 2×10-4, 38.859, and 0.99, respectively. The residual Pix2Pix model's results showed a negligible mean SUV difference of 8×10-4(P-value = 0.10), indicating its accuracy in PET image correction. The residual Pix2Pix model exhibits high precision with a strong correlation coefficient of R2 = 0.99 to CT-based methods. The findings indicate that this approach surpasses the conventional method in terms of precision and efficacy.
Conclusions
The proposed residual Pix2Pix framework enables accurate and feasible attenuation correction of brain F-FDG PET without CT. However, clinical trials are required to evaluate its clinical performance. The PET images reconstructed by the framework have low errors compared to the accepted test reliability of PET/CT, indicating high quantitative similarity.&#xD.

IoT-based automated system for water-related disease prediction

Having access to potable water is a fundamental right to well-being. Despite this, 3.4 million people die from diseases caused by water each year, and 1.1 billion people lack access to potable drinking water. Although industrialization, durable infrastructure, and rapid development have increased living standards, the water problem has left humanity defenseless. As different human activities have contaminated these water reserves, according to an estimate, water is the cause of 80% of ailments. As a result, it is necessary to permit enough infrastructure to ensure the security of a reliable supply of potable water. Thus, a real-time WBPCB dataset with 17 features and a proposed IoT-based system to collect data are used in this research to address the issue. The research paper provides a system for predicting diseases and forecasting long-term trends. Classification is performed using Random Forest, XGBoost, and AdaBoost, which have accuracy rates of 99.66%, 99.52%, and 99.64%, respectively. Forecasting is performed using LSTM, which has an MSE value for the pH parameter of 0.1631. The paper introduces TS-SMOTE, a novel hybridized time-series SMOTE data augmentation approach. Additionally, it offers an IoT system that uses H-ANFIS to gather data in real-time and identify attacks.

Efficient Pruned-DFT FBMC-OQAM for Performance Enhancement of MIMO Channel Equalization Techniques

A The next generation of wireless systems, like 5G/6G, ought to accommodate a wide range of potential use cases like massive real-time and machine-type communications. Accordingly, such systems need to provide high throughput, low latency, and a low peak to average power ratio (PAPR). It is not feasible to fulfil each of these needs with a single 5G/6G technique. On one hand, MIMO technique can potentially improve spectral efficiency and hence support more date rates. On the other hand, the utilization of multi-carriers’ techniques like FBMC/OQAM, or offset quadrature amplitude modulation, offers a compelling substitute for the traditional cyclic prefix-based orthogonal frequency division multiplexing (CP-OFDM) because of its excellent spectral efficiency and extremely low out-of-band radiation. However, the FBMC/OQAM orthogonality constraint is loosened, confined to the real field alone, resulting in intrinsic interference. This interference causes incompatibilities between FBMC/OQAM and certain MIMO schemes. Also, equalizing the time-varying MIMO channel is even more difficult when the complex valued symbol—which includes both real and imaginary FBMC/OQAM task, primarily due to the general non-flatness of the subchannels. From this perspective, we first suggest in this paper an efficient pruned-DFT-based implementation of MIMO to restoring the complex orthogonality and also reduce the complexity of the whole system. Then, we optimize MIMO channel equalization by efficiently separating and equalizing multiple parallel channels using various equalization techniques. The numerical results, presented as MSE versus subcarrier index, show that Pruned DFT technique consistently achieves lower MSE values compared to the standard MIMO FBMC-OQAM across various configurations, which indicates better error performance and its robustness in dynamic channel conditions.

Prediction of the Number of Motorized Vehicles in Ternate City Using the Average Based Fuzzy Time Series Model Method

Prediction or forecasting is one of the most important elements in decision-making. The impact caused is the number of motorized vehicles, residents, roads, and area area. By predicting the number of motor vehicles, the prediction data can be used from a program to reduce the impact of a high number of motor vehicles. This study aims to determine the Prediction of the Number of Motorized Vehicles in Ternate City using the Average Based Fuzzy Time Series Model Method in Ternate City from 2019 to 2024. Settlement using Average Based Method data and fuzzy time series interval numbers have been determined at the beginning of the calculation process, this process is very influential in the formation of fuzzyrelationship on each number to compare each other which will certainly have an impact on the difference in the results of the reduction calculation. The test results are known that the Fuzzy time series is one of the methods for prediction. One type of method is the average-based fuzzy time series with the average total value calculated using the Mean Absolute Percentage Error (MAPE) method obtained from the number of each indicator of 2.98% which shows that this study is included in the category of good used in the prediction of motor vehicles in Ternate City because it has an accuracy value of less than 20%. From the predictions carried out, the MAPE value of the test was 1.01%, the MSE value of forecasting was 1400.5, and the MAD value of forecasting was 27.93.

Analisis Peramalan Persediaan Sparepart Menggunakan Metode Exponential Smoothing di PT. XYZ

XYZ is a manufacturing company that produces Yamaha brand motorbike parts such as electrical switches, electrical sockets, lever assembly and horns. Many of the products sent were returned by customers because they did not meet quality standards, for example in March 2024 there were 1,420 pcs out of a total of 19,900 pcs that were returned. This means that companies have to increase production time and costs to replace defective products that are returned because they do not have safety stock. Forecasting is needed to control the production system so that it does not experience over stock and safety stock shortages. This research aims to provide recommendations for forecasting methods that companies can use to minimize the occurrence of production excesses and shortages in the company. Forecasting is done based on historical company sales data for 12 months. The method used is the exponential smoothing method which is then tested whether this method can be used in the future. This calculation uses the help of POM-QM (Production Operation Management – Quantitative Method) software. Calculations are carried out by testing the MAD, MSE, and MAPE values to obtain calculation error values. The results obtained by forecasting the main sw srtg lock assembly product using the exponential smoothing method were 15,708 for demand for the next period, MAD 3.38, MSE 22.84 and MAPE value 26%. Based on these results, the exponential smoothing method can be a recommendation for companies to forecast future demand. This is because the value of forecasting accuracy or MAPE is reasonable. The smallest percentage of MAPE values has a fairly minimal possibility of error in forecasting results.

Optimizing deep neural network architectures for renewable energy forecasting

An accurate renewable energy output forecast is essential for energy efficiency and power system stability. Long Short-Term Memory(LSTM), Bidirectional LSTM(BiLSTM), Gated Recurrent Unit(GRU), and Convolutional Neural Network-LSTM(CNN-LSTM) Deep Neural Network (DNN) topologies are tested for solar and wind power production forecasting in this study. ARIMA was compared to the models. This study offers a unique architecture for Deep Neural Networks (DNNs) that are specifically tailored for renewable energy forecasting, optimizing accuracy by advanced hyperparameter tuning and the incorporation of essential meteorological and temporal variables. The optimized LSTM model outperformed others, with MAE (0.08765), MSE (0.00876), RMSE (0.09363), MAPE (3.8765), and R2 (0.99234) values. The GRU, CNN-LSTM, and BiLSTM models predicted well. Meteorological and time-based factors enhanced model accuracy. The addition of sun and wind data improved its prediction. The results show that advanced deep neural network (DNN) models can predict renewable energy, highlighting the importance of carefully selecting characteristics and fine-tuning the model. This work improves renewable energy estimates to promote a more reliable and environmentally sustainable electricity system.

Using data-driven models to simulate the performance of surfactants in reducing heavy oil viscosity

There is a substantial body of literature exploring the challenges associated with exploring and exploiting these underground resources. Unconventional resources, particularly heavy oil reservoirs, are critical for meeting ever-increasing global energy demand. By injecting surfactants into heavy oil, chemically enhanced oil recovery (EOR) may enable emulsification, which may reduce the viscosity of heavy oil and facilitate extraction and transportation. In this work, a large experimental dataset, containing 2020 data points, was extracted from the literature for modeling oil-in-water (O/W) emulsion viscosity using machine learning (ML) methods. The algorithms used pressure, temperature, salinity, surfactant concentration, type of surfactant, shear rate, and crude oil density as inputs. For this purpose, five ML algorithms were selected and optimized, including adaptive boosting (AB), convolutional neural network (CNN), ensemble learning (EL), artificial neural network (ANN), and decision tree (DT). A combined simulated annealing (CSA) method was utilized to optimize all algorithms. With AARE, R2, MAE, MSE, and RMSE values of 8.982, 0.996, 0.004, 0.0002, and 0.0132, respectively, the ANN predictor exhibited higher accuracy in predicting O/W emulsion viscosity for total data (train and test subsets combined). A Monte-Carlo sensitivity analysis was also performed to determine the impact of input features on the model output. By using the proposed ML predictor, expensive and time-consuming experiments can be eliminated and emulsion viscosity predictions can be expedited without the need for costly experiment.

ANN modeling and RSM optimization of ultrasound-assisted extraction of protodioscin-rich extracts from Tribulus terrestris L.

Tribulus terrestris L. is a herb renowned for its abundance of saponins, flavonoids, and alkaloids, which are utilized in treating various health conditions. Protodioscin functions by enhancing the conversion of testosterone into potent dihydrotestosterone, stimulating an increase in libido, red blood cell production from the bone marrow, and muscle development. Contemporary ultrasound-assisted-extraction (UAE) process employing green extraction solvents was selected to design the required separation system. The experimental plan was developed based on the independent operating variables – extraction time, operating temperature and solvent system composition in order to determine the influence of defined parameters and their interactions on the extraction yield and the presence of protodioscin. The 3D-RSM approach was introduced to determine the optimal values of studied independent variables in the area of maximal extraction yield. UAE process performed at optimal operating conditions generated maximal extraction yield (31 %, w/w) and protodioscin content of 5.9 mg/g dry plant matrix. Experimental data was used to develop an ANN for the defined extraction system using the operating variables values as the input matrix and observed yield as target matrix. Successfully designed and trained ANN generated high correlation (r = 0.9992) between observed data and predictive model’ outputs, and MSE value of 0.29107.

Inpainting of damaged temple murals using edge- and line-guided diffusion patch GAN.

Mural paintings are vital cultural expressions, enriching our lives by beautifying spaces, conveying messages, telling stories, and evoking emotions. Ancient temple murals degrade over time due to natural aging, physical damage, etc. Preserving these cultural treasures is challenging. Image inpainting is often used for digital restoration, but existing methods typically overlook naturally degraded areas, using randomly generated binary masks or small, narrow regions for repair. This study proposes a novel architecture to reconstruct large areas of naturally degraded murals, maintaining intrinsic details, avoiding color bias, and preserving artistic excellence. The architecture integrates generative adversarial networks (GANs) and the diffusion model, including a whole structure formation network (WSFN), a semantic color network (SCN), and a diffusion mixture distribution (DIMD) discriminator. The WSFN uses the original image, a line drawing, and an edge map to capture mural details, which are then texturally inpainted in the SCN using gated convolution for enhanced results. Special attention is given to globally extending the receptive field for large-area inpainting. The model is evaluated using custom-degraded mural images collected from Tamil Nadu temples. Quantitative analysis showed superior results than state-of-the-art methods, with SSIM, MSE, PSNR, and LPIPS values of 0.8853, 0.0021, 29.8826, and 0.0426, respectively.

Marine steel corrosion prediction and zonation using feature extraction and machine learning in the seas around China

To reduce the losses caused by the marine corrosion of steel, it is important to establish a prediction model to determine the corrosion rate of steel in depth-varying aggressive marine environments. The use of statistical feature extraction methods and machine learning modeling for marine steel corrosion prediction and zoning in the seas around China is investigated. In this study, 856 samples were collected. Mean and standard deviation were selected as environmental characteristics and corrosion loss time-varying relationships were log-transformed. Subsequently, four main supervised machine learning (ML) algorithms including Decision Tree (DT), Random Forest (RF), Gradient Boosting (GB), and XGBoost were explored for predicting corrosion loss in different depth-varying marine exposure zones. The GB model showed the best prediction accuracy and generalization ability with MSE, RMSE, MAE, and R2 values of 0.08, 0.43, 0.19, and 0.92, respectively. The spatial and temporal distribution of corrosion loss and zoning map in the seas around China were obtained. According to the corrosion zoning map of the splash zone, the South China Sea has a higher degree of corrosion, particularly in its northwestern region.

Implementasi Fast Fourier Transform dalam Penyelesaian Persamaan Difusi Panas Satu Dimensi

The Fast Fourier Transform (FFT) method for solving the 1-D heat diffusion equation offers an efficient approach for resolving partial differential equations (PDEs) with various time steps . FFT is used to transform the 1-D heat diffusion equation into the frequency domain and back to the time domain through inverse FFT. Using mathematical modeling with initial and Dirichlet boundary conditions, the numerical solutions produced by FFT are compared with analytical solutions. The accuracy of the method is validated using MAE and MSE calculated in Matlab. At several time intervals , the obtained MAE and MSE values indicate a good agreement between the numerical and analytical solutions, with very small errors. Numerical stability analysis confirms the reliability of the FFT method across various The variation in time step has a significant impact on the accuracy and stability of the solution. Smaller time steps improve accuracy and stability but require longer computation times. The optimal time step selected in this study is Increasing the number of discretization points also enhances accuracy but implies an increase in computational load and memory usage. The FFT method demonstrates good numerical consistency with increasing