“predict”Search All-EnPress Publisher LLC.

Feb 24, 2024

Data mining model to prediction thermal efficiency in ORC

The Organic Rankine Cycle (ORC) is an electricity generation system that uses organic fluid instead of water in the low temperature range. The Organic Rankine cycle using zeotropic working fluids has wide application potential. In this study, data mining (DM) model is used for performance analysis of organic Rankine cycle (ORC) using zeotropik working fluids R417A and R422D. Various DM models, including Linear Regression (LR), Multi-Layer Perceptron (MLP), M5 Rules, M5 Model Tree, Random Committee (RC), and Decision Tree (DT) models are used. The MLP model emerged as the most effective approach for predicting the thermal efficiency of both R417A and R422D. The MLP’s predicted results closely matched the actual results obtained from the thermodynamic model using Genetron software. The Root Mean Square Error (RMSE) for the thermal efficiency was exceptionally low, at 0.0002 for R417A and 0.0003 for R422D. Additionally, the R-squared (R²) values for thermal efficiency were very high, reaching 0.9999 for R417A and R422D. The findings demonstrate the effectiveness of the DM model for complex tasks like estimating ORC thermal efficiency. This approach empowers engineers with the ability to predict thermal efficiency in organic Rankine systems with high accuracy, speed, and ease.

Abstract

Download PDF(1.05M)

XML

2

211

Aug 8, 2024

Deciphering the complexity of COVID-19 transmission: Unveiling precision through robust vaccination policies and advanced predictive modeling with random forest regression

In the realm of COVID-19 transmission data, scientists are scrutinizing policies to identify the ideal vaccination rate for halting the virus. This study aimed to pinpoint the minimal vaccinated percentage needed to break the virus cycle within communities. The underlying motivation stems from the urgent need to contain COVID-19’s spread and reduce the strain on healthcare systems worldwide. With fluctuating infection rates and the emergence of new variants, understanding the optimal vaccination rate has become a cornerstone in public health planning and pandemic response. Using diverse machine learning methods, this study analyzed infection peaks and hospitalization rates during vaccination campaigns across countries. The goal was to find the vaccination threshold necessary to prevent virus resurgence, even with new variants. This critical milestone is crucial for health systems to combat the pandemic effectively. The study’s analysis revealed the correlation between vaccination rates and hospitalizations, highlighting immunization’s pivotal role. Employing Random Forest regression, the study successfully predicted new cases and hospitalization rates, offering valuable insights into pandemic management strategies. For future research, we recommend exploring the impact of vaccination on the evolution of virus variants and the potential influence of socio-economic factors on vaccination uptake. Moreover, a broader analysis across different geographical regions can further validate the study’s findings and enhance global pandemic preparedness.

Abstract

Download PDF(555.11KB)

XML

0

209

Nov 10, 2023

Comparison of Ridge Regression and GA-RF Models for Boston House Price Prediction

The purpose of this paper is to explore the performance of ridge regression and the random forest model improved by genetic algorithm in predicting the Boston house price data set and conduct a comparative analysis. To achieve it, the data is divided into training set and test set according to the ratio of 70-30. The RidgeCV library is used to select the best regularization parameter for the Ridge regression model, and for the random forest model, the genetic algorithm is used to optimize the model's hyperparameters. The result shows that compared with ridge regression, the random forest model improved by genetic algorithm can perform better in the regression problem of Boston house prices.

Abstract

Download PDF(1.75M)

XML

2

207

Sept 18, 2021

Evaluating models and effective factors obtained from remote sensing (RS) and geographic information system(GIS) in the prediction of forest fire risk: A structured review

Fire, a phenomenon occurs in most parts of the world and causes severe financial losses, even, irreparable damages. Many parameters are involved in the occurrence of a fire; some of which are constant over time (at least in a fire cycle), but the others are dynamic and vary over time. Unlike the earthquake, the disturbance of fire depends on a set of physical, chemical, and biological relations. Monitoring the changes to predict the occurrence of fire is efficient in forest management. Method: In this research, the Persian and English databases were structurally searched using the keywords of fire risk modeling, fire risk, fire risk prediction, remote sensing and the reviewed papers that predicted the fire risk in the field of remote sensing and geographic information system were retrieved. Then, the modeling and zoning data of fire risk prediction were extracted and analyzed in a descriptive manner. Accordingly, the study was conducted in 1995-2017. Findings: Fuzzy analytic hierarchy process (AHP) zoning method was more practical among the applied methods and the plant moisture stress measurement was the most efficient among the remote sensing indices. Discussion and Conclusion: The findings indicate that RS and GIS are effective tools in the study of fire risk prediction.

Abstract

Download PDF(460.72KB)

XML

1

205

Jan 14, 2025

An insight from machine learning perspective for COVID-19 survival prediction in Malaysia based on demographic factor

Malaysia reported its first imported COVID-19 case on 23 January 2020, which marked the country's first confirmed positive case. The first case in Malaysia was from eight close contacts in Johor. The global health landscape has been significantly impacted by the COVID-19 pandemic, with mortality or survival being critical outcomes of interest. This study aims to predict COVID-19 survival occurrences in Malaysia by utilizing machine learning approaches based on demographic factors. The dataset used in this study comprises demographic information of 2,151,315 COVID-19 patients, including nationality, regions, age groups, gender, medical history, vaccine brands, and the number of vaccine doses received between 2020 and 2022. Four machine learning algorithms, namely Logistic Regression, Naïve Bayes, Support Vector Machine, and Artificial Neural Network were employed to assess the relationship between demographic factors and COVID-19 survival. To evaluate the model performance, the datasets are categorized into imbalanced and balanced (down-sampling). The results indicate that the balanced dataset (down-sampling) outperforms the imbalanced dataset in terms of overall accuracy, sensitivity, specificity, precision, and Area Under the Curve (AUC). Based on the analysis, the Artificial Neural Network (ANN) classifier exhibited the highest performance with a specificity 95.2% on a balanced dataset. The model excels in accurately identifying survivors, thereby minimizing false mortality predictions and is selected as the best model for predicting COVID-19 survival. Its capacity to process larger sample sizes, combined with numerous interconnected nodes, enables it to identify complex patterns and extract meaningful insights from diverse datasets, such as demographic factors. Additionally, the optimization of parameters, including the number of layers, learning rate, and activation functions, significantly contributed to its superior accuracy. The study identifies that those of chronic diseases, male, and aged 45 and above as the notable factors associated with lower survival rates among COVID-19 patients. The findings underscore the importance of completing the vaccination series by obtaining at least the second dose, as the first dose alone may not offer sufficient protection. In conclusion, this study successfully achieves its objectives by identifying the optimal dataset configuration and predictive model for forecasting COVID-19 survival based on demographic factors. This network could serve as a benchmark model classifier, offering a valuable tool to predict and promote vaccinations, as well as optimize the general healthcare system during the pandemic outbreak. The study not only contributes to the theoretical understanding of effective COVID-19 prediction but also emphasizes the practical implications of integrating advanced machine learning techniques into pandemic management strategies. Future research can build upon these findings by exploring additional machine learning techniques and considering geographical and environmental factors to further enhance the accuracy of long-term predictions.

Abstract

Download PDF(1.50M)

XML

10

205

Jan 15, 2025

Smallholder's sustainable oil palm production commitment: Predictive role of organizational, work-related, psychological, and personal factors

This paper focuses on examining the relationship among organizational factor, work-related factor, psychological factor, personal factor and the commitment of oil palm smallholders toward Malaysian Sustainable Palm Oil (MSPO) certification. The study employed a descriptive research methodology and a structured survey instrument to gather data from oil palm smallholders (n = 441) through simple random sampling technique. Data analysis was conducted using SPSS and partial least square structural equation modeling (PLS-SEM) to test the proposed relationship. The findings reveal that organizational factors significantly impact the affective (β = 0.345, p < 0.05), normative (β = 0.424, p < 0.05), and continuance commitment (β = 0.339, p < 0.05) of oil palm smallholders. Additionally, work-related factors show a substantial effect on these same dimensions of commitment; affective (β = 0.277, p < 0.05), normative (β = 0.263, p < 0.05), and continuance (β = 0.413, p < 0.05). Psychological factors significantly impact the affective (β = 0.216, p < 0.05) and normative commitment (β = 0.146, p < 0.05), with no statistically significant influence on continuance commitment. Conversely, personal factors exhibit limited influence, affecting only continuance commitment (β = 0.104, p < 0.05) to a minor degree, with no statistically significant impact on affective and normative commitment. The present research is among the few empirical findings that have examined the oil palm smallholders' commitment towards MSPO certification. By emphasizing the role of organizational and work-related factors, the study offers valuable insights for stakeholders within the oil palm sector, highlighting areas to enhance smallholder commitment toward sustainability standards. Consequently, this study contributes a unique perspective to the existing body of literature on sustainable practices in the oil palm industry.

Abstract

Download PDF(722.24KB)

XML

3

199