Predicting Stages of Liver Cirrhosis Using Data Mining and Machine Learning Techniques DOI Open Access
Dashti Ali, Maalim A. Aljabery

Informatica, Год журнала: 2024, Номер 48(21)

Опубликована: Ноя. 28, 2024

Liver cirrhosis often occurs as a result of the lengthy and persistent progression chronic liver disorders. It is key crucial cause death on global scale. Early diagnosis identification are essential for preventing disease's complete devastation tissue. This paper aims to build an intelligent automated system that can predict stages employing Machine Learning (ML) algorithms, including Random Forest (RF), Extra Trees (ET), Support Vector (SVM). The dataset used in this research sourced from Zenodo website, which linked GitHub website. was our initial use data, publicly accessible. Data mining techniques were also implemented analyze data before predicting outcome. Due considerable imbalance dataset's classes, we applied Synthetic Minority Oversampling Technique (SMOTE) mitigate bias problem machine learning model. A newly proposed model feature selection Chi-Square Recursive Feature Elimination Cross-Validation (RFECV) with classifiers RF SVM (RF-RFECV, SVM-RFECV). experimental findings demonstrate Extra-Trees using Chi-square method (ET-Chi-Square) achieved maximum level accuracy 93.87%. Additionally, it obtained recall, F1-score, precision values 94% each, Area Under Curve (AUC) 99%. Our exhibited exceptional performance compared previous relevant research.

Язык: Английский

An Interpretable Hybrid Deep Learning Model for Molten Iron Temperature Prediction at the Iron-Steel Interface Based on Bi-LSTM and Transformer DOI Creative Commons

Zhenzhong Shen,

Weigang Han,

Yanzhuo Hu

и другие.

Mathematics, Год журнала: 2025, Номер 13(6), С. 975 - 975

Опубликована: Март 15, 2025

Hot metal temperature is a key factor affecting the quality and energy consumption of iron steel smelting. Accurate prediction drop in hot ladle very important for optimizing transport, improving efficiency, reducing consumption. Most existing studies focus on molten torpedo tanks, but there significant research gap drop, especially as increasingly used to replace tank transportation process, this has not been fully addressed literature. This paper proposes an interpretable hybrid deep learning model combining Bi-LSTM Transformer solve complexity prediction. By leveraging Catboost-RFECV, most influential variables are selected, captures both local features with global dependencies Transformer. Hyperparameters optimized automatically using Optuna, enhancing performance. Furthermore, SHAP analysis provides valuable insights into factors influencing drops, enabling more accurate temperature. The experimental results demonstrate that proposed outperforms each individual ensemble terms R2, RMSE, MAE, other evaluation metrics. Additionally, identifies contributing drop.

Язык: Английский

Процитировано

0
Risk Assessment of TBM Construction Based on a Matter-Element Extension Model with Optimized Weight Distribution DOI Creative Commons
Tao Fu, Kebin Shi, R Shi

и другие.

Applied Sciences, Год журнала: 2024, Номер 14(13), С. 5911 - 5911

Опубликована: Июль 6, 2024

In order to effectively address the potential hazards associated with construction of Phase II YE Water Supply Project’s KS tunnel in Xinjiang, this study employs WBS-RBS (Work Breakdown Structure and Risk Structure) method for risk identification. This approach aims identify various risks that may arise during TBM (Tunnel Boring Machine) construction. To prevent incomplete factor identification resulting from subjective judgment, a index system is established based on results. Subsequently, matter-element extension model utilized quantify factors within system, comprehensive weights are determined using variable weight theory assess levels. Importance analysis each then conducted those significant impact evaluation outcomes. Finally, by comparing actual engineering cases other models, paper verifies reliability its constructed assessment proposes measures controlling these evaluations. The provides clear definition safety encountered conducts assessments as valuable reference research related boring machine period engineering.

Язык: Английский

Процитировано

1
Explainable hybrid deep learning framework for enhancing multi-step solar ultraviolet-B radiation predictions DOI Creative Commons
Salvin S. Prasad, Lionel Joseph, Sujan Ghimire

и другие.

Atmospheric Environment, Год журнала: 2024, Номер unknown, С. 120951 - 120951

Опубликована: Дек. 1, 2024

Язык: Английский

Процитировано

1
Predicting Stages of Liver Cirrhosis Using Data Mining and Machine Learning Techniques DOI Open Access
Dashti Ali, Maalim A. Aljabery

Informatica, Год журнала: 2024, Номер 48(21)

Опубликована: Ноя. 28, 2024

Liver cirrhosis often occurs as a result of the lengthy and persistent progression chronic liver disorders. It is key crucial cause death on global scale. Early diagnosis identification are essential for preventing disease's complete devastation tissue. This paper aims to build an intelligent automated system that can predict stages employing Machine Learning (ML) algorithms, including Random Forest (RF), Extra Trees (ET), Support Vector (SVM). The dataset used in this research sourced from Zenodo website, which linked GitHub website. was our initial use data, publicly accessible. Data mining techniques were also implemented analyze data before predicting outcome. Due considerable imbalance dataset's classes, we applied Synthetic Minority Oversampling Technique (SMOTE) mitigate bias problem machine learning model. A newly proposed model feature selection Chi-Square Recursive Feature Elimination Cross-Validation (RFECV) with classifiers RF SVM (RF-RFECV, SVM-RFECV). experimental findings demonstrate Extra-Trees using Chi-square method (ET-Chi-Square) achieved maximum level accuracy 93.87%. Additionally, it obtained recall, F1-score, precision values 94% each, Area Under Curve (AUC) 99%. Our exhibited exceptional performance compared previous relevant research.

Язык: Английский

Процитировано

0