Article
Energy & Fuels
Xingye Liu, Qiang Ge, Xiaohong Chen, Jingye Li, Yangkang Chen
Summary: A new reservoir characterization framework is designed with the introduction of ELM, allowing simultaneous prediction of multiple parameters with biased dropout and dropconnect operations for regularization. The method performs well on well and seismic datasets, showing higher efficiency and lower training time compared to traditional approaches.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2021)
Article
Psychology, Multidisciplinary
Jingfang Liu, Mengshi Shi
Summary: This study uses machine learning technology to detect users with depression by analyzing user-shared content and posting behaviors. A hybrid feature selection and stacking ensemble strategy is proposed to improve the recognition accuracy. The experimental results show that this method achieves a high accuracy of 90.27% in identifying online patients.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
Sura Emanet, Gozde Karatas Baydogmus, Onder Demir
Summary: This study focuses on developing an advanced Intrusion Detection System (IDS) with high accuracy through feature selection and ensemble learning methods. The researchers reduced the dataset and implemented ensemble learning to optimize IDS performance. The study's significance lies in its contribution to advancing IDS capabilities and improving computer security. The findings validate the effectiveness of ensemble learning in enhancing IDS performance.
PEERJ COMPUTER SCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Peng Zhou, Xia Wang, Liang Du
Summary: Unsupervised feature selection is an important task in machine learning but suffers from stability and robustness issues due to the absence of labels. This paper proposes a novel bi-level feature selection ensemble method that not only ensembles at the feature level but also learns a consensus clustering result to guide the feature selection, outperforming other state-of-the-art methods.
INFORMATION FUSION
(2023)
Article
Materials Science, Multidisciplinary
Junya Wang, Pengcheng Xu, Xiaobo Ji, Minjie Li, Wencong Lu
Summary: This study proposes a new ensemble feature selection method named MIC-SHAP, which combines the SHAP method and the MIC method, and evaluates its effectiveness in materials machine learning. The results show that MIC-SHAP method outperforms commonly used feature selection methods, with high feature reduction rate and prediction accuracy.
MATERIALS TODAY COMMUNICATIONS
(2023)
Article
Geosciences, Multidisciplinary
Frank Male, Jerry L. Jensen
Summary: This article discusses the issues arising from incorrect applications of statistics in reservoir characterization analysis, particularly in interdisciplinary applications. It also highlights the negative implications of these misapplications and suggests alternative approaches for better results.
Article
Ecology
Dimitrios Effrosynidis, Avi Arampatzis
Summary: The study found that the wrapper methods SHAP and Permutation Importance are the most effective, while filter methods perform poorly and embedded methods are intermediate. LightGBM performed better among the two machine learning algorithms used. The ensemble method Reciprocal Ranking outperformed all other methods and showed high stability.
ECOLOGICAL INFORMATICS
(2021)
Article
Environmental Sciences
Chandan Kumar, Gabriel Walton, Paul Santi, Carlos Luza
Summary: This study investigates the use of the ensemble framework combining feature selection and machine learning models for landslide susceptibility mapping in the arid region of southern Peru. The performance of various machine learning algorithms was evaluated, and the importance of different landslide influencing factors (LIFs) was measured. The results showed that the combination of k-nearest neighbors and rotation forest or artificial neural network had the best performance in predicting landslide susceptibility. The obtained susceptibility maps can effectively prioritize landslide mitigation activities.
Article
Microbiology
Songbo Liu, Chengmin Cui, Huipeng Chen, Tong Liu
Summary: This study introduces an ensemble learning-based method for identifying important features in phage protein, aiming to understand its relationship with host bacteria and develop antimicrobial agents. The selected features are found to have significant biological significance based on the analysis conducted.
FRONTIERS IN MICROBIOLOGY
(2022)
Article
Computer Science, Artificial Intelligence
K. Janani, S. S. Mohanrasu, Chee Peng Lim, Balachandran Manavalan, R. Rakkiyappan
Summary: Feature selection is necessary due to the rapid increase in digital technology, which allows for the generation of large quantities of high-dimensional data in a short amount of time. Ensemble feature selection has emerged as a potential approach to data mining, with the advantage of identifying multiple optimal features.
APPLIED SOFT COMPUTING
(2023)
Article
Engineering, Biomedical
Mai Othman, Ahmed Mustafa Elbasha, Yasmine Salah Naga, Nancy Diaa Moussa
Summary: This research compares different machine learning tools to predict the occurrence of hemodialysis complications early on, using the least number of predictors for practical implementation. Applying various algorithms to big datasets can improve accuracy and simplify clinical practice.
BIOMEDICAL ENGINEERING ONLINE
(2022)
Article
Chemistry, Analytical
Soumya Deep Roy, Soham Das, Devroop Kar, Friedhelm Schwenker, Ram Sarkar
Summary: Breast cancer, a deadly disease, can have significantly improved survival rates through early detection and diagnosis. Treatment protocols vary depending on the stage of the cancer.
Article
Computer Science, Artificial Intelligence
Qing Wu, Yan-Lin Fu, Dong-Shun Cui, En Wang
Summary: This paper proposes a C-loss-based doubly regularized extreme learning machine to address the overfitting and dimensionality reduction problems in extreme learning machines. The proposed method simultaneously completes feature selection and training processes and achieves better regression results and faster training speed in multiple experiments.
COGNITIVE COMPUTATION
(2023)
Article
Chemistry, Multidisciplinary
Mohammed Hadwan, Mohammed Al-Sarem, Faisal Saeed, Mohammed A. Al-Hagery
Summary: Analyzing the sentiment of Arabic texts is a significant research challenge. Existing studies on Arabic sentiment analysis have focused on Twitter data while neglecting the reviews on Google Play or the App Store. This paper aims to analyze user opinions of six healthcare applications and proposes an improved sentiment classification approach using machine learning models.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Hakan Ezgi Kiziloz
Summary: This study formally compares different classifier ensemble methods in the feature selection domain and finds that ensemble methods outperform single classifiers, albeit with longer execution time, and are more effective in minimizing the number of features.
Article
Energy & Fuels
Zeeshan Tariq, Mohamed Mahmoud, Olalekan Alade, Abdulazeez Abdulraheem, Ayyaz Mustafa, Esmail M. A. Mokheimer, Murtada Al-Jawad, Ayman Al-Nakhli
Summary: The study demonstrates that thermochemical fracturing can reduce breakdown pressure in layered rock, resulting in deep and long fractures compared to conventional hydraulic fracturing, leading to a potential increase in oil flowrates up to 76%.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2021)
Article
Energy & Fuels
Ahmed Alsaihati, Salaheldin Elkatatny, Ahmed Abdulhamid Mahmoud, Abdulazeez Abdulraheem
Summary: Standard torque and drag modeling programs are widely used in the oil and gas industry, but face accuracy issues, requiring adjustments to match actual conditions. This study aims to develop an intelligent system to predict surface drilling torque, detect operational problems ahead of time, and extend response time limits.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2021)
Article
Energy & Fuels
Amjed Hassan, Abdulazeez Abdulraheem, Mohamed Awadh
Summary: This study introduces a new approach to evaluate the performance of highly deviated water injection wells by utilizing reservoir properties and well geometry. An artificial neural network model was used to extract an empirical correlation for estimating the injectivity index, which proved to be more accurate and reliable than existing models. The developed equation allows for an accurate, easy, and direct determination of well injectivity for highly deviated wells, demonstrating the effectiveness of the proposed approach.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2021)
Article
Chemistry, Multidisciplinary
Ahmed Alsaihati, Salaheldin Elkatatny, Abdulazeez Abdulraheem
Summary: This study introduced different intelligent machines for real-time accurate estimation of ECD in horizontal wells and demonstrated the use of PCA for dimensionality reduction. By developing and validating data from Well-1 and Well-2, it was found that the RF model outperformed others in predicting ECD.
Article
Engineering, Mechanical
Ahmed Alsabaa, Hany Gamal, Salaheldin Elkatatny, Abdulazeez Abdulraheem
Summary: The rheological properties of drilling fluid are crucial for the success of drilling projects, particularly for all-oil mud. This paper aims to develop intelligent predictive models by linking high-frequency mud parameters with low-frequency rheological measurements. New empirical correlations have been established to assess rheological properties, and artificial neural networks have been used to optimize models for accurately monitoring rheological properties in real-time.
FLOW MEASUREMENT AND INSTRUMENTATION
(2021)
Article
Energy & Fuels
Osama Mutrif Siddig, Saad Fahaid Al-Afnan, Salaheldin Mahmoud Elkatatny, Abdulazeez Abdulraheem
Summary: This article aims to create a continuous profile of Young's modulus using drilling rig sensor records. Three machine learning algorithms were used to correlate drilling data with Young's modulus, and satisfactory results were obtained. This approach shows promise for predicting geomechanical properties using drilling data and artificial intelligence techniques.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2022)
Article
Energy & Fuels
Zeeshan Tariq, Mohamed Mahmoud, Abdulazeez Abdulraheem
Summary: The study demonstrates the use of machine learning techniques to predict PVT properties of crude oil, with proposed models showing higher accuracy and outperforming previous ones, as well as other commonly used machine learning techniques.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2021)
Article
Energy & Fuels
Hany Gamal, Ahmed Alsaihati, Salaheldin Elkatatny, Saleh Haidary, Abdulazeez Abdulraheem
Summary: This study utilized artificial intelligence to predict rock strength in real-time, with a PCA-based random forest model outperforming a functional network model in terms of accuracy. The developed models provide an accurate estimation of UCS from drilling data, improving efficiency and well stability.
JOURNAL OF ENERGY RESOURCES TECHNOLOGY-TRANSACTIONS OF THE ASME
(2021)
Article
Energy & Fuels
Abdul Asad, Abeeb A. Awotunde, Mohammad S. Jamal, Qinzhuo Liao, Abdulazeez Abdulraheem
Summary: Horizontal wells are crucial in enhancing hydrocarbon recovery from thin reservoirs, but sand production may occur in weakly consolidated formations, leading to issues such as wellbore instability and production loss. Erosion due to high-velocity gas flow in open-hole horizontal wells can impact gas production rate and well flowing pressure.
JOURNAL OF NATURAL GAS SCIENCE AND ENGINEERING
(2021)
Article
Chemistry, Multidisciplinary
Ahmed Abdelaal, Salaheldin Elkatatny, Abdulazeez Abdulraheem
Summary: This study developed three models using support vector machines, functional networks, and random forest to predict real-time pore pressure gradient using mechanical and hydraulic drilling parameters. The models exhibited high accuracy in both training and testing, with the random forest model outperforming the others.
Article
Computer Science, Artificial Intelligence
Teslim Olayiwola, Zeeshan Tariq, Abdulazeez Abdulraheem, Mohamed Mahmoud
Summary: Shear wave velocity is crucial in subsurface engineering applications, and traditional methods for estimating it involve high cost and time consumption. To address this, a new method utilizing machine learning algorithms for feature selection was proposed in this study, showing improved prediction accuracy compared to previous methods.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Multidisciplinary Sciences
Osama Siddig, Hany Gamal, Salaheldin Elkatatny, Abdulazeez Abdulraheem
Summary: This study presents a method for real-time prediction of geomechanical properties using drilling data and machine learning techniques without additional cost. Through training and testing the models, the high predictive accuracy and match of this method were confirmed.
SCIENTIFIC REPORTS
(2021)
Review
Computer Science, Interdisciplinary Applications
Fatai Anifowose, Mokhles Mezghani, Saleh Badawood, Javed Ismail
Summary: This article highlights the current limitations in the utility of mud gas data and proposes leveraging machine learning and digital transformation to expand its real-time applications and enhance reservoir characterization workflow, ultimately accelerating the digital transformation of the petroleum industry.
APPLIED COMPUTING AND GEOSCIENCES
(2022)
Article
Multidisciplinary Sciences
Ashraf Ahmed, Salaheldin Elkatatny, Hany Gamal, Abdulazeez Abdulraheem
Summary: This study developed several artificial intelligence models for real-time prediction of bulk density in complex lithology using drilling parameters as inputs. Validation on data from both a vertical well and another well demonstrated the reliability and high accuracy of the models in predicting bulk density.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2022)
Article
Multidisciplinary Sciences
Ammar Abdlmutalib, Osman Abdullatif, Abdulazeez Abdulraheem, Mohamed Yassin
Summary: This study evaluated the main factors controlling rock strength and elastic properties of three carbonate mudrocks units in Central Saudi Arabia's Jurassic succession. Weak to moderate correlations were observed between mechanical properties and porosity, as well as between particle size and unconfined compressive strength. The sedimentary layering and associated anisotropy significantly control these correlations.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2022)