Assessing the Relation between Mud Components and Rheology for Loss Circulation Prevention Using Polymeric Gels: A Machine Learning Approach

The traditional way to mitigate loss circulation in drilling operations is to use preventative and curative materials. However, it is difficult to quantify the amount of materials from every possible combination to produce customized rheological properties. In this study, machine learning (ML) is used to develop a framework to identify material composition for loss circulation applications based on the desired rheological characteristics. The relation between the rheological properties and the mud components for polyacrylamide/polyethyleneimine (PAM/PEI)-based mud is assessed experimentally. Four different ML algorithms were implemented to model the rheological data for various mud components at different concentrations and testing conditions. These four algorithms include (a) k-Nearest Neighbor, (b) Random Forest, (c) Gradient Boosting, and (d) AdaBoosting. The Gradient Boosting model showed the highest accuracy (91 and 74% for plastic and apparent viscosity, respectively), which can be further used for hydraulic calculations. Overall, the experimental study presented in this paper, together with the proposed ML-based framework, adds valuable information to the design of PAM/PEI-based mud. The ML models allowed a wide range of rheology assessments for various drilling fluid formulations with a mean accuracy of up to 91%. The case study has shown that with the appropriate combination of materials, reasonable rheological properties could be achieved to prevent loss circulation by managing the equivalent circulating density (ECD).

Download Full-text

Development of Digital Twins for Drilling Fluids: Local Velocities for Hole Cleaning and Rheology Monitoring

10.1115/omae2021-62987 ◽

2021 ◽

Author(s):

Mehrdad Gharib Shirangi ◽

Roger Aragall ◽

Reza Ettehadi ◽

Roland May ◽

Edward Furlong ◽

...

Keyword(s):

Machine Learning ◽

Rheological Properties ◽

Drilling Fluid ◽

Training Data ◽

Drilling Fluids ◽

Hole Cleaning ◽

Digital Twins ◽

Wide Range ◽

Drilling Operations ◽

Cuttings Bed

Abstract In this work, we present our advances to develop and apply digital twins for drilling fluids and associated wellbore phenomena during drilling operations. A drilling fluid digital twin is a series of interconnected models that incorporate the learning from the past historical data in a wide range of operational settings to determine the fluids properties in realtime operations. From several drilling fluid functionalities and operational parameters, we describe advancements to improve hole cleaning predictions and high-pressure high-temperature (HPHT) rheological properties monitoring. In the hole cleaning application, we consider the Clark and Bickham (1994) approach which requires the prediction of the local fluid velocity above the cuttings bed as a function of operating conditions. We develop accurate computational fluid dynamics (CFD) models to capture the effects of rotation, eccentricity and bed height on local fluid velocities above cuttings bed. We then run 55,000 CFD simulations for a wide range of operational settings to generate training data for machine learning. For rheology monitoring, thousands of lab experiment records are collected as training data for machine learning. In this case, the HPHT rheological properties are determined based on rheological measurement in the American Petroleum Institute (API) condition together with the fluid type and composition data. We compare the results of application of several machine learning algorithms to represent CFD simulations (for hole cleaning application) and lab experiments (for monitoring HPHT rheological properties). Rotating cross-validation method is applied to ensure accurate and robust results. In both cases, models from the Gradient Boosting and the Artificial Neural Network algorithms provided the highest accuracy (about 0.95 in terms of R-squared) for test datasets. With developments presented in this paper, the hole cleaning calculations can be performed more accurately in real-time, and the HPHT rheological properties of drilling fluids can be estimated at the rigsite before performing the lab experiments. These contributions advance digital transformation of drilling operations.

Download Full-text

Evaluation of Three Different Machine Learning Methods for Object-Based Artificial Terrace Mapping—A Case Study of the Loess Plateau, China

Remote Sensing ◽

10.3390/rs13051021 ◽

2021 ◽

Vol 13 (5) ◽

pp. 1021

Author(s):

Hu Ding ◽

Jiaming Na ◽

Shangjing Jiang ◽

Jie Zhu ◽

Kai Liu ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Loess Plateau ◽

Water Conservation ◽

Nearest Neighbor ◽

Gradient Boosting ◽

K Nearest Neighbor ◽

The Loess Plateau ◽

Object Based ◽

Extreme Gradient Boosting

Artificial terraces are of great importance for agricultural production and soil and water conservation. Automatic high-accuracy mapping of artificial terraces is the basis of monitoring and related studies. Previous research achieved artificial terrace mapping based on high-resolution digital elevation models (DEMs) or imagery. As a result of the importance of the contextual information for terrace mapping, object-based image analysis (OBIA) combined with machine learning (ML) technologies are widely used. However, the selection of an appropriate classifier is of great importance for the terrace mapping task. In this study, the performance of an integrated framework using OBIA and ML for terrace mapping was tested. A catchment, Zhifanggou, in the Loess Plateau, China, was used as the study area. First, optimized image segmentation was conducted. Then, features from the DEMs and imagery were extracted, and the correlations between the features were analyzed and ranked for classification. Finally, three different commonly-used ML classifiers, namely, extreme gradient boosting (XGBoost), random forest (RF), and k-nearest neighbor (KNN), were used for terrace mapping. The comparison with the ground truth, as delineated by field survey, indicated that random forest performed best, with a 95.60% overall accuracy (followed by 94.16% and 92.33% for XGBoost and KNN, respectively). The influence of class imbalance and feature selection is discussed. This work provides a credible framework for mapping artificial terraces.

Download Full-text

The Classification of Skateboarding Tricks : A Transfer Learning and Machine Learning Approach

Mekatronika ◽

10.15282/mekatronika.v2i2.6683 ◽

2020 ◽

Vol 2 (2) ◽

pp. 1-12

Author(s):

Muhammad Nur Aiman Shapiee ◽

Muhammad Ar Rahim Ibrahim ◽

Muhammad Amirul Abdullah ◽

Rabiu Muazu Musa ◽

Noor Azuan Abu Osman ◽

...

Keyword(s):

Machine Learning ◽

Classification Accuracy ◽

Nearest Neighbor ◽

Olympic Games ◽

Learning Approach ◽

K Nearest Neighbor ◽

Test Dataset ◽

Machine Learning Approach ◽

Competitive Games

The skateboarding scene has arrived at new statures, particularly with its first appearance at the now delayed Tokyo Summer Olympic Games. Hence, attributable to the size of the game in such competitive games, progressed creative appraisal approaches have progressively increased due consideration by pertinent partners, particularly with the enthusiasm of a more goal-based assessment. This study purposes for classifying skateboarding tricks, specifically Frontside 180, Kickflip, Ollie, Nollie Front Shove-it, and Pop Shove-it over the integration of image processing, Trasnfer Learning (TL) to feature extraction enhanced with tradisional Machine Learning (ML) classifier. A male skateboarder performed five tricks every sort of trick consistently and the YI Action camera captured the movement by a range of 1.26 m. Then, the image dataset were features built and extricated by means of three TL models, and afterward in this manner arranged to utilize by k-Nearest Neighbor (k-NN) classifier. The perception via the initial experiments showed, the MobileNet, NASNetMobile, and NASNetLarge coupled with optimized k-NN classifiers attain a classification accuracy (CA) of 95%, 92% and 90%, respectively on the test dataset. Besides, the result evident from the robustness evaluation showed the MobileNet+k-NN pipeline is more robust as it could provide a decent average CA than other pipelines. It would be demonstrated that the suggested study could characterize the skateboard tricks sufficiently and could, over the long haul, uphold judges decided for giving progressively objective-based decision.

Download Full-text

Bacterial Immunogenicity Prediction by Machine Learning Methods

Vaccines ◽

10.3390/vaccines8040709 ◽

2020 ◽

Vol 8 (4) ◽

pp. 709

Author(s):

Ivan Dimitrov ◽

Nevena Zaharieva ◽

Irini Doytchinova

Keyword(s):

Machine Learning ◽

Nearest Neighbor ◽

Predictive Ability ◽

Initial Step ◽

Majority Voting ◽

Gradient Boosting ◽

Support Vector ◽

K Nearest Neighbor ◽

Test Set ◽

Extreme Gradient Boosting

The identification of protective immunogens is the most important and vigorous initial step in the long-lasting and expensive process of vaccine design and development. Machine learning (ML) methods are very effective in data mining and in the analysis of big data such as microbial proteomes. They are able to significantly reduce the experimental work for discovering novel vaccine candidates. Here, we applied six supervised ML methods (partial least squares-based discriminant analysis, k nearest neighbor (kNN), random forest (RF), support vector machine (SVM), random subspace method (RSM), and extreme gradient boosting) on a set of 317 known bacterial immunogens and 317 bacterial non-immunogens and derived models for immunogenicity prediction. The models were validated by internal cross-validation in 10 groups from the training set and by the external test set. All of them showed good predictive ability, but the xgboost model displays the most prominent ability to identify immunogens by recognizing 84% of the known immunogens in the test set. The combined RSM-kNN model was the best in the recognition of non-immunogens, identifying 92% of them in the test set. The three best performing ML models (xgboost, RSM-kNN, and RF) were implemented in the new version of the server VaxiJen, and the prediction of bacterial immunogens is now based on majority voting.

Download Full-text

Ability of a Machine Learning Algorithm to Predict the Need for Perioperative Red Blood Cells Transfusion in Pelvic Fracture Patients: A Multicenter Cohort Study in China

Frontiers in Medicine ◽

10.3389/fmed.2021.694733 ◽

2021 ◽

Vol 8 ◽

Author(s):

Xueyuan Huang ◽

Yongjun Wang ◽

Bingyu Chen ◽

Yuanshuai Huang ◽

Xinhua Wang ◽

...

Keyword(s):

Machine Learning ◽

Cohort Study ◽

Random Forest ◽

Blood Cells ◽

Nearest Neighbor ◽

Learning Algorithm ◽

Kappa Coefficient ◽

Gradient Boosting ◽

Machine Learning Algorithm ◽

K Nearest Neighbor

Background: Predicting the perioperative requirement for red blood cells (RBCs) transfusion in patients with the pelvic fracture may be challenging. In this study, we constructed a perioperative RBCs transfusion predictive model (ternary classifications) based on a machine learning algorithm.Materials and Methods: This study included perioperative adult patients with pelvic trauma hospitalized across six Chinese centers between September 2012 and June 2019. An extreme gradient boosting (XGBoost) algorithm was used to predict the need for perioperative RBCs transfusion, with data being split into training test (80%), which was subjected to 5-fold cross-validation, and test set (20%). The ability of the predictive transfusion model was compared with blood preparation based on surgeons' experience and other predictive models, including random forest, gradient boosting decision tree, K-nearest neighbor, logistic regression, and Gaussian naïve Bayes classifier models. Data of 33 patients from one of the hospitals were prospectively collected for model validation.Results: Among 510 patients, 192 (37.65%) have not received any perioperative RBCs transfusion, 127 (24.90%) received less-transfusion (RBCs < 4U), and 191 (37.45%) received more-transfusion (RBCs ≥ 4U). Machine learning-based transfusion predictive model produced the best performance with the accuracy of 83.34%, and Kappa coefficient of 0.7967 compared with other methods (blood preparation based on surgeons' experience with the accuracy of 65.94%, and Kappa coefficient of 0.5704; the random forest method with an accuracy of 82.35%, and Kappa coefficient of 0.7858; the gradient boosting decision tree with an accuracy of 79.41%, and Kappa coefficient of 0.7742; the K-nearest neighbor with an accuracy of 53.92%, and Kappa coefficient of 0.3341). In the prospective dataset, it also had a food performance with accuracy 81.82%.Conclusion: This multicenter retrospective cohort study described the construction of an accurate model that could predict perioperative RBCs transfusion in patients with pelvic fractures.

Download Full-text

COMPARISON OF MACHINE LEARNING CLASSIFICATION ALGORITHM ON HOTEL REVIEW SENTIMENT ANALYSIS (CASE STUDY: LUMINOR HOTEL PECENONGAN)

Jurnal Pilar Nusa Mandiri ◽

10.33480/pilar.v16i1.1131 ◽

2020 ◽

Vol 16 (1) ◽

pp. 59-64

Author(s):

Jaja Miharja ◽

Jordy Lasmana Putra ◽

Nur Hadianto

Keyword(s):

Machine Learning ◽

Nearest Neighbor ◽

Classification Algorithm ◽

K Nearest Neighbor ◽

Business Decisions ◽

Machine Learning Classification ◽

Business People ◽

Auc Value ◽

The Right

Analysis of hotel review sentiment is very helpful to be used as a benchmark or reference for making hotel business decisions today. However, all the review information obtained must be processed first by using an algorithm. The purpose of this study is to compare the Classification Algorithm of Machine Learning to obtain information that has a better level of accuracy in the analysis of hotel reviews. The algorithm that will be used is k-NN (k-Nearest Neighbor) and NB (Naive Bayes). After doing the calculation, the following accuracy level is obtained: k-NN of 60,50% with an AUC value of 0.632 and NB of 85,25% with an AUC value of 0.658. These results can be determined by the right algorithm to assist in making accurate decisions by business people in the analysis of hotel reviews using the NB Algorithm.

Download Full-text

Predicting Fine Particulate Matter (PM2.5) in the Greater London Area: An Ensemble Approach using Machine Learning Methods

Remote Sensing ◽

10.3390/rs12060914 ◽

2020 ◽

Vol 12 (6) ◽

pp. 914 ◽

Cited By ~ 4

Author(s):

Mahdieh Danesh Yazdi ◽

Zheng Kuang ◽

Konstantina Dimakopoulou ◽

Benjamin Barratt ◽

Esra Suel ◽

...

Keyword(s):

Machine Learning ◽

Random Forest ◽

Nearest Neighbor ◽

Meteorological Data ◽

Fine Particulate Matter ◽

Gradient Boosting ◽

K Nearest Neighbor ◽

Learning Methods ◽

Machine Learning Methods ◽

Technological Advances

Estimating air pollution exposure has long been a challenge for environmental health researchers. Technological advances and novel machine learning methods have allowed us to increase the geographic range and accuracy of exposure models, making them a valuable tool in conducting health studies and identifying hotspots of pollution. Here, we have created a prediction model for daily PM2.5 levels in the Greater London area from 1st January 2005 to 31st December 2013 using an ensemble machine learning approach incorporating satellite aerosol optical depth (AOD), land use, and meteorological data. The predictions were made on a 1 km × 1 km scale over 3960 grid cells. The ensemble included predictions from three different machine learners: a random forest (RF), a gradient boosting machine (GBM), and a k-nearest neighbor (KNN) approach. Our ensemble model performed very well, with a ten-fold cross-validated R2 of 0.828. Of the three machine learners, the random forest outperformed the GBM and KNN. Our model was particularly adept at predicting day-to-day changes in PM2.5 levels with an out-of-sample temporal R2 of 0.882. However, its ability to predict spatial variability was weaker, with a R2 of 0.396. We believe this to be due to the smaller spatial variation in pollutant levels in this area.

Download Full-text

Sentiment Analysis for Iraqis Dialect in Social Media

Iraqi Journal of Information & Communications Technology ◽

10.31987/ijict.1.2.17 ◽

2018 ◽

Vol 1 (2) ◽

pp. 24-32

Author(s):

Lamiaa Abd Habeeb

Keyword(s):

Machine Learning ◽

Social Media ◽

Nearest Neighbor ◽

Learning Algorithm ◽

Learning Approach ◽

Machine Learning Algorithm ◽

K Nearest Neighbor ◽

Multinomial Models ◽

Ensemble Machine Learning ◽

Machine Learning Approach

In this paper, we designed a system that extract citizens opinion about Iraqis government and Iraqis politicians through analyze their comments from Facebook (social media network). Since the data is random and contains noise, we cleaned the text and builds a stemmer to stem the words as much as possible, cleaning and stemming reduced the number of vocabulary from 28968 to 17083, these reductions caused reduction in memory size from 382858 bytes to 197102 bytes. Generally, there are two approaches to extract users opinion; namely, lexicon-based approach and machine learning approach. In our work, machine learning approach is applied with three machine learning algorithm which are; Naïve base, K-Nearest neighbor and AdaBoost ensemble machine learning algorithm. For Naïve base, we apply two models; Bernoulli and Multinomial models. We found that, Naïve base with Multinomial models give highest accuracy.

Download Full-text

Investigating Machine Learning Approaches for Bitcoin Ransomware Payment Detection Systems

Volume 5 - 2020, Issue 9 - September - International Journal of Innovative Science and Research Technology ◽

10.38124/ijisrt20sep784 ◽

2020 ◽

Vol 5 (9) ◽

pp. 1216-1222

Author(s):

Kirat Jadhav

Keyword(s):

Machine Learning ◽

Detection Rate ◽

Nearest Neighbor ◽

Gradient Boosting ◽

Learning Approaches ◽

K Nearest Neighbor ◽

Detection Systems ◽

Digital World ◽

F Measure ◽

Machine Learning Models

Cryptocurrencies have revolutionized the process of trading in the digital world. Roughly one decade since the induction of the first bitcoin block, thousands of cryptocurrencies have been introduced. The anonymity offered by the cryptocurrencies also attracted the perpetuators of cybercrime. This paper attempts to examine the different machine learning approaches for efficiently identifying ransomware payments made to the operators using bitcoin transactions. Machine learning models may be developed based on patterns differentiating such cybercrime operations from normal bitcoin transactions in order to identify and report attacks. The machine learning approaches are evaluated on bitcoin ransomware dataset. Experimental results show that Gradient Boosting and XGBoost algorithms achieved better detection rate with respect to precision, recall and F-measure rates when compared with k-Nearest Neighbor, Random Forest, Naïve Bayes and Multilayer Perceptron approaches

Download Full-text

Stress Classification of ECG-Derived HRV Features Extracted from Wearable Devices

10.20944/preprints202103.0644.v1 ◽

2021 ◽

Author(s):

Kayisan Mary Dalmeida ◽

Giovanni Luca Masala

Keyword(s):

Machine Learning ◽

Nearest Neighbor ◽

Wearable Devices ◽

Mental Wellbeing ◽

Gradient Boosting ◽

Support Vector ◽

K Nearest Neighbor ◽

Automobile Crashes ◽

Machine Learning Model ◽

Stress Classification

Stress has been identified as one of the major causes of automobile crashes which then lead to high rates of fatalities and injuries each year. Stress can be measured via physiological measurements and in this study the focus will be based on the features that can be extracted by common wearable devices. Hence the study will be mainly focusing on the heart rate variability (HRV). This study is aimed to develop a good predictive model that can accurately classify stress levels from ECG-derived HRV features, obtained from automobile drivers, testing different machine learning methodologies such as K-Nearest Neighbor (KNN), Support Vector Machines (SVM), Multilayer Perceptron (MLP), Random Forest (RF) and Gradient Boosting (GB). Moreover, the models obtained with highest predictive power will be used as reference for the development of a machine learning model that would be used to classify stress from HRV features derived from HRV measurements obtained from wearable devices. We demonstrate that MLP was the ideal stress classifier by achieving a Recall of 80%. The proposed method can be also used on all applications in which is important to monitor the stress level e. g. in physical rehabilitation, anxiety relief or mental wellbeing.

Download Full-text