Predictive mapping of aquatic ecosystems by means of support vector machines and random forests

Abstract Fluid loss into formations is a common operational issue that is frequently encountered when drilling across naturally or induced fractured formations. This could pose significant operational risks, such as well-control, stuck pipe, and wellbore instability, which, in turn, lead to an increase of well time and cost. This research aims to use and evaluate different machine learning techniques, namely: support vector machines, random forests, and K-nearest neighbors in detecting loss circulation occurrences while drilling using solely drilling surface parameters. Actual field data of seven wells, which had suffered partial or severe loss circulation, were used to build predictive models, while Well-8 was used to compare the performance of the developed models. Different performance metrics were used to evaluate the performance of the developed models. Recall, precision, and F1-score measures were used to evaluate the ability of the developed model to detect loss circulation occurrences. The results showed the K-nearest neighbors classifier achieved a high F1-score of 0.912 in detecting loss circulation occurrence in the testing set, while the random forests was the second-best classifier with almost the same F1-score of 0.910. The support vector machines achieved an F1-score of 0.83 in predicting the loss circulation occurrence in the testing set. The K-nearest neighbors outperformed other models in detecting the loss circulation occurrences in Well-8 with an F1-score of 0.80. The main contribution of this research as compared to previous studies is that it identifies losses events based on real-time measurements of the active pit volume.

Download Full-text

Exploring Support Vector Machines and Random Forests to Detect Advanced Fee Fraud Activities on Internet

2011 IEEE 11th International Conference on Data Mining Workshops ◽

10.1109/icdmw.2011.81 ◽

2011 ◽

Cited By ~ 2

Author(s):

Abiodun Modupe ◽

Oludayo O. Olugbara ◽

Sunday O. Ojo

Keyword(s):

Support Vector Machines ◽

Random Forests ◽

Support Vector ◽

Vector Machines

Download Full-text

Beyond the Hype: Deep Neural Networks Outperform Established Methods Using A ChEMBL Bioactivity Benchmark Set

10.1101/168914 ◽

2017 ◽

Author(s):

Eelke B. Lenselink ◽

Niels ten Dijke ◽

Brandon Bongers ◽

George Papadatos ◽

Herman W.T. van Vlijmen ◽

...

Keyword(s):

Neural Networks ◽

Logistic Regression ◽

Support Vector Machines ◽

Random Forests ◽

Deep Neural Networks ◽

Direct Result ◽

Support Vector ◽

Temporal Validation ◽

Vector Machines ◽

The Mean

AbstractThe increase of publicly available bioactivity data in recent years has fueled and catalyzed research in chemogenomics, data mining, and modeling approaches. As a direct result, over the past few years a multitude of different methods have been reported and evaluated, such as target fishing, nearest neighbor similarity-based methods, and Quantitative Structure Activity Relationship (QSAR)-based protocols. However, such studies are typically conducted on different datasets, using different validation strategies, and different metrics.In this study, different methods were compared using one single standardized dataset obtained from ChEMBL, which is made available to the public, using standardized metrics (BEDROC and Matthews Correlation Coefficient). Specifically, the performance of Naive Bayes, Random Forests, Support Vector Machines, Logistic Regression, and Deep Neural Networks was assessed using QSAR and proteochemometric (PCM) methods. All methods were validated using both a random split validation and a temporal validation, with the latter being a more realistic benchmark of expected prospective execution.Deep Neural Networks are the top performing classifiers, highlighting the added value of Deep Neural Networks over other more conventional methods. Moreover, the best method (‘DNN_PCM’) performed significantly better at almost one standard deviation higher than the mean performance. Furthermore, Multi task and PCM implementations were shown to improve performance over single task Deep Neural Networks. Conversely, target prediction performed almost two standard deviations under the mean performance. Random Forests, Support Vector Machines, and Logistic Regression performed around mean performance. Finally, using an ensemble of DNNs, alongside additional tuning, enhanced the relative performance by another 27% (compared with unoptimized DNN_PCM).Here, a standardized set to test and evaluate different machine learning algorithms in the context of multitask learning is offered by providing the data and the protocols.

Download Full-text