Regression Analysis with Scikit-Learn (part 1 - Linear)

Lavin, Matthew J.

doi:10.46430/phen0099

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where x max and x min are the maximum and the minimum values for feature X, respectively. Lastly, we split the dataset using scikit's train_test_split function [49], which randomly distributes the dataset into two smaller datasets: a training dataset, which is used to fit the model, and a testing dataset, which is used for unbiased model evaluation and tuning. We dedicate 75% of the complete dataset for the training dataset and 25% for the testing dataset.…”

Section: Data Scalingmentioning

confidence: 99%

Deep Learning Model Transposition for Network Intrusion Detection Systems

2023

View full text Add to dashboard Cite

Companies seek to promote a swift digitalization of their business processes and new disruptive features to gain an advantage over their competitors. This often results in a wider attack surface that may be exposed to exploitation from adversaries. As budgets are thin, one of the most popular security solutions CISOs choose to invest in is Network-based Intrusion Detection Systems (NIDS). As anomaly-based NIDS work over a baseline of normal and expected activity, one of the key areas of development is the training of deep learning classification models robust enough so that, given a different network context, the system is still capable of high rate accuracy for intrusion detection. In this study, we propose an anomaly-based NIDS using a deep learning stacked-LSTM model with a novel pre-processing technique that gives it context-free features and outperforms most related works, obtaining over 99% accuracy over the CICIDS2017 dataset. This system can also be applied to different environments without losing its accuracy due to its basis on context-free features. Moreover, using synthetic network attacks, it has been shown that this NIDS approach can detect specific categories of attacks.

show abstract

Section: Data Scalingmentioning

confidence: 99%

Deep Learning Model Transposition for Network Intrusion Detection Systems

2023

View full text Add to dashboard Cite

show abstract

Proposed Methodology and Application of Statistical Analysis Methods on MPD Surface Back Pressure Control System's Performance Evaluation in Extended Reach Drilling (ERD) Wells

Houng,

Palacios

2023

Day 1 Tue, October 03, 2023

View full text Add to dashboard Cite

Over the years, the performance of MPD systems is often called into question when it comes to Surface Back Pressure (SBP) applications to maintain the desired downhole pressure set point, thus eroding the confidence level in applying constant bottomhole pressures at target depths – whether at bit or a fixed depth. In this paper, the performance of various MPD systems is evaluated utilizing statistical analysis, including offline Change Point (CP) inference and Regression analysis on the downhole Pressure While Drilling (PWD) data as a result of the SBP applied during drilling operations. The paper also proposes an objective methodology in the evaluation process, minimizing the influence of various MPD systems’ operating philosophies. The main criteria of the evaluation process are to determine the variances between the modelled and actual MPD setpoint downhole pressure against PWD data at target depth, depending on various operation types. In order to reduce the influence of varying operating philosophies across different MPD systems, the methodology proposed focuses on drilling operations and common data across wells. Analytical methods, including offline Change Point Analysis, are used to identify the sequence of events, operation types and pumps-off events. The trending of ESD and ECD are then determined based on operation categories. Finally, the variances and standard deviation between PWD data and setpoint EMWs are determined using regression analysis as well as normal median and mean values analysis to evaluate the performance of the MPD system and also to determine factors that could affect the performance of the system.

show abstract