A Novel Method with Stacking Learning of Data-Driven Soft Sensors for Mud Concentration in a Cutter Suction Dredger

Wang, Bin; Fan, Shidong; Pan, Junjun; Zhu, Hongtao; Xiong, Ting; Wei, Wei; Fang, Zhenlong

doi:10.3390/s20216075

Cited by 14 publications

(8 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…50 numerical errors would dominate the result. Trees of even higher depth are sometimes used in practice [54].…”

Section: Banzhaf Values Vs Shapley Valuesmentioning

confidence: 99%

Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf

Karczmarz,

Mukherjee,

Sankowski

et al. 2021

Preprint

View full text Add to dashboard Cite

Shapley values are one of the main tools used to explain predictions of tree ensemble models. The main alternative to Shapley values are Banzhaf values that have not been understood equally well. In this paper we make a step towards filling this gap, providing both experimental and theoretical comparison of these model explanation methods. Surprisingly, we show that Banzhaf values offer several advantages over Shapley values while providing essentially the same explanations. We verify that Banzhaf values:

show abstract

“…50 numerical errors would dominate the result. Trees of even higher depth are sometimes used in practice [54].…”

Section: Banzhaf Values Vs Shapley Valuesmentioning

confidence: 99%

Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf

Karczmarz,

Mukherjee,

Sankowski

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…It leverages the techniques mentioned with boosting. Some of the major benefits of XGBoost are that it is highly scalable/parallelizable, quick to execute, and typically outperforms other algorithms [ 98 , 99 ].…”

Section: Methods and Datasetsmentioning

confidence: 99%

Using Embedded Feature Selection and CNN for Classification on CCD-INID-V1—A New IoT Dataset

Liu

Thapa

Shaver

et al. 2021

Sensors

View full text Add to dashboard Cite

As Internet of Things (IoT) networks expand globally with an annual increase of active devices, providing better safeguards to threats is becoming more prominent. An intrusion detection system (IDS) is the most viable solution that mitigates the threats of cyberattacks. Given the many constraints of the ever-changing network environment of IoT devices, an effective yet lightweight IDS is required to detect cyber anomalies and categorize various cyberattacks. Additionally, most publicly available datasets used for research do not reflect the recent network behaviors, nor are they made from IoT networks. To address these issues, in this paper, we have the following contributions: (1) we create a dataset from IoT networks, namely, the Center for Cyber Defense (CCD) IoT Network Intrusion Dataset V1 (CCD-INID-V1); (2) we propose a hybrid lightweight form of IDS—an embedded model (EM) for feature selection and a convolutional neural network (CNN) for attack detection and classification. The proposed method has two models: (a) RCNN: Random Forest (RF) is combined with CNN and (b) XCNN: eXtreme Gradient Boosting (XGBoost) is combined with CNN. RF and XGBoost are the embedded models to reduce less impactful features. (3) We attempt anomaly (binary) classifications and attack-based (multiclass) classifications on CCD-INID-V1 and two other IoT datasets, the detection_of_IoT_botnet_attacks_N_BaIoT dataset (Balot) and the CIRA-CIC-DoHBrw-2020 dataset (DoH20), to explore the effectiveness of these learning-based security models. Using RCNN, we achieved an Area under the Receiver Characteristic Operator (ROC) Curve (AUC) score of 0.956 with a runtime of 32.28 s on CCD-INID-V1, 0.999 with a runtime of 71.46 s on Balot, and 0.986 with a runtime of 35.45 s on DoH20. Using XCNN, we achieved an AUC score of 0.998 with a runtime of 51.38 s for CCD-INID-V1, 0.999 with a runtime of 72.12 s for Balot, and 0.999 with a runtime of 72.91 s for DoH20. Compared to KNN, XCNN required 86.98% less computational time, and RCNN required 91.74% less computational time to achieve equal or better accurate anomaly detections. We find XCNN and RCNN are consistently efficient and handle scalability well; in particular, 1000 times faster than KNN when dealing with a relatively larger dataset-Balot. Finally, we highlight RCNN and XCNN’s ability to accurately detect anomalies with a significant reduction in computational time. This advantage grants flexibility for the IDS placement strategy. Our IDS can be placed at a central server as well as resource-constrained edge devices. Our lightweight IDS requires low train time and hence decreases reaction time to zero-day attacks.

show abstract

“…RMSE and MAE reflect the predictive error, with lower values indicating better algorithm performance. R 2 , assessing goodness of fit, ranges from 0 to 1, with a score closer to 1 indicating a superior model fit [35][36][37]. Root mean square error (RMSE):…”

Section: Calculation Of Indicesmentioning

confidence: 99%

A Bayesian Network Model for Risk Management during Hydraulic Fracturing Process

Badjadi,

Zhu,

Zhang

et al. 2023

Water

View full text Add to dashboard Cite

The escalating production of shale gas and oil, witnessed prominently in developed nations over the past decade, has sparked interest in prospective development, even in developing countries like Algeria. However, this growth is accompanied by significant opposition, particularly concerning the method of extraction: hydraulic fracturing, or ‘fracking’. Concerns regarding its environmental impact, water contamination, greenhouse gas emissions, and potential health effects have sparked widespread debate. This study thoroughly examines these concerns, employing an innovative approach to assess the risks associated with hydraulic fracturing operations in shale gas reservoirs. Through the integration of diverse data sources, including quantitative and qualitative data, observational records, expert judgments, and global sensitivity analysis using the Sobol method, a comprehensive risk assessment model, was developed. This model carefully considered multiple condition indicators and extreme working conditions, such as pressures exceeding 110 MPa and temperatures surpassing 180° F. The integration of these varied data streams enabled the development of a robust Bayesian belief network. This network served as a powerful tool for the accurate identification of process vulnerabilities and the formulation of optimal development strategies. Remarkably, this study’s results showed that this approach led to a notable 12% reduction in operational costs, demonstrating its practical efficacy. Moreover, this study subjected its model to rigorous uncertainty and sensitivity analyses, pinpointing the most severe risks and outlining optimal measures for their reduction. By empowering decision-makers to make informed choices, this methodology not only enhances environmental sustainability and safety standards but also ensures prolonged well longevity while maximizing productivity in hydraulic fracturing operations.

show abstract

A Novel Method with Stacking Learning of Data-Driven Soft Sensors for Mud Concentration in a Cutter Suction Dredger

Cited by 14 publications

References 41 publications

Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf

Improved Feature Importance Computations for Tree Models: Shapley vs. Banzhaf

Using Embedded Feature Selection and CNN for Classification on CCD-INID-V1—A New IoT Dataset

A Bayesian Network Model for Risk Management during Hydraulic Fracturing Process

Contact Info

Product

Resources

About