Performance of ANN in Pattern Recognition For Process Improvement Using Levenberg- Marquardt And Quasi-Newton Algorithms

Saravanan, A.; Nagarajan, Prabhat; Ramaiah, M. S.

doi:10.9790/3021-03340813

Cited by 8 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To accomplish this, it relies on the utilization of both the first and second derivatives of the function. In cases involving higher dimensions, Newton's method extends its application by incorporating the gradient and the Hessian matrix, which encapsulates the second derivatives of the function, with the objective of function minimization 100 .…”

Section: Theory and Methodologymentioning

confidence: 99%

Investigating the effect of textural properties on CO2 adsorption in porous carbons via deep neural networks using various training algorithms

Mehrmohammadi,

Ghaemi

2023

Sci Rep

View full text Add to dashboard Cite

The adsorption of carbon dioxide (CO2) on porous carbon materials offers a promising avenue for cost-effective CO2 emissions mitigation. This study investigates the impact of textural properties, particularly micropores, on CO2 adsorption capacity. Multilayer perceptron (MLP) neural networks were employed and trained with various algorithms to simulate CO2 adsorption. Study findings reveal that the Levenberg–Marquardt (LM) algorithm excels with a remarkable mean squared error (MSE) of 2.6293E−5, indicating its superior accuracy. Efficiency analysis demonstrates that the scaled conjugate gradient (SCG) algorithm boasts the shortest runtime, while the Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm requires the longest. The LM algorithm also converges with the fewest epochs, highlighting its efficiency. Furthermore, optimization identifies an optimal radial basis function (RBF) network configuration with nine neurons in the hidden layer and an MSE of 9.840E−5. Evaluation with new data points shows that the MLP network using the LM and bayesian regularization (BR) algorithms achieves the highest accuracy. This research underscores the potential of MLP deep neural networks with the LM and BR training algorithms for process simulation and provides insights into the pressure-dependent behavior of CO2 adsorption. These findings contribute to our understanding of CO2 adsorption processes and offer valuable insights for predicting gas adsorption behavior, especially in scenarios where micropores dominate at lower pressures and mesopores at higher pressures.

show abstract

Section: Theory and Methodologymentioning

confidence: 99%

Investigating the effect of textural properties on CO2 adsorption in porous carbons via deep neural networks using various training algorithms

Mehrmohammadi,

Ghaemi

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Second-order methods are based on the Newton, Gauss-Newton or Levenberg-Marquardt (LM) update rules [19][20][21][22]. LM training yields better results, faster, than first-order methods [19,23,24]. However, LM cannot be used to train large-scale ANNs, even on modern computers, because of complexity issues [22].…”

Section: Second-order Updatesmentioning

confidence: 99%

“…Second-order order training via the LM algorithm [19] is known to get better results than first-order methods in fewer iterations [19][20][21][22][23][24]. The MATLAB documentation states, "trainlm is often the fastest back-propagation algorithm in the toolbox, and is highly recommended as a first-choice supervised algorithm, although it does require more memory than other algorithms."…”

Section: First-order Training Analysismentioning

confidence: 99%

Machine Learning Approach to RF Transmitter Identification

Youssef

Bouchard

Haigh

et al. 2018

IEEE J. Radio Freq. Identif.

121

View full text Add to dashboard Cite

This document does not contain technology or technical data controlled under either the U.S. International Traffic in Arms Regulations or the U.S. Export Administration Regulations.With the development and widespread use of wireless devices in recent years (mobile phones, Internet of Things, Wi-Fi), the electromagnetic spectrum has become extremely crowded. In order to counter security threats posed by rogue or unknown transmitters, it is important to identify RF transmitters not by the data content of the transmissions but based on the intrinsic physical characteristics of the transmitters. RF waveforms represent a particular challenge because of the extremely high data rates involved and the potentially large number of transmitters present in a given location. These factors outline the need for rapid fingerprinting and identification methods that go beyond the traditional hand-engineered approaches. In this study, we investigate the use of machine learning (ML) strategies to the classification and identification problems, and the use of wavelets to reduce the amount of data required. Four different ML strategies are evaluated: deep neural nets (DNN), convolutional neural nets (CNN), support vector machines (SVM), and multi-stage training (MST) using accelerated Levenberg-Marquardt (A-LM) updates. The A-LM MST method preconditioned by wavelets was by far the most accurate, achieving 100% classification accuracy of transmitters, as tested using data originating from 12 different transmitters. We discuss strategies for extension of MST to a much larger number of transmitters.

show abstract

“…The dataset available for the training and validation of the network was referred from Santhosh et al [11] and consists of the sampling of 37 signals from instrument readings which hence represent the input of the ANN implemented. Also the ANN architecture adopted in the current study corresponds to that suggested by Santhosh et al [11] and consists of a fully connected multilayer network trained adopting the well-known LevenbergMarquardt algorithm, which has been demonstrated to outperform the classic backpropagation algorithm as well as quasi-Newton algorithms in pattern recognition applications [25], [26]. The available dataset was split into three subsets, one dedicated to training containing 70% of the overall data and the other two used for test and validation, overall including 30% of the initial data.…”

Section: A Case Studymentioning

confidence: 99%

Uncertainty quantification methods for neural networks pattern recognition

Tolo¹,

Santhosh²,

Vinod³

et al. 2017

2017 IEEE Symposium Series on Computational Intelligence (SSCI)

View full text Add to dashboard Cite

On-line monitoring techniques have attracted increasing attention as a promising strategy for improving safety, maintaining availability and reducing the cost of operation and maintenance. In particular, pattern recognition tools such as Artificial neural networks are today largely adopted for sensor validation, plant component monitoring, system control, and fault-diagnostics based on the data acquired during operation. However, classic artificial neural networks do not provide an error context for the model response, whose robustness remains thus difficult to estimate. Indeed, experimental data generally exhibit a time/space-varying behaviour and are hence characterized by an intrinsic level of uncertainty that unavoidably affects the performance of the tools adopted and undermine the accuracy of the analysis. For this reason, the propagation of the uncertainty and the quantification of the so called margins of uncertainty in output are crucial in making risk-informed decision. The current study presents a comparison between two different approaches for the quantification of uncertainty in artificial neural networks. The first technique presented is based on the error estimation by a series association scheme, the second approach couples Bayesian model selection technique and model averaging into a unified framework. The efficiency of these two approaches are analysed in terms of their computational cost and predictive performance, through their application to a nuclear power plant fault diagnosis system.

show abstract

Performance of ANN in Pattern Recognition For Process Improvement Using Levenberg- Marquardt And Quasi-Newton Algorithms

Cited by 8 publications

References 4 publications

Investigating the effect of textural properties on CO2 adsorption in porous carbons via deep neural networks using various training algorithms

Investigating the effect of textural properties on CO2 adsorption in porous carbons via deep neural networks using various training algorithms

Machine Learning Approach to RF Transmitter Identification

Uncertainty quantification methods for neural networks pattern recognition

Contact Info

Product

Resources

About