No. 1

No. 2

No. 3

No. 4

No. 5

No. 6

       Measurement of Physical Quantities

        No. 1

      Pages: 

1-9

Neven Kanchev, Nikolay Stoyanov, Georgi Milushev:

Prediction of the Natural Gas Compressibility Factor by using MLP and RBF Artificial Neural Networks

Abstract: 

The compressibility factor indicates the deviation of the real natural gas from the ideal behavior. It is one of the most important parameters in the natural gas industry. In the present study, two different types of neural networks – multi-layer perceptron (MLP) and radial basis functions (RBF) – were used to predict the compressibility factor Z of natural gas. The pressure, temperature, and speed of sound (SoS) were chosen as input parameters for the artificial neural network (ANN) models. The training and testing of the MLP-ANN and RBF-ANN were carried out on the basis of 151 days of continuous measurements. Different variants of both types of neural networks were implemented and a comparative analysis of their modeling capabilities was performed. The models developed show a very high prediction accuracy, with the results obtained showing a certain advantage of the RBF-ANN. The comparative analysis was performed on the basis of standard performance indicators such as R², root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE). The present study shows an intelligent method implemented in two different variants to determine the compressibility factor of natural gas without the need to use the equation of state.

10-14

Mohamed Yacin Sikkandar, S. Sabarunisha Begum, Ahmad Alassaf, Ibrahim AlMohimeed, Khalid Alhussaini, Adham Aleid, Abdulrahman Khalid Alhaidar:

Optimization Driven Variational Autoencoder GAN for Artifact Reduction in EEG Signals for Improved Neurological Disorder and Disability Assessment

Abstract: 

This study introduces an innovative method for minimizing artifacts in electroencephalography (EEG) signals by integrating brainstorm optimization (BSO) with a variational autoencoder generative adversarial network (VAE-GAN), resulting in the BrOpt_VAGAN model. EEG signals are critical for the diagnosis of neurological disorders, for brain-computer interface (BCI) applications, and for the monitoring of neurological disabilities. However, EEG data often contains artifacts from physiological sources — such as electro- oculographic (EOG), electromyographic (EMG), and electrocardiographic (ECG) signals — which can distort the accuracy of brain activity readings. Our proposed BrOpt_VAGAN model combines BSO with a VAE-GAN framework to more effectively remove these artifacts, thus improving the clarity and accuracy of EEG signals. In this model, the VAE first reduces the raw EEG signals into a lower-dimensional representation that captures the essential signal patterns while filtering out the noise. The GAN component then refines this representation via adversarial training, effectively minimizing artifacts and improving the quality of the processed EEG data. BSO optimally adjusts the encoding and decoding parameters within the VAE-GAN structure, enabling the model to handle different noise levels and helps to find different neurological disorders. Preliminary results show that BrOpt_VAGAN performs significantly better with an accuracy of 98.5 % and an error rate of 11.23 %, enabling a clearer and more precise EEG signal reconstruction.

 No. 1    No. 2    No. 3   No. 4   No. 5  No. 6

Journal is open for your papers

 Download and print the front cover