Comparison of Machine Learning Methods for Image Reconstruction Using the LSTM Classifier in Industrial Electrical Tomography

Abstract

Electrical tomography is a non-invasive method of monitoring the interior of objects, which is used in various industries. In particular, it is possible to monitor industrial processes inside reactors and tanks using tomography. Tomography enables real-time observation of crystals or gas bubbles growing in a liquid. However, obtaining high-resolution tomographic images is problematic because it involves solving the so-called ill-posed inverse problem. Noisy input data cause problems, too. Therefore, the use of appropriate hardware solutions to eliminate this phenomenon is necessary. An important cause of obtaining accurate tomographic images may also be the incorrect selection of algorithmic methods used to convert the measurements into the output images. In a dynamically changing environment of a tank reactor, selecting the optimal algorithmic method used to create a tomographic image becomes an optimization problem. This article presents the machine learning method’s original concept of intelligent selection depending on the reconstructed case. The long short-term memory network was used to classify the methods to choose one of the five homogenous methods—elastic net, linear regression with the least-squares learner, linear regression with support vector machine learner, support vector machine model, or artificial neural networks. In the presented research, tomographic images of selected measurement cases, reconstructed using five methods, were compared. Then, the selection methods’ accuracy was verified thanks to the long short-term memory network used as a classifier. The results proved that the new concept of long short-term memory classification ensures better tomographic reconstructions efficiency than imaging all measurement cases with single homogeneous methods.

Autonomous Mobile Robots in Automotive Remanufacturing: A Case Study for Intra-Logistics Support

“…The aim is to minimize the human role in intralogistics processes through system autonomy, which uses computational intelligence [28] and machine learning to adapt to changing situations. This progressive trend requires diverse artificial intelligence techniques [29][30][31]. These elements are part of the idea of Logistics 4.0, where intralogistics is one of its essential parts [19].…”

Spiral Search Ant Colony Optimization Based AlexNet Model for Emotion Recognition

“…The LSTM network expands the RNN [21,22]. The LSTM model is versatile in dealing with parameters with enormous dimensions and employs each layer's nonlinear activation patterns, allowing it to recognize nonlinear trends in data and retain knowledge from the past over an extended period.…”

A Rapid, Low-Cost, and High-Precision Multifrequency Electrical Impedance Tomography Data Acquisition System for Plant Phenotyping

“…where l i is the length of i-th edge in the mesh, and the index i covers all the edges. Several machine learning algorithms such as an artificial neural network (ANN), a least angle regression (LARS), and an elastic net were also studied previously for EIT inverse solution [35][36][37]. A classic deterministic Gauss-Newton with Laplacian regularization method were compared with the machine learning algorithms [35].…”