scholarly journals The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography

Energies ◽  
2021 ◽  
Vol 14 (22) ◽  
pp. 7617
Author(s):  
Grzegorz Kłosowski ◽  
Anna Hoła ◽  
Tomasz Rymarczyk ◽  
Łukasz Skowron ◽  
Tomasz Wołowiec ◽  
...  
Keyword(s):  
Electrical Impedance ◽  
Short Term Memory ◽  
Brick Wall ◽  
Time Step ◽  
Impedance Tomography ◽  
Single Time ◽  
Measurement Vector ◽  
Lstm Network ◽  
Tomographic Measurement ◽  
Selection Of

This paper refers to an original concept of tomographic measurement of brick wall humidity using an algorithm based on long short-term memory (LSTM) neural networks. The measurement vector was treated as a data sequence with a single time step in the presented study. This approach enabled the use of an algorithm utilising a recurrent deep neural network of the LSTM type as a system for converting the measurement vector into output images. A prototype electrical impedance tomograph was used in the research. The LSTM network, which is often employed for time series classification, was used to tackle the inverse problem. The task of the LSTM network was to convert 448 voltage measurements into spatial images of a selected section of a historical building’s brick wall. The 3D tomographic image mesh consisted of 11,297 finite elements. A novelty is using the measurement vector as a single time step sequence consisting of 448 features (channels). Through the appropriate selection of network parameters and the training algorithm, it was possible to obtain an LSTM network that reconstructs images of damp brick walls with high accuracy. Additionally, the reconstruction times are very short.

Study of Magnetoacoustic Tomography with Injecting Current by Experiment

2013 ◽  
Vol 756-759 ◽  
pp. 4677-4680 ◽  
Author(s):  
Xin Huang ◽  
Guo Qiang Liu ◽  
Hui Xia
Keyword(s):  
Power Supply ◽  
Magnetic Induction ◽  
Theoretical Basis ◽  
Electrical Impedance ◽  
Imaging Method ◽  
Impedance Tomography ◽  
Good Spatial Resolution ◽  
Ac Power ◽  
Good Contrast ◽  
Selection Of

Magnetoacoustic Tomography (MAT) is a new imaging method. MAT combines the good contrast of electrical impedance tomography with the good spatial resolution of ultrasound imaging. Magnetoacoustic Tomography includes Magnetoacoustic Tomography with magnetic induction and Magnetoacoustic Tomography with injecting current. In this paper we researched the later imaging method mainly; in paper we studied the parameters of AC power supply, which was injected to the imaging sample. At the same time, the waveforms of experiment were given and analyzed, which provides theoretical basis for the selection of power supply used in the subsequent experiments.

scholarly journals A Visual Object Tracking Algorithm Based on Dynamics Pattern and Convolutional Feature

2019 ◽  
Vol 37 (6) ◽  
pp. 1310-1319
Author(s):  
Boyan Zhang ◽  
Yong Zhong ◽  
Zhendong Li
Keyword(s):  
Short Term Memory ◽  
Motion Blur ◽  
Feature Representation ◽  
Visual Object ◽  
Visual Feature ◽  
Illumination Variation ◽  
Time Step ◽  
Bounding Box ◽  
Feature Based ◽  
Lstm Network

Deep visual feature-based method has demonstrated impressive performance in visual tracking attributing to its powerful capability of visual feature representation. However, in some complex environments such as dramatic change of appearance, illumination variation and rotation, the extracted deep visual feature is insufficient for accurately characterizing the target. To solve this problem, we present an integrated tracking framework which combines a Long Short-Term Memory (LSTM) network and a Convolutional Neural Network (CNN). Firstly, the LSTM extracted dynamics feature of target on time sequence, resulting the state of target at present time step. With that state, the accurate preprocessed bounding box was obtained. Then, deep convolutional feature of the target was extracted using a CNN, based on the processed bounding box. Finally, the position of the target was determined based on the score of the feature. During tracking stage, in order to improve the adaptation of the network, the parameters of the network were updated using samples of the target captured while successful tracking. The experiment shows that the proposed method achieves outstanding tracking performance and robustness in cases of partial occlusion, out-of-view, motion blur and fast motion.

scholarly journals Quality Assessment of the Neural Algorithms on the Example of EIT-UST Hybrid Tomography

Sensors ◽  
2020 ◽  
Vol 20 (11) ◽  
pp. 3324
Author(s):  
Grzegorz Kłosowski ◽  
Tomasz Rymarczyk ◽  
Tomasz Cieplak ◽  
Konrad Niderla ◽  
Łukasz Skowron
Keyword(s):  
Electrical Impedance ◽  
Ultrasonic Tomography ◽  
Tomographic Image ◽  
Impedance Tomography ◽  
Multiple Neural Networks ◽  
Percent Concentration ◽  
Measurement Vector ◽  
Artificial Neural Network Ann ◽  
The Individual ◽  
Made In

The paper presents the results of research on the hybrid industrial tomograph electrical impedance tomography (EIT) and ultrasonic tomography (UST) (EIT-UST), operating on the basis of electrical and ultrasonic data. The emphasis of the research was placed on the algorithmic domain. However, it should be emphasized that all hardware components of the hybrid tomograph, including electronics, sensors and transducers, have been designed and mostly made in the Netrix S.A. laboratory. The test object was a tank filled with water with several dozen percent concentration. As part of the study, the original multiple neural networks system was trained, the characteristic feature of which is the generation of each of the individual pixels of the tomographic image, using an independent artificial neural network (ANN), with the input vector for all ANNs being the same. Despite the same measurement vector, each of the ANNs generates its own independent output value for a given tomogram pixel, because, during training, the networks get their respective weights and biases. During the tests, the results of three tomographic methods were compared: EIT, UST and EIT-UST hybrid. The results confirm that the use of heterogeneous tomographic systems (hybrids) increases the reliability of reconstruction in various measuring cases, which is used to solve quality problems in managing production processes.

CALIBRATION OF A LOW COST ELECTRICAL IMPEDANCE TOMOGRAPHY SYSTEM WITH A RING OF RESISTORS AND A KCL SOLUTION

2019 ◽  
Author(s):  
Bruno Furtado de Moura ◽  
francisco sepulveda ◽  
Jorge Luis Jorge Acevedo ◽  
Wellington Betencurte da Silva ◽  
Rogerio Ramos ◽  
...  
Keyword(s):  
Electrical Impedance Tomography ◽  
Electrical Impedance ◽  
Low Cost ◽  
Impedance Tomography ◽  
Tomography System

Is Hydraulics Over-Used or Under-Used in Storm Drainage?

1994 ◽  
Vol 29 (1-2) ◽  
pp. 53-61
Author(s):  
Ben Chie Yen
Keyword(s):  
Unsteady Flow ◽  
Computational Time ◽  
Time Step ◽  
Flow Routing ◽  
Kinematic Wave Equation ◽  
Storm Drainage ◽  
Saint Venant Equations ◽  
Unsteady Flow Routing ◽  
Selection Of

Urban drainage models utilize hydraulics of different levels. Developing or selecting a model appropriate to a particular project is not an easy task. Not knowing the hydraulic principles and numerical techniques used in an existing model, users often misuse and abuse the model. Hydraulically, the use of the Saint-Venant equations is not always necessary. In many cases the kinematic wave equation is inadequate because of the backwater effect, whereas in designing sewers, often Manning's formula is adequate. The flow travel time provides a guide in selecting the computational time step At, which in turn, together with flow unsteadiness, helps in the selection of steady or unsteady flow routing. Often the noninertia model is the appropriate model for unsteady flow routing, whereas delivery curves are very useful for stepwise steady nonuniform flow routing and for determination of channel capacity.

Sign in / Sign up

Export Citation Format

Share Document