Some new Contributions to Neural Networks and Wavelets with Applications
In this Ph.D. thesis, we focus on some problems of general interest both in engineering sciences and applied mathematics. The close connection between some problems concerning neural networks, wavelets, structural health monitoring, and modern Fourier analysis is highlighted and applied in various w...
Main Author: | |
---|---|
Format: | Doctoral or Postdoctoral Thesis |
Language: | English |
Published: |
UiT Norges arktiske universitet
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/28699 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/28699 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/28699 2023-05-15T14:27:55+02:00 Some new Contributions to Neural Networks and Wavelets with Applications Tangrand, Kristoffer Meyer 2023-03-21 https://hdl.handle.net/10037/28699 eng eng UiT Norges arktiske universitet UiT The Arctic University of Norway Paper A: Tangrand, K. & Bremdal, B. (2019). The FlexNett Simulator. IOP Conference Series: Earth and Environmental Science (EES), 352 , 012005. Also available in Munin at https://hdl.handle.net/10037/16729 . Paper B: Tangrand, K. & Bremdal, B. (2020). Using Deep Learning Methods to Monitor Non-Observable States in a Building. Proceedings of the Northern Lights Deep Learning Workshop, 1 , 1-6. Also available in Munin at https://hdl.handle.net/10037/21194 . Paper C: Dechevsky, L. & Tangrand, K. (2022). Wavelet Neural Networks versus Wavelet-based Neural Networks. Technical report, UiT The Arctic University of Norway, 48 pages. Also available on Arxiv.org at https://doi.org/10.48550/arXiv.2211.00396 . Paper D: Tangrand, K. & Singh, H. Analysis of Civil Engineering Infrastructure in Norway With Solutions Based on Structural Health Monitoring and Artificial Intelligence. (Submitted manuscript). Paper E: Tangrand, K., Singh, H. & Grip, N. (2022). A Comprehensive Study of Wavelets and Artificial Intelligence Algorithms for SHM andits Application on a Concrete Railway Arch Bridge. Technical report, UiT The Arctic University of Norway, 2022, 17 pp. Paper F: Baramidze, D., Persson, L.E., Tangrand, K. & Tephnadze, G. H p – L p Type Inequalities for Subsequences of Nörlund Means of Walsh-Fourier Series. (Accepted manuscript). 978-82-7823-245-3 978-82-7823-246-0 https://hdl.handle.net/10037/28699 openAccess Copyright 2023 The Author(s) DOKTOR-008 Doctoral thesis Doktorgradsavhandling 2023 ftunivtroemsoe 2023-03-09T00:04:22Z In this Ph.D. thesis, we focus on some problems of general interest both in engineering sciences and applied mathematics. The close connection between some problems concerning neural networks, wavelets, structural health monitoring, and modern Fourier analysis is highlighted and applied in various ways. The main body of the Ph.D. thesis consists of six papers, A–F, which are put into a more general frame in the introduction. In Paper A we present a case for how systematic use of energy flexibility can be an important instrument for managing peak loads and voltage problems in weak power grids. The FLEXNETT Simulator addresses production and energy dynamics down to every 10 minutes. A recurrent neural network was used to generate realistic values for the simulator. In Paper B we made a case for using a combination of time series from nonintrusive ambient sensors and recurrent neural networks to predict room usage at a university campus. Training data was created by collecting measurements from ambient sensors measuring room CO 2 , humidity, temperature, light, motion, and sound. The findings in papers A and B led to inquiries concerning the learning ability of machine learning models. In Paper C we propose a new approach to machine learning of geometric manifolds in R n using single-layer or deep neural networks, Wavelet-Based Neural Networks (WBNN). Deep WBNNs provide a highly efficient computing architecture for the acceleration of the rate of convergence of the approximation process by using iterative algorithms. The investigations in paper C inspired further research on actual engineering problems where, e.g., wavelets are of crucial importance. In Paper D we investigate the impact of extreme arctic conditions on civil engineering infrastructures. Research and development of new methods are needed for damage detection in these structures. Advances in artificial intelligence could help solve the problem of structural damage detection, especially in arctic regions. In paper E, a new example of the applications ... Doctoral or Postdoctoral Thesis Arctic Arctic University of Tromsø: Munin Open Research Archive Arctic |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
DOKTOR-008 |
spellingShingle |
DOKTOR-008 Tangrand, Kristoffer Meyer Some new Contributions to Neural Networks and Wavelets with Applications |
topic_facet |
DOKTOR-008 |
description |
In this Ph.D. thesis, we focus on some problems of general interest both in engineering sciences and applied mathematics. The close connection between some problems concerning neural networks, wavelets, structural health monitoring, and modern Fourier analysis is highlighted and applied in various ways. The main body of the Ph.D. thesis consists of six papers, A–F, which are put into a more general frame in the introduction. In Paper A we present a case for how systematic use of energy flexibility can be an important instrument for managing peak loads and voltage problems in weak power grids. The FLEXNETT Simulator addresses production and energy dynamics down to every 10 minutes. A recurrent neural network was used to generate realistic values for the simulator. In Paper B we made a case for using a combination of time series from nonintrusive ambient sensors and recurrent neural networks to predict room usage at a university campus. Training data was created by collecting measurements from ambient sensors measuring room CO 2 , humidity, temperature, light, motion, and sound. The findings in papers A and B led to inquiries concerning the learning ability of machine learning models. In Paper C we propose a new approach to machine learning of geometric manifolds in R n using single-layer or deep neural networks, Wavelet-Based Neural Networks (WBNN). Deep WBNNs provide a highly efficient computing architecture for the acceleration of the rate of convergence of the approximation process by using iterative algorithms. The investigations in paper C inspired further research on actual engineering problems where, e.g., wavelets are of crucial importance. In Paper D we investigate the impact of extreme arctic conditions on civil engineering infrastructures. Research and development of new methods are needed for damage detection in these structures. Advances in artificial intelligence could help solve the problem of structural damage detection, especially in arctic regions. In paper E, a new example of the applications ... |
format |
Doctoral or Postdoctoral Thesis |
author |
Tangrand, Kristoffer Meyer |
author_facet |
Tangrand, Kristoffer Meyer |
author_sort |
Tangrand, Kristoffer Meyer |
title |
Some new Contributions to Neural Networks and Wavelets with Applications |
title_short |
Some new Contributions to Neural Networks and Wavelets with Applications |
title_full |
Some new Contributions to Neural Networks and Wavelets with Applications |
title_fullStr |
Some new Contributions to Neural Networks and Wavelets with Applications |
title_full_unstemmed |
Some new Contributions to Neural Networks and Wavelets with Applications |
title_sort |
some new contributions to neural networks and wavelets with applications |
publisher |
UiT Norges arktiske universitet |
publishDate |
2023 |
url |
https://hdl.handle.net/10037/28699 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic Arctic |
genre_facet |
Arctic Arctic |
op_relation |
Paper A: Tangrand, K. & Bremdal, B. (2019). The FlexNett Simulator. IOP Conference Series: Earth and Environmental Science (EES), 352 , 012005. Also available in Munin at https://hdl.handle.net/10037/16729 . Paper B: Tangrand, K. & Bremdal, B. (2020). Using Deep Learning Methods to Monitor Non-Observable States in a Building. Proceedings of the Northern Lights Deep Learning Workshop, 1 , 1-6. Also available in Munin at https://hdl.handle.net/10037/21194 . Paper C: Dechevsky, L. & Tangrand, K. (2022). Wavelet Neural Networks versus Wavelet-based Neural Networks. Technical report, UiT The Arctic University of Norway, 48 pages. Also available on Arxiv.org at https://doi.org/10.48550/arXiv.2211.00396 . Paper D: Tangrand, K. & Singh, H. Analysis of Civil Engineering Infrastructure in Norway With Solutions Based on Structural Health Monitoring and Artificial Intelligence. (Submitted manuscript). Paper E: Tangrand, K., Singh, H. & Grip, N. (2022). A Comprehensive Study of Wavelets and Artificial Intelligence Algorithms for SHM andits Application on a Concrete Railway Arch Bridge. Technical report, UiT The Arctic University of Norway, 2022, 17 pp. Paper F: Baramidze, D., Persson, L.E., Tangrand, K. & Tephnadze, G. H p – L p Type Inequalities for Subsequences of Nörlund Means of Walsh-Fourier Series. (Accepted manuscript). 978-82-7823-245-3 978-82-7823-246-0 https://hdl.handle.net/10037/28699 |
op_rights |
openAccess Copyright 2023 The Author(s) |
_version_ |
1766302001390419968 |