2020
DOI: 10.1007/978-3-030-65347-7_21
|View full text |Cite
|
Sign up to set email alerts
|

Graph Signal Processing on Complex Networks for Structural Health Monitoring

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
6
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
2
2

Relationship

3
4

Authors

Journals

citations
Cited by 8 publications
(6 citation statements)
references
References 18 publications
0
6
0
Order By: Relevance
“…In future work, we aim to extend the analysis towards further real-world complex networks in order to capture and investigate further real-world phenomena about potential anomalies, e.g., in feature-rich networks [4] as well as taking temporal relations into account [4,41]. In addition, we plan to analyze other centrality measures in order to compare those results with eigenvector centrality in terms of detection performance.…”
Section: Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…In future work, we aim to extend the analysis towards further real-world complex networks in order to capture and investigate further real-world phenomena about potential anomalies, e.g., in feature-rich networks [4] as well as taking temporal relations into account [4,41]. In addition, we plan to analyze other centrality measures in order to compare those results with eigenvector centrality in terms of detection performance.…”
Section: Discussionmentioning
confidence: 99%
“…According to the classical definition of [32], "an outlier is an observation that differs so much from other observations as to arouse suspicion that it was generated by a different mechanism". Here, there exists a variety of techniques, e.g., using subspace clustering [33,34], tensor factorization [35], community detection [36], adapting deep learning (classification/condition monitoring) techniques [37][38][39], or graph/signal processing methods [40,41]. Identifying anomalies in network data is a prominent novel research area.…”
Section: Anomaly Detectionmentioning
confidence: 99%
“…In particular, complex structures encountered in complex (networked) systems and structures, such as computer networks, social networks, infrastructure networks, sensor networks, as well as cyber-physical networks play an important role throughout our everyday life. However, the network concept transcends such explicit structures, towards more implicit networks observed in physical structures of interdependent elements or components (Bloemheuvel et al 2020;Worden 2021). In particular, in the field of complex networks and feature rich networks both the need as well as the opportunities in studying such complex network topologies, has made the use of complex network models pervasive in many fields of research such as computer science, physics, engineering and the social sciences, also joining into interdisciplinary research contexts, cf.…”
Section: Complex Networkmentioning
confidence: 99%
“…Overall, in this paper -a substantially adapted and extended revision of (Bloemheuvel et al 2020) -we present a computational framework for modeling complex sensor network data in the form of complex networks including GSP and GNN for Structural Health Monitoring (SHM) (Miao 2014;Sony et al 2019;Abdulkarem et al 2020) and analysis. Compared to (Bloemheuvel et al 2020), we have specifically extended the presentation of the proposed approach, the contextualization as well as the experimentation. Most importantly, we have included a novel component into our framework, i. e., the GNN-based method for incorporating predictive analytics into our computational framework.…”
Section: Introductionmentioning
confidence: 99%
“…In addition, we furthermore aim at proposing deep learning approaches able to leverage heterogeneous information sources (multi-source satellite images, sen-sors, and more) in order to produce accurate estimations regarding the soil carbon and the biodiversity of a certain area, cf., [20,23]. The eventual use of sensors also opens up to the use of advanced geometric deep learning techniques, i. e., graph convolutional networks able to exploit non-euclidean structures in the data, such as network graphs, e. g., [9,33]. Note that the use of advanced deep learning techniques allows to work on data fusion at a feature level.…”
Section: Explainable Ai and Decision Supportmentioning
confidence: 99%