Graph Signal Processing on Complex Networks for Structural Health Monitoring

Bloemheuvel, Stefan; Hoogen, Jurgen van den; Atzmueller, Martin

doi:10.1007/978-3-030-65347-7_21

Cited by 8 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

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%

“…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%

See 1 more Smart Citation

Many-Objective Optimization for Anomaly Detection on Multi-Layer Complex Interaction Networks

Maulana

Atzmueller

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Anomaly detection in complex networks is an important and challenging task in many application domains. Examples include analysis and sensemaking in human interactions, e.g., in (social) interaction networks, as well as the analysis of the behavior of complex technical and cyber-physical systems such as suspicious transactions/behavior in financial or routing networks; here, behavior and/or interactions typically also occur on different levels and layers. In this paper, we focus on detecting anomalies in such complex networks. In particular, we focus on multi-layer complex networks, where we consider the problem of finding sets of anomalous nodes for group anomaly detection. Our presented method is based on centrality-based many-objective optimization on multi-layer networks. Starting from the Pareto Front obtained via many-objective optimization, we rank anomaly candidates using the centrality information on all layers. This ranking is formalized via a scoring function, which estimates relative deviations of the node centralities, considering the density of the network and its respective layers. In a human-centered approach, anomalous sets of nodes can then be identified. A key feature of this approach is its interpretability and explainability, since we can directly assess anomalous nodes in the context of the network topology. We evaluate the proposed method using different datasets, including both synthetic as well as real-world network data. Our results demonstrate the efficacy of the presented approach.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Anomaly Detectionmentioning

confidence: 99%

Many-Objective Optimization for Anomaly Detection on Multi-Layer Complex Interaction Networks

Maulana

Atzmueller

2021

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…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%

A Computational Framework for Modeling Complex Sensor Network Data Using Graph Signal Processing and Graph Neural Networks in Structural Health Monitoring

Bloemheuvel¹,

Hoogen²,

Atzmueller³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Complex networks lend themselves to the modeling of multidimensional data, such as relational and/or temporal data. In particular, when such complex data and their inherent relationships need to be formalized, complex network modeling and its resulting graph representations enable a wide range of powerful options. In this paper, we target this -connected to specific machine learning approaches on graphs for structural health monitoring on an analysis and predictive (maintenance) perspective. Specifically, we present a framework based on Complex Network Modeling, integrating Graph Signal Processing (GSP) and Graph Neural Network (GNN) approaches. We demonstrate this framework in our targeted application domain of Structural Health Monitoring (SHM). In particular, we focus on a prominent real-world structural health monitoring use case, i. e., modeling and analyzing sensor data (strain, vibration) of a large bridge in the Netherlands. In our experiments, we show that GSP enables the identification of the most important sensors, for which we investigate a set of search and optimization approaches. Furthermore, GSP enables the detection of specific graph signal patterns (mode shapes), capturing physical functional properties of the sensors in the applied complex network. In addition, we show the efficacy of applying GNNs for strain prediction on this kind of data.

show abstract

“…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%

Gaia-AgStream: An Explainable AI Platform for Mining Complex Data Streams in Agriculture

Schoenke¹,

Aschenbruck

Interdonato

et al. 2021

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

We present a position paper about our concept for an artificial intelligence (AI) and data streaming platform for the agricultural sector. The goal of our project is to support agroecology in terms of carbon farming and biodiversity protection by providing an AI and data streaming platform called Gaia-AgStream that accelerates the adoption of AI in agriculture and is directly usable by farmers as well as agricultural companies in general. The technical innovations we propose focus on smart sensor networks, unified uncertainty management, explainable AI, root cause analysis and hybrid AI approaches. Our AI and data streaming platform concept contributes to the European open data infrastructure project Gaia-X in terms of interoperability for data and AI models as well as data sovereignty and AI infrastructure. Our envisioned platform and the developed AI components for carbon farming and biodiversity will enable farmers to adopt sustainable and resilient production methods while establishing new and diverse revenue streams by monetizing carbon sequestration and AI ready data streams. The open and federated platform concept allows to bring together research, industry, agricultural start-ups and farmers in order to form sustainable innovation networks. We describe core concepts and architecture of our proposed approach in these contexts, outline practical use cases for our platform and finally outline challenges and future prospects.

show abstract

Graph Signal Processing on Complex Networks for Structural Health Monitoring

Cited by 8 publications

References 18 publications

Many-Objective Optimization for Anomaly Detection on Multi-Layer Complex Interaction Networks

Many-Objective Optimization for Anomaly Detection on Multi-Layer Complex Interaction Networks

A Computational Framework for Modeling Complex Sensor Network Data Using Graph Signal Processing and Graph Neural Networks in Structural Health Monitoring

Gaia-AgStream: An Explainable AI Platform for Mining Complex Data Streams in Agriculture

Contact Info

Product

Resources

About