Hierarchical Pattern Matching for Anomaly Detection in Time Series
Computer Communications - 2022
Abstract: As companies rely on an ever increasing number of connected devices for their day to day operations, a need arises for automated anomaly detectors to constantly observe crucial device metrics in real time to prevent downtime and data loss. As production environments tend to monitor a huge amount of these metrics, it prevents current state-of-the-art techniques to be deployed as the required computational resources is too high. This paper proposes a lightweight anomaly detection method that can be deployed in these environments without a reduction in accuracy. The approach works fully online, and does not require an extensive history set to be kept in memory. The method is benchmarked on the publicly available Numenta dataset, as well as a network monitoring dataset from different environments provided by a network management solution vendor. These benchmarks show the proposed technique to be very competitive with the current state-of-the-art and exceeding it in production applicability.
@article{vanonsem_hierarchical_2022,
title = {Hierarchical pattern matching for anomaly detection in time series},
journal = {Computer Communications},
volume = {193},
pages = {75-81},
year = {2022},
issn = {0140-3664},
doi = {https://doi.org/10.1016/j.comcom.2022.06.027},
url = {https://www.sciencedirect.com/science/article/pii/S0140366422002298},
author = {M. {Van Onsem} and D. {De Paepe} and S. {Vanden Hautte} and P. Bonte and V. Ledoux and A. Lejon and F. Ongenae and D. Dreesen and S. {Van Hoecke}},
keywords = {Anomaly detection, Network monitoring, Time series}
}
An Incremental Grey-Box Current Regression Model for Anomaly Detection of Resistance Mash Seam Welding in Steel Mills
Applied Science - Special Issue: Applications of Artificial Intelligence Systems - 2022
Abstract: Annealing and galvanization production lines in steel mills run continuously to maximize production throughput. As a part of this process, individual steel coils are joined end-to-end using mash seam welding. Weld breaks result in a production loss of multiple days, so non-destructive, data-driven techniques are used to detect and replace poor quality welds in real-time. Statistical models are commonly used to address this problem as they use data readily available from the welding machine and require no specialized equipment. While successful in finding anomalies, these statistical models do not provide insight into the underlying process and are slow to adapt to changes in the machine’s or material’s behavior. We combine knowledge-based and data-driven techniques to create an incremental grey-box welding current prediction model for detecting anomalous welds, resulting in a powerful and interpretable model. In this work, we detail our approach and show evaluation results on industrial welding data collected over a period of 15 months containing behavioral shifts attributed to machine maintenance. Due to its incremental nature, our model resulted in two-thirds fewer rejected welds compared to statistical models, thus greatly reducing production overhead. Grey-box modeling can be applied to other welding features or domains and results in models that are more desirable for the industry.
@article{depaepe_seam_welding_2022,
author = {De Paepe, Dieter and Van Yperen-De Deyne, Andy and Defever, Jan and Van Hoecke, Sofie},
title = {An Incremental Grey-Box Current Regression Model for Anomaly Detection of Resistance Mash Seam Welding in Steel Mills},
journal = {Applied Sciences},
volume = {12},
year = {2022},
number = {2},
article-number = {913},
url = {https://www.mdpi.com/2076-3417/12/2/913},
issn = {2076-3417},
doi = {10.3390/app12020913}
}
A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project
Applied Science - Special Issue: Innovations in Intelligent Machinery and Industry 4.0 - 2021
Abstract: Companies are increasingly gathering and analyzing time-series data, driven by the rising number of IoT devices. Many works in literature describe analysis systems built using either data-driven or semantic (knowledge-driven) techniques. However, little to no works describe hybrid combinations of these two. Dyversify, a collaborative project between industry and academia, investigated how event and anomaly detection can be performed on time-series data in such a hybrid setting. We built a proof-of-concept analysis platform, using a microservice architecture to ensure scalability and fault-tolerance. The platform comprises time-series ingestion, long term storage, data semantification, event detection using data-driven and semantic techniques, dynamic visualization, and user feedback. In this work, we describe the system architecture of this hybrid analysis platform and give an overview of the different components and their interactions. As such, the main contribution of this work is an experience report with challenges faced and lessons learned.
@article{depaepe_stack_2021,
author = {De Paepe, Dieter and Vanden Hautte, Sander and Steenwinckel, Bram and Moens, Pieter and Vaneessen, Jasper and Vandekerckhove, Steven and Volckaert, Bruno and Ongenae, Femke and Van Hoecke, Sofie},
title = {A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project},
journal = {Applied Sciences},
volume = {11},
year = {2021},
number = {24},
article-number = {11932},
url = {https://www.mdpi.com/2076-3417/11/24/11932},
issn = {2076-3417},
doi = {10.3390/app112411932}
}
Event-Driven Dashboarding and Feedback for Improved Event Detection in Predictive Maintenance Applications
Applied Science - Special Issue: Overcoming the Obstacles to Predictive Maintenance - 2021
Abstract: Manufacturers can plan predictive maintenance by remotely monitoring their assets. However, to extract the necessary insights from monitoring data, they often lack sufficiently large datasets that are labeled by human experts. We suggest combining knowledge-driven and unsupervised data-driven approaches to tackle this issue. Additionally, we present a dynamic dashboard that automatically visualizes detected events using semantic reasoning, assisting experts in the revision and correction of event labels. Captured label corrections are immediately fed back to the adaptive event detectors, improving their performance. To the best of our knowledge, we are the first to demonstrate the synergy of knowledge-driven detectors, data-driven detectors and automatic dashboards capturing feedback. This synergy allows a transition from detecting only unlabeled events, such as anomalies, at the start to detecting labeled events, such as faults, with meaningful descriptions. We demonstrate all work using a ventilation unit monitoring use case. This approach enables manufacturers to collect labeled data for refining event classification techniques with reduced human labeling effort.
@article{moens_dashboarding_2021,
author = {Moens, Pieter and Vanden Hautte, Sander and De Paepe, Dieter and Steenwinckel, Bram and Verstichel, Stijn and Vandekerckhove, Steven and Ongenae, Femke and Van Hoecke, Sofie},
title = {Event-Driven Dashboarding and Feedback for Improved Event Detection in Predictive Maintenance Applications},
journal = {Applied Sciences},
volume = {11},
year = {2021},
number = {21},
article-number = {10371},
url = {https://www.mdpi.com/2076-3417/11/21/10371},
issn = {2076-3417},
doi = {10.3390/app112110371}
}
Insight Mining in Time Series Data with Applications for Anomaly Detection
PhD Thesis - 2021
@phdthesis{depaepe_phd_2021,
title = {Insight Mining in Time Series Data with Applications for Anomaly Detection},
school = {Ghent University},
author = {De Paepe, Dieter},
year = 2021,
month = jun,
address = {Ghent, Belgium}
}
FLAGS: A methodology for adaptive anomaly detection and root cause analysis on sensor data streams by fusing expert knowledge with machine learning
Future Generation Computer Systems - 2021
Abstract: Anomalies and faults can be detected, and their causes verified, using both data-driven and knowledge-driven techniques. Data-driven techniques can adapt their internal functioning based on the raw input data but fail to explain the manifestation of any detection. Knowledge-driven techniques inherently deliver the cause of the faults that were detected but require too much human effort to set up. In this paper, we introduce FLAGS, the Fused-AI interpretabLe Anomaly Generation System, and combine both techniques in one methodology to overcome their limitations and optimize them based on limited user feedback. Semantic knowledge is incorporated in a machine learning technique to enhance expressivity. At the same time, feedback about the faults and anomalies that occurred is provided as input to increase adaptiveness using semantic rule mining methods. This new methodology is evaluated on a predictive maintenance case for trains. We show that our method reduces their downtime and provides more insight into frequently occurring problems.
@article{steenwinckel_2021,
title = "FLAGS: A methodology for adaptive anomaly detection and root cause analysis on sensor data streams by fusing expert knowledge with machine learning",
journal = "Future Generation Computer Systems",
volume = "116",
pages = "30 - 48",
year = "2021",
issn = "0167-739X",
doi = "https://doi.org/10.1016/j.future.2020.10.015",
url = "http://www.sciencedirect.com/science/article/pii/S0167739X20329927",
author = "Steenwinckel, Bram and De Paepe, Dieter and Vanden Hautte, Sander and Heyvaert, Pieter and Bentefrit, Mohamed and Moens, Pieter and Dimou, Anastasia and Van Den Bossche, Bruno and De Turck, Filip and Van Hoecke, Sofie and Ongenae, Femke",
keywords = "Anomaly detection, Root cause analysis, Machine learning, Semantic web, Internet of Things, Fused AI, User feedback",
}
Mining Recurring Patterns in Real-Valued Time Series using the Radius Profile
Proceedings of the 20th International Conference on Data Mining (ICDM) - 2020
Abstract: Time series analysis is becoming more popular in both research and industry. One recent innovation is the Ostinato algorithm, which finds the best preserved patterns that are repeated in a collection of series, i.e. consensus motifs and corresponding radii. However, Ostinato only works as a batch algorithm, can only find the top-k patterns, only finds patterns that are repeated in multiple series and has a runtime that depends on the input series and setup parameters. To tackle these limitations, we present two algorithms in this paper that can answer broader questions. First, we created an anytime version of Ostinato, called Anytime Ostinato, that finds the exact consensus radius for each subsequence, i.e. the radius profile, or can estimate these radii in a fraction of the time. Second, we designed a batch algorithm, called Single Series Ostinato, that finds the radius profile for a single series allowing us to detect repeating patterns in a single series, which is not possible for Ostinato. In this paper we explain both algorithms and apply them to the REFIT and PAMAP2 datasets respectively.
@inproceedings{depaepe_radius_2020,
author = {De Paepe, Dieter and Van Hoecke, Sofie},
booktitle = {Proceedings of the 20th International Conference on Data Mining (ICDM)},
title = {Mining Recurring Patterns in Real-Valued Time Series using the Radius Profile},
year = {2020},
publisher = {IEEE},
pages = {984-989},
doi = {10.1109/ICDM50108.2020.00113}
}
Implications of Z-Normalization in the Matrix Profile
Pattern Recognition Applications and Methods - 2020
Abstract: Companies are increasingly measuring their products and services, resulting in a rising amount of available time series data, making techniques to extract usable information needed. One state-of-the-art technique for time series is the Matrix Profile, which has been used for various applications including motif/discord discovery, visualizations and semantic segmentation. Internally, the Matrix Profile utilizes the z-normalized Euclidean distance to compare the shape of subsequences between two series. However, when comparing subsequences that are relatively flat and contain noise, the resulting distance is high despite the visual similarity of these subsequences. This property violates some of the assumptions made by Matrix Profile based techniques, resulting in worse performance when series contain flat and noisy subsequences. By studying the properties of the z-normalized Euclidean distance, we derived a method to eliminate this effect requiring only an estimate of the standard deviation of the noise. In this paper we describe various practical properties of the z-normalized Euclidean distance and show how these can be used to correct the performance of Matrix Profile related techniques. We demonstrate our techniques using anomaly detection using a Yahoo! Webscope anomaly dataset, semantic segmentation on the PAMAP2 activity dataset and for data visualization on a UCI activity dataset, all containing real-world data, and obtain overall better results after applying our technique. Our technique is a straightforward extension of the distance calculation in the Matrix Profile and will benefit any derived technique dealing with time series containing flat and noisy subsequences.
@InProceedings{depaepe_znorm_2020,
author = "De Paepe, Dieter and Avendano, Diego Nieves and Van Hoecke, Sofie",
editor = "De Marsico, Maria and Sanniti di Baja, Gabriella and Fred, Ana",
title = "Implications of Z-Normalization in the Matrix Profile",
booktitle = "Pattern Recognition Applications and Methods",
year = "2020",
publisher = "Springer International Publishing",
address = "Cham",
pages = "95--118",
doi = "https://doi.org/10.1007/978-3-030-40014-9_5",
isbn = "978-3-030-40014-9"
}
A Generalized Matrix Profile Framework with Support for Contextual Series Analysis
Engineering Applications of Artificial Intelligence - 2020
Abstract: The Matrix Profile is a state-of-the-art time series analysis technique that can be used for motif discovery, anomaly detection, segmentation and others, in various domains such as healthcare, robotics, and audio. Where recent techniques use the Matrix Profile as a preprocessing or modeling step, we believe there is unexplored potential in generalizing the approach. We derived a framework that focuses on the implicit distance matrix calculation. We present this framework as the Series Distance Matrix (SDM). In this framework, distance measures (SDM-generators) and distance processors (SDM-consumers) can be freely combined, allowing for more flexibility and easier experimentation. In SDM, the Matrix Profile is but one specific configuration. We also introduce the Contextual Matrix Profile (CMP) as a new SDM-consumer capable of discovering repeating patterns. The CMP provides intuitive visualizations for data analysis and can find anomalies that are not discords. We demonstrate this using two real world cases. The CMP is the first of a wide variety of new techniques for series analysis that fits within SDM and can complement the Matrix Profile.
@article{depaepe_sdm_2020,
title = "A generalized matrix profile framework with support for contextual series analysis",
journal = "Engineering Applications of Artificial Intelligence",
volume = "90",
pages = "103487",
year = "2020",
issn = "0952-1976",
doi = "https://doi.org/10.1016/j.engappai.2020.103487",
url = "http://www.sciencedirect.com/science/article/pii/S0952197620300087",
author = "Dieter De Paepe and Sander Vanden Hautte and Bram Steenwinckel and Filip De Turck and Femke Ongenae and Olivier Janssens and Sofie Van Hoecke",
keywords = "Time series, Anomaly detection, Matrix Profile, Distance matrix, Series Distance Matrix, Contextual Matrix Profile",
}
A Dynamic Dashboarding Application for Fleet Monitoring Using Semantic Web of Things Technologies
Sensors - 2020
Abstract: In industry, dashboards are often used to monitor fleets of assets, such as trains, machines or buildings. In such industrial fleets, the vast amount of sensors evolves continuously, new sensor data exchange protocols and data formats are introduced, new visualization types may need to be introduced and existing dashboard visualizations may need to be updated in terms of displayed sensors. These requirements motivate the development of dynamic dashboarding applications. These, as opposed to fixed-structure dashboard applications, allow users to create visualizations at will and do not have hard-coded sensor bindings. The state-of-the-art in dynamic dashboarding does not cope well with the frequent additions and removals of sensors that must be monitored—these changes must still be configured in the implementation or at runtime by a user. Also, the user is presented with an overload of sensors, aggregations and visualizations to select from, which may sometimes even lead to the creation of dashboard widgets that do not make sense. In this paper, we present a dynamic dashboard that overcomes these problems. Sensors, visualizations and aggregations can be discovered automatically, since they are provided as RESTful Web Things on a Web Thing Model compliant gateway. The gateway also provides semantic annotations of the Web Things, describing what their abilities are. A semantic reasoner can derive visualization suggestions, given the Thing annotations, logic rules and a custom dashboard ontology. The resulting dashboarding application automatically presents the available sensors, visualizations and aggregations that can be used, without requiring sensor configuration, and assists the user in building dashboards that make sense. This way, the user can concentrate on interpreting the sensor data and detecting and solving operational problems early.
@article{vandenhautte_dynamic_dashboard_2020,
author = {Vanden Hautte, Sander and Moens, Pieter and Van Herwegen, Joachim and De Paepe, Dieter and Steenwinckel, Bram and Verstichel, Stijn and Ongenae, Femke and Van Hoecke, Sofie},
title = {A Dynamic Dashboarding Application for Fleet Monitoring Using Semantic Web of Things Technologies},
journal = {Sensors},
volume = {20},
year = {2020},
number = {4},
article-number = {1152},
url = {https://www.mdpi.com/1424-8220/20/4/1152},
issn = {1424-8220},
doi = {10.3390/s20041152}
}
Raising interoperability among base registries: The evolution of the Linked Base Registry for addresses in Flanders
Journal of Web Semantics - 2019
Abstract: The transformation of society towards a digital economy and government austerity creates a new context leading to changing roles for both government and private sector. Boundaries between public and private services are blurring, enabling government and private sector to collaborate and share responsibilities. In Belgium, the regional Government of Flanders embedded the re-use of public sector information in its legislation and published a data portal containing well over 4000 Open Datasets. Due to a lack of interoperability, interconnecting and interpreting these sources of information remain challenges for public administrations, businesses and citizens. To dissolve the boundaries between the data silos, the Flemish government applied Linked Data design principles in an operational public sector context. This paper discusses the trends we have identified while ‘rewiring’ the Authentic Source for addresses to a Linked Base Registry. We observed the impact on multiple interoperability levels; namely on the legal, organisational, semantic and technical level. In conclusion Linked Data can increase semantic and technical interoperability and lead to a better adoption of government information in the public and private sector. We strongly believe that the insights from the past thirteen years in the region of Flanders could speed up processes in other countries that are facing the complexity of raising technical and semantic interoperability.
@article{buyle_semantics_2018,
title = "Raising interoperability among base registries: The evolution of the Linked Base Registry for addresses in Flanders",
journal = "Journal of Web Semantics",
volume = "55",
pages = "86 - 101",
year = "2019",
issn = "1570-8268",
doi = "https://doi.org/10.1016/j.websem.2018.10.003",
url = "http://www.sciencedirect.com/science/article/pii/S1570826818300519",
author = {Buyle, Raf and Vanlishout, Ziggy and Coetzee, Serena and De Paepe, Dieter and Van Compernolle, Mathias and Thijs, Geert and Van Nuffelen, Bert and De Vocht, Laurens and Mechant, Peter and De Vidts, Bjorn and Mannens, Erik},
}
Eliminating Noise in the Matrix Profile
Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - 2019
Abstract: As companies are increasingly measuring their products and services, the amount of time series data is rising and techniques to extract usable information are needed. One recently developed data mining technique for time series is the Matrix Profile. It consists of the smallest z-normalized Euclidean distance of each subsequence of a time series to all other subsequences of another series. It has been used for motif and discord discovery, for segmentation and as building block for other techniques. One side effect of the z-normalization used is that small fluctuations on flat signals are upscaled. This can lead to high and unintuitive distances for very similar subsequences from noisy data. We determined an analytic method to estimate and remove the effects of this noise, adding only a single, intuitive parameter to the calculation of the Matrix Profile. This paper explains our method and demonstrates it by performing discord discovery on the Numenta Anomaly Benchmark and by segmenting the PAMAP2 activity dataset. We find that our technique results in a more intuitive Matrix Profile and provides improved results in both usecases for series containing many flat, noisy subsequences. Since our technique is an extension of the Matrix Profile, it can be applied to any of the various tasks that could be solved by it, improving results where data contains flat and noisy sequences
@inproceedings{depaepe_icpram_2019,
title = {Eliminating Noise in the Matrix Profile},
author = {De Paepe, Dieter and Janssens, Olivier and Van Hoecke, Sofie},
booktitle = {Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
pages = {83-93},
year = {2019},
month = {feb},
publisher = {SciTePress},
organization = {INSTICC},
doi = {10.5220/0007314100830093},
isbn = {978-989-758-351-3},
issn = {2184-4313}
}
Towards adaptive anomaly detection and root cause analysis by automated extraction of knowledge from risk analyses
Proceedings of the 9th international semantic sensor networks workshop, co-located with 17th international semantic web conference (ISWC 2018) - 2018
Abstract: Sensors inside internet-connected devices analyse the environment and monitor possible unwanted behaviour. Current risk analysis tools, such as Fault Tree Analysis (FTA) and Failure Mode and Effect Analysis (FMEA), provide prior information on these malfunctions. Many people are involved in this risk analyses process, resulting in disambiguations and incompleteness. Ontologies could resolve this issue by providing a uniform structure for the failures and their causes. However, domain experts are not always ontology experts, resulting in a lot of human effort to keep the ontologies up to date. In this paper, automated mappings from the FMEA data to a domain-specific ontology and the generation of rules from a constructed FTA were researched to annotate and reason on sensor observations semantically. The approach is demonstrated with a use case to investigate the possible failures and causes of reduced passenger comfort levels inside a train.
@inproceedings{SteenwinckelISWC_2018_2,
author = {Steenwinckel, Bram and Heyvaert, Pieter and De Paepe, Dieter and Janssens, Olivier and Vanden Hautte, Sander and Dimou, Anastasia and De Turck, Filip and Van Hoecke, Sofie and Ongenae, Femke},
booktitle = {Proceedings of the 9th international semantic sensor networks workshop, co-located with 17th international semantic web conference (ISWC 2018)},
issn = {1613-0073},
language = {eng},
location = {Monterey, CA, USA},
pages = {17--31},
title = {Towards adaptive anomaly detection and root cause analysis by automated extraction of knowledge from risk analyses},
url = {http://ceur-ws.org/Vol-2213/paper2.pdf},
volume = {2213},
year = {2018},
}
Automated extraction of rules and knowledge from risk analyses: a ventilation unit demo
Proceedings of the ISWC 2018 posters & demonstrations, industry and blue sky ideas tracks, co-located with 17th international Semantic Web conference (ISWC 2018) - 2018
Abstract: Assessing upfront the causes and effects of failures is an important aspect of system manufacturing. Nowadays, these analyses are performed by a large number of experts. To enable semantic unification and easy operationalization of these risk analyses, this paper demonstrates an approach to automatically map the captured information into an ontology and accompanying rules. The approach is demonstrated with a use case to identify anomalies and their causes within a ventilation unit.
@inproceedings{SteenwinckelISWC_2018,
author = {Steenwinckel, Bram and Heyvaert, Pieter and De Paepe, Dieter and Janssens, Olivier and Vanden Hautte, Sander and Dimou, Anastasia and De Turck, Filip and Van Hoecke, Sofie and Ongenae, Femke},
booktitle = {Proceedings of the ISWC 2018 posters \& demonstrations, industry and blue sky ideas tracks, co-located with 17th international Semantic Web conference (ISWC 2018)},
editor = {van Erp, Marieke and Atre, Medha and Lopez, Vanessa and Srinivas, Kavitha and Fortuna, Carolina},
issn = {1613-0073},
language = {eng},
location = {Monterey, CA, USA},
pages = {4},
title = {Automated extraction of rules and knowledge from risk analyses: a ventilation unit demo},
url = {http://ceur-ws.org/Vol-2180/paper-63.pdf},
volume = {2180},
year = {2018},
}
Semantics in the wild : a digital assistant for Flemish citizens
Proceedings of the 11th International Conference on Theory and Practice of Electronic Governance - 2018
Abstract: Public service fragmentation across more than 800 digital channels of government administrations in the region of Flanders (Belgium), causes administrative burden and frustrations, as citizens expect a coherent service. Given the autonomy of the various entities, the fragmentation of information and budget constraints, it is not feasible to rewire the entire e-gov ecosystem to a single portal. Therefore, the Flemish Government is building a smart digital assistant, which supports citizens on the governmental portals, by integrating status information of various transactions. This paper outlines our ongoing research on a method for raising semantic interoperability between different information systems and actors. In this approach, semantic agreements are maintained and implemented end-to-end using the design principles of Linked Data. The lessons learned can speed-up the process in other countries that face the complexity of integrating e-government portals.
@inproceedings{BuyleICEGOV_2018,
author = {Buyle, Raf and Van Compernolle, Mathias and De Paepe, Dieter and Scheerlinck, Jens and Mechant, Peter and Mannens, Erik and Vanlishout, Ziggy},
booktitle = {Proceedings of the 11th International Conference on Theory and Practice of Electronic Governance},
isbn = {9781450354219},
language = {eng},
location = {Galway, Iceland},
pages = {1--6},
title = {Semantics in the wild : a digital assistant for Flemish citizens},
url = {http://dx.doi.org/10.1145/3209415.3209421},
year = {2018},
}
Constraints for a large-scale ITS data-sharing system: a use case in the city of Ghent
Proceedings of the 12th ITS European Congress - 2017
Abstract: Thanks to architectural constraints adopted by its stakeholders, the World Wide Web was able to scale up to its current size. To realize the ITS directive, which stimulates sharing data on large scale between different parties across Europe, a large-scale information system is needed as well. We discuss three constraints which lie at the basis of the success of the Web, and apply these to transport data publishing: stateless interaction, cacheability and a uniform interface. The city of Ghent implemented these constraints for publishing the dynamic capacity of the parking sites. The information system, allowing federated queries from the browser, achieves a good user perceived performance, a good network efficiency, achieves a scalable server infrastructure, and enables a simple to reuse dataset. To persist such a transport data information system, still a well-maintained Linked Data vocabulary is needed. We propose to add these URIs into the DATEX2 specification.
@inproceedings{colpaert_its_2017,
author = {Colpaert, Pieter and Van der Perre, Peter and De Paepe, Dieter and Thoeye, Thimo and Verborgh, Ruben and Mannens, Erik},
title = {Constraints for a large-scale ITS data-sharing system: a use case in the city of Ghent},
booktitle = {Proceedings of the 12th ITS European Congress},
year = 2017,
month = jun,
url = {https://pietercolpaert.be/papers/its-eu2017/paper.pdf},
}
Automated UML-Based Ontology Generation in OSLO²
Proceedings of the 14th ESWC: Posters and Demos - 2017
Abstract: In 2015, Flanders Information started the OSLO2 project, aimed at easing the exchange of data and increasing the interoperability of Belgian government services. RDF ontologies were developed to break apart the government data silos and stimulate data reuse. However, ontology design still encounters a number of difficulties. Since domain experts are generally unfamiliar with RDF, a design process is needed that allows these experts to efficiently contribute to intermediate ontology prototypes. We designed the OSLO2 ontologies using UML, a modeling language well known within the government, as a single source specification. From this source, the ontology and other relevant documents are generated. This paper describes the conversion tooling and the pragmatic approaches that were taken into account in its design. While this tooling is somewhat focused on the design principles used in the OSLO2 project, it can serve as the basis for a generic conversion tool. All source code and documentation are available online.
@inproceedings{depaepe_eswc_demo_2017,
author = {De Paepe, Dieter and Thijs, Geert and Verborgh, Ruben and Mannens, Erik and Buyle, Raf},
title = {Automated {UML}-Based Ontology Generation in {OSLO²}},
booktitle = {Proceedings of the 14th ESWC: Posters and Demos},
editor = {Blomqvist, Eva and Hose, Katja and Paulheim, Heiko and {\L}awrynowicz, Agnieszka and Ciravegna, Fabio and Hartig, Olaf},
series = {Lecture Notes in Computer Science},
volume = 10577,
publisher = {Springer},
pages = {93--97},
isbn = {978-3-319-70407-4},
year = 2017,
month = may,
doi = {10.1007/978-3-319-70407-4_18},
url = {https://doi.org/10.1007/978-3-319-70407-4_18}
}
Geodata interoperability and harmonization in transport: a case study of open transport net
Open Geospatial Data, Software and Standards - 2017
Abstract: In Europe, a lot of data portals are emerging on the local, national or interregional levels. These portals have a common objective to share data and information to its citizens and businesses, and to make information more accessible. However, studies showed that people are still facing difficulties in finding and reusing public sector information. To facilitate data reuse, the information should be available in a machine-readable format and agreed metadata standard, so that interoperability and discoverability could be enhanced.
@article{Veeckman2017,
author = "Veeckman, Carina and Jedli{\v{c}}ka, Karel and De Paepe, Dieter and Kozhukh, Dmitrii and Kafka, {\v{S}}t{\v{e}}p{\'a}n and Colpaert, Pieter and {\v{C}}erba, Otakar",
title = "Geodata interoperability and harmonization in transport: a case study of open transport net",
journal = "Open Geospatial Data, Software and Standards",
year = "2017",
volume = "2",
number = "1",
pages = "3",
issn = "2363-7501",
doi = "10.1186/s40965-017-0015-6",
url = "http://dx.doi.org/10.1186/s40965-017-0015-6"
}
The Public Sector DNA on the web: semantically marking up government portals
Proceedings of the Workshop on Smart Descriptions & Smarter Vocabularies - 2016
Abstract: Base registries contain core public sector data. They are fundamental building blocks in supporting interaction between government and private sector. To enable the private sector to discover, adopt and use information from base registries (e.g. addresses of organizations and public services), the government needs a distribution model. Therefore, the Flemish government is working on a technical strategy to add markup to government portals to embed their ‘DNA’, semantic annotations, on third-party private sector platforms, to dissolve the existing governmental silos and to provide better public services. In this context, this paper reviews a potential strategy to ‘open up’ base registries that combines the best of both worlds: bridging between the schema.org and the European ISA Core vocabularies.
@inproceedings{buyle_sdsvoc_2016,
author = {Buyle, Raf and De Vocht, Laurens and De Paepe, Dieter and Van Compernolle, Mathias and Nolf, Geraldine and Vanlishout, Ziggy and De Vidts, Bj\"orn and Mannens, Erik and Mechant, Peter},
title = {The Public Sector {DNA} on the web: semantically marking up government portals},
booktitle = {Proceedings of the Workshop on Smart Descriptions \& Smarter Vocabularies},
year = 2016,
month = nov,
url = {https://www.w3.org/2016/11/sdsvoc/SDSVoc16_paper_1},
}
OSLO - Open Standards for Linked Organisations
Proceedings of the International Conference on Electronic Governance and Open Society: Challenges in Eurasia - 2016
Abstract: Each government level uses their own different information system. At the same time citizens expect a user-centric approach and instant access to their data or to open government data. Therefore the applications at various government levels need to be interoperable in support of the ‘once only-principle’: data is inputted and registered only once and then reused. Given government budget constraints and it being an expensive and no trivial task to (re)model, translate and transform data over and over, public administrations need to reduce interoperability costs. This is achieved by semantically aligning the information between the different information systems of each government level. Semantically interoperable systems facilitate citizen-centered e-government services. This paper illustrates how the OSLO program paved the way bottom-up from a broad basis of stakeholders towards a government-endorsed strategy. OSLO applied a more generic process and methodology and provide practical insights on how to overcome the encountered hurdles: political support and adoption; reaching semantic agreement. The lessons learned in the region of Flanders, Belgium can speed-up the process in other countries that face the complexity of integrating information intensive processes between different applications, administrations and government levels.
@inproceedings{buyle_egose_2016,
author = {Buyle, Raf and De Vocht, Laurens and Van Compernolle, Mathias and De Paepe, Dieter and Verborgh, Ruben and Vanlishout, Ziggy and De Vidts, Bj\"orn and Mechant, Peter and Mannens, Erik},
title = {OSLO: Open Standards for Linked Organizations},
booktitle = {Proceedings of the International Conference on Electronic Governance and Open Society: Challenges in Eurasia},
year = 2016,
month = nov,
pages = {126--134},
isbn = {978-1-4503-4859-1},
doi = {10.1145/3014087.3014096},
url = {https://dl.acm.org/authorize?N20629},
}
Rule-Based Reasoning using State Space Search
Proceedings of the 15th International Semantic Web Conference: Posters and Demos - 2016
Abstract: Semantic Web reasoners are powerful tools that allow the extraction of implicit information from RDF data. This information is reachable through the definition of ontologies and/or rules provided to the reasoner. To achieve this, various algorithms are used by different reasoners. In this paper, we explain how state space search can be applied to perform backward-chaining rule-based reasoning. State space search is an approach used in the Artificial Intelligence domain that solves problems by modeling them as a graph and searching (using diverse algorithms) for solutions within this graph. State space search offers inherent proof generation and the ability to plug in different search algorithms to determine the characteristics of the reasoner such as: speed, memory or ensuring shortest proof generation.
@inproceedings{depaepe_iswc_poster_2016,
author = {De Paepe, Dieter and Verborgh, Ruben and Mannens, Erik},
title = {Rule-Based Reasoning using State Space Search},
booktitle = {Proceedings of the 15th International Semantic Web Conference: Posters and Demos},
year = 2016,
month = oct,
series = {CEUR Workshop Proceedings},
volume = 1690,
issn = {1613-0073},
editor = {Kawamura, Takahiro and Paulheim, Heiko},
url = {http://ceur-ws.org/Vol-1690/paper55.pdf},
}
Textile and Clothing Business Labs
Proceedings of the 13th Extended Semantic Web Conference: Project Networking - 2016
Abstract: The European textile and clothing (henceforth T&C) sector is forced to heavily invest in research and development in order to fight against global competition focused on cheap, fast fashion products. Micro businesses or individuals have trouble keeping up to date with these innovations. TCBL is a Horizon 2020 funded innovation action that started in July 2015 and will run for 4 years. TCBL aims to help the European T&C industry find new business models aimed at sustainability and innovation. Local business labs will help bring people together and offer a place with access to specialized machinery. An online community will be founded and act as a cross-boundary meeting place. A knowledge repository, the Knowledge Spaces, will support people eager to learn or share knowledge, thereby stimulating innovation. Semantic interpretation of the user interactions with the Knowledge Spaces will form the basis for an analytic tool which will help anticipate user needs.
@inproceedings{depaepe_eswc_pn_2016,
author = {De Paepe, Dieter and Maschler, Tobias and Wild, Fridolin and Ferro, Erico and Marsh, Jesse and Verborgh, Ruben and Mannens, Erik and Van de Walle, Rik},
booktitle = {Proceedings of the 13th Extended Semantic Web Conference: Project Networking},
title = {Textile and Clothing Business Labs},
year = 2016,
month = jun,
url = {http://2016.eswc-conferences.org/sites/default/files/papers/EU-Project-Networking-Session/Textile%20and%20Clothing%20Business%20Labs.pdf},
}