A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project
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 th...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/24/11932 |
| _version_ | 1797506749627891712 |
|---|---|
| author | Dieter De Paepe Sander Vanden Hautte Bram Steenwinckel Pieter Moens Jasper Vaneessen Steven Vandekerckhove Bruno Volckaert Femke Ongenae Sofie Van Hoecke |
| author_facet | Dieter De Paepe Sander Vanden Hautte Bram Steenwinckel Pieter Moens Jasper Vaneessen Steven Vandekerckhove Bruno Volckaert Femke Ongenae Sofie Van Hoecke |
| author_sort | Dieter De Paepe |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T04:36:23Z |
| format | Article |
| id | doaj.art-21e47f8755144c40a18078d3d6824e44 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T04:36:23Z |
| publishDate | 2021-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-21e47f8755144c40a18078d3d6824e442023-11-23T03:40:36ZengMDPI AGApplied Sciences2076-34172021-12-0111241193210.3390/app112411932A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify ProjectDieter De Paepe0Sander Vanden Hautte1Bram Steenwinckel2Pieter Moens3Jasper Vaneessen4Steven Vandekerckhove5Bruno Volckaert6Femke Ongenae7Sofie Van Hoecke8IDLab, Ghent University—imec, 9052 Gent, BelgiumIDLab, Ghent University—imec, 9052 Gent, BelgiumIDLab, Ghent University—imec, 9052 Gent, BelgiumIDLab, Ghent University—imec, 9052 Gent, BelgiumIDLab, Ghent University—imec, 9052 Gent, BelgiumRenson Ventilation, 8790 Waregem, BelgiumIDLab, Ghent University—imec, 9052 Gent, BelgiumIDLab, Ghent University—imec, 9052 Gent, BelgiumIDLab, Ghent University—imec, 9052 Gent, BelgiumCompanies 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.https://www.mdpi.com/2076-3417/11/24/11932time seriesdata analyticsmachine learningsemantic webreasoningmicroservice architecture |
| spellingShingle | Dieter De Paepe Sander Vanden Hautte Bram Steenwinckel Pieter Moens Jasper Vaneessen Steven Vandekerckhove Bruno Volckaert Femke Ongenae Sofie Van Hoecke A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project Applied Sciences time series data analytics machine learning semantic web reasoning microservice architecture |
| title | A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project |
| title_full | A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project |
| title_fullStr | A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project |
| title_full_unstemmed | A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project |
| title_short | A Complete Software Stack for IoT Time-Series Analysis that Combines Semantics and Machine Learning—Lessons Learned from the Dyversify Project |
| title_sort | complete software stack for iot time series analysis that combines semantics and machine learning lessons learned from the dyversify project |
| topic | time series data analytics machine learning semantic web reasoning microservice architecture |
| url | https://www.mdpi.com/2076-3417/11/24/11932 |
| work_keys_str_mv | AT dieterdepaepe acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT sandervandenhautte acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT bramsteenwinckel acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT pietermoens acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT jaspervaneessen acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT stevenvandekerckhove acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT brunovolckaert acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT femkeongenae acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT sofievanhoecke acompletesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT dieterdepaepe completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT sandervandenhautte completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT bramsteenwinckel completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT pietermoens completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT jaspervaneessen completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT stevenvandekerckhove completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT brunovolckaert completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT femkeongenae completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject AT sofievanhoecke completesoftwarestackforiottimeseriesanalysisthatcombinessemanticsandmachinelearninglessonslearnedfromthedyversifyproject |