Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing
This paper studies an advanced machine learning method, specifically few-shot classification with meta-learning, applied to distributed acoustic sensing (DAS) data. The study contributes two key aspects: (i) an investigation of different pre-processing methods for DAS data and (ii) the implementatio...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/1/49 |
| _version_ | 1797358183472168960 |
|---|---|
| author | Huynh Van Luong Nikos Deligiannis Roman Wilhelm Bernd Drapp |
| author_facet | Huynh Van Luong Nikos Deligiannis Roman Wilhelm Bernd Drapp |
| author_sort | Huynh Van Luong |
| collection | DOAJ |
| description | This paper studies an advanced machine learning method, specifically few-shot classification with meta-learning, applied to distributed acoustic sensing (DAS) data. The study contributes two key aspects: (i) an investigation of different pre-processing methods for DAS data and (ii) the implementation of a neural network model based on meta-learning to learn a representation of the processed data. In the context of urban infrastructure monitoring, we develop a few-shot classification framework that classifies query samples with only a limited number of support samples. The model consists of an embedding network trained on a meta dataset for feature extraction and is followed by a classifier for performing few-shot classification. This research thoroughly explores three types of data pre-processing, that is, decomposed phase, power spectral density, and frequency energy band, as inputs to the neural network. Experimental results show the efficient learning capabilities of the embedding model when working with various pre-processed data, offering a range of pre-processing options. Furthermore, the results demonstrate outstanding few-shot classification performance across a large number of event classes, highlighting the framework’s potential for urban infrastructure monitoring applications. |
| first_indexed | 2024-03-08T14:58:14Z |
| format | Article |
| id | doaj.art-3b9f14858153419792a7660132dd8d95 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T14:58:14Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3b9f14858153419792a7660132dd8d952024-01-10T15:08:20ZengMDPI AGSensors1424-82202023-12-012414910.3390/s24010049Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic SensingHuynh Van Luong0Nikos Deligiannis1Roman Wilhelm2Bernd Drapp3AP Sensing GmbH, Herrenberger Str. 130, 71034 Böblingen, GermanyDepartment of Electronics and Informatics, Vrije Universiteit Brussel, Pleinlaan 2, B-1050 Brussels, BelgiumAP Sensing GmbH, Herrenberger Str. 130, 71034 Böblingen, GermanyAP Sensing GmbH, Herrenberger Str. 130, 71034 Böblingen, GermanyThis paper studies an advanced machine learning method, specifically few-shot classification with meta-learning, applied to distributed acoustic sensing (DAS) data. The study contributes two key aspects: (i) an investigation of different pre-processing methods for DAS data and (ii) the implementation of a neural network model based on meta-learning to learn a representation of the processed data. In the context of urban infrastructure monitoring, we develop a few-shot classification framework that classifies query samples with only a limited number of support samples. The model consists of an embedding network trained on a meta dataset for feature extraction and is followed by a classifier for performing few-shot classification. This research thoroughly explores three types of data pre-processing, that is, decomposed phase, power spectral density, and frequency energy band, as inputs to the neural network. Experimental results show the efficient learning capabilities of the embedding model when working with various pre-processed data, offering a range of pre-processing options. Furthermore, the results demonstrate outstanding few-shot classification performance across a large number of event classes, highlighting the framework’s potential for urban infrastructure monitoring applications.https://www.mdpi.com/1424-8220/24/1/49meta-learningfew-shot classificationdistributed acoustic sensingartificial intelligenceneural networks |
| spellingShingle | Huynh Van Luong Nikos Deligiannis Roman Wilhelm Bernd Drapp Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing Sensors meta-learning few-shot classification distributed acoustic sensing artificial intelligence neural networks |
| title | Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing |
| title_full | Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing |
| title_fullStr | Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing |
| title_full_unstemmed | Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing |
| title_short | Few-Shot Classification with Meta-Learning for Urban Infrastructure Monitoring Using Distributed Acoustic Sensing |
| title_sort | few shot classification with meta learning for urban infrastructure monitoring using distributed acoustic sensing |
| topic | meta-learning few-shot classification distributed acoustic sensing artificial intelligence neural networks |
| url | https://www.mdpi.com/1424-8220/24/1/49 |
| work_keys_str_mv | AT huynhvanluong fewshotclassificationwithmetalearningforurbaninfrastructuremonitoringusingdistributedacousticsensing AT nikosdeligiannis fewshotclassificationwithmetalearningforurbaninfrastructuremonitoringusingdistributedacousticsensing AT romanwilhelm fewshotclassificationwithmetalearningforurbaninfrastructuremonitoringusingdistributedacousticsensing AT bernddrapp fewshotclassificationwithmetalearningforurbaninfrastructuremonitoringusingdistributedacousticsensing |