EdgeMLOps: Operationalizing ML models with Cumulocity IoT and thin-edge.io for Visual quality Inspection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913668546953216 |
|---|---|
| author | Chaturvedi, Kanishk Gasthuber, Johannes Abdelaal, Mohamed |
| author_facet | Chaturvedi, Kanishk Gasthuber, Johannes Abdelaal, Mohamed |
| contents | This paper introduces EdgeMLOps, a framework leveraging Cumulocity IoT and thin-edge.io for deploying and managing machine learning models on resource-constrained edge devices. We address the challenges of model optimization, deployment, and lifecycle management in edge environments. The framework's efficacy is demonstrated through a visual quality inspection (VQI) use case where images of assets are processed on edge devices, enabling real-time condition updates within an asset management system. Furthermore, we evaluate the performance benefits of different quantization methods, specifically static and dynamic signed-int8, on a Raspberry Pi 4, demonstrating significant inference time reductions compared to FP32 precision. Our results highlight the potential of EdgeMLOps to enable efficient and scalable AI deployments at the edge for industrial applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_17062 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EdgeMLOps: Operationalizing ML models with Cumulocity IoT and thin-edge.io for Visual quality Inspection Chaturvedi, Kanishk Gasthuber, Johannes Abdelaal, Mohamed Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition This paper introduces EdgeMLOps, a framework leveraging Cumulocity IoT and thin-edge.io for deploying and managing machine learning models on resource-constrained edge devices. We address the challenges of model optimization, deployment, and lifecycle management in edge environments. The framework's efficacy is demonstrated through a visual quality inspection (VQI) use case where images of assets are processed on edge devices, enabling real-time condition updates within an asset management system. Furthermore, we evaluate the performance benefits of different quantization methods, specifically static and dynamic signed-int8, on a Raspberry Pi 4, demonstrating significant inference time reductions compared to FP32 precision. Our results highlight the potential of EdgeMLOps to enable efficient and scalable AI deployments at the edge for industrial applications. |
| title | EdgeMLOps: Operationalizing ML models with Cumulocity IoT and thin-edge.io for Visual quality Inspection |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2501.17062 |