Abstract
Internet of Things (IoT) applications generate vast amounts of real-time data. Temporal analysis of these data series to discover behavioural patterns may lead to qualified knowledge affecting a broad range of industries. Hence, the use of machine learning (ML) algorithms over IoT data has the potential to improve safety, economy, and performance in critical processes. However, creating ML workflows at scale is a challenging task that depends upon both production and specialized skills. Such tasks require investigation, understanding, selection, and implementation of specific ML workflows, which often lead to bottlenecks, production issues, and code management complexity and even then may not have a final desirable outcome. This paper proposes the Machine Learning Framework for IoT data (ML4IoT), which is designed to orchestrate ML workflows, particularly on large volumes of data series. The ML4IoT framework enables the implementation of several types of ML models, each one with a different workflow. These models can be easily configured and used through a simple pipeline. ML4IoT has been designed to use container-based components to enable training and deployment of various ML models in parallel. The results obtained suggest that the proposed framework can manage real-world IoT heterogeneous data by providing elasticity, robustness, and performance.
Highlights
Gartner [1], predicts that the Internet of Things (IoT) will reach 26 billion internet-connected devices by 2020, impacting a wide range of industries
WORK This study has proposed the Machine Learning Framework for IoT data (ML4IoT) to address the challenges involved in integrating Big Data enabling tools and Machine learning (ML) frameworks to provide a unified platform for executing end-to-end ML workflows on IoT data
Its main goal was to provide orchestration services for training and inference of ML models on IoT data, which enables automated execution of ML workflows on top of various big data tools and ML frameworks
Summary
Gartner [1], predicts that the Internet of Things (IoT) will reach 26 billion internet-connected devices by 2020, impacting a wide range of industries. Uber has built its ML orchestration platform called Michelangelo [12], Airbnb has Bighead [13], Netflix has developed the Meson platform [14], Google has introduced TensorFlow Extended (TFX) [15], and Facebook has implemented its data pipeline platform for generating and predicting models [16] These are all in-house proprietary platforms to make sure that their time and money are not wasted in developing repetitive ML workflows and management tools. To address the challenges of running multiple ML workflows in parallel, ML4IoT has been designed to use container-based components that provide a convenient mechanism to enable the training and deployment of numerous ML models in parallel.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
