Research Article
Automated Workflow Formation for IoT Analytics: A Case Study
@INPROCEEDINGS{10.1007/978-3-319-47075-7_5, author={Tanushyam Chattopadhyay and Avik Ghose and Arijit Mukherjee and Santa Maiti and Arpan Pal}, title={Automated Workflow Formation for IoT Analytics: A Case Study}, proceedings={Internet of Things. IoT Infrastructures. Second International Summit, IoT 360° 2015, Rome, Italy, October 27-29, 2015, Revised Selected Papers, Part II}, proceedings_a={IOT360}, year={2017}, month={6}, keywords={Model driven development IoT analytics Automated work flow creation}, doi={10.1007/978-3-319-47075-7_5} }- Tanushyam Chattopadhyay
Avik Ghose
Arijit Mukherjee
Santa Maiti
Arpan Pal
Year: 2017
Automated Workflow Formation for IoT Analytics: A Case Study
IOT360
Springer
DOI: 10.1007/978-3-319-47075-7_5
Abstract
The rapid deployment of sensors across the world in various sectors has fuelled a growing demand of smart applications and services that can leverage this boom of Internet of Things (IoT). However, developing analytical applications for IoT is a difficult process as applications tend to be cross-domain and there are close relationships with the physical world. It is unreasonable to imagine that the application developers will possess all relevant skills and knowledge related to the domain, physical world, signal processing and deployment infrastructure. This paper presents an method that assists the IoT application developer by (i) providing an annotated repository of algorithms, (ii) recommending algorithms depending on the signal type to reduce the effort required from a signal processing expert, and (iii) providing a framework to execute the IoT application thereby reducing the development cost and time by capturing the knowledge of experts in models. We have evaluated our method by comparing the accuracy for a typical IoT application obtained by using the algorithms used by signal processing experts against the algorithms recommended by our method.