Adaptive edge analytics - A framework to improve performance and prognostics capabilities for dairy IoT sensor
Intelligent Human Systems Integration: Proceedings of the 1st International Conference on Intelligent Human Systems Integration (IHSI 2018): Integrating People and Intelligent Systems, January 7-9, 2018, Dubai, United Arab Emirates
Waldemar Karwowski, Tareq Ahram
Edge analytics is an approach to data collection and analysis in which an automated analytical computation is performed on data at a sensor, network switch or other devices instead of waiting for the data to be sent back to a centralized data store. The data collection merits for normal edge operations but limits for the handling of anomaly events and prediction of prognostics conditions. In this paper, we propose an innovative machine learning edge approach that extends Kalman filter for anomaly detection so as to (a) allow the edge to adaptively collect granular data when abnormal or anomaly data markers witnessed for prognostics and (b) relaxes the data collection frequency for normal device operation cycles. In summary, the adaptive edge analytics fine-tunes the data collection and analysis so that overall health and longevity of the device can be improved. The paper presents prototyping dairy IoT sensor solution design as well as its application and certain experimental results.
Adaptive edge, Bluetooth, Dairy IoT sensor, Decision tree, Edge analytics, Embedded device, Hanumayamma dairy IoT sensor, Humidity sensors, Internet of things (IoT), Kalman filter, Machine learning, OSA-CBM, Regression analysis
Santosh Kedari, Jaya Shankar Vuppalapati, Anitha Ialapakurti, Sharat Kedari, Rajasekar Vuppalapati, and Chandrasekar Vuppalapati. "Adaptive edge analytics - A framework to improve performance and prognostics capabilities for dairy IoT sensor" Intelligent Human Systems Integration: Proceedings of the 1st International Conference on Intelligent Human Systems Integration (IHSI 2018): Integrating People and Intelligent Systems, January 7-9, 2018, Dubai, United Arab Emirates (2018): 639-645. https://doi.org/10.1007/978-3-319-73888-8_99