Researchers in this study tested learning-based sensor scheduling for event classification on embedded edge devices.
In this paper, researchers propose a reinforcement learning-based sensor scheduler that dynamically determines the sensing interval for each classification moment by learning the patterns of event classes. The initial results are promising compared to the existing scheduling approach. Incremental learning on embedded edge devices is feasible nowadays due to the increasing computational power of these devices and the reduction techniques applied to simplify the model. However, edge devices still require significant time to update the learning model and such time is hard to obtain due to other tasks, such as sensor data pulling, data preprocessing, and classification. In order to secure the time for incremental learning and to reduce energy consumption, researchers need to schedule sensing activities without missing any events in the environment. (Published Abstract Provided)
Similar Publications
- Modeling local behavior for predicting social interactions towards human tracking
- A Review of the Evolution of the NCS-NCVS Police Reporting and Response Questions and Their Application to Older Women Experiencing Violent Victimization
- Life impact following childhood Image-Based Sexual Abuse victimization among a sample of young adults