Poster Abstract: Learning-based Sensor Scheduling for Event Classification on Embedded Edge Devices
Poster Abstract: Learning-based Sensor Scheduling for Event Classification on Embedded Edge Devices
复制标题
海报摘要：嵌入式边缘设备上基于学习的事件分类传感器调度
DOI：
10.1145/3576842.3589176
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Kim, Hyoseung
中科院分区：
文献类型：
--
作者：
Bukhari, Abdulrahman;Kim, Hyoseung
由于嵌入式边缘设备的计算能力不断增强以及用于简化模型的简化技术，如今嵌入式边缘设备上的增量学习是可行的。然而，边缘设备仍然需要大量时间来更新学习模型，并且由于传感器数据拉取、数据预处理和分类等其他任务而很难获得这样的时间。为了确保增量学习的时间并减少能源消耗，我们需要在不遗漏环境中任何事件的情况下安排传感活动。在本文中，我们提出了一种基于强化学习的传感器调度器，它通过学习事件类别的模式来动态确定每个分类时刻的感测间隔。与现有的调度方法相比，初步结果是有希望的。
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 be obtained 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, we need to schedule sensing activities without missing any events in the environment. In this paper, we 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.
DOI：
10.1109/rtcsa55878.2022.00013
发表时间：
2022-08
期刊：
2022 IEEE 28th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)
影响因子：
--
作者：
Abdulrahman Bukhari;Seyedmehdi Hosseinimotlagh;Hyoseung Kim
通讯作者：
Abdulrahman Bukhari;Seyedmehdi Hosseinimotlagh;Hyoseung Kim