Design of Data Reduction Approach for AIoT on Embedded Edge Node
Kuei‐Chung Chang, Ming-Han Chiang · 2019
In recent years, the Internet-of-Things and AI technologies have promoted the rapid development of intelligent applications. However, due to the large increase in the number of devices connected to the Internet, the amount of data transmitted at the same time is very large for data collection. Also, the database and storage requirements are also important challenges. In order to mitigate the above problems, the paper proposes a data reduction mechanism for transmitting sensor data under the condition of less data transmission and low storage requirement for further deep-learning applications. We deploy the proposed architecture in a cooperated precision machinery factory in Taichung to collect sensor data. Experimental results show that the amount of collected data can be reduced significantly as well as keep the same features for further training of AI applications.