Issue link: https://resources.mouser.com/i/1499313
6 BRINGING INTELLIGENCE TO THE EDGE Data engineering depends on the device configuration and how the data are stored. To ensure the success and accuracy of an ML project, proper data engineering is essential and IoT applications are no exception. This includes understanding the data format, quality, and type, as well as how the data might be cleaned (e.g., granting access for initial data exploration and deploying processes that transform the data to be usable). Data engineering is typically performed by data engineers who require access to the data they need to work with; in cases where access is not permissible due to device location, lack of connectivity, or privacy concerns, the feasibility of project success may decrease. Conclusion When deciding whether to introduce AI to IoT endpoints, design engineers must take a variety of considerations into account. From assessing the expected value of the AI versus the cost and impact on device performance, to evaluating the feasibility of the ML lifecycle within the existing constraints, and finally to understanding the data requirements and what data engineering might be needed, engineers should carefully consider each element of the decision. With the right approach and research, design engineers can make an informed decision that incorporates the costs and benefits of introducing AI to an IoT device, helping to ensure the success of the project. ■ Learn More Renesas MCU Family The impact of these constraints often extends beyond the initial data annotation and model training phases of the ML lifecycle. Model performance monitoring and updates are key, requiring retraining on new data if performance has declined as well as connectivity to push new deployments to devices. Engineers should consider monitoring in terms of the model and the data: Assessing feasibility includes determining whether data drift between the training data and new points being measured can be captured. For example, monitoring is more difficult for endpoints where data are stored only for a short period of time, which may impact the final decision about whether to introduce ML to the process. Addressing the Age-Old Question of Data Regardless of the final application, when deciding whether to embark on an ML project, one of the most common questions is whether enough data exist. This goes hand in hand with labeling requirements—for example, whether the task requires annotated data for a supervised training approach and whether the data are currently in the required state. Within the IoT context, if the data cannot be pooled in the cloud, design engineers must determine whether enough data exist per device for the task at hand and if they need to be labeled. Data quality is essential for successful ML projects, so engineers should also evaluate the ability to manage noise and the heterogeneity of sensor data to an acceptable standard.