End-to-End Data Quality Assessment Using Trust for Data Shared IoT Deployments

Continued development of communication technologies has led to widespread Internet-of-Things (IoT) integration into various domains, including health, manufacturing, automotive, and precision agriculture. This further the increased sharing data among such domains foster innovation. Most these IoT deployments, however, are based on heterogeneous, pervasive sensors, which can lead quality issues in recorded data. inaccurate or inconsistent There is a significant need assess collected data, should it be shared with multiple application as inconsistencies could have financial health ramifications. article builds recent research trust metrics presents framework integrate cycle for real-time assessment. Critically, this adopts mechanism facilitate end-user parameterization metric tailoring its use framework. Trust well-established that been used determine validity piece source crowd-sourced other unreliable collection techniques IoT. The discusses how trust-based eliminates requirement gold standard provides visibility assessment throughout big model. To qualify measure quality, an experiment conducted using from deployment sensors air low-cost were colocated reference sensor. calculated compared two well-understood root mean square error (RMSE), absolute (MAE). A strong correlation between comparison shows may indicative quality. incorporates additional benefit ability low context scenarios, opposed RMSE MAE, require comparison.