|Title||IoT Quality Control for Data and Application Needs|
|Publication Type||Journal Article|
|Year of Publication||2017|
|Authors||Tanvi Banerjee, Amit Sheth|
|Journal||IEEE Intelligent Systems|
|Keywords||IoT, mHealth, sensor analysis, sensor data quality|
With the rapid growth of sensors and devices that communicate—that is, the Internet of Things (IoT)—smart devices have permeated every facet of modern life. These IoT devices are within our bodies, on our bodies, in the environment both inside and outside our homes, observing our behavior patterns on a day-to-day basis, and assisting in production systems and surveillance. Figure 1 highlights some of the more popular IoT applications in the world.
However, with these sensors’ ubiquity and pervasiveness comes vast amounts of data that need to be processed and analyzed to extract meaningful or actionable information from the data for recommending appropriate changes in the real world. This requires using not only semantic approaches, but also data streamlining to ensure that the decisions made are not erroneous. Moreover, due to the sheer volume of the data from these IoT devices, any errors from user entry, data corruption, data accumulation, data integration, or data processing can snowball, causing massive errors that can detrimentally affect the decision-making process. Consequently, there needs to be a clear understanding of the challenges associated with data quality and a way to evaluate and ensure that data quality is maintained for different applications.