Data quality enhancement in Internet of Things environment

The Internet of Things (IoT) is the first real evolution of the Internet, in contrast with the Web which has been evolving over time. IoT enables the crossing-over of the physical and cyber worlds by deploying sensor devices on a global scale. This crossing-over promises exciting applications that, thanks to intelligent ubiquitous services, will facilitate our daily life. However, the data that represent the bridge between the real and the digital worlds are endangered and their quality is uncertain. In fact, data are the base of insights mining which are used to make intelligent decisions and provide services. If the data are inaccurate, decisions are likely to be unsound. Data accuracy and trustworthiness are crucial to gain user engagement and acceptance of the IoT paradigm and services. This paper aims at enhancing data quality in the context of the Internet of Things by providing an overview of the state of the art of data quality in the context of IoT. Data outliers and their underlying knowledge are surveyed alongside their discovery and detection process. The outliers´ impact in the context of IoT and its applications is identified. Techniques for data cleaning are reviewed and compared with respect to an extended taxonomy. Finally, open challenges and possible future research directions are discussed.