Validation of Data from Sensor Systems
Hillner, Patrik (2019)
Hillner, Patrik
Åbo Akademi University
2019
This publication is copyrighted. You may download, display and print it for Your own personal use. Commercial use is prohibited.
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2019111237809
https://urn.fi/URN:NBN:fi-fe2019111237809
Tiivistelmä
The validation of data is a crucial part of managing data in an ever-growing world of sensors and data analysis. In the implementation of Internet of Things (IoT), the weight of the amount of data is felt as the bandwidth a device has at its disposal, as well as at the cloud, where all data is gathered for processing, further analysis, or storage. To ensure that the data used for analysis and data stored is of high enough quality, the data should be validated. The validation of data also ensures that the analyses made are not based on faulty data. The goal of this thesis is to find different approaches used to validate data of different types, raw sensor data and data derived from the raw sensor data that function as a key performance index (KPI), run some tests on some methods described by authors of those approaches, and give a verdict on how they applied to different types of data.