A statistical approach to time series sensor data evaluation using Apache Spark modules

The most important driving force in today's industry is fast and efficient data processing and evaluation. To this end, it is important for the industry to pay attention and resources to real-time analysis of the large amount of data collected, so that valuable information can be used to detect outliers in a timely manner, false data, or predictions to prevent unexpected costs. This data analysis requires the usage of a variety of algorithms appropriate to the purpose, with a very wide range of possibilities. To provide fast data analysis that can be used in the industry, in this paper we show how statistical analysis of time series data can be performed using the capabilities of the Apache Spark unified engine.