Abstract: Sensor networks have become an important source of data with numerous applications in monitoring various real-life phenomena as well as industrial applications and traffic control. Sensor data is subject to several sources of errors as the data captured from the physical world through these sensor devices tend to be incomplete, noisy, and unreliable. Such errors may seriously impact the answer to any query posed to the sensors yielding imprecise or even incorrect and misleading answers for critical decisions or activation of actuators. Play, thus, a fundamental role data cleaning procedures to overcome these problems. The most recent applications in this research field conceive the use of machine learning techniques. Machine learning approaches have assumed a prominent role in data analysis especially for their ability to deal with very large amount of noisy and incomplete data. In this paper, we propose the application of the well known ANFIS model for reducing the uncertainty associated with the data thus obtaining a more accurate estimate of sensor readings. The obtained cleaning results demonstrate its effectiveness if the cleaning model has to be implemented at sensor level rather than at base-station level.
