Event under the auspices of the Ministry of Economy of Slovak Republic

Electrician forms’ evaluation using machine learning methods

Péter Holcsik
Óbuda University, Research Group of AD&TE

Miklós Tompa
Decision3 Hungary, Research Group of AD&TE


     Last modified: 2017-06-13

Abstract
Nowadays, the utility of an electrician must fill out a form for each work using their tablets. However, evaluation of these forms are limited, it is feasible only with manually interpretation of free text fields. The AD&TE Research Group's aim was to develop a new method for processing of the form field. For this, the group used random forest machine learning algorithms to analyze the forms filled in by the mechanics after power errors. The implemented method has over 90% accuracy in determining whether the form is filled after a certain type of fault (temporary short circuit). It has been proved, that in the investigated cases by using machine learning analysis workflows that require free text analysis can be radically simplified, and accelerated.

Keywords: machine learning; random forest; smart switchboard; power companies; electricians record;

 

Proceedings Indexing

Recent proceedings have been recognized by Thomson Reuters for including in Conference Proceedings Citation Index - Science (CPCI-S).

View More

Original Research Reporting

We recognize international reporting standards. Authors of reports of original research should present an accurate account of the work performed as well as an objective discussion of its significance. .

View More

Call for Papers Announcement

We call for papers that address theoretical, experimental, systems-related and power network management issues...

View More