Machine learning applications in Gravitational Wave research to classify transient signals

<!--HTML--><p><span><span><span>Most of the data collected by Gravitational Wave (GW) interferometers are&nbsp;essentially background noise containing many noise transient signals, which has&nbsp;to be analyzed in a fast and efficient way to increase the detection confidence&nbsp;and to obtain information about likely noise sources.</span></span></span></p> <p><span><span><span>Characterizing the noise transient signals (glitches) is an important task to&nbsp;reduce the impact of transient noise on the detectors. Inspecting glitches&nbsp;manually is a time-consuming and error-prone task and the increase of&nbsp;sensitivity in advanced detectors will lead to more classes of glitches. The use&nbsp;of machine learning looks a promising way to tackle the classification of&nbsp;glitches. </span></span></span></p> <p><span><span><span>We present classification strategy based on image or time-series data set.</span></span></span></p>