Detection and Classification of Noisy Nonstationary Signals by Methods of Machine Learning

Student: Vdovin Nikolay

Faculty: HSE Tikhonov Moscow Institute of Electronics and Mathematics (MIEM HSE)

Educational Programme: Applied Mathematics (Bachelor)

Year of Graduation: 2017

The possibility of event recognition using signals from a phase-sensitive optical reflectometer was investigated. The aim of the work was the development of a method for event recognizing by signals from a reflectometer using the classification algorithm Random Forest. In the course of the work, a method for features extracting based on a discrete Fourier transform was developed. The proposed method showed its effectiveness in comparison with other methods. As a result, it was possible to achieve recognition accuracy of more than 90% in 6 types of events.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses