Detection and Classification of Noisy Non-stationary Signals by Methods of Machine Learning

Student: Chesnokov German

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

Educational Programme: Applied Mathematics (Bachelor)

Final Grade: 10

Year of Graduation: 2018

This work considers the classification problem for signals obtained from a phase-sensitive optical time-domain reflectometer. Three ways of constructing a feature space were proposed. Each of the ways is based on moving from time domain to frequency domain. The quality comparison of several machine learning methods was conducted, as well as a convolutional neural network architecture for raw signals classification was suggested. The neural network achieved the maximum classification accuracy of 98.6% among all algorithms.

Full text (added May 24, 2018)

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