Advanced feature engineering and dimensionality reduction for structural connectome classification

Student: Petrov Dmitry

Supervisor: Leonid E Zhukov

Educational Programme: Data Science (Master)

Final Grade: 9

Year of Graduation: 2016

In this work we investigated Autism Spectrum Disorder vs Typically Developing classification task based on structural connectomes. Using combination of different weighting schemes, topological normalizations and graph metrics we constructed about 500 feature sets and tested them using selected classifiers and cross-validation techniques. We found features obtained with combination of weighting by distance and topolgical normalization which achieved 0.8 ROC AUC score. It is comparable with results described in recent studies. We also tried dimensionality reduction on the best obtained features, but didn't find simple geometry in our data.

Full text (added June 4, 2016)

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