BLAŠKOVÁ, B. Developing Brain Computer Interface for Imagined Movements [online]. Brno: Vysoké učení technické v Brně. Fakulta informačních technologií. 2023.
The student has done an excellnt work and developed an algorithm using microstates for classification of the BCI signals. The proposed algorithm combines microstates with the traditional method of frequency domain analysis and the proposed method significantly increases the accuracy, sensitivity and specificity.
| Kritérium | Známka | Body | Slovní hodnocení |
|---|---|---|---|
| Informace k zadání | The thesis was related to Brain Computer Interface. The student developed an algorithm for assessment of brain EEG signals to detect the intention of right and left direction. Thorough investigation of microstates in Brain Computer Interfaces (BCI) have not been reported. The student embarked on this task and analyzed the microstates for the BCI. A new algorithm is developed for this analysis. The results are promising and the thesis met all the requirements. | ||
| Práce s literaturou | The student engaged in thorough literature review and chapters 2 and 3 show the details of the literature review. A detailed analysis of existing methods is provided and the gaps are identified. During the literature review, it was found that microstate analysis have not been investigated in detail and this led to the proposal of incorporating microstate analysis for the proposed algorithm. | ||
| Aktivita během řešení, konzultace, komunikace | The student had a very positive attitude and started working on the topic in the summer of 2022. I had weekly meetings with the student and she regularly came for the meetings. She was very active and worked very hard and with dedication. She came well prepared for the meetings. | ||
| Aktivita při dokončování | The work turned out to be challenging and required extra time from the student. She willingly gave the extra time for completing the project. As a result, she successfully developed the algorithm based on microstates for the analysis of BCI signals. | ||
| Publikační činnost, ocenění | The work is sufficient to be published in high impact factor journal. The student is willing to prepare the draft for the journal paper. |
It is a very nice work based on state-of-the-art techniques for neuroimaging analysis using signal processing and machine learning, which leads to the originality of the thesis. The work demonstrates the author's deep interest in the problem and the ability to analytical thinking. Except for minor shortcomings like small errors in English, the work is very well executed in terms of structure and language. The work with literature is excellent, and the output can be used in further work of the CANE group. I recommend it for some of the awards at the FIT or BUT level.
| Kritérium | Známka | Body | Slovní hodnocení |
|---|---|---|---|
| Náročnost zadání | A very demanding and novel research assignment required an understanding and experimental mastery of signal processing applied to neuroimaging modalities. | ||
| Rozsah splnění požadavků zadání | The assignment was completely fulfilled, and the expected results were achieved. She did time and frequency domain analysis along with microstates, an extension to the state of the art. | ||
| Rozsah technické zprávy | The work is within the usual range and to the point. It explains and covers all the necessary points. Especially the microstate part is very well written and explained. | ||
| Prezentační úroveň technické zprávy | 90 | The thesis is well written. The presentation is good and clear. There is a coherency in all the chapters. The flow is also excellent. It's very easy to read and follow the thesis chapter-wise. | |
| Formální úprava technické zprávy | 91 | Formally, the work is very nicely executed, it is logically structured and readable. The level of the language is excellent, and the work is written in quality English with an absolute minimum of errors. The figures and table are well arranged. | |
| Práce s literaturou | 95 | The work with literature is exemplary. The student read and give a very good overview of the state of the art. Also, the sources are duly cited in the work. And the comparison summary is given in Chapter 2. | |
| Realizační výstup | 90 | The output of the work is a set of scripts using Python language libraries for machine learning and EEG modality. Above all, the results represented a number of experiments with a very interesting architecture. | |
| Využitelnost výsledků | The thesis has a strong potential use in the work of the BUT CANE group. It would also deserve publication in some reputed journal. In addition, it offers a number of expansion options for future work. |
eVSKP id 144825