• Nebyly nalezeny žádné výsledky

Thesis reviewer’s report Thesis title:

N/A
N/A
Protected

Academic year: 2022

Podíl "Thesis reviewer’s report Thesis title:"

Copied!
1
0
0

Načítání.... (zobrazit plný text nyní)

Fulltext

(1)

Thesis reviewer’s report

Thesis title: Handling Quality Analysis and Evaluation Using Machine Learning Thesis author: Leonid Tulin

Goal of the thesis has been to lay out foundations for systematic evaluation of driver experience during vehicle maneuvers. The guidelines for the thesis break it down to four tasks. This report follows the same structure rating each of the tasks individually first and then making an overall conclusion.

The first three tasks define a methodology for the driver experience evaluation:

• Task nr.1: familiarize with criteria for evaluation of human-machine interfaces. This task is only partially completed. It is documented so briefly and at such a generic level that only limited relevance to the rest of the work can be found.

• Task nr.2: prepare experiments and collect data. This task is completed to a larger degree. It is hard to quantify the completion level more precisely due to gaps in the documentation.

• Task nr.3: propose machine learning methods for task of classification (sic). One should ask classification of what. Unfortunately, the thesis does not address the ambiguity of this task either. In total, only two to three paragraphs deal with the classification topic.

The last task is to test the methodology in a simulator. This is the best documented task and it is clearly demonstrated that a number of experiments was conducted on third party simulators provided to Mr. Tulin.

The extent of the work done seems legitimate even though not overly complex or comprehensive. Preparation of methodology is set as a goal for the thesis in its Guidelines, however, I could not find any methodology in the report. I would rate the assignment fulfillment and technical level with C.

The report structure, contents and language are all far from ideal. I consider the report barely acceptable, i.e.

rate it E.

Overall I recommend to rate the thesis with D.

Ondrej Holub

PECZ-ESC Team Leader

Porsche Engineering Services, spol. s.r.o.

Radlicka 714/113a

158 00 Praha 5, Czech Republic

E-Mail ondrej.holub@porsche-engineering.cz

Odkazy

Související dokumenty

In my opinion, this limit should be based on the long time deterioration of the barrel joints in reverse load conditions (permissible limit state, Melbourne et al., Bridge

Student approached to the whole work very seriously, he regularly consulted the results of his work, which he synoptically summarized and evaluated. The main

Master’s thesis details Master’s thesis title in English: Two-Level Energy Management Strategy for Hybrid Electric Vehicle Using Planned-Trip Information Master’s thesis title in

Master’s thesis review / Posudek oponenta Author of the reviewed thesis: ​ Varun Burde Thesis title: ​Deep neural network for city mapping using Google Street View data.. The aim of

The goal of the thesis was to review different indoor localisation techniques and select two of them for implementation, tests and fusion. The thesis has quite detailed state of

The goal of this thesis is to apply different portfolio optimization strategies and to compare their out-of-sample results.. For the propose of this thesis, the author used weekly

This thesis provides originally Bayesian analysis of some sophisticated models with three or more parameters which result from mixture failure rate.. The models under analysing

The goal of the thesis is to: ”…analyse diversity management tools of existing multinational company in Prague.” The thesis has a logical structure.. Individual parts are