Improve Research Reproducibility A Bio-protocol resource
Concise Method
tooltip

3.4. Dataset Preparation

TP Tanmoy Sarkar Pias
DE David Eisenberg
JF Jorge Fresneda Fernandez
ask Ask a question
Favorite

Each class data are concatenated to make a complete set of all classes. Thus, now the full dataset dimension is (10,800, 100, 6), where 10,800 = 2700 × 4.

Labels are created for each class, where car = 0, rail = 1, bus = 2, and bike = 3. In addition, one hot encoding is used, as they are similar to categorical classes. For example, the bus class will be represented as [0, 1, 0, 0].

Now, this dataset is divided into the train set (70%) and the test set (30%) randomly. The train set dimension is (7560, 100, 6), and the test set dimension is (3240, 100, 6).

Copyright and License information:  ©2022 by the authors.
Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).

Do you have any questions about this protocol?

Post your question to gather feedback from the community. We will also invite the authors of this article to respond.

post Post a Question
0 Q&A