Getting Started v2 - RodentDataAnalytics/mwm-ml-gen GitHub Wiki
This section provides an overview of the mwm-ml-gen functionalities. For in-depth explanations please choose your topic from the sidebar on the right.
Contents
The Main Graphical User Interface (GUI)
Run with MATLAB:
Type gui in the command line.
Paths and Files Format:
In this panel the user specifies the input folder containing his data, the output folder in which the generated results, figures and objects will be saved and the specific format of his data.
Note: as default output folder the folder ./cache is used. This folder is automatically created on the software's home folder upon the first run of the program.
Experiment Settings:
In this panel the user specifies the experimental setup of his data, how many sessions are available and how many days they are containing and how many trials were performed each day.
Experiment Properties:
In this panel the user specifies the setup of his experiment, such as the dimensions of the arena and the platform as well as their location in place.
Save & Load Settings:
The user can save or load the above settings to or from a .MAT file.
Segmentation:
The segmentation panel requires input of the panels described above as well as the setup of the segmentation process. During this process the user's data are loaded, processed and the resulted trajectories are then slitted into segments.
Labelling and Classification:
Following the segmentation panel the labelling & classification panel requires as an input the labels data and the output of the segmentation process in order to classify all the trajectories segments.
Results:
The results panel contains buttons which present the results and generate figures similar to the ones shown in the publication.
The Browse Trajectories GUI
This GUI is used as a tool to help the user to provide labels for the trajectories segments.
Upon loaded, either from the Main GUI (button: Browse Trajectories) or by the command line (command: browse_trajectories), this tool can be used to visualize the trajectories and their segments as well as to indicate various info and statistics such as animal average speed, animal latency, features values, segments length, etc.
With the visualization of each segment the user is given the ability to provide accurate labels and save his labelling work in order to use it latter for the classification process.