Results v2 - RodentDataAnalytics/mwm-ml-gen GitHub Wiki
The Results panel contains a series of buttons for the visualization of various results such as animal metrics and animal strategies.
- Demo
- Metrics
- Strategies
- Transitions
- Confusion Matrix
- Trans Probabilities
- Manually Exclude Animals for Groups Equalizing
This button is use to generate the published results. In the publication three different setups have been used and relevant information can be found on Table 2, page 6. By pressing this button a dialog box pops-up asking which of the three setups the program will use to generate the respective results.
Important note: The setup 3 will generate figures very close to the ones shown in the paper but not exactly the same. The reason for this is because the final figures were produced by the combination of the three classification setups. This dissimilarity creates only quantitative differences and the conclusions remain qualitatively the same.
Generates three figures showing the (a) the escape latency; (b) the average movement speed and (c) the average path length of the animals over the trials for one or two animal groups. Requires a Segmentation Configurations object and in case this object has more than one animal groups the user is asked to specify which one or two groups he wishes to plot. If two groups are given then the white lines will refer to the group 1 and the black lines to the group 2. Moreover, in this case, the p-values of the Friedman test will be computed.
In case the user specifies two animal groups with uneven number of animals then he needs to select and exclude animals either from group A or group B to equalize them. For more information refer to section 7. Manually Exclude Animals to Equalize Groups.
Example:
Friedman p-value (latency [s]): 0.154238
Friedman p-value (speed [cm/s]): 1.9846e-08
Friedman p-value (path length [m]): 0.00171107
Generates eight figures showing the average segment lengths for each strategy adopted by the animals. Requires a Segmentation Configurations object and a Classification Configurations object and in case these objects have more than one animal groups the user is asked to specify which one or two groups he wishes to plot. If two groups are given then the white lines will refer to the group 1 and the black lines to the group 2. Moreover, in this case, the p-values of the Friedman test will be computed.
In case the user specifies two animal groups with uneven number of animals then he needs to select and exclude animals either from group A or group B to equalize them. For more information refer to section 7. Manually Exclude Animals to Equalize Groups.
Example:
Class: thigmotaxis p_frdm: 0.0138572
Class: incursion p_frdm: 0.00232876
Class: scanning p_frdm: 0.030009
Class: focused search p_frdm: 0.289729
Class: chaining response p_frdm: 0.0413942
Class: self orienting p_frdm: 0.757259
Class: scanning surroundings p_frdm: 0.169372
Class: target scanning p_frdm: 0.29054
Generates a figure showing the number of transitions between strategies adopted by the animals. Requires a Segmentation Configurations object and a Classification Configurations object and in case these objects have more than one animal groups the user is asked to specify which one or two groups he wishes to plot. If two groups are given then the white lines will refer to the group 1 and the black lines to the group 2. Moreover, in this case, the p-values of the Friedman test will be computed.
Example:
p_frdm: 0.0471534
Calculates the confusion matrix for the classification of the segments. Values are the total number of miss-classifications for a 10-fold cross validation of the clustering algorithm. Values in the diagonal show the number of correct classification for this class. This matrix can be used to identify classes that are not well separated in the classification process (non-diagonal values different than zero). Requires a Segmentation Configurations object and a Classification Configurations object.
Example:
Calculates the transition probabilities of strategies adopted by the animals within trials. Requires a Segmentation Configurations object and a Classification Configurations object and in case these objects have more than one animal groups the user is asked to specify which one or two groups he wishes to plot. If two groups are given then two matrices, one for each group, will be generated.
Example:
1. Information on how many animals exist in each of the two specified groups and how many animals need to be removed from one of them in order for both groups to have the same number of animals.
2. The left listbox lists all the animal ids of the group with the larger number of animals. Each of these ids can be selected and moved to the right listbox which will contain the excluded animals. The buttons => and <= are used to move the animal ids between the two listboxes. If the button => is greyed then no more animals may be excluded as the two groups are now having the same number of animals. If <= is greyed then the right listbox does not have any animal ids.
3. In order to ease the exclusion process four sort buttons are placed which sort the animal ids by animal speed (Sort by Speed), animal path length (Sort by Path Length), animal latency (Sort by Latency) and animal id value (Sort by Value). The animals are always sorted in ascending order.
4. After the appropriate number of animal ids has been reached the OK button will become clickable and pressing it would resume the program's result process. Clicking the Cancel button would lead back to the Main GUI.
Note: The Segmentation Configurations object and the Classification Configurations object are automatically selected from the Segmentation Configurations Object Path and the Classification Configurations Object Path respectively. If the user wishes to use other objects he needs to change these two paths.