| Autor: |
González-Pérez, María I., Faulhaber, Bastian, Williams, Mark, Brosa, Josep, Aranda, Carles, Pujol, Nuria, Verdún, Marta, Villalonga, Pancraç, Encarnação, Joao, Busquets, Núria, Talavera, Sandra |
| Rok vydání: |
2022 |
| DOI: |
10.6084/m9.figshare.20012405 |
| Popis: |
Additional file 1: Text S1. Mel spectrogram and MFCC generation process. Figure S1. Diagram to illustrate MFCC generation. Figure S2. Histogram plots showing the distributions of fundamental frequency (top) and fundamental peak power (bottom) for a Genus, b Aedes sex and c Culex sex. Text S2. Description of the machine learning algorithms used in this work. Figure S3. Representation of the machine learning classifications (in bold text), with their respective classes immediately below and indicated by the arrow heads. Figure S4. Schematic overview of the training, validation and testing approach. 1 Dataset is randomly separated into training and test sets, accounting for 75% and 25% of the whole dataset respectively. 2 Training set is separated using fourfold cross-validation into four folds with an equal number of samples in each fold. 3 Four iterations of training and validation take place using a different fold for validation in each iteration. 4 Model with best average validation score, obtained by averaging the four cross-validation results, is selected. 5 Model is evaluated using test set (containing data which was previously unused) to obtain test score. Table S1. Hyperparameters of the trained models which achieved the highest accuracies. |
| Databáze: |
OpenAIRE |
| Externí odkaz: |
|
