Architectural flow of hybrid models for data classification. by Faten Al-hussein (20707521)

Features selected by optimization algorithms. by Afnan M. Alhassan (18349378)

“…Consequently, the prediction of BrC depends critically on the quick and precise processing of imaging data. The primary reason deep learning models are used in breast cancer detection is that they can produce findings more quickly and accurately than current machine learning-based techniques. …”

Image_1_Evaluation of an Automatic Classification Algorithm Using Convolutional Neural Networks in Oncological Positron Emission Tomography.PNG by Pierre Pinochet (10201040)

Hybrid feature selection algorithm of CSCO-ROA. by Afnan M. Alhassan (18349378)

“…Consequently, the prediction of BrC depends critically on the quick and precise processing of imaging data. The primary reason deep learning models are used in breast cancer detection is that they can produce findings more quickly and accurately than current machine learning-based techniques. …”

Table_2_Compact machine learning model for the accurate prediction of first 24-hour survival of mechanically ventilated patients.XLSX by Quynh T. Nguyen (7817855)

Table_1_Compact machine learning model for the accurate prediction of first 24-hour survival of mechanically ventilated patients.XLSX by Quynh T. Nguyen (7817855)

Table_3_Compact machine learning model for the accurate prediction of first 24-hour survival of mechanically ventilated patients.XLSX by Quynh T. Nguyen (7817855)

Table_2_Compact machine learning model for the accurate prediction of first 24-hour survival of mechanically ventilated patients.XLSX by Quynh T. Nguyen (7817855)

Table_1_Compact machine learning model for the accurate prediction of first 24-hour survival of mechanically ventilated patients.XLSX by Quynh T. Nguyen (7817855)

Table_3_Compact machine learning model for the accurate prediction of first 24-hour survival of mechanically ventilated patients.XLSX by Quynh T. Nguyen (7817855)

Out-of-distribution classification performance versus diversity before and after matching. by Oualid Benkarim (9707986)

Participant diversity is a major determinant for the classification accuracy of predictive models. by Oualid Benkarim (9707986)

The robustness test results of the model. by Xini Fang (20861990)

“…Following this, the FCM clustering algorithm is utilized for pre-processing sample data to improve the efficiency and accuracy of data classification. …”

Construction process of RF. by Xini Fang (20861990)

“…Following this, the FCM clustering algorithm is utilized for pre-processing sample data to improve the efficiency and accuracy of data classification. …”

Data_Sheet_1_Using random forest algorithm for glomerular and tubular injury diagnosis.docx by Wenzhu Song (12532351)

pyAKI data model. by Christian Porschen (12967868)

Normalised confusion matrix of predictions of unfamiliar insects present in the test dataset, based on the best YOLOv5 model. by Kim Bjerge (14797213)

Subjects:

Number of insect classes in the dataset used for training, validation and test. by Kim Bjerge (14797213)

Subjects:

Seasonality and variation in the number of individual detections for each of the nine insect taxa counted in images collected from 10 cameras every day. by Kim Bjerge (14797213)

Subjects:

Training and validation with class, object and box loss for YOLOv5 models with nine classes. by Kim Bjerge (14797213)

Subjects: