Training results of each algorithm on the DOTA dataset. by Xuhui Liu (546025)

Presents the comparison of various density based algorithms. by Shahneela Pitafi (20454775)

Subjects:

Improved random forest algorithm. by Zhen Zhao (159931)

“…Additionally, considering the imbalanced in population spatial distribution, we used the K-means ++ clustering algorithm to cluster the optimal feature subset, and we used the bootstrap sampling method to extract the same amount of data from each cluster and fuse it with the training subset to build an improved random forest model. …”

K-means++ clustering algorithm. by Zhen Zhao (159931)

“…Additionally, considering the imbalanced in population spatial distribution, we used the K-means ++ clustering algorithm to cluster the optimal feature subset, and we used the bootstrap sampling method to extract the same amount of data from each cluster and fuse it with the training subset to build an improved random forest model. …”

Federated averaging algorithm pseudocode. by Hadi Mohammadian KhalafAnsar (22783784)

Comparison of training parameters of ASCAD dataset. by Hai Huang (140371)

Subjects:

Data augmentation parameters used during training. by Sai Balakavi (21728626)

Comparison of training parameters of AES_RD dataset. by Hai Huang (140371)

Subjects:

Hyperparameter configurations and callbacks used during the training process. by Sai Balakavi (21728626)

Epoch-level training and validation metrics for the UNET model. by Sai Balakavi (21728626)

Epoch-level training and validation metrics for the UNET-GRU model. by Sai Balakavi (21728626)

Comparison of training parameters of DPA contest v4 dataset. by Hai Huang (140371)

Subjects:

Pixel counts and area (in hectares) of burnt and unburnt regions in training, test, and validation sets. by Sai Balakavi (21728626)

Custom UNET architecture used in the training process for the encoder, decoder, filters, and activation functions. by Sai Balakavi (21728626)

Custom UNET-GRU architecture used in the training process with the encoder, decoder, filters, and activation functions. by Sai Balakavi (21728626)

The patchwise contrastive learning method based on PatchNCE loss. by Yang Zhang (30734)

Algorithm schematic diagram of the CSM module. by Huiying Zhang (200681)

“…<div><p>An MDCFVit-YOLO model based on the YOLOv8 algorithm is proposed to address issues in nighttime infrared object detection such as low visibility, high interference, and low precision in detecting small objects. …”

Flow chart of Novel enhanced DBSCAN based model. by Shahneela Pitafi (20454775)

Subjects:

Loss function curves for the training. by Xuhui Liu (546025)

“…Finally, we use the KFIoU and Focal Loss as the regression loss and classification loss of the algorithm to improve the accuracy of the training. …”

Decomposition and Holt-Winters enhanced by the Whale Optimization Algorithm by Watha Minsan (21263795)