Flow chart of particle swarm algorithm. by Nour Eldeen Mahmoud Khalifa (19259450)

The initial and final values for each PSO parameter in all application. by Rutinaldo Aguiar Nascimento (14259594)

Experimental comparison of different clustering algorithms. by Ning Zhao (84707)

Subjects:

Flow chart of density peak clustering algorithm. by Ning Zhao (84707)

Subjects:

Recall curve of higher-order hybrid clustering algorithm incorporating LDA model. by Ning Zhao (84707)

Subjects:

Results of ablation experiment. by Ning Zhao (84707)

Subjects:

Model frame drawing. by Ning Zhao (84707)

Subjects:

Training process. by Ning Zhao (84707)

Subjects:

Data set parameters. by Ning Zhao (84707)

Subjects:

Comparison of clustering performance under different text vector formation methods. by Ning Zhao (84707)

Subjects:

Weighted covariance matrix based GEDM model. by Ning Zhao (84707)

Subjects:

Proposed architecture testing phase. by Yasir Khan Jadoon (21433231)

“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”

Case 1 (100 × 20). by Rutinaldo Aguiar Nascimento (14259594)

Case 1 (100 × 20). by Rutinaldo Aguiar Nascimento (14259594)

Comparison with existing SOTA techniques. by Yasir Khan Jadoon (21433231)

“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”

Proposed inverted residual parallel block. by Yasir Khan Jadoon (21433231)

“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”

Inverted residual bottleneck block. by Yasir Khan Jadoon (21433231)

“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”

Sample classes from the HMDB51 dataset. by Yasir Khan Jadoon (21433231)

“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”

Sample classes from UCF101 dataset [40]. by Yasir Khan Jadoon (21433231)

“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”

Self-attention module for the features learning. by Yasir Khan Jadoon (21433231)

“…The proposed architecture is trained on the selected datasets, whereas the hyperparameters are chosen using the particle swarm optimization (PSO) algorithm. The trained model is employed in the testing phase for the feature extraction from the self-attention layer and passed to the shallow wide neural network classifier for the final classification. …”