The bottleneck residual block for Resnet50. by Nour Eldeen Mahmoud Khalifa (19259450)

“…The third phase is the training and testing phase. Finally, the best-performing model was selected and compared with the currently established models (Alexnet, Squeezenet, Googlenet, Resnet50).…”

DeepDate model’s architecture design. by Nour Eldeen Mahmoud Khalifa (19259450)

“…The third phase is the training and testing phase. Finally, the best-performing model was selected and compared with the currently established models (Alexnet, Squeezenet, Googlenet, Resnet50).…”

DataSheet1_A two-phase robust comprehensive optimal scheduling strategy for regional distribution network based on multiple scenarios.ZIP by Hongde Ma (20137539)

Random forest model performs better than support vector machine algorithms and when it primarily uses spontaneous photopic ERG of 60-s duration in humans. by Ramsés Noguez Imm (6658637)

Truck collision avoidance trajectory planning system. by Du Chigan (22320279)

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. …”

Residual behavior. 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. …”

UK Biobank data wrangling statistics and results. by Simeone Marino (81051)

Spontaneous ERG-based random forest model discriminates control and disease cases in rodent models of obesity and type 1 diabetes and predicts disease evolution in the type 1 diabe... by Ramsés Noguez Imm (6658637)

Optimal Timings Codebook.xlsx by Emma Spillane (11249121)

Overall framework diagram. by Yanhua Xian (21417128)

“…Secondly, addressing the issue of weight and threshold initialization in BPNN, the Coati Optimization Algorithm (COA) was employed to optimize the network (COA-BPNN). …”

Data_Sheet_1_Multiclass Classification Based on Combined Motor Imageries.pdf by Cecilia Lindig-León (7889777)

“…And we propose two new multilabel uses of the Common Spatial Pattern (CSP) algorithm to optimize the signal-to-noise ratio, namely MC2CMI and MC2SMI approaches. …”

Optimal Time Intervals of Breech Births Dataset by Emma Spillane (11249121)

Analysis and design of algorithms for the manufacturing process of integrated circuits by Sonia Fleytas (16856403)

“…From this, we propose: (i) a new ILP model, and (ii) a new solution representation, which, unlike the reference work, guarantees that feasible solutions are obtained throughout the generation of new individuals. Based on this new representation, we proposed and evaluated other approximate methods, including a greedy algorithm and a genetic algorithm that improve the state-of-the-art results for test cases usually used in the literature. …”

Summary of LITNET-2020 dataset. by Asmaa Ahmed Awad (16726315)

“…The ILSTM was then used to build an efficient intrusion detection system for binary and multi-class classification cases. The proposed algorithm has two phases: phase one involves training a conventional LSTM network to get initial weights, and phase two involves using the hybrid swarm algorithms, CBOA and PSO, to optimize the weights of LSTM to improve the accuracy. …”