Training results under different parameters. حسب Yang Zhang (30734)

"…Furthermore, the implementation of a nonmonotonic strategy for dynamically adjusting the loss function weights significantly boosts the model’s detection precision and training efficiency. …"

The efficient multi-scale attention. حسب Yang Zhang (30734)

"…Furthermore, the implementation of a nonmonotonic strategy for dynamically adjusting the loss function weights significantly boosts the model’s detection precision and training efficiency. …"

The improved network diagram of YOLOv9s. حسب Yang Zhang (30734)

"…Furthermore, the implementation of a nonmonotonic strategy for dynamically adjusting the loss function weights significantly boosts the model’s detection precision and training efficiency. …"

Wilcoxon test results for feature selection. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

Feature selection metrics and their definitions. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

Statistical summary of all models. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

Classification performance after optimization. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

ANOVA test for optimization results. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

Feature selection results. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

ANOVA test for feature selection. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

Wilcoxon test results for optimization. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

Classification performance of ML and DL models. حسب Amal H. Alharbi (21755906)

"…We applied this hybrid strategy to a Radial Basis Function Network (RBFN), and validated its performance improvements through extensive experiments, including ANOVA and Wilcoxon tests for both feature selection and optimization phases. …"

Skipping frames and interpolating skeletons with a spline achieves similar accuracy and faster computational time. حسب Weheliye H. Weheliye (22022140)

"…(C) Computation time per input frame for the different models as a function of worm number. Tierpsy only uses CPU computation while Omnipose uses GPU and CPU because we use Tierpsy’s skeletonization algorithm to convert segmented regions to skeletons. …"

PhyCysID: Plant Cystatin Protein Prediction by an Artificial Intelligence Approach حسب Sadaf Aqil (22183571)

"…As a case study, a curated dataset of phytocystatin sequences from the UniProt database was used to evaluate the algorithm’s performance. The PhyCysID web server enables rapid classification of both individual and batch-submitted sequences in less than 15 s, providing high-throughput analysis for an accurate identification of phytocystatin class and function. …"

PhyCysID: Plant Cystatin Protein Prediction by an Artificial Intelligence Approach حسب Sadaf Aqil (22183571)

"…As a case study, a curated dataset of phytocystatin sequences from the UniProt database was used to evaluate the algorithm’s performance. The PhyCysID web server enables rapid classification of both individual and batch-submitted sequences in less than 15 s, providing high-throughput analysis for an accurate identification of phytocystatin class and function. …"

PhyCysID: Plant Cystatin Protein Prediction by an Artificial Intelligence Approach حسب Sadaf Aqil (22183571)

"…As a case study, a curated dataset of phytocystatin sequences from the UniProt database was used to evaluate the algorithm’s performance. The PhyCysID web server enables rapid classification of both individual and batch-submitted sequences in less than 15 s, providing high-throughput analysis for an accurate identification of phytocystatin class and function. …"

PhyCysID: Plant Cystatin Protein Prediction by an Artificial Intelligence Approach حسب Sadaf Aqil (22183571)

"…As a case study, a curated dataset of phytocystatin sequences from the UniProt database was used to evaluate the algorithm’s performance. The PhyCysID web server enables rapid classification of both individual and batch-submitted sequences in less than 15 s, providing high-throughput analysis for an accurate identification of phytocystatin class and function. …"

Structure and parameters of pipeline network. حسب Huichao Guo (14515171)

"…The experimental results show that compared with the traditional particle swarm optimization algorithm, NACFPSO performs well in both convergence speed and scheduling time, with an average convergence speed of 81.17 iterations and an average scheduling time of 200.00 minutes; while the average convergence speed of the particle swarm optimization algorithm is 82.17 iterations and an average scheduling time of 207.49 minutes. …"

Experimental parameter combinations. حسب Huichao Guo (14515171)

"…The experimental results show that compared with the traditional particle swarm optimization algorithm, NACFPSO performs well in both convergence speed and scheduling time, with an average convergence speed of 81.17 iterations and an average scheduling time of 200.00 minutes; while the average convergence speed of the particle swarm optimization algorithm is 82.17 iterations and an average scheduling time of 207.49 minutes. …"

Experimental results. حسب Huichao Guo (14515171)

"…The experimental results show that compared with the traditional particle swarm optimization algorithm, NACFPSO performs well in both convergence speed and scheduling time, with an average convergence speed of 81.17 iterations and an average scheduling time of 200.00 minutes; while the average convergence speed of the particle swarm optimization algorithm is 82.17 iterations and an average scheduling time of 207.49 minutes. …"