UAV paths for the Priority-Driven scenario (sensor colors indicate priority, yellow high to blue low). by Bashir Olaniyi Sadiq (22478011)

The overall algorithm structure. by Jiren CAO (20442214)

“…The model aimed at maximize the corporate revenue and maximize passenger travel benefit, and was solved by large neighborhood search heuristic algorithm and path size logit assignment based on capacity constraint-passenger flow increment accurate algorithm. …”

The application of machine learning in the integration and optimization of natural protected areas by Qiuyan Liang (21585203)

“…This study constructed a spatial integration and optimization path for NPAs based on the random forest classification model and the regional growing algorithm, and conducted an empirical test using the northern Guangdong region with basic data as an example. …”

Data Sheet 1_Multi-stage bidirectional informed-RRT * plant protection UAV path planning method based on A * algorithm domain guidance.pdf by Jian Li (41607)

“…Therefore, there is an urgent need to develop an intelligent path planning algorithm. To address this issue, this study proposes an improved Informed-RRT* path planning algorithm guided by domain-partitioned A* algorithm. …”

UAV paths for Coverage-Driven scenario (blue circles: sensors, red squares: relays, black lines: UAV trajectories). by Bashir Olaniyi Sadiq (22478011)

Control parameters of the SOMA algorithm. by Quoc Bao Diep (18452207)

“…We introduce a new cost function designed to minimize the distance to the target while maximizing the distance from obstacles, effectively balancing these competing objectives to ensure safety and efficiency. To optimize this cost function, we employ the self-organizing migrating algorithm, a swarm intelligence algorithm inspired by the cooperative and competitive behaviors observed in natural organisms. …”

Path smoothing. by Yu Gu (162342)

“…Divide the entire path planning process into two stages: quickly finding the initial path and optimizing the path. …”

Convergence curve of the GL-SSL Model’s training loss function, illustrating the trend of loss reduction over 300 iterations, reflecting the model’s stability and rapid convergence... by Jiangjiang He (9676377)

Subjects:

Heatmap illustrating the impact of data noise on GL-SSL Model performance—showing the trend of performance fluctuations under different noise levels and experimental runs, highligh... by Jiangjiang He (9676377)

Subjects:

Ablation Study Results of GL-SSL Model on Global Shipping Data. by Jiangjiang He (9676377)

Subjects:

Ablation Study Results of GL-SSL Model on AIS Data. by Jiangjiang He (9676377)

Subjects:

Architecture of the GCN Module in the GL-SSL Model for Smart Port Path Optimization, Illustrating the Aggregation of Spatial Topological Features from Port Transportation Networks... by Jiangjiang He (9676377)

Subjects:

Ablation Study Results of GL-SSL Model on Port of Rotterdam Data. by Jiangjiang He (9676377)

Subjects:

Training Time vs. Network Size. This graph shows that as the port network size (number of nodes) increases from 100 to 500, model training time increases linearly. by Jiangjiang He (9676377)

Subjects:

Illustration of crossover. by Ruochen Zhang (3434996)

Subjects:

The mean value of the maximum ACC for each number of added edges <i>k</i> for 10 runs acquired by MOEA/D-SW, MA-SW, GA-SW, GR-SW, NW model, and NSGA-II. by Ruochen Zhang (3434996)

Subjects:

S1 Dataset - by Ruochen Zhang (3434996)

Subjects:

The topologies of edging solution with <i>k</i> = 10 on Zachary’s Karate Club network. by Ruochen Zhang (3434996)

Subjects:

The mean value of the maximum ACC/APL for each number of added edges <i>k</i> for 10 runs acquired by MOEA/D-SW, MA-SW, GA-SW, GR-SW, NW model, and NSGA-II. by Ruochen Zhang (3434996)

Subjects:

Statistical tests of ACC on the random network. by Ruochen Zhang (3434996)

Subjects: