An image classification approach for hole detection in wireless sensor networks

Cheong, Se-Hang; Ng, Kim-Hou; Si, Yain-Whar

doi:10.1007/s11227-021-04276-4

Cited by 1 publication

(1 citation statement)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the rapid development of WSN technology, it has been widely applied in industrial and scientific research, including applications in habitat monitoring, industrial machinery condition monitoring, and environmental science research [27] [28] [29]. Moreover, WSNs have begun to find applications in people's daily lives, such as smart home sensing and indoor positioning [30] [31] [32] [33]. The deployment problem is a primary task for Wireless Sensor Networks to fulfill their designated functions.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Tasmanian Devil Optimizer for Global Optimization and Application in Wireless Sensor Network Deployment

Wang,

Lyu

2024

IEEE Access

View full text Add to dashboard Cite

The Tasmanian Devil Optimization (TDO) algorithm, a recently popular metaheuristic algorithm, exhibits issues such as slow convergence, low precision, and susceptibility to getting stuck in local optima when applied to practical problems. In order to address these drawbacks, we propose an improved version called the Adaptive Tasmanian Devil Optimizer (ATDO). In the enhancements, we introduce a best point set population initialization to enhance ATDO's exploration capabilities. The adoption of an adaptive Levy flight strategy improves convergence precision and speed. The introduction of a Brownian random walk strategy effectively prevents the problem of being trapped in local optimal solutions. Additionally, the use of a cosine-type change-based differential evolution algorithm's crossover strategy enhances the overall population quality. To validate the performance of ATDO, a detailed analysis is conducted in terms of population diversity, exploration-exploitation balance, and convergence behavior. Furthermore, we apply ATDO to CEC-2017 for global optimization performance evaluation. Results from Wilcoxon rank-sum and Friedman average rank tests demonstrate that, compared to TDO and other optimization algorithms, ATDO exhibits superior comprehensive performance. Finally, we apply ATDO to wireless sensor network layout optimization and two engineering optimization problems, experimental results show that ATDO outperforms other comparative algorithms, further validating its scalability and excellence.INDEX TERMS Adaptive Tasmanian Devil Optimizer, global optimization, metaheuristic algorithm, wireless sensor network deployment.

show abstract