Enhanced Border Surveillance Through a Hybrid Swarm Optimization Algorithm

Protecting borders from the illicit transfer of people, goods, and drones is essential for a country’s security and economic strength. Conventionally, most borders deploy manual surveillance that entails high costs for training and supplies, while making security personnel vulnerable due to direct exposure to the threats. A move toward technology-assisted border surveillance is the need of time to help reduce the extra cost and loss of human lives while improving surveillance quality. To achieve this, a technology-assisted solution is proposed in this article by employing a swarm of unmanned aerial vehicles (UAVs). In contrast to the existing relevant methods that primarily focus on providing coverage on a 2-D plane, a hybrid optimization algorithm is proposed for optimal placement of UAVs in a 3-D environment providing maximum coverage in an aerial plane while minimizing resource usage. The proposed algorithm, termed genetic local particle (GLP)-Hybrid, combines particle swarm optimization (PSO) algorithm properties with selected additional features such as genetic algorithm (GA) operations to incorporate diversity in the solution. The proposed algorithm outperformed the PSO and GA when examined in a suburban region. The proposed approach proved invaluable in all 24 test cases formulated by varying area sizes and region types, making it suitable for situations demanding near-perfect precision.