Particle Swarm Optimization for Adaptive Social-distance of Neighborhood in the IoT and COVID-19 Era

Abstract

While it is well understood that the emerging Social Internet of Things (SIoT) offers a description of a new world of billions of humans which are intelligently communicate and interact with each other. SIoT presents new challenges for suggesting useful objects with certain services for people. This is due to the limitation of social networks between human and objects, such as the evaluation of the various patterns inherent in human walk in cities. In this study we focus services on the problem of recommendation on SIoT which is very important for many applications such as urban computing, smart cities, and health care. The optimized results of swarm of certain infected people COViD-19 introduced in this paper aims at finding a given region of interest. Guided by a fitness function, the particle swarm optimization (PSO) algorithm has proved its efficiency to explore the search space and find the optimal solution. However, in real world scenarios in which the peoples are simulated as particles, there are practical constraints that should be taken into considerations. The most two significant constraints are (1) given the social-distance, the measurement of input variable fluctuations and their possibility of occurring via probability distribution function over the whole particles. (2) given the limited the communication range of particle/people/users, therefore, the spread of the diseases are simulated and evaluated using neighborhood particle swarm optimization (NPSO).