ACP-Based Modeling of the Parallel Vehicular Crowd Sensing System: Framework, Components and an Application Example

Toward parallel intelligence: An interdisciplinary solution for complex systems

“…These software-defined artificial components, which can be categorized into two groups, basic and domain specific, are then integrated to form cohesive software-defined artificial systems. 66 The basic components encapsulate more than just the physical aspects of the actual systems; they also encompass cyber and social dimensions, including structures such as artificial platforms 57 and artificial populations. 67 Besides, domain-specific components vary across various complex systems.…”

“…11 , 55 , 56 The formalization of CPSS in 2010 fundamentally shaped the solution form of ACP-based parallel systems, enhancing its applications in various fields. 4 , 57 As the research progressed, relevant studies appeared in a variety of fields, each interpreting and applying the parallel systems method in terms tailored to their unique perspectives. Researchers began to recognize that these studies need clear objectives and guidance.…”

“… 48 , 49 , 50 A parallel vehicular crowdsensing system has also been developed to produce high-fidelity data for various traffic scenarios, sensing tasks, and road networks to guide the optimization of sensing campaigns. 57 …”

MetaEdu: a new framework for future education

“…In recent years, the ACP method has been widely applied to many domains. Ren et al successfully used it to design a parallel vehicular crowd sensing (VCS) system [37]. In particular, various computational experiments considering human and social factors were conducted, evaluated, and shared with the real VCS system to improve its efficiency and robustness.…”

Sparse heterogeneous grid traffic prediction with cross-adaptive multi-graph attention

“…Accurate predictions of traffic conditions facilitate proactive decision-making, leading to improved traffic flow, reduced travel time, and enhanced overall transportation efficiency. [1] However, due to the complex and dynamic nature of urban road networks, accurately forecasting traffic conditions remains a challenging problem. [2] In recent years, the availability of large-scale traffic data and advances in machine learning techniques have propelled research efforts in developing more sophisticated traffic prediction models.…”