Article Preview
TopBackground
Effective traffic management requires the consideration of a number of dynamically changing factors: quality of roads and congestion, ramifications of transport infrastructure, weather conditions, timetables of enterprises operation, schedules of mass events (for example, sports competitions) etc. As advanced vehicles (cars, buses etc.) and road infrastructure are becoming more instrumented with sensors, actuators, and processing units, use of the concept of the IoT is becoming more attractive for solving this problem.
A lot of research has been devoted in recent years to different aspects of the use of IoT for traffic management, see (Anass, Yassine & Mohammed, 2016) and (Pyykönen, Laitinen, Viitanen, Eloranta & Korhonen, 2013).
To avoid emergency situations on the roads, the intelligence level of vehicles can be increased by providing them with reasoning capabilities. Such an approach enables to avoid the use of a central decision point since each vehicle is a decision point. The advantage of this approach is immediate solutions because every vehicle responds to neighboring vehicles and collaborates with them to reach a consensus in real time. Such an approach is considered in (Bermejo, Villadangos, Astrain & Cordoba 2013), where automatic reasoning is realized using ontologies.
Another approach to traffic management using knowledge integration and reasoning based on sensor ontology are considered in (Hotea & Groza, 2013).
In (Li, Gu & Zhang, 2012) the significance of increasing situational awareness and, consequently, the solution of situation assessment task is substantiated.
In (Al-Sakran, 2015) an architecture that integrates IoT with agent technology into a single platform is proposed. Agents handle effective communication and interfaces among a large number of heterogeneous highly distributed and decentralized devices within the IoT. The architecture introduces the use of an active radio-frequency identification (RFID), wireless sensor technologies, object ad-hoc networking, and Internet-based information systems in which tagged traffic objects can be automatically represented, tracked, and queried over a network.
However, the issues of software design automation for situation assessment sub-systems (SAS) were not considered.
Given the constant growth in number and type of information sources, the higher level of situational awareness is required to make high-quality decisions. Since the data supplied by the sensors are low-level, they must be processed to build a high-level model of the situation. In addition, to make informed decisions, it is also necessary to forecast the transport situation (for example, by the end of the mass sporting event). Within the cognitive agent architecture, this task is solved by SAS.