Search

The development of urban environments leads to many issues; one of them is the traffic blockage. For this fast world, adequate traffic measures should be taken with the help of modern technology. To control this traffic issue, we need effective computation and prediction of traffic flow. To achieve this, the traffic flow data should be collected and analyzed properly (Wang et al., 2020). Wireless Sensor Network (WSN) is an auto-configured group of sensors that monitor and record physical parameters of the environment like temperature, pressure, sound, motion, etc. and organize the data at a central location. These WSNs find their application in various fields like military for battlefield surveillance, health monitoring systems, etc. One such application can be used in the traffic management system. The traffic flow data can be collected using the WSN; it constitutes wireless modules and magnetometer sensors, which give the vehicle flow data along with their speed and location accurately. This system is cost-effective, consumes less power and requires less maintenance. The data is collected and transmitted to the cloud server using the mobile internet. The traffic flow data is then computed using a method based on incremental noise addition for chaotic identification. This method involves the addition of noise signals with different intensities incrementally by the Pseudo-Periodic Surrogate (PPS) method, and the mean value of delayed Mutual Information (MI) is used to measure the complexity of the signal. Depending upon the trends of the changes in the noise mixed-signal, the characteristics can be determined. Hence, we conclude that this method helps in developing out an organized traffic management system. [ABSTRACT FROM AUTHOR]