Mobile App for Predicting Mobility Patterns of Local Commute in IoT based Cloud
In recent years, public and private transportation has become a very important aspect. Transportation vehicles like bus, train are mostly recommended by local commute people on metropolitan areas. Now a days, the people to travel farther and expand their control over larger areas, but at the same time there are many limitation like providing the vehicles only in shortest region without payment preference. Public transport can be inherently slower due to strongly enforced speed limits during peak hours. In existing system, crowd sensing is difficult to schedule the transportation vehicles during peak hours, in turn the accuracy is very less to analyze the mobility patterns of bus travelers. There are many new innovations and discoveries have been evolved to solve such issues. To overcome the above issues, in our proposed system we are developing mobile application for predicting mobility patterns of local commute. The system is integrated in IoT based Cloud environment to analyze the mobility patterns during real time accessibility. Infrared (IR) Sensor is used for crowd sensing which QR code is scanned and mode of payment will be done through the Android mobile application. In proposed system, crowd-sensing is done through data mining technique such as SVM (Support Vector Machine) prediction algorithm.This classification algorithm enhances the proposed system through online access to analyze the availability of transport more accurately. The system uses the Fire-Base Public cloud platform for data storage and retrieval of data during transportation analysis. The proposed system with real-time technology concept increases performance metrics like reliability, more accurate detection of crowd and reduces the time consumption of the passenger. Finally, this mobile application is achievable in all around the cities.