As the population increases, vehicle usage has been increased considerably. Traffic becomes the most crucial factor at the time of traffic management which needs to be controlled for the improved traffic management. However traffic management would be more difficult task in case of increased vehicles usage by different number of peoples. Internet of Thing makes things easier by interconnecting vehicles with the server through the internet. IoT can monitor the vehicle periodically and track their location by sending periodic information to the server. This is focused in the proposed research framework by collecting and analyzing the traffic information so that traffic can be controlled very effectively. The significant target of this proposed framework is to carry out a novel IoT based Traffic Management (IoT-TM) that can make short term decision about the traffic management, thus the accurate and efficient traffic clearance can be achieved. In this research method, data set is gathered from the multiple traffic profiles which includes attributes such as time consumption, traffic rate, number of vehicles and so on. These data's would be learned in the training phase by using the Hybrid Artificial Neural Network with Hidden Markov Model (HANN-HMM) which can accurately learn the traffic profile information with reduced time. To perform accurate recognition of the traffic optimized feature selection is done before learning by using Hybrid Ant colony Glow worm swarm optimization approach. The complete interpretation of the aniticipated investigational framework has been conducted on MATLAB environment from which it is proved that the proposed research method namely IoT-TM can make better decision about the traffic management than the existing research systems.
[1]
Dipak Ghosal,et al.
Adaptive Traffic Signal Control With Vehicular Ad hoc Networks
,
2013,
IEEE Transactions on Vehicular Technology.
[2]
Gian Luca Foresti,et al.
Special issue on video communications, processing, and understanding for third generation surveillance systems
,
2001
.
[3]
Guna Seetharaman,et al.
Efficient feature extraction and likelihood fusion for vehicle tracking in low frame rate airborne video
,
2010,
2010 13th International Conference on Information Fusion.
[4]
Ivan Laptev,et al.
Efficient Feature Extraction, Encoding, and Classification for Action Recognition
,
2014,
2014 IEEE Conference on Computer Vision and Pattern Recognition.
[5]
Andreas Festag,et al.
Cooperative intelligent transport systems standards in europe
,
2014,
IEEE Communications Magazine.
[6]
Jun Ding,et al.
Multi-modal traffic signal control with priority, signal actuation and coordination
,
2014
.
[7]
Kongqiao Wang,et al.
Robust CoHOG Feature Extraction in Human-Centered Image/Video Management System
,
2012,
IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).