Hybrid long short-term memory deep learning model and Dijkstra’s Algorithm for fastest travel route recommendation considering eco-routing factors

ABSTRACT

The exponential growth of vehicles has led to increased traffic congestion and pollutants emission in cities. Intelligent transportation systems (ITS) shall be built by integrating Artificial Intelligence(AI). Planning optimal route with minimum travel time is a great challenge for the traffic management system. A hybrid model integrating long-short-term memory(LSTM) deep-learning model and Dijkstra’s algorithm for recommending the fastest route is proposed in this work. The proposed hybrid approach reduces the travel time to a greater extent. Vehicle speed greatly influences eco-driving factors such as fuel consumption and exhaust emission. Thus, for each road links, the fuel consumption and emission of pollutants such as carbon monoxide(CO), nitrogen oxides(NOx), and hydrocarbon(HC) are estimated for different type of vehicles. The results showed the proposed approach decreases fuel consumption, CO emission, NOx emission, and HC emission up to 54.5%, 61.5%, 64.2%, and 81.9%, respectively, compared to the traditional shortest path.

KEYWORDS:

• Long Short Term Memory (LSTM)
• Dijkstra’s Algorithm
• traffic speed
• Eco-route
• Intelligent Transportation Systems
• hybrid model

Acknowledgments

The authors would like to thank our Institute, Thiagarajar College of Engineering, Madurai, India, for providing the support to carry out this research work.

Disclosure statement

No potential conflict of interest was reported by the author(s).