1. BAYERO UNIVERSITY KANO
FACULTY OF ENGINEERING
DEPARTMENT OF CIVIL ENGINEERIG
REVIEW OF MICROSCOPIC TRAFFIC MODEL USING ARTIFICIAL
INTELLIGENCESS
BY
NURA TUKUR MUHD
SPS/20/MCE/00027
COURSE CODE: CIV 8331
COURSE TITLE: ADVANCED TRAFFIC ENGINEERING
SUPERVISED BY ENGR. PROF. H.M ALHASSAN FNICE
2. OUTLINES OF PRESENTATION
Introduction
Aim And Objectives
Applications of AI
Advantage and disadvantages of AI in transportation
Current research
Future research
Recommendation and Conclusion
References
3. INTRODUCTION
.Artificial Intelligence, or AI, is profoundly impacting the ways in which people across the globe interact. Being a powerful set of
technologies, people have been helped in solving almost every everyday problem, which makes AI’s applicable in numerous fields.
[Sadek A.W 2007]. One of which is transportation that has already been disrupted the ways in which the people and goods are
moved. In addition,
.AI has also been playing an important role in transportation section from scanning of the traffic patterns to the reduction of the
road accidents, and from the optimization of the routes to the minimization of the emission [Qi L, 2008]. All of these have been
made into reality through data collection and analysis; thereby indicating that AI has been critical for the creation of opportunities
to make transport much safer, cleaner, efficient and reliable at the same time. In both emerging markets and advanced economies,
AI’s multiple applications have exemplified the contributions through evolving technologies, while effectively managing the
challenges posed by these technologies [Sumalee A, 2018].
4. Aim
To review microscopic traffic model using artificial intelligence
Objectives
To know the application of artificial intelligence in traffic model
To know about the current and future research on artificial intelligence in traffic model
5. APPLICATION OF ARTIFICIAL INTELLIGENCE (AI) IN TRANSPORT AND TRAFFIC
MANAGEMENT
AI has radically and fundamentally changed the world economy, and has been predicted to continue doing so in the
future. ]. The forecast also takes account of the transportation sector, where the application of AI has been predicted
to result in additional disruptions. During 2017, the transportation-related AI technologies in the global market
reached between $1.2 to $1.4 billion, which is expected to grow to $3 .1 to $3.5 billion by 2023.
AI is applicable to various areas which include,
(a) Traffic operations
(b) Travel and demand modeling
(c) Transportation safety, security and public transportation,
(d) Planning design and controlling transport network,
(e) Incident detection,
(f) Predictive model
6. Planning Designing and Controlling Transportation Network Structure through AI
The purpose of planning has been to work on the identification of the community needs, while deciding on the best approach or
approaches through which the demands can be met without increasing the negative consequences for the environmental,
economic and social aspects in transportation. Network Design Problem (NDP) has been identified to be associated with the
purpose of designing optimal road method in transportation management [Bagloee et al, 2015]. In this context, it has been
identified that there are both continuous and discrete problems associated with transportation.
AI is a dynamic research area that keeps on improving and new methods and applications are introduced frequently to utilize the
strength of AI to improve the planning, decision making and management of road.
7. Incident Detection
An algorithm for incident detection has been first implemented using statistical techniques such as California
Algorithm. However, it is difficult to use an algorithm on arterial roads, because of the street parking and traffic
signals. For this reason, algorithms have been developed to neural networks approaches.
Predictive Models
The rapid development of intelligent transport systems (ITS) has increased the need to propose advanced methods
methods to Predict traffic information. These methods play an important role in the success of ITS subsystems
such as advanced traveler information systems, advanced traffic management systems, advanced public
transportation systems, and commercial vehicle operations. Intelligent predictive systems are developed using
historical data extracted from sensors attac
8. ADVANTAGES OF AI IN TRAFFIC MODELS
1. AI will reduce traffic accidents and increase safety, The number of accidents involving truck drivers at
night is a large issue and can be improved with the use of smart unmanned vehicles The personal &
financial costs of these accidents are quite substantial, labor costs in this sector will continually decrease
with the increased use of AI, providing higher safety in traffic.
2. Artificial intelligence (AI) will create significant opportunities for automakers to reduce production costs
and introduce new revenue streams, including self-driving technology, predictive maintenance, and route
optimization, The long driving hours and stopping for a break will no longer be a concern with fully
automated fleets.
3. AI increases the ability to process and predict data and outcomes than humans, so, travel and transport
operators will schedule public and private transportation services in a significantly improved manner.
9. DISADVANTAGES OF AI IN TRAFFIC MODELS
1. AI will impact a significant number of blue-collar jobs in the transportation industry, Automakers can use AI
to adapt to a changing transportation landscape, However, costs will still be a major barrier to adoption, more
than half (53%) of global business and IT leaders cited the high costs associated with AI technology as a major
deterrent to adoption.
2. Artificial intelligence will enhance the efficiency of the systems it integrates with, however, power will need to
to be used much more intelligently by all of the systems in order to truly utilize the potential of newer
technologies.
10. CURRENT STATE OF RESEARCH
The researchers are working currently in so many areas which include (a) microscopic modelling of freeway traffic using ANN (b)
modelling of urban traffic system using AI
a. Macroscopic Modeling of Freeway Traffic Using an Artificial Neural Network
Traffic control systems are a significant tool for facilitating the full utilization of available capacity (8). Advanced traffic control
technologies may lead to more efficient use of existing freeway systems, thereby reducing traffic congestion, delay, emissions, and
energy consumption, and improving safety.
b. Modelling of an Urban traffic System Using Artificial Intelligence
Drivers across the world, we may have noticed that the amount of time they spend waiting in traffic is greater than it has ever been in
recent times. Statistics from the United Kingdom (UK) has shown a 2.4% increase in traffic (10). . Specifically, urban roads witnessed an
average increase of 2%, which has directly resulted in greater levels of congestion (11).
11. FUTURE STATE OF AI RESEARCH
The findings of this research has clarified about MTM being a robust model because of its ability of covering multiple tasks
associated with AI, and the fact that it does not concentrate or need deep understanding of the processes. The fast computation
tool can help in reducing the time, while improving the performance. Mostly researches have only focused on one or two of the
traffic parameters for the purpose of developing the model.
The future researchers can focus on enhancing the predictive operations through the use of more than two features. Researchers
also work on more than one hidden layer for the models structure
12. CONCLUSION
Conclusively, this research has presented an review of the microscopic traffic model using AI in a various related traffic issues. The
AI has been proven to be critical in increasing and improving the transportation system in general, which can become more
instrumented towards the provision of much-need data for the development of traffic. This research has focused on the application
areas, advantages and disadvantages which the research believed and found to be more critical in terms of their influence on the
public transportation.
RECOMMENDATIONS
It has review that AI in microscopic traffic made a further research in microscopic modelling of freeways, design traffic simulation ,
traffic violation data analysis, and lane changing prediction at highways which gives positive development in transportation by
preventing many failures encounters in transportation.
13. REFERENCE
1. Sadek, A.W., 2007. Artificial intelligence applications in transportation. Artificial Intelligence in Transportation:
Information for Application, pp.1-6.
2. Qi, L., 2008, August. Research on intelligent transportation system technologies and applications. In 2008
Workshop on Power Electronics and Intelligent Transportation System (pp. 529-531). IEEE.
3. Sumalee, A. and Ho, H.W., 2018. Smarter and more connected: Future intelligent transportation system. IATSS
Research, 42(2), pp.67-71
4. Bughin, J., Seong, J., Manyika, J., Chui, M. and Joshi, R., 2018. Notes from the AI frontier: Modeling the impact of AI
on the world economy. McKinsey Global Institute.
5. Houng, X., joung, W., Wang, P., Shen, D., Chen, S., Wang, X., Zhang, Q. and Yang, L., 2015. Big data for social
transportation. IEEE Transactions on Intelligent Transportation Systems, 17(3), pp.620-630.
6. Bagloee, S.A., Sarvi, M. and Patriksson, M., 2017. A hybrid branch‐and‐bound and benders decomposition
for the network design problem. Computer‐ Aided Civil and Infrastructure Engineering, 32(4), pp.319-343.
7. Rodrigue, J.P., 1997. Parallel modelling and Neural Networks: an overview for transportation/land use systems.
Transportation Research Part C: Emerging Technologies, 5(5), pp. 10. Jeong, R. and Rilett, R., 2004, October. Bus arrival
time prediction using artificial neural network model.
8. Traffic Control Systems Handbook. Publication LP-123. ITE, Washington, D.C., 1985.s
9. Derzko, N. A., A. J. Ugge, and E. R. Case. Evaluation of Dynamic Freeway Flow Model by Using Field Data. In
Transportation Research Record 905, TRB, National Research Council, Washington, D.C., 1983, pp. 52–60
10. D. for Transport, Road Traffic Estimates: Great Britain 2014, 2015.
11. INRIX, “Growing economy drives traffic congestion up in over three quarters of uk cities,” 2015. [Online].
Available: http://inrix.com/press/ scorecard-report-united-kingdom/
12. D. A. Roozemond, “Using autonomous intelligent agents for urban traffic control systems,” Proc. 6th World Congr.
Intell. Transp. Syst, 1999.