Top Rated Pune Call Girls Budhwar Peth ⟟ 6297143586 ⟟ Call Me For Genuine Se...
CIV8331 ASSIGNMENT PRESENTATION.pptx
1. CIV8331: ADVANCED TRAFFIC ENGINEERING
ASSIGNMENT
ON
REVIEW OF MICROSCOPIC MODEL USING ARTIFICIAL
INTELLIGENCE (AI)
BY
SALISU, jAmilu adamu
Sps/20/mce/00055
SUPERVISED BY
ENGR. PROF. H. M. ALHASSAN
DECEMBER, 2022
DEPARTMENT OF CIVIL ENGINEERING
FACULTY OF ENGINEERING
BAYERO UNIVERSITY, KANO
2. OUTLINE
•Introduction
•Artificial Intelligence Methods
•Artificial Intelligence Models
•Artificial Intelligence Application Areas
•Advantages of Artificial Intelligence
•Disadvantages of Artificial Intelligence
•Current State of Research
•Future Research
•Conclusion
•Recommendations for Future Research
•References
3. INTRODUCTION
ARTIFICIAL INTELLIGENCE
Artificial intelligence (AI) attempts to understand and build
intelligent entities that think and act rationally like humans
for solving problems or making decisions (Russel and
Norvig, 2003). According to Zuylen (2012), AI also means
computer systems that demonstrate complex living-system
like behaviors.
McCulloch and Pitt (1943) conducted the first work
generally known as AI in 1943. They designed a model of
artificial neurons based on three sources: “knowledge of
basic physiology and function of neurons in brains”, “a
formal analysis of proportional logic”, and “Turing’s theory
of computation”. They showed that a suitably defined
network of connected neurons could learn and compute any
4. ARTIFICIAL INTELLIGENCE METHODS
At the present time, AI methods can be divided into
two broad categories: (a) symbolic AI, which focuses
on the development of knowledge-based systems
(KBS); and (b) computational intelligence, which
includes such methods as neural networks (NN), fuzzy
systems (FS), and evolutionary computing. A very
brief introduction to these AI methods is given
below.
•Knowledge-Based Systems
A KBS can be defined as a computer system capable
of giving advice in a particular domain, utilizing
knowledge provided by a human expert. A
distinguishing feature of KBS lies in the separation
behind the knowledge, which can be represented in a
5. ARTIFICIAL INTELLIGENCE MODELS
A. ANN Model
Artificial neural network (ANN) models process
information using functional architecture and
mathematical models that are similar to the neuron
structure of the human brain. These models learn
human behaviors from training and are capable of
demonstrating those human behaviors in a new
situation. In recent years, neural networks have been
used for modeling driver behavior in the
transportation field. For instance, Hunt and Lyons
predicted drivers’ lane-changing decisions using
neural networks on dual carriageways. Neural
6. ARTIFICIAL INTELLIGENCE APPLICATION AREAS
AI application areas are quite diverse. This section lists some
of those application areas to which AI methods has been
applied over the years, and explains how these may be
relevant to transportation applications. Among the most
important of AI application areas are the following:
• Control focuses on controlling a system so as to achieve a
desired output. Control applications abound in
transportation. Examples include signal control of traffic at
road intersections, ramp metering on freeways, dynamic
route guidance, positive train control on railroads, and air
traffic control.
• Clustering refers to the problem of grouping cases with
similar characteristics together, and identifying the number
7. ADVANTAGES OF ARTIFICIAL INTELLIGENCE
AI provides numerous advantages in its applications in a wide
range of fields. Among the most important of advantages are
the following.
1. AI has demonstrated very high reliability in a variety of
applications due to its ability to mimic human thinking and
behavior. AI provides rational predictions or decisions with
higher accuracy than traditional function fitting methods.
2. AI provides fast solutions to complex problems. By
automating data gathering, processing and the decision-
making process, AI supports faster decision making in
complex situations.
3. AI is capable of processing both qualitative and quantitative
data. (Chowdhury and Sadek, 2012).
8. DISADVANTAGES OF ARTIFICIAL INTELLIGENCE
Nevertheless, like any other tools, there are some concerns
for AI techniques. Chowdhury and Sadek (2012) discuss two
major concerns of AI.
1. Some AI paradigms lack good interpretations of the models
and are usually seen as a “black box” approach that simply
represent the relationship between independent and
dependent variables based on training data. One solution
they proposed to alleviate this concern is to build hybrid
models by combining multiple AI paradigms or coupling AI
with traditional approaches.
2. Selecting the best value for parameters in AI models is
more of an art than science. For example, researchers using
genetic algorithms need to make some important decisions
about the population size, the number of generations,
9. CURRENT STATE OF RESEARCH
1. In 2010, Google presented its Toyota Prius automated
car in the United States. It is estimated to save over 30,000
lives and save the yearly costs related to road accidents to
270 billion in the USA. In addition, it will decrease the
need for parking lots as the vehicle will park itself in
remote areas.
2. A global study on a different aspect of what makes the
cognitive intelligent vehicle more appealing to passengers
has been conducted by (Stanley and Gyimesi, 2016). These
aspects were as follows:
Self-healing: Vehicles can recognize the error with
themselves and fix it.
Self-socializing: The ability of a vehicle to interact with the
10. FUTURE RESEARCH
1. Edara Praveen
University of Missouri
The fields of AI and advanced computing provide immense
value to transportation research. Their applications in
mining traffic datasets, forecasting traffic parameters,
explaining traffic phenomena, and intelligent real-time
traffic control, are a few examples of their valuable
contributions that I have personally explored. Like
statistical and econometric modeling, the algorithms and
methods in the area of artificial intelligence and advanced
computing are inherently complex and often involve
rigorous mathematical underpinnings. Over the years,
researchers have applied different AI techniques and
algorithms to transportation areas and thereby making
11. CONCLUSIONS
The review focused on a Artificial Intelligence (AI) in traffic
flow model. Moreover, in recent years, AI has been
developed to use in traffic demand prediction, weather
condition prediction, and future traffic state for
management and control purposes and to alleviate
congestion and fast decision making during hazardous
situation i.e., road accidents. Furthermore, automated
vehicles and automated public transportation systems are
also increasingly benefiting from AI tools to avoid
disruptions, accidents, and congestion. Key limitations of AI
were also addressed in particular the perception that neural
networks are “black boxes” and also the issue surrounding
introduction of bias in the training data as a result of having
12. RECOMMENDATIONS FOR FUTURE RESEARCH
1. Evaluate and analyse different driver behaviour:
Another way to directly analyse different driver behaviour
and at the same time benefit from large data set, could be
training several models. First, the data could be clustered
according using other machine learning techniques such as
neural networks. Then a different set of models could be
trained from the different subset of data. Hence, every
individual model depending the clustered objective, could
depict different traffic behavior according to the driver
characteristics, meteorological conditions, or day type
among others.
2. Analysis of the drivers reaction time: In thesis, we did
not explore the effects of there action time and it was
13. REFERENCE
1. Stanley, B.; Gyimesi, K. A New Relationship—People and
Cars; IBM Institute for Business Value:Armonk, NY, USA, 2016;
p. 21.
2. Chowdhury, M., and A. W. Sadek, “Advantages and
Limitations of Artificial
Intelligence,” Transportation Research Circular, no. E-C168,
pp. 6-8, November 2012.
3. Zuylen, H. V., “Difference between artificial intelligence and
traditional methods,” Transportation Research Circular, no. E-
C168, pp. 3-5, November 2012.
4. Russel, S., and P. Norvig, Artificial Intelligence A Modern
Approach. 2nd ed.
Englewood Cliffs, NJ, USA: Prentice-Hall, 2003, pp. 653-663.