Toward More Effective Transportation Applications of Computational Intelligence Paradigms

Abstract

While information technology has facilitated the collection of neverbefore-seen quantities of data, these data have not always provided the information needed by transportation professionals to support sound decision making. Computational intelligence (CI) has great potential to support the needs of transportation professionals. CI is a result of synergy among information processing technologies such as artificial neural networks (ANNs), fuzzy sets, and genetic algorithms. As the number of CI applications to transportation problems grows, so does the need to evaluate these systems. The issue of validating and evaluating transportation CI applications is addressed. A case study that evaluates the effectiveness of two CI paradigms, case-based reasoning and ANNs, for estimating the benefits of real-time traffic diversion is presented. The case study illustrates the need for regarding validation and evaluation as a part of the development effort and the need for tuning the design parameters of CI paradigms.

Forecasting the Accident Frequency and Risk Factors: A Case Study of Erzurum, Turkey

“…The latter one, CI, combines elements of learning, adaptation, evolution and fuzzy logic to create models that are "intelligent" in that structure emerging from an unstructured beginning (the data) [50][51][52]. Nowadays, CI models, have been commonly applied to diverse transportation challenges, partially owing to the fact that they are very generic, exact and traditional mathematical models that can readily simulate numerical model components.…”

Air demand modelling: overview and application to a developing regional airport

“…RUMs are a family of behavioural models trying to simulate user behaviour starting from some mathematical hypotheses. Recently, other paradigms have been proposed to understand user preferences, by using Neural Networks (NN) and fuzzy-NN approaches [32,33,34]. However, NN do not allow the explicit values of the parameters to be computed, so the interpretation of the model in terms of elasticity values, parameter ratios and so on cannot be obtained.…”

Artificial Intelligence in Transportation: Information for Application

“…However, agents can use any advanced computing technique that facilitates learning, including artificial NNs (ANNs) and GAs. In fact, Sadek et al (2003) note that "CI [computational intelligence] is the study of the design of intelligent agents, in which an agent is regarded as something that acts in an environment. … Commonly used techniques to implement intelligent agents in CI include ANNs, fuzzy logic, KBS, CBR, and probabilistic reasoning (including genetic algorithms).…”