Traffic Control and Transport Planning:: A Fuzzy Sets and Neural Networks Approach
Springer Science & Business Media, Dec 6, 2012 - Mathematics - 387 pages
When solving real-life engineering problems, linguistic information is often encountered that is frequently hard to quantify using "classical" mathematical techniques. This linguistic information represents subjective knowledge. Through the assumptions made by the analyst when forming the mathematical model, the linguistic information is often ignored. On the other hand, a wide range of traffic and transportation engineering parameters are characterized by uncertainty, subjectivity, imprecision, and ambiguity. Human operators, dispatchers, drivers, and passengers use this subjective knowledge or linguistic information on a daily basis when making decisions. Decisions about route choice, mode of transportation, most suitable departure time, or dispatching trucks are made by drivers, passengers, or dispatchers. In each case the decision maker is a human. The environment in which a human expert (human controller) makes decisions is most often complex, making it difficult to formulate a suitable mathematical model. Thus, the development of fuzzy logic systems seems justified in such situations. In certain situations we accept linguistic information much more easily than numerical information. In the same vein, we are perfectly capable of accepting approximate numerical values and making decisions based on them. In a great number of cases we use approximate numerical values exclusively. It should be emphasized that the subjective estimates of different traffic parameters differs from dispatcher to dispatcher, driver to driver, and passenger to passenger.
What people are saying - Write a review
We haven't found any reviews in the usual places.
Other editions - View all
aircraft airport approximate reasoning algorithm artificial neural networks ATIS backpropagation neural network Belgrade calculated capacity confidence intervals considered constraints corresponding costs defined demand depot determine developed dispatcher dispatcher’s drivers empty barges equal estimated travel example flight frequency foreign per diem functions of fuzzy fuzzy logic fuzzy rules fuzzy sets fuzzy systems fuzzy variable genetic algorithms grade of membership initial route input variable intersection ith pilot itinerary-fare class combinations large number Let us denote linear programming linguistic Mamdani medium membership functions neural network nodes number of barges number of empty number of passengers number of vehicles objective function obtained operator output variable Pancevo path perceived travel possible preference index pusher tugs random variable represents rotation route choice schedule shown in Figure simulated annealing solution solving stop Table tabu search Teodorovic and Kikuchi total number transportation request triangular fuzzy number trip type of vehicle vehicle routing