Pawan Lingras

Researchers have modelled existing hyperlink structure using graph theory. Such graph theoretical models have been useful for efficient Web navigation, especially for designing Web crawlers and search engines. This paper describes how sequence analysis of Web page accesses can be used to create weighted directed graphs. The information contained in such graphs can be used to improve the Web surfing experience. The paper proposes a concept of neighbourhood modelled after neighbourhood systems and rough sets to evaluate the effectiveness of navigation provided by a given hyperlink structure and Web usage data. Furthermore, a modification of the minimum spanning tree algorithm is used to create a hyperlink structure that provides optimal navigation.

Hyperlink structure of a Web site can be improved based on the Web usage information. Creating adaptive Web sites based on Web usage mining is receiving increasing interest from the researchers. It is important to develop theoretical frameworks for such a research. This paper discusses how neighbourhood sets can be a useful framework for analyzing Web access sequences.

Complexity of rules created by support vector machine (SVM) based multiclassifiers is an important issue in adopting these classifiers. Recently, we have shown how traditional SVMs can be represented using interval or rough sets. We have also extended the rough SVMs to multiclassification using both the 1-v-r and 1-v-1 approaches. In this paper, we describe an algorithmic implementation of the previously proposed mathematical formulation for 1-v-r approach. Analysis of the time requirements shows that the proposed classifier has a competitive linear time requirement. The approach presented here also will also help practitioners simplify the rules used in the classification process

Research for advanced traveler information systems (ATIS) has been focused on urban roads. However, research for short-term traffic prediction on all categories of highways is needed, as highway agencies expect to implement intelligent transportation systems across their jurisdictions. In this study, genetic algorithms were used to design time delay neural network (TDNN) models as well as locally weighted regression models to predict short-term traffic for six rural roads from Alberta, Canada. These roads are from various trip-pattern groups and functional classes. Refined TDNN models developed in this study can limit most average errors less than 10% for all study roads. Refined regression models show even higher accuracy. Average errors for the refined regression models are less than 2% for roads with stable patterns. Even for roads with unstable patterns, average errors are below 4%, and the 95th percentile errors are less than 7%. It is believed that such accurate predictions would be useful for highway agencies to implement statewide ATIS.

Estimating missing values is known as data imputation. The proper imputation of missing values of permanent traffic counts (PTCs) could result in significant cost savings for highway agencies in their traffic data programs. However, little research has been done on missing values and only limited research has used factor or time series analysis models for predicting them. Moreover, studies of the effect of the imputations on traffic parameters estimations are not available. This study used factor models, genetically designed neural network and regression models, and autoregressive integrated moving average (ARIMA) models to update pseudo‐missing values of six PTCs from Alberta, Canada. The influences of these imputations on the estimations of annual average daily traffic (AADT) and design hourly volume (DHV) were studied. It was found that simple models usually resulted in large AADT and DHV estimation errors. As models were refined, resulting estimations for individual missing hourly volumes significantly improved. Usually these models provided highly accurate AADT and DHV estimations.