Mario Cools

Assessing the Impact of Weather on Traffic Intensity

Abstract This paper focuses on the effect of weather conditions on daily traffic intensities (the number of cars passing a specific segment of a road). The main objective is to examination whether or not weather conditions uniformly alter daily traffic intensities in Belgium, or in other words whether or not road usage on a particular location determines the size of the impacts of various weather conditions. This general examination is a contribution that allows policymakers to assess the appropriateness of countrywide versus local traffic management strategies. In addition, a secondary goal of this paper is to validate findings in international literature within a Belgian context. To achieve these goals, the paper analyzes the effects of weather conditions on both upstream (toward a specific location) and downstream (away from a specific location) traffic intensities at three traffic count locations typified by a different road usage. Perhaps the most interesting results of this study for policymakers ar...

Changes in Travel Behavior in Response to Weather Conditions: Do Type of Weather and Trip Purpose Matter?

Weather can influence travel demand, traffic flow, and traffic safety. A hypothesis—the type of weather determined the likelihood of a change in travel behavior, and changes in travel behavior because of weather conditions depended on trip purpose—was assayed. A stated adaptation study was conducted in Flanders (the Dutch-speaking region of Belgium). A survey, completed by 586 respondents, was administered both on the Internet and as a traditional paper-and-pencil questionnaire. To ensure optimal correspondence between the survey sample composition and the Flemish population, observations in the sample were weighted. To test the main hypotheses, Pearson chi-square independence tests were performed. Results from both the descriptive analysis and the independence tests confirm that the type of weather matters and that changes in travel behavior in response to these weather conditions are highly dependent on trip purpose. This dependence of behavioral adjustments on trip purpose provides policy makers with a deeper understanding of how weather conditions affect traffic. Further generalizations of the findings are possible by shifting the scope toward revealed travel behavior. Triangulation of both stated and revealed travel behavior on the one hand and traffic intensities on the other hand is a key challenge for further research.

Annotating mobile phone location data with activity purposes using machine learning algorithms

Individual human travel patterns captured by mobile phone data have been quantitatively characterized by mathematical models, but the underlying activities which initiate the movement are still in a less-explored stage. As a result of the nature of how activity and related travel decisions are made in daily life, human activity-travel behavior exhibits a high degree of spatial and temporal regularities as well as sequential ordering. In this study, we investigate to what extent the behavioral routines could reveal the activities being performed at mobile phone call locations that are captured when users initiate or receive a voice call or message. Our exploration consists of four steps. First, we define a set of comprehensive temporal variables characterizing each call location. Feature selection techniques are then applied to choose the most effective variables in the second step. Next, a set of state-of-the-art machine learning algorithms including Support Vector Machines, Logistic Regression, Decision Trees and Random Forests are employed to build classification models. Alongside, an ensemble of the results of the above models is also tested. Finally, the inference performance is further enhanced by a post-processing algorithm. Using data collected from natural mobile phone communication patterns of 80 users over a period of more than one year, we evaluated our approach via a set of extensive experiments. Based on the ensemble of the models, we achieved prediction accuracy of 69.7%. Furthermore, using the post processing algorithm, the performance obtained a 7.6% improvement. The experiment results demonstrate the potential to annotate mobile phone locations based on the integration of data mining techniques with the characteristics of underlying activity-travel behavior, contributing towards the semantic comprehension and further application of the massive data.

Meteorological variation in daily travel behaviour: evidence from revealed preference data from the Netherlands

This study investigates the meteorological variation in revealed preference travel data. The main objective of this study is to investigate the impact of weather conditions on daily activity participation (trip motives) and daily modal choices in the Netherlands. To this end, data from the Dutch National Travel Household Survey of 2008 were matched to hourly weather data provided by the Royal Dutch Meteorological Institute and were complemented with thermal indices to indicate the level of thermal comfort and additional variables to indicate the seasonality of the weather conditions. Two multinomial logit–generalised estimation equations (MNL-GEE) models were constructed, one to assess the impact of weather conditions on trip motives and one to assess the effect of weather conditions on modal choice. The modelling results indicate that, depending on the travel attribute of concern, other factors might play a role. Nonetheless, the thermal component, as well as the aesthetical component and the physical component of weather play a significant role. Moreover, the parameter estimates indicate significant differences in the impact of weather conditions when different time scales are considered (e.g. daily versus hourly based). The fact that snow does not play any role at all was unexpected. This finding can be explained by the relatively low occurrence of this weather type in the study area. It is important to consider the effects of weather in travel demand modelling frameworks because this will help to achieve higher accuracy and more realistic traffic forecasts. These will in turn allow policy makers to make better long-term and short-term decisions to achieve various political goals, such as progress towards a sustainable transportation system. Further research in this respect should emphasise the role of weather conditions and activity-scheduling attributes.

Building a validation measure for activity-based transportation models based on mobile phone data

Abstract Activity-based micro-simulation transportation models typically predict 24-h activity-travel sequences for each individual in a study area. These sequences serve as a key input for travel demand analysis and forecasting in the region. However, despite their importance, the lack of a reliable benchmark to evaluate the generated sequences has hampered further development and application of the models. With the wide deployment of mobile phone devices today, we explore the possibility of using the travel behavioral information derived from mobile phone data to build such a validation measure. Our investigation consists of three steps. First, the daily trajectory of locations, where a user performed activities, is constructed from the mobile phone records. To account for the discrepancy between the stops revealed by the call data and the real location traces that the user has made, the daily trajectories are then transformed into actual travel sequences. Finally, all the derived sequences are classified into typical activity-travel patterns which, in combination with their relative frequencies, define an activity-travel profile. The established profile characterizes the current activity-travel behavior in the study area, and can thus be used as a benchmark for the assessment of the activity-based transportation models. By comparing the activity-travel profiles derived from the call data with statistics that stem from traditional activity-travel surveys, the validation potential is demonstrated. In addition, a sensitivity analysis is carried out to assess how the results are affected by the different parameter settings defined in the profiling process.

Investigating the Variability in Daily Traffic Counts Through Use of ARIMAX and SARIMAX Models: Assessing the Effect of Holidays on Two Site Locations

In this paper, daily traffic counts are explained and forecast by different modeling philosophies: an approach using autoregressive integrated moving average (ARIMA) models with explanatory variables (i.e., the ARIMAX model) and approaches using a seasonal autoregressive integrated moving average (SARIMA) model as well as a SARIMA model with explanatory variables (i.e., the SARIMAX model). Special emphasis is placed on the investigation of seasonality in daily traffic data and on the identification and comparison of holiday effects at different sites. To get insight into prior cyclic patterns in the daily traffic counts, spectral analysis provides the required framework to highlight periodicities in the data. The analyses use data from single inductive loop detectors, which were collected in 2003, 2004, and 2005. Four traffic count locations are investigated in this study: an upstream and a downstream traffic count site on a highway used extensively by commuters, and an upstream and a downstream traffic count site on a highway typically used for leisure travel. The different modeling techniques show that weekly cycles appear to determine the variation in daily traffic counts. The comparison between seasonal and holiday effects at different site locations reveals that both the ARIMAX and the SARIMAX modeling approaches are valid frameworks for identifying and quantifying possible influencing effects. The techniques yield the insight that holidays have a noticeable impact on highways extensively used by commuters, while having a more ambiguous impact on highways typically used for leisure travel. Future research challenges are the modeling of daily traffic counts on secondary roads and the simultaneous modeling of underlying reasons for travel and revealed traffic patterns.

Investigating Effect of Holidays on Daily Traffic Counts: Time Series Approach

Different modeling philosophies are explored to explain and to forecast daily traffic counts. The main objectives of this study are the analysis of the impact of holidays on daily traffic and the forecasting of future traffic counts. Data from single inductive-loop detectors, collected in 2003, 2004, and 2005, were used for the analysis. The different models investigated showed that the variation in daily traffic counts could be explained by weekly cycles. The Box-Tiao modeling approach was applied to quantify the effect of holidays on daily traffic. The results showed that traffic counts were significantly lower for holiday periods. When the different modeling techniques were compared with a large forecast horizon, Box-Tiao modeling clearly outperformed the other modeling strategies. Simultaneous modeling of both the underlying reasons of travel and the revealed traffic patterns certainly is a challenge for further research.

Characterizing activity sequences using profile Hidden Markov Models

Activity sequences extracted from travel diaries are characterized by pHMMs.The models quantify the probabilities of activities and their sequential order.They can be used for an improved understanding of activity-travel behavior.This method can be integrated into activity-based transportation model validation.It is widely applicable to analyze a group of any related but short sequences. In literature, activity sequences, generated from activity-travel diaries, have been analyzed and classified into clusters based on the composition and ordering of the activities using Sequence Alignment Methods (SAM). However, using these methods, only the frequent activities in each cluster are extracted and qualitatively described; the infrequent activities and their related travel episodes are disregarded. Thus, to quantify the occurrence probabilities of all the daily activities as well as their sequential orders, we develop a novel process to build multiple alignments of the sequences and subsequently derive profile Hidden Markov Models (pHMMs). This process consists of 4 major steps. First, activity sequences are clustered based on a pre-defined scheme. The frequent activities along with their sequential orders are then identified in each cluster, and they are subsequently used as a template to guide the construction of a multiple alignment of the cluster of sequences. Finally, a pHMM is employed to convert the multiple alignment into a position-specific scoring system, representing the probability of each frequent activity at each important position of the alignment as well as the probabilities of both insertion and deletion of infrequent activities.By applying the derived pHMMs to a set of activity-travel diaries collected in Belgium as well as a group of mobile phone call location data recorded in Switzerland, the potential and effectiveness of the models in capturing the sequential features of each cluster and distinguishing them from those of other clusters, are demonstrated. The proposed method can also be utilized to improve activity-based transportation model validation and travel survey designs. Furthermore, it offers a wide application in characterizing a group of any related sequences, particularly sequences varying in length and with a high frequency of short sequences that are typically present in human behavior.

Semantic Annotation of Global Positioning System Traces: Activity Type Inference

Because of the rapid development of technology, larger data sets on activity travel behavior have become available. These data sets often lack semantic interpretation. This lack of interpretation implies that annotation of activity type and transportation mode is necessary. This paper aims to infer activity types from Global Positioning System (GPS) traces by developing a decision tree–based model. The model considers only activity start times and activity durations. On the basis of the decision tree classification, a probability distribution and a point prediction model were constructed. The probability matrix described the probability of each activity type for each class (i.e., combination of activity start time and activity duration). In each class, the point prediction model selected the activity type that had the highest probability. Two types of data were collected in 2006 and 2007 in Flanders, Belgium (i.e., activity travel data and GPS data). The optimal classification tree constructed contained 18 leaves. Consequently, 18 if–then rules were derived. An accuracy of 74% was achieved when the tree was trained. The accuracy of the model for the validation set (72.5%) showed that overfitting was minimal. When the model was applied to the test set, the accuracy was almost 76%. The models indicated the importance of time information in the semantic enrichment process. This study contributes to future data collection in that it enables researchers to infer activity types directly from activity start time and duration information obtained from GPS data. Because no location information is needed, this research can be easily and readily applied to millions of individual agents.

Assessing the Quality of Origin–Destination Matrices Derived from Activity Travel Surveys: Results from a Monte Carlo Experiment

To support policy makers combating travel-related externalities, quality data are required for the design and management of transportation systems and policies. To this end, much money has been spent on collecting household- and person-based data. The main objective of this paper is to assess the quality of origin–destination (O-D) matrices derived from household activity travel surveys. To this purpose, a Monte Carlo experiment is set up to estimate the precision of O-D matrices given different sampling rates. The Belgian 2001 census data, containing work- and school-related travel information for all 10,296,350 residents, are used for the experiment. For different sampling rates, 2,000 random stratified samples are drawn. For each sample, three O-D matrices are composed: one at the municipality level, one at the district level, and one at the provincial level. The correspondence between the samples and the population is assessed by using the mean absolute percentage error (MAPE) and a censored version of the MAPE (MCAPE). The results show that no accurate O-D matrices can be derived directly from these surveys. Only when half of the population is queried is an acceptable O-D matrix obtained at the provincial level. Therefore, use of additional information to grasp better the behavioral realism underlying destination choices and collection of information about particular O-D pairs by means of vehicle intercept surveys are recommended. In addition, results suggest using the MCAPE next to traditional criteria to examine dissimilarities between different O-D matrices. An important avenue for further research is the investigation of the effect of sampling proportions on travel demand model outcomes.