Search

Due to globalization and rapid development, the demand for travel and congestion are increasing, stressing the road networks. Furthermore, road networks are subjected to planned and unplanned disruptions, and these disruptions affect the road network performance by either damaging its components, fluctuating the travel demand, or doing both at the same time. Thus, assessing the change in travel demand and travel patterns during such disruptions is essential. Conventionally, travel demand has been estimated using a household travel survey (HTS). However, the HTS is not feasible for disrupted conditions because of its large sample size requirement and time-consuming methodology. However, with the advent of crowdsourced data, new methodologies have been proposed for estimating the travel demand, but most of these studies have focused on estimating demand for a typical day and not disrupted scenarios. Moreover, data sources utilized till now have low sample sizes or are unavailable for developing countries. To bridge this gap, the current study utilizes an automated planning tool called Rapidex to estimate the travel demand and pattern change for a planned disruption, i.e., the 18th G20 Summit, Delhi, using crowdsourced travel time data from TomTom API. Upon comparing the results of travel demand and travel patterns of typical days with G20 days, it was observed that travel demand was lower during G20. Moreover, it was observed that the zones where railway stations, interstate bus terminals, and G20 activities were focused had higher generation and attraction share than typical days. Other zones within the regulated area had lower generation and attraction rates, which can be because of travel restrictions imposed in these zones. [ABSTRACT FROM AUTHOR]

A well developed and maintained highway infrastructure is essential for the economic and social prosperity of modern societies. Highway maintenance poses significant challenges pertaining to the ever-increasing ongoing traffic, insufficient budget allocations and lack of resources. Road potholes detection and timely repair is a major contributing factor to sustaining a safe and resilient critical road infrastructure. Current pothole detection methods require laborious manual inspection of roads and lack in terms of accuracy and inference speed. This paper proposes a novel application of Convolutional Neural Networks on accelerometer data for pothole detection. Data is collected using an iOS smartphone installed on the dashboard of a car, running a dedicated application. The experimental results show that the proposed CNN approach has a significant advantage over the existing solutions, with respect to accuracy and computational complexity in pothole detection. [ABSTRACT FROM AUTHOR]