A Bayesian analysis of the effect of estimating annual average daily traffic for heavy-duty trucks using training and validation data-sets

Tsapakis, Ioannis; Schneider, William H.; Nichols, Andrew P

doi:10.1080/03081060.2013.770944

Cited by 17 publications

(13 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Neto et al [1] utilized support vector machine for regression (SVR), by applying data-dependent parameters based on the distribution of the training data. Similarly, Tsapakis et al [16] designed twelve models based on regression and Bayesian analysis, using various parameters (such as roadway functional class, population density, and spatial location) collected from five regions in the state of Ohio, USA. Finally, other research work has addressed the feature selection problem for AADT prediction.…”

Section: Related Workmentioning

confidence: 99%

“…e processing time grows slowly with increasing bit-length, because more ciphertexts are needed to store the entire Bloom filter. Even in the worst-case configuration, when q � 2 16 and m � 16000, the cost is just 1.8 sec, which is long enough for the vehicle to compute a new Bloom filter before reaching the next RSU. It is also possible for the vehicle to precompute (offline) several Bloom filters before the start of a new trip.…”

Section: Computational Overheadmentioning

confidence: 99%

“…Here, the server application employs all sixteen CPU cores, so the cost is greatly reduced. With the worst-case configuration, i.e., q � 2 16 and m � 16000, the decryption cost for one Bloom filter is just 310 ms. On the other hand, Figure 17 depicts the processing time required at the server to estimate the traffic flow across N receivers, using equation (10). As we explained in Section 5, the cost grows exponentially with N, because it necessitates the enumeration of all combinations of i out of N elements, for i � 1 to N. is cost clearly limits the maximum path length N that can be supported, but Figure 17 shows that the cost is quite reasonable for N < 15.…”

Section: Computational Overheadmentioning

confidence: 99%

See 2 more Smart Citations

Privacy-Preserving Multipoint Traffic Flow Estimation for Road Networks

Bentafat

Rathore

Bakiras

2021

Security and Communication Networks

View full text Add to dashboard Cite

Intelligent transportation systems necessitate a fine-grained and accurate estimation of vehicular traffic flows across critical paths of the underlying road network. However, such statistics should be collected in a manner that does not disclose the trajectories of individual users. To this end, we introduce a privacy-preserving protocol that leverages roadside units (RSUs) to communicate with the passing vehicles, in order to construct encrypted Bloom filters stemming from random vehicle IDs that are chosen secretly by the individual vehicles. Each Bloom filter represents the set of vehicle IDs that contacted the RSU but may also be used to estimate the traffic flow between any number of RSUs. More precisely, we designed a probabilistic model that approximates multipoint traffic flows by estimating the number of common vehicles among a given set of RSUs. Through extensive simulation experiments, we demonstrate that our protocol is very accurate—with a minor deviation from the real traffic flow—and show that it reduces the estimation error by a large factor, when compared to the current state-of-the-art approaches. Furthermore, our implementation of the underlying cryptographic primitives illustrates the feasibility, practicality, and scalability of the system.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Computational Overheadmentioning

confidence: 99%

Section: Computational Overheadmentioning

confidence: 99%

See 1 more Smart Citation

Privacy-Preserving Multipoint Traffic Flow Estimation for Road Networks

Bentafat

Rathore

Bakiras

2021

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Gazis and Liu [ 9 ] considered the sharing error at two adjacent road links and developed an extended Kalman filter approach for traffic flow estimation. The Bayesian and Markov models rely on prior knowledge to obtain estimated parameters [ 10 , 11 , 12 ]; these models require substantial historical data as prior knowledge. In the context of big data, machine-learning-based methods have emerged.…”

Section: Introductionmentioning

confidence: 99%

Spatial Copula Model for Imputing Traffic Flow Data from Remote Microwave Sensors

Luan

et al. 2017

Sensors

View full text Add to dashboard Cite

Issues of missing data have become increasingly serious with the rapid increase in usage of traffic sensors. Analyses of the Beijing ring expressway have showed that up to 50% of microwave sensors pose missing values. The imputation of missing traffic data must be urgently solved although a precise solution that cannot be easily achieved due to the significant number of missing portions. In this study, copula-based models are proposed for the spatial interpolation of traffic flow from remote traffic microwave sensors. Most existing interpolation methods only rely on covariance functions to depict spatial correlation and are unsuitable for coping with anomalies due to Gaussian consumption. Copula theory overcomes this issue and provides a connection between the correlation function and the marginal distribution function of traffic flow. To validate copula-based models, a comparison with three kriging methods is conducted. Results indicate that copula-based models outperform kriging methods, especially on roads with irregular traffic patterns. Copula-based models demonstrate significant potential to impute missing data in large-scale transportation networks.

show abstract

“…Subsequent studies will therefore deal with the possible tools for maintaining the level of public transportation at its current level of 20-21% despite of decreasing tendencies, and how such measures can provide a financial return [7,8]. The most important issue in the case of goods transport is identifying the modes of transport that are worth developing in the interest of simultaneously attaining both emissions reduction and increases in cost efficiency without incurring additional costs for society, for example through the amortization of the road system at an increased rate [9,10]. It can be established based on previous analyses that the cost effectiveness of large investments within the sector is often questionable [11,12].…”

Section: Introductionmentioning

confidence: 99%

The cost benefit analysis of low-carbon transportation development opportunities for the 2020-2030 EU programming period

Fogarassy¹,

Horváth²,

Kovács³

2015

HAE

View full text Add to dashboard Cite

Within the European Union's climate policy, transportation qualifies as one of the most significant sectors since it is responsible for 20% of total GHG (greenhouse gas) emissions. In the 2005-2020 period, the EU is expected to emit a total of 90 MtCO2e. Although this figure qualifies as a 12% decrease in terms of total volume, 80% of it cannot be regarded as cost efficient; in fact, the majority of these emissions fall into the highest CO 2e avoidance cost category within the European Union. However, Hungary is in an exceptional situation, as the cheap potential for reducing emissions is significantly higher than the EU average. Hungary is presently one of the countries best performing its 2020 climate policy targets, since its GHG emissions resulting from past years' production is still far behind the "emission baseline" threshold defined on the basis of production in the 1980's. Due to slow and controversial development, Hungary's vehicle park will continue to show a significant dependency on fossil fuels (gasoline, diesel) in 2030. It should be noted that this situation could endanger the long term (2050) commitments for GHG reductions. The aim of the present study was to examine the environmental and financial effects of development projects that contribute to the restructuring of the transport sector and the attaining of climate policy targets as well as implementing these developments in the most cost effective manner possible.

show abstract

A Bayesian analysis of the effect of estimating annual average daily traffic for heavy-duty trucks using training and validation data-sets

Cited by 17 publications

References 14 publications

Privacy-Preserving Multipoint Traffic Flow Estimation for Road Networks

Privacy-Preserving Multipoint Traffic Flow Estimation for Road Networks

Spatial Copula Model for Imputing Traffic Flow Data from Remote Microwave Sensors

The cost benefit analysis of low-carbon transportation development opportunities for the 2020-2030 EU programming period

Contact Info

Product

Resources

About