Highway Capacity Manual改訂の動向--テイラ-教授の講演より

Neural networks have been extensively applied to short-term traffic prediction in the past years. This study proposes a novel architecture of neural networks, Long Short-Term Neural Network (LSTM NN), to capture nonlinear traffic dynamic in an effective manner. The LSTM NN can overcome the issue of back-propagated error decay through memory blocks, and thus exhibits the superior capability for time series prediction with long temporal dependency. In addition, the LSTM NN can automatically determine the optimal time lags. To validate the effectiveness of LSTM NN, travel speed data from traffic microwave detectors in Beijing are used for model training and testing. A comparison with different topologies of dynamic neural networks as well as other prevailing parametric and nonparametric algorithms suggests that LSTM NN can achieve the best prediction performance in terms of both accuracy and stability.

Long short-term memory neural network for traffic speed prediction using remote microwave sensor data

This study examined the effects of land use and attitudinal characteristics on travel behavior for five diverse San Francisco Bay Area neighborhoods. First, socio-economic and neighborhood characteristics were regressed against number and proportion of trips by various modes. The best models for each measure of travel behavior confirmed that neighborhood characteristics add significant explanatory power when socio-economic differences are controlled for. Specifically, measures of residential density, public transit accessibility, mixed land use, and the presence of sidewalks are significantly associated with trip generation by mode and modal split. Second, 39 attitude statements relating to urban life were factor analyzed into eight factors: pro-environment, pro-transit, suburbanite, automotive mobility, time pressure, urban villager, TCM, and workaholic. Scores on these factors were introduced into the six best models discussed above. The relative contributions of the socio-economic, neighborhood, and attitudinal blocks of variables were assessed. While each block of variables offers some significant explanatory power to the models, the attitudinal variables explained the highest proportion of the variation in the data. The finding that attitudes are more strongly associated with travel than are land use characteristics suggests that land use policies promoting higher densities and mixtures may not alter travel demand materially unless residents' attitudes are also changed.

A Micro-Analysis of Land Use and Travel in Five Neighborhoods in the San Francisco Bay Area

A micro-analysis of land use and travel in five neighborhoods in the San Francisco Bay Area

This paper contests the conventional wisdom that travel is a derived demand, at least as an absolute. Rather, we suggest that under some circumstances, travel is desired for its own sake. We discuss the phenomenon of undirected travel – cases in which travel is not a byproduct of the activity but itself constitutes the activity. The same reasons why people enjoy undirected travel (a sense of speed, motion, control, enjoyment of beauty) may motivate them to undertake excess travel even in the context of mandatory or maintenance trips. One characteristic of undirected travel is that the destination is ancillary to the travel rather than the converse which is usually assumed. We argue that the destination may be to some degree ancillary more often than is realized. Measuring a positive affinity for travel is complex: in self-reports of attitudes toward travel, respondents are likely to confound their utility for the activities conducted at the destination, and for activities conducted while traveling, with their utility for traveling itself. Despite this measurement challenge, preliminary empirical results from a study of more than 1900 residents of the San Francisco Bay Area provide suggestive evidence for a positive utility for travel, and for a desired travel time budget (TTB). The issues raised here have clear policy implications: the way people will react to policies intended to reduce vehicle travel will depend in part on the relative weights they assign to the three components of a utility for travel. Improving our forecasts of travel behavior may require viewing travel literally as a “good” as well as a “bad” (disutility).

/pdf/how-derived-is-the-demand-for-travel-some-conceptual-and-4bv6ffijpm.pdf

How derived is the demand for travel? some conceptual and measurement considerations

Contents: Transportation Modes. Vehicle Motion, Human Factors, Geometric and Pavement Design. Vehicular Flow Models. Capacity Analysis. Flow Interruptions. Urban Transportation. Transportation Planning. Sequential Demand-forecasting Models. Traffic Impact and Parking Studies. Air Quality, Noise and Energy Impacts. Evaluation and Choice.

Transportation engineering and planning

The analyses conducted in this research were based on three methodologies for the field measurement of saturation headways. The first method (MI), the one on which most past studies were based, measured the characteristics of Vehicles 4 to 12 in a standing queue. M2, the method found in the Highway Capacity Manual (HCM), counted all vehicles in a standing queue, regardless of queue length. M3 included arrivals that joined the standing queue as long as vehicles were up to 140 ft from the stop line. This study focused on one approach of a high-design intersection with heavy, random arrivals. The large number of observations and the practically ideal traffic conditions enabled the acquisition of several statistically significant results on saturation flow (s), start-up lost time (SULT), and start-up response time (SRT): (a) when long queues are present, the typical field measurement of s based on the first 12 vehicles is an overestimate of s for through vehicles and an underestimate of s for protected left-t...

Detailed observations of saturation headways and start-up lost times

Investigation of driver injury severities in rural single-vehicle crashes under rain conditions using mixed logit and latent class models.

While decision makers support the promotion of advanced vehicle types, and incentives are provided to consumers to own and use cleaner vehicles, policies barely rely on the life cycle impacts of transportation vehicles. The increasing number of alternative fuel vehicles urges policy makers to consider life cycle impacts and support dynamic policies to benefit users of cleaner vehicles. To improve the effectiveness of transportation policies a life cycle cost method is created that responds to various vehicle fuels and technologies. A method is developed that integrates indirect costs (externalities), including emissions (i.e., global and local air pollution) and time losses with direct total cost of ownership. Life cycle emissions and time losses are converted into costs for three representative urban light duty vehicles: internal combustion, hybrid and electric vehicle. The results, which are based on vehicle technology characteristics and transportation impacts on environment, facilitate vehicle comparisons and support policy making in transportation.

Total cost of ownership and externalities of conventional, hybrid and electric vehicle

A methodology that quantifies potential conflicts between left-turning vehicles and opposing through vehicles and pedestrians is presented. The methodology was based on and designed to be compatible with the Highway Capacity Manual 2000. A model was developed to combine delay and safety to get a comprehensive level-of-service indicator, the delay and safety index (DS). A case study of two intersections shows that if potential conflict is not considered, the signal timing plan with permitted left turns delivers a better level of service than that with protected left turns. However, if potential conflict is considered, the level of service under protected left-turn phasing is better than that under permitted left-turn phasing, according to the DS, when the safety weight factors exceed a certain value. The proposed method models the trade-off between safety and efficiency explicitly and considers both vehicle-to-vehicle and vehicle-to-pedestrian conflicts associated with left turns.

Panos D. Prevedouros

Papers

Transportation engineering and planning

Detailed observations of saturation headways and start-up lost times

Investigation of driver injury severities in rural single-vehicle crashes under rain conditions using mixed logit and latent class models.

Total cost of ownership and externalities of conventional, hybrid and electric vehicle

Signalized Intersection Level of Service Incorporating Safety Risk