Reliability and Sharpness in Border Crossing Traffic Interval Prediction
نویسندگان
چکیده
Short-term traffic volume prediction models have been extensively studied in the past few decades. However, most of the previous studies only focus on single-value prediction. Considering the uncertain and chaotic nature of the transportation system, an accurate and reliable prediction interval with upper and lower bounds may be better than a single point value for transportation management. In this paper, we introduce a neural network model called Extreme Learning Machine (ELM) for interval prediction of short-term traffic volume and improve it with the heuristic particle swarm optimization algorithm (PSO). The hybrid PSOELM model can generate the prediction intervals under different confidence levels and guarantee the quality by minimizing a multi-objective function which considers two criteria reliability and interval sharpness. The PSO-ELM models are built based on an hourly traffic dataset and compared with ARMA and Kalman Filter models. The results show that ARMA models are the worst for all confidence levels, and the PSO-ELM models are comparable with Kalman Filter from the aspects of reliability and narrowness of the intervals, although the parameters of PSOELM are fixed once the training is done while Kalman Filter is updated in an on-line approach. Additionally, only the PSO-ELMs are able to produce intervals with coverage probabilities higher than or equal to the confidence levels. For the points outside of the prediction levels given by PSO-ELMs, they lie very close to the bounds.
منابع مشابه
Prediction and Display of Delay at Road Border Crossings
Land border crossings in North America that serve high volumes of automobile and truck traffic experience congestion and delay, resulting in adverse effects on level of service, transportation costs, commerce, tourism, and the environment. Although efforts have been underway to expedite the customs inspection process (without compromising security), improving the reliability of delay estimates ...
متن کاملInformal International Border Crossing, Refugee and Illegal Migrant Workers: Issue in Travel Medicine
متن کامل
Estimation of Wind Power Prediction Intervals Using Stochastic Methods and Artificial Intelligence Model Ensembles
This paper describes different methods to estimate the uncertainty of wind power forecasts in terms of prediction intervals. The single methods and an ensemble average model have been applied to shortest-term wind power forecasts (forecast horizon = 1, 2, 4 & 8 h) of 62 spatially distributed wind farms in Germany to obtain intervals with a nominal reliability of 90, 95 and 98 %. Furthermore the...
متن کاملAdaptive Online Traffic Flow Prediction Using Aggregated Neuro Fuzzy Approach
Short term prediction of traffic flow is one of the most essential elements of all proactive traffic control systems. Although various methodologies have been applied to forecast traffic parameters, several researchers have showed that compared with the individual methods, hybrid methods provide more accurate results . These results made the hybrid tools and approaches a more common method for ...
متن کاملRelationship between Pedestrians’ Speed, Density and Flow Rate of Crossings through Urban Intersections (Case Study: Rasht Metropolis) (RESEARCH NOTE)
Travels within the city are done in different ways, by vehicle or on foot. Thus, inevitably, a part of the travel is always done on foot. Since intersections as traffic nodes are determinant factor in transportation network capacity, any disruption in them leads to severe reduction in network capacity. Unfortunately, pedestrian behavior has received little attention in Iran. While this is a ver...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- CoRR
دوره abs/1711.04848 شماره
صفحات -
تاریخ انتشار 2017