Search

Short-term traffic flow prediction is an important basis of intelligent transportation systems. Its accuracy directly affects the performance of traffic control and induction. To improve prediction accuracy, in this paper, a traffic flow prediction model is proposed by combining hierarchical agglomerative clustering (HAC), standardized Euclidean distance (SED), and a long short-term memory network (LSTM). The proposed model is called the CHS-LSTM model. In this model, HAC is used to carry out cluster analysis on the original traffic flow data sample set of target detection sections. Based on the results of cluster analysis, traffic flow data are divided into several categories. For different categories of traffic flow, SED is used to calculate the spatial correlation of the road network where the target sections are located, and the K sections most relevant to the target detection sections are used in the construction of an input data matrix for LSTM. The prediction result with the minimum root-mean-square error is regarded as the final prediction result. The electronic toll collection data of Taiwan are used as the fundamental data in this paper to verify the performance and effectiveness of the CHS-LSTM model. The experimental results indicate that the CHS-LSTM model can effectively improve the prediction accuracy of LSTM. Moreover, compared with well-known models generally used for predicting the intensity of traffic flow, our proposed model also shows its superiority. [ABSTRACT FROM AUTHOR]

The concentrations of 56 volatile organic hydrocarbons (VOCs) were measured simultaneously in the southbound bore, the northbound bore and the exhaust air shafts of the Hsuehshan tunnel near Yilan, Taiwan during 2007 and 2008. A total of 60 integrated air samples were collected using stainless steel canisters and analyzed using GC/FID and GC/MS. The highest temperature and lowest relative humidity were observed at the exit of the tunnel owing to the accumulation in the tunnel of waste heat that was exhausted from vehicles. The five most abundant species in all samples were ethylene, acetylene, isopentane, propylene, and toluene. The exit/entrance ratios of total non-methane hydrocarbon (NMHC) concentration were 7.8 and 4.8 for the southbound and northbound bores, respectively. Furthermore, the most abundant species of emission rate (ER) is toluene (21.93-42.89 mg s), followed by isopentane, ethylene, propylene and 1-butene, with ER ranging from 2.50 to 9.31 mg s for the three shafts. The ozone formation potential (OFP)/total NMHC ratios in three exhaust air shafts show that the reactivities of these emissions are similar to those of vehicle emissions. [ABSTRACT FROM AUTHOR]

A river-dredging project has been undertaken in Nantou, Taiwan. A large number of diesel vehicles carrying gravel and sand shuttle back and forth on the main roads. Ten stations along major thoroughfares were selected as the exposure sites for testing, while a small village located about 9 km from a main traffic route was selected as the control site. Levels of household dust loading at the exposure sites (60.3 mg/m) were significantly higher than those at the control site (38.2 mg/m). The loading (μg/m) of t-PAHs (total polycyclic aromatic hydrocarbons) in the household dust at the exposure sites was significantly higher ( P < 0.05) than was the case at the control site. The diagnostic ratios of PAHs showed that diesel emissions were the dominant source of PAHs at the exposure sites. The lack of a significant correlation between the concentrations of Fe and t-PAHs suggested that the t-PAHs in household dust might come from diverse sources. However, a significant correlation ( P = 0.003) between the concentrations of Mo and t-PAHs implied that the most of the t-PAHs in the household dust might have resulted from diesel emissions. The lifetime cancer risks of BaP from household dust exposure were markedly higher than those resulting from inhalation exposure. [ABSTRACT FROM AUTHOR]