Search

IoT devices collect time-series traffic data, which is stochastic and complex in nature. Traffic flow prediction is a thorny task using this kind of data. A smart traffic congestion prediction system is a need of sustainable and economical smart cities. An intelligent traffic congestion prediction model using Seasonal Auto-Regressive Integrated Moving Average (SARIMA) and Bidirectional Long Short-Term Memory (Bi-LSTM) is presented in this study. The novelty of this model is that the proposed model is hybridized using a Back Propagation Neural Network (BPNN). Instead of traditionally presuming the relationship of forecasted results of the SARIMA and Bi-LSTM model as a linear relationship, this model uses BPNN to discover the unknown function to establish a relation between the forecasted values. This model uses SARIMA to handle linear components and Bi-LSTM to handle non-linear components of the Big IoT time-series dataset. The "CityPulse EU FP7 project" is a freely available dataset used in this study. This hybrid univariate model is compared with the single ARIMA, single LSTM, and existing traffic prediction models using MAE, MSE, RMSE, and MAPE as evaluation indicators. This model provides the lowest values of MAE, MSE, RMSE, and MAPE as 0.499, 0.337, 0.58, and 0.03, respectively. The proposed model can help to predict the vehicle count on the road, which in turn, can enhance the quality of life for citizens living in smart cities. [ABSTRACT FROM AUTHOR]

In this article, we determine the integral transforms of several two-boundary functionals for a difference of a compound Poisson process and a compound renewal process. Another part of the article is devoted to studying the above-mentioned process reflected at its infimum. We use the results obtained to study a G δ|M ϰ|1|B system with batch arrivals and finite buffer in the case when δ∼ge( λ). We derive the distributions of the main characteristics of the queuing system, such as the busy period, the time of the first loss of a customer, the number of customers in the system, the virtual waiting time in transient and stationary regimes. The advantage is that these results are given in a closed form, namely, in terms of the resolvent sequences of the process. [ABSTRACT FROM AUTHOR]

In this article we determine the Laplace transforms of the one-boundary characteristics and the distribution of the number of intersections of a fixed interval by a difference of a compound Poisson process and a compound renewal process. The results obtained are applied for a particular case of this process, namely, for the difference of the compound Poisson process and the renewal process whose jumps are geometrically distributed. The advantage is that these results are in a closed form, in terms of resolvent sequences of the process. In this case, under certain assumptions, we find the limit distributions of the one-boundary and two-boundary characteristics of the process. In addition, we prove the weak convergence of these distributions to the corresponding distributions of a symmetric Wiener process. [ABSTRACT FROM AUTHOR]

A two-sided exit problem is solved for a difference of a compound Poisson process and a compound renewal process. The Laplace transforms of the joint distribution of the first exit time, the value of the overshoot, and the value of a linear component at this instant are determined. The results obtained are applied to solve the two-sided exit problem for a particular case of this process, namely, the difference of the compound Poisson process and the renewal process whose jumps are geometrically distributed. The advantage is that these results are in a closed form, in terms of resolvent sequences of the process. [ABSTRACT FROM AUTHOR]