In this paper, we propose a new data-driven traffic state estimation model that estimates traffic flow based on average speed data only. The model is devised to implement a cost-effective framework that aggregates heterogeneous sources of vehicles' GPS and speed measurements to infer traffic flow using a novel triplet system called Conditionally Gaussian Observed Markov Fuzzy Switching Systems (CGOMFSM). Unlike its hard counterpart, CGOMFSM allows for a transient and gradual representation of traffic state transition and hence improves the estimation performance using a tractable scheme. The potential of the proposed model is illustrated through an application to the problem of traffic incident detection, particularly sporadic traffic congestion caused by unexpected road conditions. The performance of the proposed model is assessed using real traffic datasets from England highways. A simulation of traffic in the city of Salalah in Oman was conducted to evaluate the efficacy of the CGOMFSM-based traffic estimation and incident detection schemes with different penetration rates.

Public and shared transportation are among the sectors that have been severely affected by the COVID-19 pandemic, as they were perceived to be risky environments for disease transmission. Given that the end of the pandemic is not certain and in order to anticipate future pandemics, attempts have been made to design public and shared mobility systems that are pandemic resilient, avoiding the social and economic burdens of disrupting transportation services. In this paper, we introduce a new ridesharing form based on a novel concept called social bubble vanpooling (SBV) which tries to provide a trade-off between minimizing the risk of exposure of riders to communicable diseases, minimizing the operational costs of ridesharing operators, and providing public health authorities with full contact-tracing capability in ridesharing-related cases, if needed. We propose a new clustering approach where riders are pooled into social bubbles composed of people who are spatio-temporally connected and have similar vulnerability levels with respect to a communicable diseases. We used individual agent-based simulation experiments based on a data sample collected from a real population of riders, and we compared the performance of the proposed SBV with trip-based and long committed ridesharing models. We found that (1) enforcing contact tracing and quarantine is more effective in controlling the spread of the disease when the bubble-based ridesharing scheme is adopted as a commuting mode and (2) it is possible to sustain transportation services without compromising the efforts to mitigate the spread of the pandemic. The proposed ridesharing model appears to be a viable solution when the mobility of individuals is subject to tight restrictions to stop the spread of a communicable airborne disease (such as COVID-19). The flexibility of the model allows maintaining transportation services with profitable operational costs while upholding the precautionary measures to fight the pandemic.

Efficient and accurate prediction of traffic state plays a major role in the implementation of effective intelligent transportation systems. Therefore, traffic forecasting has been attracting a significant interest over the last decades striving to efficiently achieve highest accuracy of reliable prediction algorithms. In this paper, we present a novel prediction algorithm based on the Conditionally Gaussian Observed Markov Fuzzy Switching Model (CGOMFSM). The proposed scheme relies on a triplet representation of traffic encompassing traffic flow, speed and a switch process in order to infer parameters that govern the dynamics of traffic. This work investigates the impact of explicit incorporation of fuzzy switching processes on the accuracy of traffic data prediction. It aims to overcome the shortcomings of several existing prediction schemes in which the crisp modeling of traffic dynamics is hindering the effectiveness of prediction. The experimental study shows that the proposed algorithm yields satisfactory results for a prediction horizon up to 60 minutes for data collected at regular 15-minutes intervals.