Asphaltic concrete mixtures are among the most common construction materials for the pavement of roads. As a multi-phase composite mixture with randomly distributed aggregates inside the mastic part, the mechanical properties of such materials can be influenced by different factors. Cracking and induced fracture is among the common degradation and failure modes in these construction mixtures that often takes place in cold regions. In this research, the effects of some influencing parameters including temperature, air void percentage and loading rate are investigated experimentally on the fracture toughness (KIc) and work of fracture (WIc) of hot mix asphalt material. Edge notched semi-circular bend (SCB) specimen was employed to conduct mode I fracture experiments. The thickness of SCB samples were considered as variable and the HMA mixtures were tested with two SCB thicknesses of 30 and 60 mm. The experimental results showed that both fracture toughness and fracture work are increased by increasing the thickness. However, the effect of thickness on the fracture work was much more significant than the KIc value. Also, the fracture and cracking resistance parameters were increased by decreasing the temperature and air void content. Both KIc and WIc values were also increased by increasing the loading rate in the investigated range of 1 to 8 mm/min. The most influencing parameters on the change of fracture resistance parameters were the temperature, loading rate, air void content and thickness, respectively.

Providing recommendations in cold start situations is one of the most challenging problems for collaborative filtering based recommender systems (RSs). Although user social context information has largely contributed to the cold start problem, most of the RSs still suffer from the lack of initial social links for newcomers. For this study, we are going to address this issue using a proposed user similarity detection engine (USDE). Utilizing users’ personal smart devices enables the proposed USDE to automatically extract real-world social interactions between users. Moreover, the proposed USDE uses user clustering algorithm that includes contextual information for identifying similar users based on their profiles. The dynamically updated contextual information for the user profiles helps with user similarity clustering and provides more personalized recommendations. The proposed RS is evaluated using movie recommendations as a case study. The results show that the proposed RS can improve the accuracy and personalization level of recommendations as compared to two other widely applied collaborative filtering RSs. In addition, the performance of the USDE is evaluated in different scenarios. The conducted experimental results on USDE show that the proposed USDE outperforms widely applied similarity measures in cold start and data sparsity situations.