User profiles representing users’ preferences and interests play an important role in many applications of personalized recommendation. With the rapid growth of social platforms, there is a critical need for efficient solutions to learn user profiles from the information they shared on social platforms so as to improve the quality of recommendation services. The problem of user profile learning is significantly challenging due to difficulty in handling data from multiple sources, in different formats and often associated with uncertainty. In this paper, we introduce an integrated approach that combines advanced Machine Learning techniques with evidential reasoning based on Dempster-Shafer theory of evidence for user profiling and recommendation. The developed methods for user profile learning and multi-criteria collaborative filtering are demonstrated with experimental results and analysis that show the effectiveness and practicality of the integrated approach. A proposal for extending multi-criteria recommendation systems by incorporating user profiles learned from different sources of data into the recommendation process so as to provide better recommendation capabilities is also highlighted.

For automated container terminals, the effective integrated scheduling of different kinds of equipment such as quay cranes (QCs), automated guided vehicles (AGVs), and yard cranes (YCs) is of great significance in reducing energy consumption and achieving sustainable development. Aiming at the joint scheduling of AGVs and YCs with consideration of conflict-free path planning for AGVs as well as capacity constraints on AGV-mate which is also called buffer bracket in blocks, a mixed integer programming model is established to minimize the energy consumption of AGVs and YCs for the given loading/unloading task. A solution method based on a novel bi-level genetic algorithm (BGA), in which the outer and the inner layer search the optimal dispatching strategy for QCs and YCs, respectively, is designed. The validity of the model and the algorithm is verified by simulation experiments, which take the Port of Qingdao as an example and the performance under different conflicting resolution strategies is compared. The results show that, for the given task, the proposed solution to conflict-free path and the schedule provided by the algorithm can complete the task with minimum energy consumption without loss of AGVs utilization, and the number of AGV-mates should be adjusted according to the task rather than keeping unchanged. Comparison results indicate that our proposed approach could efficiently find solutions within 6% optimality gaps. Energy consumption is dropped by an average of 15%.

Morning commute problem has always been concerned by researchers in transportation research field. For the bottleneck existing in the road network between home and school, this paper studies the household travel with different kinds of activities, i.e., home-school-home trip and home-school-workplace trip. Individuals just send their children to school and then go home, which is named school travel. Individuals need to send their children to school firstly and then go to work, which is named household travel. Firstly, according to the proportions of two types of travelers and school-work start time difference, the possible equilibrium cases are solved and the conditions for the occurrence of each case are revealed. Different from the traditional bottleneck model with a unique equilibrium traffic pattern, the mixed travel case has six possible equilibrium traffic patterns. Secondly, the cost of traveler is analyzed for all possible equilibrium traffic patterns. Result shows that equilibrium trip costs of two types of travelers are more sensitive to the number of travelers in that class than the number in another class in all possible equilibrium cases. Finally, the influence of school-work start time difference on the total travel cost is discussed. Result shows that the total system travel cost can be reduced by appropriately adjusting the difference of school-work start time.

Project management literature provides various approaches to organize project management. Simultaneously, several factors influence product development about its efficiency and effectiveness. This paper analyses the factors that affect product development and evaluates their integration level in project management concerning modern requirements imposed in a volatile, uncertain, complex, and ambiguous (VUCA) environment. It concludes by identifying undervalued influencing factors worth investigating in future research.

Social trust network (STN) and minimum cost consensus (MCC) models have been widely used to address consensus issues in multi-attribute group decision-making (MAGDM) problems with limited resources. However, most researchers have overlooked the decision maker ‘(DMs)’ confidence levels (CLs) and adjustment willingness implicit in their evaluations. To address these problems, this paper explores a confidence-based MCC model that considers DMs’ adjustment willingness in the STN. The proposed model includes several modifications to the traditional trust propagation and consensus optimization models. Firstly, the improved method for measuring CLs of DMs and the confidence-based normalization approach are defined, respectively. Secondly, the bounded trust propagation operator is proposed, which considers the credibility of mediators to complete the STN. Thirdly, the identification rules based on the consensus index and CL are defined, and the MCC model with personalized cost functions and acceptable adjustment thresholds is built to automatically generate adjustment values for non-consensus DMs. Finally, a model to identify the non-cooperative behavior at the element level is established and the hybrid MCC model with persuasion strategies is provided. Finally, a case study is processed to verify the applicability of the proposed model, and comparison and sensitivity analysis are conducted to highlight its benefits.