Probabilistic linguistic term sets (PLTSs) have many applications in the field of group decision making (GDM) because it includes both linguistic evaluation and probabilistic distribution when expressing preference information. However, the difference of information credibility in PLTSs is ignored, resulting in an inaccurate representation of decision information and unreasonable probability calculation. In this paper, we first consider the credibility of the information and propose the concept of Z-uncertain probabilistic linguistic variables (Z-UPLVs). Subsequently, the operational rules, normalization, distance and similarity measures, and comparison method of Z-UPLVs are introduced. Then, a probability calculation method based on credibility, an extended TOPSIS method, and some operators are proposed, which can be applied to emergency decision making in the Z-uncertain probabilistic linguistic (Z-UPL) environment. Finally, an emergency decision-making case of COVID-19 patients and comparative analysis illustrate the necessity and effectiveness of this method.

With the rapid development of mobile internet and location awareness techniques, massive spatio-temporal data is collected every day. Trajectory classification is critically important to many realworld applications such as human mobility understanding, urban planning, and intelligent transportation systems. A growing number of studies took advantage of the deep learning method to learn the high-level features of trajectory data for accurate estimation. However, some of these studies didn't interpret spatiotemporal information well, more importantly, they didn't fully utilize the high-level features extracted by neural networks. To overcome these drawbacks, this paper utilizes the proposed stop state and turn state to enhance spatial information, and at the same time, extracts stronger time information via Recurrence Plot (RP). Moreover, a novel Dual Convolutional neural networks based Supervised Autoencoder (Dual-CSA) is proposed by making the network aware of Predefined Class Centroids (PCC). Experiments conducted on two real-world datasets demonstrate that Dual-CSA can learn the high-level features well. The highest accuracy of the Geolife and SHL datasets are 89.475% and 89.602%, respectively, proving the superiority of our method.

No abstract

No abstract

No abstract