Taxi arrival time prediction is an essential part of building intelligent transportation systems. Traditional arrival time estimation methods mainly rely on traffic map feature extraction, which can not model complex situations and nonlinear spatial
and temporal relationships. Therefore, we propose a Multi-View Spatial-Temporal Model (MVSTM) to capture the dependence of spatial-temporal and trajectory. Specifically, we use graph2vec to model the spatial view, dual-channel temporal module to model the trajectory view, and structural embedding to model the traffic semantics. Experiments on large-scale taxi trajectory data show that our approach is more effective than the novel method. The source code can be obtained from https://github.com/775269512/SIGSPATIAL-2021-GISCUP-4th-Solution.
For an integer $n>2$, a rank-$n$ matroid is called an $n$-spike if it consists of $n$ three-point lines through a common point such that, for all $kin{1, 2, ..., n - 1}$, the union of every set of $k$ of these lines has rank $k+1$. Spikes are very sp
ecial and important in matroid theory. In 2003 Wu found the exact numbers of $n$-spikes over fields with 2, 3, 4, 5, 7 elements, and the asymptotic values for larger finite fields. In this paper, we prove that, for each prime number $p$, a $GF(p$) representable $n$-spike $M$ is only representable on fields with characteristic $p$ provided that $n ge 2p-1$. Moreover, $M$ is uniquely representable over $GF(p)$.
