Abstract With the rapid increase in urban population, traffic problems are becoming severe. Passenger flow forecasting is critical to improving ability of buses meet travel needs residents and alleviating pressure. However, factors affecting passenger have complex non-linear characteristics, which creates a bottleneck prediction. Deep learning models CNN, LSTM, BISTM gradually emerging attentio...

Compositional data are vectors typically representing proportions of a whole, that is, those whose elements strictly positive and subject to unit-sum constraint. The increasing number fields where this type arises makes the development proper statistical tools an important issue. From regression perspective, whenever multivariate response is compositional vector, model accounts for constraint w...