A Visibility Graph Averaging Aggregation Operator
This provides a domain-specific incremental improvement for time series aggregation in fields like finance.
The authors tackled the problem of data aggregation by proposing a new visibility graph averaging (VGA) operator that converts time series into graphs to determine weights, and demonstrated its advantage over classic operators by preserving time information and using more reasonable weights in an analysis of the TAIEX database.
The problem of aggregation is considerable importance in many disciplines. In this paper, a new type of operator called visibility graph averaging (VGA) aggregation operator is proposed. This proposed operator is based on the visibility graph which can convert a time series into a graph. The weights are obtained according to the importance of the data in the visibility graph. Finally, the VGA operator is used in the analysis of the TAIEX database to illustrate that it is practical and compared with the classic aggregation operators, it shows its advantage that it not only implements the aggregation of the data purely, but also conserves the time information, and meanwhile, the determination of the weights is more reasonable.