We present a new method for computing temporal aggregation based on dimension transformation. The novelty of our method lies in transforming the start time and end time of one-dimensional temporal tuples to two-dimensional data points and storing the points in a two-dimensional index. It then calculates temporal aggregates through a temporal join between the data in the index and the base intervals (defined as the intervals delimited by the start time or end time of the tuples). To enhance the performance, this Method calculates the aggregates by incrementally modifying the aggregates from that of the previous base interval without re-reading all tuples for the Current base interval. We further improve the efficiency with a new buffer page replacement technique that predicts the page access order within the index. We demonstrate the efficacy of our method through experiments.