Abstract
The Ink Drop Spread (IDS) method is a machine learning technique. This method divides a multi-input-single-output (MISO) target system into multiple single-input-single-output (SISO) systems, and models the each SISO system by plotting the input/output data. The IDS method combines the modeling results of each SISO system to learn the target. It is important for the IDS method to decide appropriate partitions of the target system in order to accurately learn the target. According to the existing research, the IDS method achieves the high accuracy for the binary class classiffication. Therefore, we apply the IDS method to the multi class classiffication. However, the existing partitioning methods have the problem that they are likely to generate too many partitions and thus require a long processing time. In this paper, we propose a new partitioning method for the IDS method which divides the input domains by considering the relationship between inputs, and apply the IDS method to the multi class classiffication.
