Hidetoshi Matsuoka

An accurate modeling method utilizing application-specific statistical information and its application to SRAM yield estimation

In this paper, we propose a new model construction method utilizing application specific physical information and present its application to SRAM yield calculation. The physical information is extracted as statistical distributions from past simulation results automatically. Experimental results show our method achieves 700x speed up over non modeling method and more than 10x speed up over the conventional modeling method. It requires only 5.3 samples to model a fifth order full cross term polynomial with 21 coefficients and is free from over-fitting and singular matrix problem. This modeling method can be a general approach to create models with application specific physical information.

Prescription Prediction towards Computer-Assisted Diagnosis for Kampo Medicine

This paper focuses on the attempt to formulate the prescription prediction logic based on the medical data analysis towards the future computer-assisted-diagnosis for Kampo medicine. We constructed and evaluated prediction models for some frequently-used prescriptions using six kinds of machine learning algorithms including artificial neural network, multinomial logit, random forest, support vector machine, k-nearest neighbor, and decision tree. The possibility of prescription prediction and the necessary amount of data required for robust prediction are clarified.