Abstract The classical uncertainty principles deal with functions on abelian groups. In this paper, we discuss the uncertainty principles for finite index subfactors which include the cases for finite groups and finite dimensional Kac algebras. We prove the Hausdorff-Young inequality, Young’s inequality, the Hirschman-Beckner uncertainty principle, the Donoho-Stark uncertainty principle. We cha...

We show that the model-calibration estimator for the finite population mean, which was proposed by Wu & Sitter (2001) through an intuitive argument, is optimal among a class of calibration estimators. We also present optimal calibration estimators for the finite population distribution function, the population variance, the variance of a linear estimator and other quadratic finite population fu...

̄ Although a number of testing methods (Myers 1979) (Suwa, Scott, & Shortliffe 1982) (Nguyen et 1987) (Ould & Unwin 1987) (Tsai & Zualkernan 1990) (Gupta 1991) (Tsai, Zualkernan, & Kirani 1992a) have been proposed for testing expert systems, recent studies (Zualkernan, Tsai, & Kirani 1992) (Tsai, Sirani, & Zualkernan 1992b) (Tsai, rani, & Zualkernan 1993) suggest that conventional testing method...

Methods of damage development analyses for various types of composite materials such as 3-D woven composite have not been established sufficiently because it is quite difficult to simulate the failure propagation. A FEM simulation of failure process of 3-D composite was executed by Mibayashi including the thermal residual stresses after the curing process, and the deformations and stresses calc...

We propose to train trading systems by optimizing financial objective functions via reinforcement learning. The performance functions that we consider as value functions are profit or wealth, the Sharpe ratio and our recently proposed differential Sharpe ratio for online learning. In Moody & Wu (1997), we presented empirical results in controlled experiments that demonstrated the advantages of ...

In many types of information systems, users face an implicit tradeoff between disclosing personal information and receiving benefits, such as discounts by an electronic commerce service that requires users to divulge some personal information. While these benefits are relatively measurable, the value of privacy involved in disclosing the information is much less tangible, making it hard to desi...

We study substructure in X-ray clusters of galaxies by application of a set of statistics, the power ratios of Buote & Tsai (1995), to a simulated cluster and in the context of a simple analytic model for merger events. The simulation involves a newly developed code for performing high resolution gravity and gas dynamics simulations in cosmological volumes. Thesis Supervisor: Edmund Bertschinge...

Thanks to Christopher Gibbons and C. J. Lee for help with the simulation code, model validation, and data management. Thanks to Wenpin Tsai and three anonymous reviewers whose input significantly improved this article.

In this paper, the issue of balance pattern of the interaction columns of a symmetrical design is considered according to orthogonal components system. The minimum interaction unbalance criterion is proposed for ranking and comparing s-level factorial designs, where s is any a prime or a prime power. It is further showed that the interaction unbalance pattern is just the generalized wordlength ...

The paper presents experimental characterization and theoretical predictions of elastic failure properties continuous carbon fiber reinforced silicon carbide (C/C-SiC) composite fabricated by Liquid Silicon Infiltration (LSI). Its mechanical were determined under uniaxial tensile, compression, pure shear loads in two sets principal coordinate systems, 0°–90° ±45°, respectively. measured the sys...