The variable sampling rate (VSR) schemes for detecting the shift in process mean have been extensively analyzed; however, adding the VSR feature to the control charts for monitoring process dispersion has not been thoroughly investigated. In this research, a novel VSR control scheme, sequential exponentially weighted moving average inverse normal transformation (EWMA INT) at fixed times chart (called (SEIFT) chart), which integrates the sequential EWMA scheme at fix times with the INT statistic, is proposed to detect both the increase and decrease in process dispersion. Moreover, the sample size at each sampling time is also allowed to vary. The Markov chain method is used to evaluate the performance of this new control chart. Numerical analysis reveals that this SEIFT chart gives significant improvement on detection ability than the fixed sampling rate schemes. Compared with other control schemes, the good properties of the INT statistic makes this SEIFT chart easy to design and convenient to implement.
Process adjustment strategy is an important part of the process improvement methods. The feedback control technique is used to compensate for the deviation of the output, and it has been intensively investigated. For continuous improvement and proactive strategies, feedback control has a delay and thus is not the ideal solution. In this article, motivated by a realistic manufacturing example, we propose the periodic shift disturbance models and investigate the feedforward control application from a new disturbance decomposition framework. We combine feedforward control with feedback control for maintaining the stability of the process and delivering products at target values. Then, we evaluate the performance of different control strategies for various disturbance models by using the output mean square error criterion. Sensitivity analysis of these control methods is made on different model parameter spaces, and robustness analysis for both model parameter and model structure misspecifications is presented. Two simulated examples show that the proposed control strategies can significantly reduce the variation of an evolving disturbance process.
In this paper we study the problem of content-based image retrieval. In this problem, the most popular performance measure is the top precision measure, and the most important component of a retrieval system is the similarity function used to compare a query image against a database image. However, up to now, there is no existing similarity learning method proposed to optimize the top precision measure. To fill this gap, in this paper, we propose a novel similarity learning method to maximize the top precision measure. We model this problem as a minimization problem with an objective function as the combination of the losses of the relevant images ranked behind the top-ranked irrelevant image, and the squared Frobenius norm of the similarity function parameter. This minimization problem is solved as a quadratic programming problem. The experiments over two benchmark data sets show the advantages of the proposed method over other similarity learning methods when the top precision is used as the performance measure.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.