Capecitabine has been investigated in early breast cancer in several studies, but it was undefined that whether it could improve survival. To investigate whether the addition of capecitabine affected survival in patients with early breast cancer, a meta-analysis was conducted and overall survival (OS), disease-free survival (DFS), and toxicity were assessed. The PubMed, Embase databases and the Cochrane Central Register of Controlled Trials were searched for studies between January 2006 and April 2016. Hazard ratios (HRs) with their 95% confidence intervals (CIs), or data for calculating HRs with 95% CI were derived. Seven trials with 9097 patients, consisted of 4 adjuvant and 3 neoadjuvant studies, were included in this meta-analysis. Adding capecitabine showed no improvement in DFS (HR = 0.93; 95% CI, 0.85-1.02; P = 0.12), whereas a significant improvement in OS was observed (HR = 0.85; 95% CI, 0.75-0.96; P = 0.008). A sub-analysis of DFS showed that benefit of capecitabine derived from patients with triple negative subtype and with extensive axillary involvement. Safety profiles were consistent with the known side-effects of capecitabine, but more patients discontinued scheduled treatment in the capecitabine group. Combining capecitabine with standard (neo)adjuvant regimens in early breast cancer demonstrated a significantly superior OS, and indicated DFS improvement in some subtypes with high risk of recurrence. Selection of subtypes was a key to identify patients who might gain survival benefit from capecitabine.

Feature selection is one of key technologies for fault diagnosis. Especially for high dimensional data, Feature selection can not only find the feature subset with sufficient information, but also improve the classification accuracy and efficiency. In order to decrease the number of diagnosis parameter in fault diagnosis of Liquid-propellant Rocket Engine, the paper proposes one feature selection method based on improved particle swarm optimization, the method applies the quantum evolution thoughts to PSO. The particle is restricted in the range from -π/2 to 0, so the particle can correspond to the quantum angle. The parameter optimization function is designed. The improved algorithm can decrease the number of parameter in fault diagnosis of Liquid-propellant Rocket Engine from 25 to 6.

In order to solve the problem of knowledge acquisition in equipment fault diagnosis,the paper introduces a method based on improved particle swarm optimization. Firstly the paper transforms the nonlinear equations which describe the system into optimization problem with constriction. Since the equation is nonlinear and multidimensional ,standard particle swarm cant solve the problem due to the weakness of premature. So one improved particle swarm optimization is proposed. During the evolution, density evaluation, clone and mutation operator is proposed under the thought of immunity. The results of simulation show that the immune particle swarm optimization can simulate effectively and acquire the system knowledge.