Handling high level of censoring for endovascular aortic repair risk prediction

Feature selection is important in medical field for many reasons. However, selecting important variables is a difficult task with the presence of censoring that is a unique feature in survival data analysis. This paper proposed an approach to deal with the censoring problem in endovascular aortic repair survival data through Bayesian networks. It was merged and embedded with a hybrid feature selection process that combines cox's univariate analysis with machine learning approaches such as ensemble artificial neural networks to select the most relevant predictive variables. The proposed algorithm was compared with common survival variable selection approaches such as; least absolute shrinkage and selection operator LASSO, and Akaike information criterion AIC methods. The results showed that it was capable of dealing with high censoring in the datasets. Moreover, ensemble classifiers increased the area under the roc curves of the two datasets collected from two centers located in United Kingdom separately. Furthermore, ensembles constructed with center 1 enhanced the concordance index of center 2 prediction compared to the model built with a single network. Although the size of the final reduced model using the neural networks and its ensembles is greater than other methods, the model outperformed the others in both concordance index and sensitivity for center 2 prediction. This indicates the reduced model is more powerful for cross center prediction.

Highly sensitive refractive index sensor based on cascaded microfiber knots with Vernier effect

We propose and experimentally demonstrate a refractive index (RI) sensor based on cascaded microfiber knot resonators (CMKRs) with Vernier effect. Deriving from high proportional evanescent field of microfiber and spectrum magnification function of Vernier effect, the RI sensor shows high sensitivity as well as high detection resolution. By using the method named "Drawing-Knotting-Assembling (DKA)", a compact CMKRs is fabricated for experimental demonstration. With the assistance of Lorentz fitting algorithm on the transmission spectrum, sensitivity of 6523nm/RIU and detection resolution up to 1.533 x 10-7 RIU are obtained in the experiment which show good agreement with the numerical simulation. The proposed all-fiber RI sensor with high sensitivity, compact size and low cost can be widely used for chemical and biological detection, as well as the electronic/magnetic field measurement

A framework for measuring global Malmquist–Luenberger productivity index with CO2 emissions on Chinese manufacturing industries

China has achieved significant progress in terms of economic and social developments since implementation of reform and open policy in 1978. However, the rapid speed of economic growth in China has also resulted in high energy consumption and serious environmental problems, which hindering the sustainability of China's economic growth. This paper provides a framework for measuring eco-efficiency with CO2 emissions in Chinese manufacturing industries. We introduce a global Malmquist-Luenberger productivity index (GMLPI) that can handle undesirable factors within Data Envelopment Analysis (DEA). This study suggested after regulations imposed by the Chinese government, in the last stage of the analysis, i.e. during 2011–2012, the contemporaneous frontier shifts towards the global technology frontier in the direction of more desirable outputs and less undesirable outputs, i.e. producing less CO2 emissions, but the GMLPI drops slightly. This is an indication that the Chinese government needs to implement more policy regulations in order to maintain productivity index while reducing CO2 emissions.