Breast cancer is a heterogeneous disease. To guide proper treatment decisions for each patient, robust prognostic biomarkers, which allow reliable prognosis prediction, are necessary. Gene feature selection based on microarray data is an approach to discover potential biomarkers systematically. However, standard pure-statistical feature selection approaches often fail to incorporate prior biological knowledge and select genes that lack biological insights. Besides, due to the high dimensionality and low sample size properties of microarray data, selecting robust gene features is an intrinsically challenging problem. We hence combined systems biology feature selection with ensemble learning in this study, aiming to select genes with biological insights and robust prognostic predictive power. Moreover, to capture breast cancer's complex molecular processes, we adopted a multi-gene approach to predict the prognosis status using deep learning classifiers. We found that all ensemble approaches could improve feature selection robustness, wherein the hybrid ensemble approach led to the most robust result. Among all prognosis prediction models, the bimodal deep neural network (DNN) achieved the highest test performance, further verified by survival analysis. In summary, this study demonstrated the potential of combining ensemble learning and bimodal DNN in guiding precision medicine.

Wireless sensor networks have been widely used in many areas, such as earthquake monitoring, building structure monitoring, and military surveillance. In this work, we focus on the wireless sensor network deployed in the battlefield, using random key predistribution scheme. Based on the node cloning attack, we proposed a new attack scheme, called compromised key redistribution attack, and discussed related attack scenarios. Furthermore, we have exposed that, when the overlapping factor of compromised key set is larger than 0.05, it is almost 90% that the number of distinct compromised keys is 10.5% of the original key pool. This result helps the adversary estimate the approximated size of original key pool by calculating the overlapping factor, thus calculate the probability that malicious nodes successfully establish malicious connections with legitimate nodes.