Motivated by the recently developed distillation approaches that aim to obtain small and fast-to-execute models, in this paper a novel Layer Selectivity Learning (LSL) framework is proposed for learning deep models. We firstly use an asymmetric dual-model learning framework, called Auxiliary Structure Learning (ASL), to train a small model with the help of a larger and well-trained model. Then, the intermediate layer selection scheme, called the Layer Selectivity Procedure (LSP), is exploited to determine the corresponding intermediate layers of source and target models. The LSP is achieved by two novel matrices, the layered inter-class Gram matrix and the inter-layered Gram matrix, to evaluate the diversity and discrimination of feature maps. The experimental results, demonstrated using three publicly available datasets, present the superior performance of model training using the LSL deep model learning framework.

Wireless sensor networks (WSNs) contain a large number of resource-constrained and energy-limited sensor nodes that are generally deployed in an open environment. Those sensor nodes communicate with each other or with a base station via wireless channels. Therefore, secure access control is an important issue in WSNs because sensor nodes are susceptible to various malicious attacks during the authentication and key establishment phase and the new node addition phase. In this study, we propose a new access control method based on elliptic curve cryptography and the chameleon hash function. This method addresses the security problems in the existing research. It also has additional advantages since it does not require time synchronization between communication nodes, nor does it require node verification tables. In addition to our proposal, the correctness, security, resistance to possible attacks, and the performance of the proposed method are analyzed and evaluated. The results of our study demonstrate that the proposed method has an outstanding performance and fulfills all the requirements for secure communication in WSNs.

No abstract

No abstract

No abstract