• Publications
  • Influence
A Novel Intrusion Detection Model for a Massive Network Using Convolutional Neural Networks
TLDR
This paper proposes a novel network intrusion detection model utilizing convolutional neural networks (CNNs), which uses CNN to select traffic features from raw data set automatically, and sets the cost function weight coefficient of each class based on its numbers to solve the imbalanced data set problem.
Design and Implementation of an SM2-Based Security Authentication Scheme With the Key Agreement for Smart Grid Communications
TLDR
A novel authentication scheme is proposed that addresses cyber-attacks using a minimal number of computations and is implemented based on mutual authentication as well as an improved SM2-based key agreement and validates the security of the approach based on the lowest possible communication and computational costs.
An Efficient ECC-Based CP-ABE Scheme for Power IoT
TLDR
A novel CP-ABE scheme based on elliptic curve cryptography (ECC) is proposed, which replaces the bilinear pairing operation with simple scalar multiplication and outsources most of the decryption work to edge devices and solves the performance bottleneck of having a single authority.
The Research and Realization about Question Answer System based on Natural Language Processing
TLDR
This thesis dissertated mainly the denotation of knowledge-information based on semantic network in QAS, the stochastic syntax-parse model named LSF ofknowledge-information in Qas, the structure and constitution of QAS and the LSF model parameters were exercised.
SSD-MSN: An Improved Multi-Scale Object Detection Network Based on SSD
TLDR
An improved multi-scale object detection network based on single shot multibox detector (SSD) is proposed, and the network is named as SSD-MSN, which achieves state-of-the-art detection performance and improves the multi- scale object detection performance effectively.
Fault Forecast and Diagnosis of Steam Turbine Based on Fuzzy Rough Set Theory
TLDR
This paper introduced rough sets data mining method to take potential diagnosis rule from the fault diagnosis decision-making table of steam turbine, and these rules can offer effective fault diagnosis service for steam turbine.
A Combination Framework for Semantic Based Query Across Multiple Ontologies
TLDR
This paper proposes a combination framework based on effective and scalable ontology interoperability for high-quality query answering and puts forward a specifical process to substantiate the combination approach.
Multi-agent Coordination Based on Semantic Approximation
Within multi-agent systems, it is almost impossible for multiple Web agents to completely share a same semantic vocabulary. Because of incomplete information and ontological heterogeneity, an agent
Semantic Query Based on Context Approximation of Ontology Structure
TLDR
The experimental results show that the approach presented is efficient to semantic queries based on distributed environments and a ranking strategy based on ontology context approximation is proposed.
...
...