-
Article
Rule-based adversarial sample generation for text classification
In Text Classification, modern neural networks have achieved great performance, but simultaneously, it is sensitive to adversarial examples. Existing studies usually use synonym replacement or token insertion ...
-
Article
GeSe: Generalized static embedding
In natural language processing, most text representation methods can be generally categorized into two paradigms: static and dynamic. Both have distinctive advantages, which are reflected in the cost of traini...
-
Article
Self attention mechanism of bidirectional information enhancement
Self attention mechanism is widely used in relation extraction, emotion classification and other tasks. It can extract a wide range of relevance information in the text. The attention mode of the existing self...
-
Article
A message transmission scheduling algorithm based on time-domain interference alignment in UWANs
High propagation delays cause message collisions at intended nodes, which seriously affects network performance. In this paper, we consider the transmission scheduling problem of messages with specified transm...
-
Article
Evolutionary selection for regression test cases based on diversity
Although there are various studies related to selecting test cases, few are available for both path coverage and coverage balance. Our method is to select test cases that both traverse target paths and achieve...
-
Article
Efficient data transfer in clustered IoT network with cooperative member nodes
Wireless Sensor Network (WSN) is composed of numerous tiny smart sensors nodes integrated with Internet of Things (IoT) play a crucial role in many applications. The IoT connects physical devices to form a net...
-
Article
Generating word and document matrix representations for document classification
We present an effective word and document matrix representation architecture based on a linear operation, referred to as doc2matrix, to learn representations for document-level classification. It uses a matrix...
-
Chapter and Conference Paper
Memory Confidentiality and Integrity Protection Technology
In most existing computer systems, data transmission and preservation in the form of plaintext are vulnerable to various attacks. In this paper, we use Parralelized memory Confidentiality and Integrity Protect...
-
Article
The impact of preprocessing steps on the accuracy of machine learning algorithms in sentiment analysis
Big data and its related technologies have become active areas of research recently. There is a huge amount of data generated every minute and second that includes unstructured data which is the topic of inter...
-
Article
Big Data Analytics, Text Mining and Modern English Language
The modern English Language took centuries to convert from old English. The word ‘hath’ of old English for example, has taken centuries to become ‘have’ in the modern English Language. If these changes had not be...
-
Article
A RSU-aided distributed trust framework for pseudonym-enabled privacy preservation in VANETs
Vehicular ad hoc networks (VANETs) have the potential to change the way of people drive, travel and so on, in which vehicle can broadcast and forward the message of road condition or emergency. When the receiv...
-
Article
Efficient key generation leveraging channel reciprocity and balanced gray code
Key generation leveraging wireless channel reciprocity can establish secret keys from unauthenticated broadcast channels and thus protect the communication of wireless networks. However, in real environments, ...
-
Article
An anonymous data reporting strategy with ensuring incentives for mobile crowd-sensing
To address the challenges of privacy preserving and incentive mechanisms, the paper proposes a system and a strategy to ensure anonymous data reporting while ensuring incentives simultaneously. The envisioned ...
-
Article
A trigger-based pseudonym exchange scheme for location privacy preserving in VANETs
Location privacy plays an important role in Vehicular Ad Hoc Networks (VANETs). Pseudonym is normally used to preserve location privacy, which can meet the requirements of both privacy and security. When the s...
-
Article
A Novel Problem Model and Solution Scheme for Roadside Unit Deployment Problem in VANETs
Being the building block of network infrastructure for Vehicular Ad-hoc Networks (VANETs), Roadside Units (RSUs) can facilitate vehicle-to-vehicle communications and bridge communications between vehicles and ...
-
Article
Outage Probability of Cognitive Selective DF Relay Networks with Multiple Primary Nodes and Heterogenous Non-Identical Constraints
Outage probability analysis of cognitive selective DF relay networks with selection combining technique taking into account all the following issues is important: multiple SU relays, multiple PUs, non-identica...
-
Chapter and Conference Paper
EFAV-MERD: Expected Forwarding Area Volume and Residual Distance Mathematic Expectation Routing Protocol for UASNs
The design of routing protocols for Underwater Acoustic Sensor Networks (UASNs) has many challenges arising from long variable propagation delay, high mobility in 3D environments, limited bandwidth, energy-con...
-
Article
Outage Probability Equivalency of Three Typical Relay Selection Schemes for Selective DF Relay Networks with Selection Combining
Outage probability of selective decode-and-forward (DF) relay networks with different relay selection schemes are usually analyzed separately in the literature. In this paper, for selective DF relay networks w...
-
Article
Open AccessA reliable data transfer protocol based on twin paths and network coding for underwater acoustic sensor network
MPNC (multiple path and network coding) is proposed as a reliable transport protocol for UWASN (underwater acoustic sensor network). In MPNC, after three disjoint paths being established, two groups of packets (A
-
Article
Outage Analysis of Cognitive AF Relay Networks with Multiple Primary Users and Heterogeneous Non-identical Parameters
In this paper, we investigate outage performance of dual-hop cognitive AF relay networks with multiple primary users (PUs) and heterogeneous non-identical parameters, including non-identical Rayleigh fading ch...
