76 Result(s)
within
**aochen **
Computer Science
Data Mining and Knowledge Discovery
-
Article
A hybrid style transfer with whale optimization algorithm model for textual adversarial attack
Deep learning has been widely used in various research fields. However, researchers have discovered that deep learning models are vulnerable to adversarial attacks. Existing word-level attacks can be seen as a...
-
Article
Reinforcement learning from constraints and focal entity shifting in conversational KGQA
The actual needs of users for information are often hidden in multiple question answering (QA) on the same topic. In order to generate answers to users’ current questions, a conversational QA system relies on ...
-
Chapter and Conference Paper
Image Blending Algorithm with Automatic Mask Generation
In recent years, image blending has gained popularity for its ability to create visually stunning content. However, the current image blending algorithms mainly have the following problems: manually creating i...
-
Chapter and Conference Paper
3RE-Net: Joint Loss-REcovery and Super-REsolution Neural Network for REal-Time Video
Real-time video over the Internet suffers from packet loss and low network bandwidth. The receiving side may receive down-sampled video with damaged frames. In this work, we are motivated to enhance the qualit...
-
Article
Emotion spreading carried by emoji in social network
This paper focuses on the spreading characteristics of emoji in social networks, especially by constructing the S3I emotion spreading model to study the evolution laws and characteristics of positive, neutral,...
-
Article
Open AccessClassification of barely visible impact damage in composite laminates using deep learning and pulsed thermographic inspection
With the increasingly comprehensive utilisation of Carbon Fibre-Reinforced Polymers (CFRP) in modern industry, defects detection and characterisation of these materials have become very important and draw sign...
-
Article
Open AccessA semi-supervised short text sentiment classification method based on improved Bert model from unlabelled data
Short text information has considerable commercial value and immeasurable social value. Natural language processing and short text sentiment analysis technology can organize and analyze short text information ...
-
Article
Toward visual quality enhancement of dehazing effect with improved Cycle-GAN
Image dehazing is a fundamental problem in computer vision. However, GT images for supervised dehazing network training are virtually impossible to obtain in the real world. Therefore, unsupervised image dehaz...
-
Article
Open AccessA machine learning-based clustering approach to diagnose multi-component degradation of aircraft fuel systems
Accurate fault diagnosis and prognosis can significantly reduce maintenance costs, increase the safety and availability of engineering systems that have become increasingly complex. It has been observed that v...
-
Chapter and Conference Paper
Steering Control Method of Mobile Forklift Based on Sensing Signal
Because the steering control method of the mobile forklift has the problem of large steering deviation, a steering control method of the mobile forklift based on sensing signal is designed. Using the yaw rate ...
-
Chapter and Conference Paper
Extraction Method of Vibroseis Phase Signal Based on Time-Varying Narrowband Filtering
When the phase travel time value increases continuously, the accuracy of the vibroseis phase signal extraction method will be disturbed. Aiming at this problem, a time-varying narrow-band filtering based vibro...
-
Chapter and Conference Paper
Emotion Detection in Unfix-Length-Context Conversation
Emotion Detection in conversation is playing more and more important role in dialogue system. Existing approaches to Emotion Detection in Conversation (EDC) use a fixed context window to recognize speakers’ emoti...
-
Article
Open AccessAutomatic reconstruction of irregular shape defects in pulsed thermography using deep learning neural network
Quantitative defect and damage reconstruction play a critical role in industrial quality management. Accurate defect characterisation in Infrared Thermography (IRT), as one of the widely used Non-Destructive T...
-
Article
Optimization analysis of football match prediction model based on neural network
How to build a football match prediction model and use scientific methods to solve the prediction problem has become a key point in the application of artificial intelligence in the sports industry. In this pa...
-
Chapter and Conference Paper
3D Visualization Supporting Situational Awareness of Model-Based System of Systems
Model-based System of Systems Engineering (MBSoSE) enables to improve the efficiency of the architecture design, and the performance analysis and modeling of highly complex system of systems (SoS). Introducing...
-
Chapter and Conference Paper
Towards a Semantics-Based Search Engine for Smart Contract Information
Most blockchains are known for transparency since all on-chain records are open and immutable. However, due to the particularity of the blockchain data structure, users cannot perform semantic searches in the ...
-
Chapter and Conference Paper
Big Data Analysis for Anti-Money Laundering: A Case of Open Source Greenplum Application
For the anti-money laundering regulations of financial institutions, it is important to do the timely big data analysis to continuously optimize the comprehensiveness, correctness and effectiveness of transact...
-
Chapter and Conference Paper
Semantic Modeling Supporting Discrete Event Simulation for Aircraft Assembly Process
Aircraft assembly is a complex process associated with different stakeholders, which strongly impacts the R&D cost for the entire aircraft lifecycle management. Traditional aircraft assembly process is designe...
-
Article
Fisher information-empowered sensing quality quantification for crowdsensing networks
The sensing quality is critical for crowdsensing networks. However, it is still challenging to achieve reliable and accurate quantification on sensing quality. As most existing methods only quantify individual...
-
Article
Overflow warning and remote monitoring technology based on improved random forest
Overflow accident is one of the accidents with the greatest impact on safe drilling. An unclear diagnosis of an overflow accident or improper post-processing may cause serious drilling accidents. Based on this...
