-
Article
Open AccessA Region-Selective Anti-compression Image Encryption Algorithm Based on Deep Networks
In recent years, related research has focused on how to safely transfer and protect the privacy of images in social network services while providing easy access by authorized users. To safeguard privacy, we su...
-
Article
Spatiotemporal variations and impact factors of nutrients in the Sanya Bay, northern South China Sea
Nutrients play a fundamental role in maintaining coastal ecosystem stability. Based on two cruise observations in the winter of 2020 and the summer of 2021, the spatiotemporal variations of dissolved inorganic...
-
Article
Personalized tag recommendation via denoising auto-encoder
Personalized tag recommender systems automatically recommend users a set of tags used to annotate items according to users’ past tagging information. Learning the representations of involved entities (i.e. use...
-
Chapter and Conference Paper
Application of PBFT Algorithm Based on Trust Model in Internet Public Welfare Organizations
With “the Internet plus” concept put forward, the Internet public welfare organizations emerge as the times require, but the Internet organizations are also facing many problems and challenges. This paper main...
-
Chapter and Conference Paper
Research of Key Technique of Simulation Test Grid for C4ISR System
Based on the analysis of simulation test bed, the simulation test grid concepts for C4ISR system is firstly proposed with the net-centric and service-oriented characteristics of new generation C4ISR system into c...
-
Chapter and Conference Paper
Hyperbolic Personalized Tag Recommendation
Personalized Tag Recommendation (PTR) aims to automatically generate a list of tags for users to annotate web resources, the so-called items, according to users’ tagging preferences. The main challenge of PTR...
-
Chapter and Conference Paper
A Novel Thought of Pruning Algorithms: Pruning Based on Less Training
Pre-training of models in pruning algorithms plays an important role in pruning decision-making. We find that excessive pre-training is not necessary for pruning algorithms. According to this idea, we propose ...
-
Chapter and Conference Paper
A Classification Method for Imbalanced Data Based on SMOTE and Fuzzy Rough Nearest Neighbor Algorithm
FRNN (Fuzzy Rough Nearest Neighbor) algorithm has exhibited good performance in classifying data with inadequate features. However, FRNN does not perform well on imbalanced data. To overcome this problem, this...
-
Chapter and Conference Paper
Sentiment Analysis with Automatically Constructed Lexicon and Three-Way Decision
An unsupervised sentiment analysis method is presented to classify user comments on laptops into positive ones and negative ones. The method automatically extracts informative features in testing dataset and l...
-
Chapter and Conference Paper
DotSlash: A Self-Configuring and Scalable Rescue System for Handling Web Hotspots Effectively
DotSlash allows different web sites to form a mutual-aid community, and use spare capacity in the community to relieve web hotspots experienced by any individual site. As a rescue system, DotSlash intervenes w...