Editorial for application-driven knowledge acquisition
- PDF / 127,556 Bytes
- 3 Pages / 439.37 x 666.142 pts Page_size
- 23 Downloads / 191 Views
Editorial for application-driven knowledge acquisition Xue Li 1 & Sen Wang 1,2 & Bohan Li 3
# Springer Science+Business Media, LLC, part of Springer Nature 2020
This special issue has 8 papers focused on innovative Application-Driven Knowledge Acquisition approaches to problems that involve big data, artificial intelligence, and machine learning applications. In the era of intelligence, the burgeoning topics of machine learning and knowledge acquisition have changed the traditional way of knowledge acquisition. Information mining based on big data has brought about tremendous changes in many fields. Like deep learning has attracted wide attention in recent years, which has been effectively applied in many fields. In this background, most researches are driven by specific applications and further integrated deep learning models with big data. As a powerful tool, it helps researchers to better mine valuable information from high-dimensional massive data to acquire knowledge more effectively. Following an open call for papers, the articles in this special issue focus on various deep learning models including recurrent neural network (RNN), long and short time memory network (LSTM), bidirectional long and short time memory network (Bi-LSTM), dynamic Bayesian network (DBN) and graph convolution network (GCN), and conduct research on multiple tasks such as knowledge acquisition, knowledge representation and data mining. The special issue received 14 paper (including recommended papers from the 14th-International Conference on Advanced Data Mining and Applications, ADMA2018, Nanjing, China). The acceptance ratio is about 28.5%. The main ideas of these papers are as follows: As the popularization of mobile smart devices, the acquisition of knowledge can hardly be separated from essential privacy protection. Aiming at the mobile Internet application scenario,
* Xue Li [email protected] Sen Wang [email protected] Bohan Li [email protected]
1
The University of Queensland, Brisbane, QLD 4072, Australia
2
Griffith University, Brisbane, Australia
3
Nanjing University of Aeronautics and Astronautics, Nanjing 211106 Jiangsu, China
World Wide Web
J Jiang, S Ji and G Long proposed a novel attention-augmented and decentralized knowledge acquisition framework based on federated learning to achieve decentralization and protect private data. T Wu, H Wang and their colleagues proposed a complete general technical framework for constructing knowledge graph from multiple online encyclopedias, including knowledge rule extraction, live knowledge extraction, lightweight entity link and semi-supervised entity link, and gives all the technical details. W Yuan, K He and their colleagues proposed a multi-view network embedding method based on node similarity ensemble. Embedding results can be further leveraged in deep learning frameworks and provide excellent support for downstream tasks. Medical data analysis based on deep learning has been widely studied in recent years. The article “Deep Learning for Heterogeneous Medical Data A
Data Loading...
