Zobrazeno 1 - 10
of 25
pro vyhledávání: '"ZHAO LI"'
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 34:186-200
Classification methods for streaming data are not new, but very few current frameworks address all three of the most common problems with these tasks: concept drift, noise, and the exorbitant costs associated with labeling the unlabeled instances in
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems. 33:6484-6493
One-shot semantic segmentation poses the challenging task of segmenting object regions from unseen categories with only one annotated example as guidance. Thus, how to effectively construct robust feature representations from the guidance image is cr
Publikováno v:
Future Generation Computer Systems. 116:145-155
Recently popularized Graph Neural Network (GNN) has been attaching great attention along with its successful industry applications. This paper focuses on two challenges traditional GNN frameworks face: (i) most of them are transductive and mainly con
Publikováno v:
IEEE Transactions on Vehicular Technology. 69:7583-7595
With the continually increasing demand for higher data rate and link density as well as better network coverage, wireless networks, including 5G-enabled vehicular communication network (VCN), will be designed/deployed to cover more overlapping areas,
Publikováno v:
Wireless Networks. 26:5393-5410
Interference management (IM) is essential to wireless communication systems, but it is also known to consume transmission resource such as power and degree of freedom, hence degrading users’ achievable spectral efficiency (SE). Therefore, it is imp
Publikováno v:
IEEE Internet of Things Journal. 6:10458-10471
Internet of Things (IoT) is a new paradigm that involves the interconnection of thousands of devices and home appliances. Due to the scarcity of the spectrum suitable for wireless electromagnetic transmission, many communication systems and devices a
Publikováno v:
IEEE transactions on neural networks and learning systems. 33(6)
Anomaly detection on attributed networks attracts considerable research interests due to wide applications of attributed networks in modeling a wide range of complex systems. Recently, the deep learning-based anomaly detection methods have shown prom
Publikováno v:
Wireless Networks. 25:5011-5025
In practical communication systems, there are always multiple subscribers competing for limited resources, such as time and frequency, hence effective user scheduling is essential to multi-user communications in achieving good system throughput and f
Publikováno v:
Big Data Mining and Analytics. 2:100-117
Spreading social influence with both positive and negative opinions in online networks Social networks are important media for spreading information, ideas, and influence among individuals. Most existing research focuses on understanding the characte
Publikováno v:
Computer Communications. 136:63-75
Due to the hierarchical structure and heterogeneity of most deployed wireless networks, multiple data transmissions using the same communication resource, such as same frequency band and time slot, are likely to occur in the same area. Hence, interfe