Cryptocurrency transaction network embedding from static and dynamic perspectives: An overview
Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests
from both industrial and academic communities. With its rapid development, the …
from both industrial and academic communities. With its rapid development, the …
[PDF][PDF] Human-cyber-physical system for Industry 5.0: A review from a human-centric perspective
Industry 5.0 heralds a new wave of the industrial revolution, placing a spotlight on human-
centric intelligent manufacturing. At the core of Industry 5.0 lies the human-cyberphysical …
centric intelligent manufacturing. At the core of Industry 5.0 lies the human-cyberphysical …
Domain adaptation multitask optimization
Multitask optimization (MTO) is a new optimization paradigm that leverages useful
information contained in multiple tasks to help solve each other. It attracts increasing …
information contained in multiple tasks to help solve each other. It attracts increasing …
Data driven vibration control: A review
With the ongoing advancements in sensor networks and data acquisition technologies
across various systems like manufacturing, aviation, and healthcare, the data driven …
across various systems like manufacturing, aviation, and healthcare, the data driven …
A fast nonnegative autoencoder-based approach to latent feature analysis on high-dimensional and incomplete data
F Bi, T He, X Luo - IEEE Transactions on Services Computing, 2023 - ieeexplore.ieee.org
High-Dimensional and Incomplete (HDI) data are frequently encountered in various Big
Data-related applications. Despite its incompleteness, an HDI data repository contains rich …
Data-related applications. Despite its incompleteness, an HDI data repository contains rich …
Integration of multikinds imputation with covariance adaptation based on evidence theory
For incomplete data classification, missing attribute values are often estimated by imputation
methods before building classifiers. The estimated attribute values are not actual attribute …
methods before building classifiers. The estimated attribute values are not actual attribute …
Predicting quality of services based on a two-stream deep learning model with user and service graphs
PY Zhang, WJ Huang, YT Chen… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Accurately predicting Quality of Service (QoS) is one of the main challenges in the area of
service recommendation, and it has thus attracted much attention in recent years. This field …
service recommendation, and it has thus attracted much attention in recent years. This field …
Learning from human educational wisdom: A student-centered knowledge distillation method
Existing studies on knowledge distillation typically focus on teacher-centered methods, in
which the teacher network is trained according to its own standards before transferring the …
which the teacher network is trained according to its own standards before transferring the …
Neural network models for time-varying tensor complementarity problems
P Wei, X Wang, Y Wei - Neurocomputing, 2023 - Elsevier
The existence and uniqueness of solutions and fast algorithms for tensor complementarity
problems are hot topics in nowadays. We present a time-varying tensor complementarity …
problems are hot topics in nowadays. We present a time-varying tensor complementarity …
Evolution and role of optimizers in training deep learning models
XH Wen, MC Zhou - IEEE/CAA Journal of Automatica Sinica, 2024 - ieeexplore.ieee.org
To perform well, deep learning (DL) models have to be trained well. Which optimizer should
be adopted? We answer this question by discussing how optimizers have evolved from …
be adopted? We answer this question by discussing how optimizers have evolved from …