A comprehensive overview of feature representation for biometric recognition
The performance of any biometric recognition system heavily dependents on finding a good
and suitable feature representation space where observations from different classes are well …
and suitable feature representation space where observations from different classes are well …
A survey on the blockchain techniques for the Internet of Vehicles security
Abstract Recently, The Internet of Vehicles (IoV) concept is becoming very popular due to
sharing of the data between vehicles and the infrastructure. The sharing of data is very …
sharing of the data between vehicles and the infrastructure. The sharing of data is very …
Active learning for deep visual tracking
Convolutional neural networks (CNNs) have been successfully applied to the single target
tracking task in recent years. Generally, training a deep CNN model requires numerous …
tracking task in recent years. Generally, training a deep CNN model requires numerous …
Self-weighted robust LDA for multiclass classification with edge classes
Linear discriminant analysis (LDA) is a popular technique to learn the most discriminative
features for multi-class classification. A vast majority of existing LDA algorithms are prone to …
features for multi-class classification. A vast majority of existing LDA algorithms are prone to …
Top-k Feature Selection Framework Using Robust 0–1 Integer Programming
Feature selection (FS), which identifies the relevant features in a data set to facilitate
subsequent data analysis, is a fundamental problem in machine learning and has been …
subsequent data analysis, is a fundamental problem in machine learning and has been …
Multigraph fusion for dynamic graph convolutional network
Graph convolutional network (GCN) outputs powerful representation by considering the
structure information of the data to conduct representation learning, but its robustness is …
structure information of the data to conduct representation learning, but its robustness is …
Action recognition using optimized deep autoencoder and CNN for surveillance data streams of non-stationary environments
Action recognition is a challenging research area in which several convolutional neural
networks (CNN) based action recognition methods are recently presented. However, such …
networks (CNN) based action recognition methods are recently presented. However, such …
Few-shot learning for fault diagnosis with a dual graph neural network
Mechanical fault diagnosis is crucial to ensure the safe operations of equipment in intelligent
manufacturing systems. Deep learning-based methods have been recently developed for …
manufacturing systems. Deep learning-based methods have been recently developed for …
Adaptive semi-supervised feature selection for cross-modal retrieval
In order to exploit the abundant potential information of the unlabeled data and contribute to
analyzing the correlation among heterogeneous data, we propose the semi-supervised …
analyzing the correlation among heterogeneous data, we propose the semi-supervised …
Architecture evolution of convolutional neural network using monarch butterfly optimization
Y Wang, X Qiao, GG Wang - Journal of Ambient Intelligence and …, 2023 - Springer
Designing suitable convolutional neural networks (CNNs) for different image data requires
much human effort and expertise, in recent years, this process has been greatly accelerated …
much human effort and expertise, in recent years, this process has been greatly accelerated …