Results 11 to 20 of about 192,056 (258)

Adaptive Decision Support System for On-Line Multi-Class Learning and Object Detection

Applied Sciences, 2021
A new online multi-class learning algorithm is proposed with three main characteristics. First, in order to make the feature pool fitter for the pattern pool, the adaptive feature pool is proposed to dynamically combine the three general features, Haar ...
Guo-Jhang Hong, Dong-Lin Li, Shreya Pare, Amit Saxena, Mukesh Prasad, Chin-Teng Lin   +5 more
doaj   +1 more source

TI-POOLING: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks [PDF]

2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
In this paper we present a deep neural network topology that incorporates a simple to implement transformation invariant pooling operator (TI-POOLING). This operator is able to efficiently handle prior knowledge on nuisance variations in the data, such as rotation or scale changes.
Dmitry Laptev, Nikolay Savinov, Joachim M. Buhmann, Marc Pollefeys   +3 more
openaire   +2 more sources

Characterizing the Core Internal Gene Pool of H9N2 Responsible for Continuous Reassortment With Other Influenza A Viruses

Frontiers in Microbiology, 2021
Reassortment among avian influenza viruses is the main source of novel avian influenza virus subtypes. Studies have shown that the H9N2 virus often donates internal segments to generate novel reassortant avian influenza viruses, acting as a reassortment ...
Haoyi Yang, Haoyi Yang, Mingda Hu, Boqian Wang, Yuan Jin, Xingfei Gong, Xingfei Gong, Long Liang, Junjie Yue, Wei Chen, Hongguang Ren   +10 more
doaj   +1 more source

A Novel Framework for Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Coefficients of Walsh Transform and Cosine Linear Discriminant Analysis

IEEE Access, 2021
In this paper, we propose a three-stage lightweight framework for centrifugal pump fault diagnosis. First, the centrifugal pump vibration signatures are fast transformed using a Walsh transform, and Walsh spectra are obtained. To overcome the hefty noise
Zahoor Ahmad, Akhand Rai, Md Junayed Hasan, Cheol Hong Kim, Jong-Myon Kim   +4 more
doaj   +1 more source

Face image classification by pooling raw features [PDF]

Pattern Recognition, 2016
We propose a very simple, efficient yet surprisingly effective feature extraction method for face recognition (about 20 lines of Matlab codes), which is mainly inspired by spatial pyramid pooling in generic image classification. We show that, coupled with a linear classifier, features formed by simply pooling local patches over a multi-level pyramid ...
Shen, F., Shen, C., Zhou, X., Yang, Y., Shen, H.   +4 more
openaire   +3 more sources

Multistage Centrifugal Pump Fault Diagnosis by Selecting Fault Characteristic Modes of Vibration and Using Pearson Linear Discriminant Analysis

IEEE Access, 2020
This paper proposes a three-stage fault diagnosis strategy for multistage centrifugal pumps. First, the proposed method identifies and selects fault characteristic modes of vibration to overcome the substantial noise produced by other unrelated macro ...
Zahoor Ahmad, Alexander E. Prosvirin, Jaeyoung Kim, Jong-Myon Kim   +3 more
doaj   +1 more source

MSFR-GCN: A Multi-Scale Feature Reconstruction Graph Convolutional Network for EEG Emotion and Cognition Recognition

IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023
Graph Convolutional Network (GCN) excels at EEG recognition by capturing brain connections, but previous studies neglect the important EEG feature itself.
Deng Pan, Haohao Zheng, Feifan Xu, Yu Ouyang, Zhe Jia, Chu Wang, Hong Zeng   +6 more
doaj   +1 more source

Efficient CNN with uncorrelated Bag of Features pooling

2022 IEEE Symposium Series on Computational Intelligence (SSCI), 2022
6 pages, 2 ...
Laakom, Firas, Raitoharju, Jenni, Iosifidis, Alexandros, Gabbouj, Moncef   +4 more
openaire   +3 more sources

Global Context and Enhanced Feature Guided Residual Refinement Network for 3D Cardiovascular Image Segmentation

IEEE Access, 2021
As an important pre-processing step in clinical applications, automatic and accurate 3D cardiovascular image segmentation has attracted more and more attention.
Jingjing Liu, Ao Wei, Zhigang Guo, Chang Tang   +3 more
doaj   +1 more source

Hybrid Feature Selection Framework for Bearing Fault Diagnosis Based on Wrapper-WPT

Machines, 2022
A framework aimed to improve the bearing-fault diagnosis accuracy using a hybrid feature-selection method based on Wrapper-WPT is proposed in this paper.
Andrei S. Maliuk, Zahoor Ahmad, Jong-Myon Kim   +2 more
doaj   +1 more source