On the Impact of Imbalanced Data in Convolutional Neural Networks Performance

被引：19

作者：

Pulgar, Francisco J. ^{[1
]}

Rivera, Antonio J. ^{[1
]}

Charte, Francisco ^{[1
]}

del Jesus, Maria J. ^{[1
]}

机构：

[1] Univ Jaen, Dept Comp Sci, Jaen, Spain

来源：

HYBRID ARTIFICIAL INTELLIGENT SYSTEMS, HAIS 2017 | 2017年 / 10334卷

关键词：

Deep learning; Convolutional neural network; Image recognition; Imbalanced dataset;

D O I：

10.1007/978-3-319-59650-1_19

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In recent years, new proposals have emerged for tackling the classification problem based on Deep Learning (DL) techniques. These proposals have shown good results in certain fields, such as image recognition. However, there are factors that must be analyzed to determine how they influence the results obtained by these new algorithms. In this paper, the classification of imbalanced data with convolutional neural networks (CNNs) is analyzed. To do this, a series of tests will be performed in which the classification of real images of traffic signals by CNNs will be performed based on data with different imbalance levels.

引用

页码：220 / 232

页数：13

共 50 条

[41] Impact of Type of Convolution Operation on Performance of Convolutional Neural Networks for Online Signature Verification
Vorugunti, Chandra Sekhar
Subramanian, Balasubramanian
Gautam, Avinash
Pulabaigari, Viswanath
[J]. FRONTIERS IN HANDWRITING RECOGNITION, ICFHR 2022, 2022, 13639 : 83 - 97
[42] Data Dropout: Optimizing Training Data for Convolutional Neural Networks
Wang, Tianyang
Huan, Jun
Li, Bo
[J]. 2018 IEEE 30TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE (ICTAI), 2018, : 39 - 46
[43] Classification of imbalanced cloud image data using deep neural networks: performance improvement through a data science competition
Matsuoka, Daisuke
[J]. PROGRESS IN EARTH AND PLANETARY SCIENCE, 2021, 8 (01)
[44] Classification of imbalanced cloud image data using deep neural networks: performance improvement through a data science competition
Daisuke Matsuoka
[J]. Progress in Earth and Planetary Science, 8
[45] The Impact of Multi-optimizers and Data Augmentation on TensorFlow Convolutional Neural Network Performance
Taqi, Arwa Mohammed
Awad, Ahmed
Al-Azzo, Fadwa
Milanova, Mariofanna
[J]. IEEE 1ST CONFERENCE ON MULTIMEDIA INFORMATION PROCESSING AND RETRIEVAL (MIPR 2018), 2018, : 140 - 145
[46] Convolutional neural networks for vibrational spectroscopic data analysis
Acquarelli, Jacopo
van Laarhoven, Twan
Gerretzen, Jan
Tran, Thanh N.
Buydens, Lutgarde M. C.
Marchiori, Elena
[J]. ANALYTICA CHIMICA ACTA, 2017, 954 : 22 - 31
[47] Occam: Optimal Data Reuse for Convolutional Neural Networks
Gondimalla, Ashish
Liu, Jianqiao
Thottethodi, Mithuna
Vijaykumar, T. N.
[J]. ACM TRANSACTIONS ON ARCHITECTURE AND CODE OPTIMIZATION, 2022, 20 (01)
[48] A Robotized Data Collection Approach for Convolutional Neural Networks
Liu, Yiming
Zhang, Shaohua
Xiao, Xiaohui
Li, Miao
[J]. INTELLIGENT ROBOTICS AND APPLICATIONS, ICIRA 2017, PT III, 2017, 10464 : 472 - 483
[49] GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR HYPERSPECTRAL DATA CLASSIFICATION
Shahraki, Farideh Foroozandeh
Prasad, Saurabh
[J]. 2018 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP 2018), 2018, : 968 - 972
[50] Functional data learning using convolutional neural networks
Galarza, J.
Oraby, T.
[J]. MACHINE LEARNING-SCIENCE AND TECHNOLOGY, 2024, 5 (01):

← 1 2 3 4 5 →