• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Yaqub, Muhammad (Yaqub, Muhammad.) | Feng, Jinchao (Feng, Jinchao.) (学者:冯金超) | Zia, M. Sultan (Zia, M. Sultan.) | Arshid, Kaleem (Arshid, Kaleem.) | Jia, Kebin (Jia, Kebin.) (学者:贾克斌) | Rehman, Zaka Ur (Rehman, Zaka Ur.) | Mehmood, Atif (Mehmood, Atif.)

收录:

Scopus SCIE PubMed

摘要:

Brain tumors have become a leading cause of death around the globe. The main reason for this epidemic is the difficulty conducting a timely diagnosis of the tumor. Fortunately, magnetic resonance images (MRI) are utilized to diagnose tumors in most cases. The performance of a Convolutional Neural Network (CNN) depends on many factors (i.e., weight initialization, optimization, batches and epochs, learning rate, activation function, loss function, and network topology), data quality, and specific combinations of these model attributes. When we deal with a segmentation or classification problem, utilizing a single optimizer is considered weak testing or validity unless the decision of the selection of an optimizer is backed up by a strong argument. Therefore, optimizer selection processes are considered important to validate the usage of a single optimizer in order to attain these decision problems. In this paper, we provides a comprehensive comparative analysis of popular optimizers of CNN to benchmark the segmentation for improvement. In detail, we perform a comparative analysis of 10 different state-of-the-art gradient descent-based optimizers, namely Adaptive Gradient (Adagrad), Adaptive Delta (AdaDelta), Stochastic Gradient Descent (SGD), Adaptive Momentum (Adam), Cyclic Learning Rate (CLR), Adaptive Max Pooling (Adamax), Root Mean Square Propagation (RMS Prop), Nesterov Adaptive Momentum (Nadam), and Nesterov accelerated gradient (NAG) for CNN. The experiments were performed on the BraTS2015 data set. The Adam optimizer had the best accuracy of 99.2% in enhancing the CNN ability in classification and segmentation.

关键词:

brain tumor optimizer Adam gradient descent deep learning convolutional neural network segmentation

作者机构:

  • [ 1 ] [Yaqub, Muhammad]Beijing Univ Technol, Fac Informat Technol, Beijing 100000, Peoples R China
  • [ 2 ] [Feng, Jinchao]Beijing Univ Technol, Fac Informat Technol, Beijing 100000, Peoples R China
  • [ 3 ] [Arshid, Kaleem]Beijing Univ Technol, Fac Informat Technol, Beijing 100000, Peoples R China
  • [ 4 ] [Jia, Kebin]Beijing Univ Technol, Fac Informat Technol, Beijing 100000, Peoples R China
  • [ 5 ] [Zia, M. Sultan]Univ Lahore, Dept Comp Sci & IT, Gujrat Campus,Main GT Rd, Gujranwala 52250, Punjab, Pakistan
  • [ 6 ] [Rehman, Zaka Ur]Univ Lahore, Dept Comp Sci & IT, Gujrat Campus,Main GT Rd, Gujranwala 52250, Punjab, Pakistan
  • [ 7 ] [Jia, Kebin]Beijing Univ Technol, Beijing Key Lab Computat Intelligence & Intellige, Beijing 100000, Peoples R China
  • [ 8 ] [Mehmood, Atif]Xidian Univ, Sch Artificial Intelligence, 2 South Taibai Rd, Xian 710071, Peoples R China

通讯作者信息:

  • 冯金超

    [Feng, Jinchao]Beijing Univ Technol, Fac Informat Technol, Beijing 100000, Peoples R China

查看成果更多字段

相关关键词:

相关文章:

来源 :

BRAIN SCIENCES

年份: 2020

期: 7

卷: 10

3 . 3 0 0

JCR@2022

ESI学科: NEUROSCIENCE & BEHAVIOR;

ESI高被引阀值:117

被引次数:

WoS核心集被引频次: 92

SCOPUS被引频次: 127

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 0

在线人数/总访问数:108/3918469
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司