A high-performance, hardware-based deep learning system for disease diagnosis

被引:0
|
作者
Siddique A. [1 ,2 ]
Iqbal M.A. [3 ]
Aleem M. [4 ]
Lin J.C.-W. [5 ]
机构
[1] National University of Computer and Emerging Sciences, Lahore Campus
[2] University of Macau, Taipa,Macau
[3] Lancaster University, Lancaster
[4] National University of Computer and Emerging Sciences, Islamabad
[5] Western Norway University of Applied Sciences, Bergen
关键词
Activation function; Cancer diagnosis; Deep learning; Field programmable gate array; Hardware friendly; Neural networks; Swish;
D O I
10.7717/PEERJ-CS.1034
中图分类号
学科分类号
摘要
Modern deep learning schemes have shown human-level performance in the area of medical science. However, the implementation of deep learning algorithms on dedicated hardware remains a challenging task because modern algorithms and neuronal activation functions are generally not hardware-friendly and require a lot of resources. Recently, researchers have come up with some hardware-friendly activation functions that can yield high throughput and high accuracy at the same time. In this context, we propose a hardware-based neural network that can predict the presence of cancer in humans with 98.23% accuracy. This is done by making use of cost-efficient, highly accurate activation functions, Sqish and LogSQNL. Due to its inherently parallel components, the system can classify a given sample in just one clock cycle, i.e., 15.75 nanoseconds. Though this system is dedicated to cancer diagnosis, it can predict the presence of many other diseases such as those of the heart. This is because the system is reconfigurable and can be programmed to classify any sample into one of two classes. The proposed hardware system requires about 983 slice registers, 2,655 slice look-up tables, and only 1.1 kilobits of on-chip memory. The system can predict about 63.5 million cancer samples in a second and can perform about 20 giga-operations per second. The proposed system is about 5-16 times cheaper and at least four times speedier than other dedicated hardware systems using neural networks for classification tasks © 2022. Siddique et al
引用
收藏
相关论文
共 50 条
  • [1] A high-performance, hardware-based deep learning system for disease diagnosis
    Siddique, Ali
    Iqbal, Muhammad Azhar
    Aleem, Muhammad
    Lin, Jerry Chun-Wei
    PEERJ COMPUTER SCIENCE, 2022, 8
  • [2] Hyperion: Hardware-Based High-Performance and Secure System for Container Networks
    You, Myoungsung
    Seo, Minjae
    Kim, Jaehan
    Shin, Seungwon
    Nam, Jaehyun
    IEEE TRANSACTIONS ON CLOUD COMPUTING, 2024, 12 (03) : 844 - 858
  • [3] EFFECTIVE HARDWARE-BASED DATA PREFETCHING FOR HIGH-PERFORMANCE PROCESSORS
    CHEN, TF
    BAER, JL
    IEEE TRANSACTIONS ON COMPUTERS, 1995, 44 (05) : 609 - 623
  • [4] Deep Learning Inferencing with High-performance Hardware Accelerators
    Kljucaric, Luke
    George, Alan D.
    ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY, 2023, 14 (04)
  • [5] Deep-Learning Inferencing with High-Performance Hardware Accelerators
    Kljucaric, Luke
    George, Alan D.
    2019 IEEE HIGH PERFORMANCE EXTREME COMPUTING CONFERENCE (HPEC), 2019,
  • [6] Stand-alone hardware-based learning system
    Clarkson, Trevor
    Ng, Chi Kwong
    Japanese Journal of Applied Physics, Part 1: Regular Papers & Short Notes & Review Papers, 1995, 34 (2 B): : 1050 - 1055
  • [7] Hardware-based high-performance string lookup with value retrieval using extended Bloom filter
    LI, Qi-yue
    QU, Yu-gui
    ZHAO, Bao-hua
    Journal of China Universities of Posts and Telecommunications, 2008, 15 (02): : 97 - 101
  • [8] STAND-ALONE HARDWARE-BASED LEARNING-SYSTEM
    CLARKSON, T
    NG, CK
    JAPANESE JOURNAL OF APPLIED PHYSICS PART 1-REGULAR PAPERS SHORT NOTES & REVIEW PAPERS, 1995, 34 (2B): : 1050 - 1055
  • [10] Influence of unique behaviors in an atomic switch operation on hardware-based deep learning
    Tomatsuri, Keita
    Hasegawa, Tsuyoshi
    JAPANESE JOURNAL OF APPLIED PHYSICS, 2024, 63 (03)