Study of the Complexity of CMOS Neural Network Implementations Featuring Heart Rate Detection

被引:0
|
作者
Baryczkowski, Piotr [1 ]
Szczepaniak, Sebastian [1 ]
Matykiewicz, Natalia [1 ]
Perz, Kacper [1 ]
Szczesny, Szymon [1 ]
机构
[1] Poznan Univ Tech, Inst Comp Sci, Fac Comp & Telecommun, Piotrowo 3A St, PL-61138 Poznan, Poland
关键词
VLSI; TinyML; wearable devices; power-efficient architecture; model hyperparameters;
D O I
10.3390/electronics12204291
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The growing popularity of edge computing goes hand in hand with the widespread use of systems based on artificial intelligence. There are many different technologies used to accelerate AI algorithms in end devices. One of the more efficient is CMOS technology thanks to the ability to control the physical parameters of the device. This article discusses the complexity of the semiconductor implementation of TinyML edge systems in relation to various criteria. In particular, the influence of the model parameters on the complexity of the system is analyzed. As a use case, a CMOS preprocessor device dedicated to detecting heart rate in wearable devices is used. The authors use the current and weak inversion operating modes, which allow the preprocessor to be powered by cells of the human energy harvesting class. This work analyzes the influence of tuning hyperparameters of the learning process on the performance of the final device. This article analyzes the relationships between the model parameters (accuracy and neural network size), input data parameters (sampling rates) and CMOS circuit parameters (circuit area, operating frequency and power consumption). Comparative analyses are performed using TSMC 65 nm CMOS technology. The results presented in this article may be useful to direct this work with the model in terms of the final implementation as the integrated circuit. The dependencies summarized in this work can also be used to initially estimate the costs of the hardware implementation of the model.
引用
收藏
页数:19
相关论文
共 50 条
  • [1] Neural network based detection of fetal heart rate patterns
    Warrick, P
    Hamilton, E
    Macieszczak, M
    PROCEEDINGS OF THE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), VOLS 1-5, 2005, : 2400 - 2405
  • [2] High Performance Recurrent Neural Network Implementations in Technologies beyond CMOS
    Ansari, Mohd. Samar
    PROCEEDINGS OF THE 3RD INTERNATIONAL CONFERENCE ON DEVICES, CIRCUITS AND SYSTEMS (ICDCS) 2016, 2016, : 212 - 216
  • [3] Bounds on the complexity of recurrent neural network implementations of finite state machines
    NEC Research Institute, 4 Independence Way, Princeton, NJ 08540, United States
    NEURAL NETW., 2 (243-252):
  • [4] Bounds on the complexity of recurrent neural network implementations of finite state machines
    Horne, BG
    Hush, DR
    NEURAL NETWORKS, 1996, 9 (02) : 243 - 252
  • [5] Artificial Neural Network Integrated Heart Rate Variability with Detection System
    Huang, Chen-Shen
    Huang, Kong-Sheng
    Jong, Gwo-Jia
    2013 INTERNATIONAL JOINT CONFERENCE ON AWARENESS SCIENCE AND TECHNOLOGY & UBI-MEDIA COMPUTING (ICAST-UMEDIA), 2013, : 275 - 279
  • [6] Low-complexity CMOS cellular neural network for binary processing
    Molinar-Solis, JE
    Gómez-Castañeda, F
    Moreno-Cadenas, JA
    7TH WORLD MULTICONFERENCE ON SYSTEMICS, CYBERNETICS AND INFORMATICS, VOL XIV, PROCEEDINGS: COMPUTER SCIENCE, ENGINEERING AND APPLICATIONS, 2003, : 388 - 390
  • [7] Multi-Class Stress Detection Through Heart Rate Variability: A Deep Neural Network Based Study
    Mortensen, Jon Andreas
    Mollov, Martin Efremov
    Chatterjee, Ayan
    Ghose, Debasish
    Li, Frank Y.
    IEEE ACCESS, 2023, 11 : 57470 - 57480
  • [8] A lightweight convolutional neural network hardware implementation for wearable heart rate anomaly detection
    Gu, Minghong
    Zhang, Yuejun
    Wen, Yongzhong
    Ai, Guangpeng
    Zhang, Huihong
    Wang, Pengjun
    Wang, Guoqing
    COMPUTERS IN BIOLOGY AND MEDICINE, 2023, 155
  • [9] Design of Receiver Frontend with Deep Neural Network for Doppler Radar Heart Rate Detection
    Lai, Wen-Cheng
    2020 THE 5TH IEEE INTERNATIONAL CONFERENCE ON INTEGRATED CIRCUITS AND MICROSYSTEMS (ICICM 2020), 2020, : 121 - 124
  • [10] High Accuracy Respiration and Heart Rate Detection Based on Artificial Neural Network Regression
    Tsai, Yu-Chiao
    Lai, Shih-Hsuan
    Ho, Ching-Ju
    Wu, Fang-Ming
    Henrickson, Lindor
    Wei, Chia-Chien
    Chen, Irwin
    Wu, Vincent
    Chen, Jyehong
    42ND ANNUAL INTERNATIONAL CONFERENCES OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY: ENABLING INNOVATIVE TECHNOLOGIES FOR GLOBAL HEALTHCARE EMBC'20, 2020, : 232 - 235