Design of Assisted Cupping Diagnosis Medical System based on FPGA Hardware Acceleration and BP Neural Network

Hantao Sun; Long Yang; Jin Wang; Dehui Zou; Zhigang Di

doi:10.54097/vy4yr435

Authors

Hantao Sun
Long Yang
Jin Wang
Dehui Zou
Zhigang Di

DOI:

https://doi.org/10.54097/vy4yr435

Keywords:

Medical Canister Diagnosis, FPGA, Hardware Acceleration, BP Neural Network, Intelligent Medical Device

Abstract

Cupping diagnosis, a characteristic TCM physical method, serves key roles in preliminary disease screening and constitution identification. Traditional manual cupping suffers from strong subjectivity, descriptive nature and fragmented workflows. To this end, an intelligent cupping diagnosis system based on FPGA hardware acceleration and BP neural network is designed. In this system, FPGA integrates multi-sensor interfaces, and via hardware acceleration completes cupping mark image enhancement, sensor data fusion and synchronous acquisition. A BP neural network diagnostic model is deployed on the upper computer to jointly analyze cupping mark image and internal cup environmental features, achieving intelligent constitution and disease diagnosis. Experimental simulations and theoretical analysis show that the system’s temperature measurement error is reduced by ~76% vs. original error, cupping mark image processing hits 79.37 fps, and the BP neural network effectively identifies six constitution types. This research provides technical reference for hardware acceleration and digital upgrading of TCM instruments, and helps advance digital and intelligent development of TCM cupping diagnosis.

Downloads

Download data is not yet available.

References

[1] Fu Haoran, Dai Guohua, Gao Wulin, et al. Approaches and Methods for Selecting Representative Diseases in Digital Research on Enhancing Syndrome Differentiation and Treatment in Traditional Chinese Medicine [J]. World Science and Technology – Modernization of Traditional Chinese Medicine, 2021, 23(04):1205-1210.

[2] Qin Xian, Shen Pengfei. The Clinical Significance of 'Pot Spots' [J]. Shanghai Journal of Traditional Chinese Medicine, 2011, 45(8):20-21.

[3] Khan I M ,Silva D B .Harnessing FPGA Technology for Energy-Efficient Wearable Medical Devices[J]. Electronics, 2024, 13(20):4094-4094. DOI:10. 3390/ ELECTR ONICS132 04094.

[4] Liang Taohua, Zhou Jiang, Xiao Guannan. Design and Implementation of a Thermohygrometer Based on DHT11 [J]. Electronic Production, 2024, 32(15):88-90.

[5] Niu Wenju, Huang Rongyu, Han Jianqiang. FPGA-Based Micro-Sensor Signal Acquisition System [J]. Sensors and Microsystems, 2019, 38(05):104-106.

[6] Miftahul K, Harditio A P, Pande W , et al.Design of Air Pressure Measuring Devices Using a Barometric Pressure 280 (BMP280) Sensor Based on Arduino Uno[J].BULETIN FISIKA,2020,21(1):14-14.DOI:10.24843/bf.2020.v21.i01.p03.

[7] Huang Zhanhua, Li Xiaowei, Wang Kangnian, et al. Design of a Multi-Sensor Fusion Synchronous Timing System Based on FPGA [J]. Instrument Technology and Sensors, 2023, (7):52-61.

[8] Yuan Weiqi, Tang Yonghua. Implementation of OmniVision Image Sensor SCCB Bus Protocol in DSP [J]. Journal of Instruments and Instrumentation, 2006, (S2): 1687-1688.

[9] Zhang Conghua, Yang Yong, Liu Ruofan, et al. Application of Graphic and Image Technology in Infrared Thermal Imaging [J]. China Testing, 2012, 38(2):77-80.

[10] Deng Tingquan, Dong Tianzhen, Xie Wei, et al. Adaptive center-weighted median filtering method for color images [J]. Control and Decision, 2013, 28(9):1372-1376.

[11] Huang Xiaoxin, Zhu Zhengtai, Li Jingtao. Underwater Image Enhancement Algorithm Based on Weighted Fusion and FPGA Design [J]. Electronics Technology, 2025, 54(1):106-110.

[12] Jiang Junlun, Feng Daqiang, Xu Xinrui, et al. Design of an Image Acquisition and Processing System Based on FPGA GPU [J]. Computer Measurement and Control, 2023, 31(8): 273-279, 305.

[13] Fu Hao, Sun Heng, Zhao Zhongkai. Measurement of Radar Signal Carrier Frequency Based on BP Neural Network [J]. Ship Electronic Warfare, 2024, 47(2):71-75.

[14] Hong Zhiwei. Design of Gigabit Ethernet Image Acquisition and Processing System Based on FPGA [D]. Jishou University, 2022.

[15] Zhao Yuan. Research on Digital Image Classification System Based on BP Neural Network [J]. Information Technology and Informatization, 2023, (12): 123-127.