Scholarlink

This paper introduces an FPGA-based system for ECG abnormality detection using pre-recorded data from the MIT-BIH Arrhythmia Database, specifically selecting ECG signals with well-defined arrhythmic events and minimal noise to ensure accurate feature extraction and classification. Traditional ECG devices often lack the necessary processing speed and portability for immediate on-the-spot analysis, particularly in emergency and remote settings (Wang et al. in An FPGA-based cloud system for massive ECG data analysis, Express briefs. IEEE Transactions on Circuits and Systems II, 2016). Leveraging FPGA’s capabilities, we implement advanced signal processing algorithms in Verilog to detect irregular heart activity efficiently (Wang et al. in An FPGA-based cloud system for massive ECG data analysis, Express Briefs. IEEE transactions on circuits and systems II, 2016; Hatai, Chakrabarti, Banerjee, FPGA implementation of a fetal heart rate measuring system. IEEE transactions on circuits and systems II: express briefs, 2019). The system processes stored ECG data, extracts features, and displays the predicted heart condition on a 7-segment display using an FPGA. To achieve seamless data processing, our approach integrates MATLAB, Python, and Verilog in a streamlined workflow. Python extracts key ECG features, including R-R intervals, QRS width, and P-wave presence. A key novelty of this work is the application of Golomb-Rice coding for ECG data compression, significantly reducing storage requirements and optimizing bandwidth usage during data transmission to the FPGA (Tsai and Hussain in VLSI implementation of lossless ECG compression algorithm for low power devices, express briefs, IEEE Transactions on Circuits and Systems II, 2020; Tsai, Hussain, and Hao VLSI implementation of ECG compression algorithm using golomb rice coding, in IEEE international conference on consumer electronics-Taiwan, 2018;Tsai et al. in VLSI implementation of multi-channel ECG lossless compression system, express briefs, IEEE transactions on circuits and systems II, 2021). Python converts the compressed data into a format compatible with Verilog, enabling efficient processing. The analyzed results are displayed on a 4-digit 7-segment display, facilitating immediate recognition of potential cardiac risks. Compared to existing state-of-the-art methods, our system demonstrates enhanced efficiency in ECG data handling by leveraging Golomb-Rice coding, which ensures compact data representation while maintaining diagnostic accuracy. Although this work primarily focuses on processing pre-recorded data, the inherent parallelism of FPGA hardware presents a promising future direction for real-time standalone ECG monitoring. The proposed system’s portability, optimized data compression, and adaptability make it highly suitable for telemedicine applications, offering a notable improvement over conventional ECG monitoring techniques in terms of storage efficiency and usability.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

ECG Abnormality Detection Using Xilinx Artix-7 Basys 3 FPGA: Optimized Diagnosis with Golomb-Rice Coding

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Aasish Sankar,
  • Naysha Kumari,
  • Shreyas Vignesh,
  • Dhanashree Bhate

摘要

This paper introduces an FPGA-based system for ECG abnormality detection using pre-recorded data from the MIT-BIH Arrhythmia Database, specifically selecting ECG signals with well-defined arrhythmic events and minimal noise to ensure accurate feature extraction and classification. Traditional ECG devices often lack the necessary processing speed and portability for immediate on-the-spot analysis, particularly in emergency and remote settings (Wang et al. in An FPGA-based cloud system for massive ECG data analysis, Express briefs. IEEE Transactions on Circuits and Systems II, 2016). Leveraging FPGA’s capabilities, we implement advanced signal processing algorithms in Verilog to detect irregular heart activity efficiently (Wang et al. in An FPGA-based cloud system for massive ECG data analysis, Express Briefs. IEEE transactions on circuits and systems II, 2016; Hatai, Chakrabarti, Banerjee, FPGA implementation of a fetal heart rate measuring system. IEEE transactions on circuits and systems II: express briefs, 2019). The system processes stored ECG data, extracts features, and displays the predicted heart condition on a 7-segment display using an FPGA. To achieve seamless data processing, our approach integrates MATLAB, Python, and Verilog in a streamlined workflow. Python extracts key ECG features, including R-R intervals, QRS width, and P-wave presence. A key novelty of this work is the application of Golomb-Rice coding for ECG data compression, significantly reducing storage requirements and optimizing bandwidth usage during data transmission to the FPGA (Tsai and Hussain in VLSI implementation of lossless ECG compression algorithm for low power devices, express briefs, IEEE Transactions on Circuits and Systems II, 2020; Tsai, Hussain, and Hao VLSI implementation of ECG compression algorithm using golomb rice coding, in IEEE international conference on consumer electronics-Taiwan, 2018;Tsai et al. in VLSI implementation of multi-channel ECG lossless compression system, express briefs, IEEE transactions on circuits and systems II, 2021). Python converts the compressed data into a format compatible with Verilog, enabling efficient processing. The analyzed results are displayed on a 4-digit 7-segment display, facilitating immediate recognition of potential cardiac risks. Compared to existing state-of-the-art methods, our system demonstrates enhanced efficiency in ECG data handling by leveraging Golomb-Rice coding, which ensures compact data representation while maintaining diagnostic accuracy. Although this work primarily focuses on processing pre-recorded data, the inherent parallelism of FPGA hardware presents a promising future direction for real-time standalone ECG monitoring. The proposed system’s portability, optimized data compression, and adaptability make it highly suitable for telemedicine applications, offering a notable improvement over conventional ECG monitoring techniques in terms of storage efficiency and usability.