An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly Detection
Extreme learning machine (ELM) has shown to be an effective and low-power approach for real-time electrocardiography (ECG) anomaly detection. However, prior ELM inference chips are noise-prone and lacking in reconfigurability. In this article, we present an arbitrarily reconfigurable ELM inference e...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Open Journal of Circuits and Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9335310/ |
| _version_ | 1818331725493698560 |
|---|---|
| author | Yu-Chuan Chuang Yi-Ta Chen Huai-Ting Li An-Yeu Andy Wu |
| author_facet | Yu-Chuan Chuang Yi-Ta Chen Huai-Ting Li An-Yeu Andy Wu |
| author_sort | Yu-Chuan Chuang |
| collection | DOAJ |
| description | Extreme learning machine (ELM) has shown to be an effective and low-power approach for real-time electrocardiography (ECG) anomaly detection. However, prior ELM inference chips are noise-prone and lacking in reconfigurability. In this article, we present an arbitrarily reconfigurable ELM inference engine fabricated in 40-nm CMOS technology for robust ECG anomaly detection. By combining Adaptive boosting (Adaboost) and Eigenspace denoising with ELM (AE-ELM), robust classification under noisy conditions is achieved and saves the number of required multiplications by 95.9%. For chip implementation, a reconfigurable VLSI architecture is designed to support arbitrary complexity of AE-ELM, accounting for dynamic change in application requirements. On the other hand, we propose to construct the input weight matrix of ELM as a Bernoulli random matrix, which further reduces the number of multiplications by 55.2%. For real-time detection, parallel computing is exploited to reduce the latency by up to 86.8%. Overall, the 0.21-mm<sup>2</sup> AE-ELM inference engine shows its robustness against noisy signals and achieves $1.83\times$ AEE compared with the state-of-the-art ELM design. |
| first_indexed | 2024-12-13T13:24:25Z |
| format | Article |
| id | doaj.art-a0a0a644a5be4a29851ba5387900703c |
| institution | Directory Open Access Journal |
| issn | 2644-1225 |
| language | English |
| last_indexed | 2024-12-13T13:24:25Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Circuits and Systems |
| spelling | doaj.art-a0a0a644a5be4a29851ba5387900703c2022-12-21T23:44:20ZengIEEEIEEE Open Journal of Circuits and Systems2644-12252021-01-01219620910.1109/OJCAS.2020.30399939335310An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly DetectionYu-Chuan Chuang0https://orcid.org/0000-0001-7940-9033Yi-Ta Chen1https://orcid.org/0000-0003-1724-0206Huai-Ting Li2An-Yeu Andy Wu3https://orcid.org/0000-0003-4731-8633Graduate Institute of Electronics Engineering, National Taiwan University, Taipei, TaiwanGraduate Institute of Electronics Engineering, National Taiwan University, Taipei, TaiwanMediaTek Inc., Hsinchu, TaiwanGraduate Institute of Electronics Engineering, National Taiwan University, Taipei, TaiwanExtreme learning machine (ELM) has shown to be an effective and low-power approach for real-time electrocardiography (ECG) anomaly detection. However, prior ELM inference chips are noise-prone and lacking in reconfigurability. In this article, we present an arbitrarily reconfigurable ELM inference engine fabricated in 40-nm CMOS technology for robust ECG anomaly detection. By combining Adaptive boosting (Adaboost) and Eigenspace denoising with ELM (AE-ELM), robust classification under noisy conditions is achieved and saves the number of required multiplications by 95.9%. For chip implementation, a reconfigurable VLSI architecture is designed to support arbitrary complexity of AE-ELM, accounting for dynamic change in application requirements. On the other hand, we propose to construct the input weight matrix of ELM as a Bernoulli random matrix, which further reduces the number of multiplications by 55.2%. For real-time detection, parallel computing is exploited to reduce the latency by up to 86.8%. Overall, the 0.21-mm<sup>2</sup> AE-ELM inference engine shows its robustness against noisy signals and achieves $1.83\times$ AEE compared with the state-of-the-art ELM design.https://ieeexplore.ieee.org/document/9335310/Adaptive boosting (Adaboost)eigenspace denoisingelectrocardiography (ECG) anomaly detectionextreme learning machine (ELM)reconfigurable chip design |
| spellingShingle | Yu-Chuan Chuang Yi-Ta Chen Huai-Ting Li An-Yeu Andy Wu An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly Detection IEEE Open Journal of Circuits and Systems Adaptive boosting (Adaboost) eigenspace denoising electrocardiography (ECG) anomaly detection extreme learning machine (ELM) reconfigurable chip design |
| title | An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly Detection |
| title_full | An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly Detection |
| title_fullStr | An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly Detection |
| title_full_unstemmed | An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly Detection |
| title_short | An Arbitrarily Reconfigurable Extreme Learning Machine Inference Engine for Robust ECG Anomaly Detection |
| title_sort | arbitrarily reconfigurable extreme learning machine inference engine for robust ecg anomaly detection |
| topic | Adaptive boosting (Adaboost) eigenspace denoising electrocardiography (ECG) anomaly detection extreme learning machine (ELM) reconfigurable chip design |
| url | https://ieeexplore.ieee.org/document/9335310/ |
| work_keys_str_mv | AT yuchuanchuang anarbitrarilyreconfigurableextremelearningmachineinferenceengineforrobustecganomalydetection AT yitachen anarbitrarilyreconfigurableextremelearningmachineinferenceengineforrobustecganomalydetection AT huaitingli anarbitrarilyreconfigurableextremelearningmachineinferenceengineforrobustecganomalydetection AT anyeuandywu anarbitrarilyreconfigurableextremelearningmachineinferenceengineforrobustecganomalydetection AT yuchuanchuang arbitrarilyreconfigurableextremelearningmachineinferenceengineforrobustecganomalydetection AT yitachen arbitrarilyreconfigurableextremelearningmachineinferenceengineforrobustecganomalydetection AT huaitingli arbitrarilyreconfigurableextremelearningmachineinferenceengineforrobustecganomalydetection AT anyeuandywu arbitrarilyreconfigurableextremelearningmachineinferenceengineforrobustecganomalydetection |