A Biomedical Sensor System With Stochastic A/D Conversion and Error Correction by Machine Learning
This paper presents a high-precision biomedical sensor system with a novel analog-frontend (AFE) IC and error correction by machine learning. The AFE IC embeds an analog-to-digital converter (ADC) architecture called successive stochastic approximation ADC. The proposed ADC integrates a stochastic f...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8636959/ |
| _version_ | 1819276177819303936 |
|---|---|
| author | Yusaku Hirai Toshimasa Matsuoka Sadahiro Tani Shodai Isami Keiji Tatsumi Masayuki Ueda Takatsugu Kamata |
| author_facet | Yusaku Hirai Toshimasa Matsuoka Sadahiro Tani Shodai Isami Keiji Tatsumi Masayuki Ueda Takatsugu Kamata |
| author_sort | Yusaku Hirai |
| collection | DOAJ |
| description | This paper presents a high-precision biomedical sensor system with a novel analog-frontend (AFE) IC and error correction by machine learning. The AFE IC embeds an analog-to-digital converter (ADC) architecture called successive stochastic approximation ADC. The proposed ADC integrates a stochastic flash ADC (SF-ADC) into a successive approximation register ADC (SAR-ADC) to enhance its resolution. The SF-ADC is also used as a digitally controlled variable threshold comparator to provide error correction of the SAR-ADC. The proposed system also calibrates the ADC error using the machine learning algorithm on an external PC without additional power dissipation at a sensor node. Due to the flexibility of the system, the design complexity of an AFE IC can be relaxed by using these techniques. The target resolution is 18 bits, and the target bandwidth (without digital low-pass filter) is about 5 kHz to deal with several types of biopotential signals. The design is fabricated in a 130-nm CMOS process and operates at 1.2-V supply. The fabricated ADC achieves the SNDR of 88 dB at a sampling frequency of 250 kHz by using the proposed calibration techniques. Due to the high-resolution ADC, the input-referred noise is 2.52 μV<sub>rms</sub> with a gain of 28.5 dB. |
| first_indexed | 2024-12-23T23:36:05Z |
| format | Article |
| id | doaj.art-0760674ca5404c5f9120ae2988c88010 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-23T23:36:05Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0760674ca5404c5f9120ae2988c880102022-12-21T17:25:51ZengIEEEIEEE Access2169-35362019-01-017219902200110.1109/ACCESS.2019.28981548636959A Biomedical Sensor System With Stochastic A/D Conversion and Error Correction by Machine LearningYusaku Hirai0https://orcid.org/0000-0002-1850-6283Toshimasa Matsuoka1https://orcid.org/0000-0003-3876-2679Sadahiro Tani2Shodai Isami3Keiji Tatsumi4Masayuki Ueda5Takatsugu Kamata6SPChange, LLC., Yokohama, JapanGraduate School of Engineering, Osaka University, Suita, JapanGraduate School of Engineering, Osaka University, Suita, JapanGraduate School of Engineering, Osaka University, Suita, JapanGraduate School of Engineering, Osaka University, Suita, JapanSPChange, LLC., Yokohama, JapanSPChange, LLC., Yokohama, JapanThis paper presents a high-precision biomedical sensor system with a novel analog-frontend (AFE) IC and error correction by machine learning. The AFE IC embeds an analog-to-digital converter (ADC) architecture called successive stochastic approximation ADC. The proposed ADC integrates a stochastic flash ADC (SF-ADC) into a successive approximation register ADC (SAR-ADC) to enhance its resolution. The SF-ADC is also used as a digitally controlled variable threshold comparator to provide error correction of the SAR-ADC. The proposed system also calibrates the ADC error using the machine learning algorithm on an external PC without additional power dissipation at a sensor node. Due to the flexibility of the system, the design complexity of an AFE IC can be relaxed by using these techniques. The target resolution is 18 bits, and the target bandwidth (without digital low-pass filter) is about 5 kHz to deal with several types of biopotential signals. The design is fabricated in a 130-nm CMOS process and operates at 1.2-V supply. The fabricated ADC achieves the SNDR of 88 dB at a sampling frequency of 250 kHz by using the proposed calibration techniques. Due to the high-resolution ADC, the input-referred noise is 2.52 μV<sub>rms</sub> with a gain of 28.5 dB.https://ieeexplore.ieee.org/document/8636959/Biomedical sensorECGerror correctionmachine learningSAR-ADCstochastic A/D conversion |
| spellingShingle | Yusaku Hirai Toshimasa Matsuoka Sadahiro Tani Shodai Isami Keiji Tatsumi Masayuki Ueda Takatsugu Kamata A Biomedical Sensor System With Stochastic A/D Conversion and Error Correction by Machine Learning IEEE Access Biomedical sensor ECG error correction machine learning SAR-ADC stochastic A/D conversion |
| title | A Biomedical Sensor System With Stochastic A/D Conversion and Error Correction by Machine Learning |
| title_full | A Biomedical Sensor System With Stochastic A/D Conversion and Error Correction by Machine Learning |
| title_fullStr | A Biomedical Sensor System With Stochastic A/D Conversion and Error Correction by Machine Learning |
| title_full_unstemmed | A Biomedical Sensor System With Stochastic A/D Conversion and Error Correction by Machine Learning |
| title_short | A Biomedical Sensor System With Stochastic A/D Conversion and Error Correction by Machine Learning |
| title_sort | biomedical sensor system with stochastic a d conversion and error correction by machine learning |
| topic | Biomedical sensor ECG error correction machine learning SAR-ADC stochastic A/D conversion |
| url | https://ieeexplore.ieee.org/document/8636959/ |
| work_keys_str_mv | AT yusakuhirai abiomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT toshimasamatsuoka abiomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT sadahirotani abiomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT shodaiisami abiomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT keijitatsumi abiomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT masayukiueda abiomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT takatsugukamata abiomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT yusakuhirai biomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT toshimasamatsuoka biomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT sadahirotani biomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT shodaiisami biomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT keijitatsumi biomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT masayukiueda biomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning AT takatsugukamata biomedicalsensorsystemwithstochasticadconversionanderrorcorrectionbymachinelearning |