| Presentation | 2020-02-26 On Machine Learning Based Accuracy Improvement for A Digital Temperature and Voltage Sensor Masayuki Gondo, Yousuke Miyake, Seiji Kajihara, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | To measure an on-chip temperature and voltage during VLSI operation, an RO(Ring Oscillator)-based digital temperature and voltage sensor has been proposed. Measurement accuracy of the RO-based sensor is decreased due to process variation. While calibration for the sensors is known as a method to relax the influence of process variation, it is not sufficient necessarily for reduction of the influence of process variation that occur in state-of-the-art VLSIs. This work proposes a method for accuracy improvement of the RO-based temperature and voltage sensors. The proposed method employs SVR(Support Vector Regression) which is one of the machine learning techniques and is efficient for reduction of the influence of process variation. In evaluation experiments for test chips with process variation show that the proposed method derives higher measurement accuracy than the existing method using multiple regression analysis. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Temperature sensor / Voltage sensor / Ring Oscillator / Machine learning / Support Vector Regression |
| Paper # | DC2019-86 |
| Date of Issue | 2020-02-19 (DC) |
| Conference Information | |
| Committee | DC |
|---|---|
| Conference Date | 2020/2/26(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | Satoshi Fukumoto(Tokyo Metropolitan Univ.) |
| Vice Chair | Hiroshi Takahashi(Ehime Univ.) |
| Secretary | Hiroshi Takahashi(Nihon Univ.) |
| Assistant | |
| Paper Information | |
| Registration To | Technical Committee on Dependable Computing |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | On Machine Learning Based Accuracy Improvement for A Digital Temperature and Voltage Sensor |
| Sub Title (in English) | |
| Keyword(1) | Temperature sensor |
| Keyword(2) | Voltage sensor |
| Keyword(3) | Ring Oscillator |
| Keyword(4) | Machine learning |
| Keyword(5) | Support Vector Regression |
| 1st Author's Name | Masayuki Gondo |
| 1st Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| 2nd Author's Name | Yousuke Miyake |
| 2nd Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| 3rd Author's Name | Seiji Kajihara |
| 3rd Author's Affiliation | Kyushu Institute of Technology(Kyutech) |
| Date | 2020-02-26 |
| Paper # | DC2019-86 |
| Volume (vol) | vol.119 |
| Number (no) | DC-420 |
| Page | pp.pp.1-6(DC), |
| #Pages | 6 |
| Date of Issue | 2020-02-19 (DC) |