ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS
To overcome the energy and bandwidth limitations of traditional IoT systems, 'edge computing' or information extraction at the sensor node has become popular. However, now it is important to create very low energy information extraction or pattern recognition systems. In this paper, we pre...
| Main Authors: | , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/155305 |
| _version_ | 1811681435003650048 |
|---|---|
| author | Bose, Sumon Kumar Kar, Bapi Roy, Mohendra Gopalakrishnan, Pradeep Kumar Zhang, Lei Patil, Aakash Basu, Arindam |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Bose, Sumon Kumar Kar, Bapi Roy, Mohendra Gopalakrishnan, Pradeep Kumar Zhang, Lei Patil, Aakash Basu, Arindam |
| author_sort | Bose, Sumon Kumar |
| collection | NTU |
| description | To overcome the energy and bandwidth limitations of traditional IoT systems, 'edge computing' or information extraction at the sensor node has become popular. However, now it is important to create very low energy information extraction or pattern recognition systems. In this paper, we present an approximate computing method to reduce the computation energy of a specific type of IoT system used for anomaly detection (e.g. in predictive maintenance, epileptic seizure detection, etc). Termed as Anomaly Detection Based Power Savings (ADEPOS), our proposed method uses low precision computing and low complexity neural networks at the beginning when it is easy to distinguish healthy data. However, on the detection of anomalies, the complexity of the network and computing precision are adaptively increased for accurate predictions. We show that ensemble approaches are well suited for adaptively changing network size. To validate our proposed scheme, a chip has been fabricated in UMC 65nm process that includes an MSP430 microprocessor along with an on-chip switching mode DC-DC converter for dynamic voltage and frequency scaling. Using NASA bearing dataset for machine health monitoring, we show that using ADEPOS we can achieve 8.95X saving of energy along the lifetime without losing any detection accuracy. The energy savings are obtained by reducing the execution time of the neural network on the microprocessor. |
| first_indexed | 2024-10-01T03:40:54Z |
| format | Journal Article |
| id | ntu-10356/155305 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:40:54Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1553052022-03-17T07:59:08Z ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS Bose, Sumon Kumar Kar, Bapi Roy, Mohendra Gopalakrishnan, Pradeep Kumar Zhang, Lei Patil, Aakash Basu, Arindam School of Electrical and Electronic Engineering Delta-NTU Corporate Laboratory VIRTUS, IC Design Centre of Excellence Engineering::Electrical and electronic engineering Edge Computing Predictive Maintenance To overcome the energy and bandwidth limitations of traditional IoT systems, 'edge computing' or information extraction at the sensor node has become popular. However, now it is important to create very low energy information extraction or pattern recognition systems. In this paper, we present an approximate computing method to reduce the computation energy of a specific type of IoT system used for anomaly detection (e.g. in predictive maintenance, epileptic seizure detection, etc). Termed as Anomaly Detection Based Power Savings (ADEPOS), our proposed method uses low precision computing and low complexity neural networks at the beginning when it is easy to distinguish healthy data. However, on the detection of anomalies, the complexity of the network and computing precision are adaptively increased for accurate predictions. We show that ensemble approaches are well suited for adaptively changing network size. To validate our proposed scheme, a chip has been fabricated in UMC 65nm process that includes an MSP430 microprocessor along with an on-chip switching mode DC-DC converter for dynamic voltage and frequency scaling. Using NASA bearing dataset for machine health monitoring, we show that using ADEPOS we can achieve 8.95X saving of energy along the lifetime without losing any detection accuracy. The energy savings are obtained by reducing the execution time of the neural network on the microprocessor. National Research Foundation (NRF) This work was supported in part by Delta Electronics, Inc., and in part by the National Research Foundation Singapore under the Corp Lab@University scheme. 2022-03-17T07:59:08Z 2022-03-17T07:59:08Z 2019 Journal Article Bose, S. K., Kar, B., Roy, M., Gopalakrishnan, P. K., Zhang, L., Patil, A. & Basu, A. (2019). ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS. IEEE Transactions On Circuits and Systems I: Regular Papers, 67(3), 913-926. https://dx.doi.org/10.1109/TCSI.2019.2958086 1549-8328 https://hdl.handle.net/10356/155305 10.1109/TCSI.2019.2958086 2-s2.0-85080854679 3 67 913 926 en IEEE Transactions on Circuits and Systems I: Regular Papers © 2019 IEEE. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Edge Computing Predictive Maintenance Bose, Sumon Kumar Kar, Bapi Roy, Mohendra Gopalakrishnan, Pradeep Kumar Zhang, Lei Patil, Aakash Basu, Arindam ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS |
| title | ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS |
| title_full | ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS |
| title_fullStr | ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS |
| title_full_unstemmed | ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS |
| title_short | ADEPOS : a novel approximate computing framework for anomaly detection systems and its implementation in 65-nm CMOS |
| title_sort | adepos a novel approximate computing framework for anomaly detection systems and its implementation in 65 nm cmos |
| topic | Engineering::Electrical and electronic engineering Edge Computing Predictive Maintenance |
| url | https://hdl.handle.net/10356/155305 |
| work_keys_str_mv | AT bosesumonkumar adeposanovelapproximatecomputingframeworkforanomalydetectionsystemsanditsimplementationin65nmcmos AT karbapi adeposanovelapproximatecomputingframeworkforanomalydetectionsystemsanditsimplementationin65nmcmos AT roymohendra adeposanovelapproximatecomputingframeworkforanomalydetectionsystemsanditsimplementationin65nmcmos AT gopalakrishnanpradeepkumar adeposanovelapproximatecomputingframeworkforanomalydetectionsystemsanditsimplementationin65nmcmos AT zhanglei adeposanovelapproximatecomputingframeworkforanomalydetectionsystemsanditsimplementationin65nmcmos AT patilaakash adeposanovelapproximatecomputingframeworkforanomalydetectionsystemsanditsimplementationin65nmcmos AT basuarindam adeposanovelapproximatecomputingframeworkforanomalydetectionsystemsanditsimplementationin65nmcmos |