A Radar-Based System for Detection of Human Fall Utilizing Analog Hardware Architectures of Decision Tree Model
A fall-detection system was implemented utilizing a 2.45 GHz continuous wave radar along with power-efficient and fully-analog integrated classifier architectures. The Power Burst Curve and the effective acceleration were derived from the short time Fourier transform, and then processed by the analo...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Open Journal of Circuits and Systems |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10542293/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592898861826048 |
|---|---|
| author | Vassilis Alimisis Dimitrios G. Arnaoutoglou Emmanouil Anastasios Serlis Argyro Kamperi Konstantinos Metaxas George A. Kyriacou Paul P. Sotiriadis |
| author_facet | Vassilis Alimisis Dimitrios G. Arnaoutoglou Emmanouil Anastasios Serlis Argyro Kamperi Konstantinos Metaxas George A. Kyriacou Paul P. Sotiriadis |
| author_sort | Vassilis Alimisis |
| collection | DOAJ |
| description | A fall-detection system was implemented utilizing a 2.45 GHz continuous wave radar along with power-efficient and fully-analog integrated classifier architectures. The Power Burst Curve and the effective acceleration were derived from the short time Fourier transform, and then processed by the analog classifier. The proposed classifier architectures are based on different approximations of the Decision tree classification model. The architectures consist of three main building blocks: sigmoid function circuit, analog multiplier and an argmax operator circuit. To assess the hardware design, a thorough analysis is performed, comparing it to commonly used analog classifiers while exploiting the extracted data. The architectures were trained using Python and were compared to software-based classifiers. The circuit designs were executed using TSMC’s 90 nm CMOS process technology and the Cadence IC Suite was employed for tasks including design, schematic implementation, and post-layout simulations. |
| format | Article |
| id | doaj-art-f0fcf29ab16f4a3b98e9e395031bfb76 |
| institution | Kabale University |
| issn | 2644-1225 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Circuits and Systems |
| spelling | doaj-art-f0fcf29ab16f4a3b98e9e395031bfb762025-01-21T00:02:55ZengIEEEIEEE Open Journal of Circuits and Systems2644-12252024-01-01522424210.1109/OJCAS.2024.340766310542293A Radar-Based System for Detection of Human Fall Utilizing Analog Hardware Architectures of Decision Tree ModelVassilis Alimisis0https://orcid.org/0000-0002-2090-1493Dimitrios G. Arnaoutoglou1https://orcid.org/0009-0004-1668-132XEmmanouil Anastasios Serlis2https://orcid.org/0009-0007-2553-5203Argyro Kamperi3Konstantinos Metaxas4George A. Kyriacou5https://orcid.org/0000-0001-5253-0896Paul P. Sotiriadis6https://orcid.org/0000-0001-6030-4645Department of Electrical and Computer Engineering, National Technical University of Athens, Athens, GreeceDepartment of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, Athens, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, Athens, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, Athens, GreeceDepartment of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, GreeceDepartment of Electrical and Computer Engineering, National Technical University of Athens, Athens, GreeceA fall-detection system was implemented utilizing a 2.45 GHz continuous wave radar along with power-efficient and fully-analog integrated classifier architectures. The Power Burst Curve and the effective acceleration were derived from the short time Fourier transform, and then processed by the analog classifier. The proposed classifier architectures are based on different approximations of the Decision tree classification model. The architectures consist of three main building blocks: sigmoid function circuit, analog multiplier and an argmax operator circuit. To assess the hardware design, a thorough analysis is performed, comparing it to commonly used analog classifiers while exploiting the extracted data. The architectures were trained using Python and were compared to software-based classifiers. The circuit designs were executed using TSMC’s 90 nm CMOS process technology and the Cadence IC Suite was employed for tasks including design, schematic implementation, and post-layout simulations.https://ieeexplore.ieee.org/document/10542293/Analog hardware classifierdecision treefall-detectionradar-based systemsigmoid-based implementationsub-threshold region |
| spellingShingle | Vassilis Alimisis Dimitrios G. Arnaoutoglou Emmanouil Anastasios Serlis Argyro Kamperi Konstantinos Metaxas George A. Kyriacou Paul P. Sotiriadis A Radar-Based System for Detection of Human Fall Utilizing Analog Hardware Architectures of Decision Tree Model IEEE Open Journal of Circuits and Systems Analog hardware classifier decision tree fall-detection radar-based system sigmoid-based implementation sub-threshold region |
| title | A Radar-Based System for Detection of Human Fall Utilizing Analog Hardware Architectures of Decision Tree Model |
| title_full | A Radar-Based System for Detection of Human Fall Utilizing Analog Hardware Architectures of Decision Tree Model |
| title_fullStr | A Radar-Based System for Detection of Human Fall Utilizing Analog Hardware Architectures of Decision Tree Model |
| title_full_unstemmed | A Radar-Based System for Detection of Human Fall Utilizing Analog Hardware Architectures of Decision Tree Model |
| title_short | A Radar-Based System for Detection of Human Fall Utilizing Analog Hardware Architectures of Decision Tree Model |
| title_sort | radar based system for detection of human fall utilizing analog hardware architectures of decision tree model |
| topic | Analog hardware classifier decision tree fall-detection radar-based system sigmoid-based implementation sub-threshold region |
| url | https://ieeexplore.ieee.org/document/10542293/ |
| work_keys_str_mv | AT vassilisalimisis aradarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT dimitriosgarnaoutoglou aradarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT emmanouilanastasiosserlis aradarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT argyrokamperi aradarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT konstantinosmetaxas aradarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT georgeakyriacou aradarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT paulpsotiriadis aradarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT vassilisalimisis radarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT dimitriosgarnaoutoglou radarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT emmanouilanastasiosserlis radarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT argyrokamperi radarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT konstantinosmetaxas radarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT georgeakyriacou radarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel AT paulpsotiriadis radarbasedsystemfordetectionofhumanfallutilizinganaloghardwarearchitecturesofdecisiontreemodel |