Machine Learning Based Object Classification and Identification Scheme Using an Embedded Millimeter-Wave Radar Sensor
A target’s movements and radar cross sections are the key parameters to consider when designing a radar sensor for a given application. This paper shows the feasibility and effectiveness of using 24 GHz radar built-in low-noise microwave amplifiers for detecting an object. For this purpose a supervi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/13/4291 |
| _version_ | 1797529018634862592 |
|---|---|
| author | Homa Arab Iman Ghaffari Lydia Chioukh Serioja Tatu Steven Dufour |
| author_facet | Homa Arab Iman Ghaffari Lydia Chioukh Serioja Tatu Steven Dufour |
| author_sort | Homa Arab |
| collection | DOAJ |
| description | A target’s movements and radar cross sections are the key parameters to consider when designing a radar sensor for a given application. This paper shows the feasibility and effectiveness of using 24 GHz radar built-in low-noise microwave amplifiers for detecting an object. For this purpose a supervised machine learning model (SVM) is trained using the recorded data to classify the targets based on their cross sections into four categories. The trained classifiers were used to classify the objects with varying distances from the receiver. The SVM classification is also compared with three methods based on binary classification: a one-against-all classification, a one-against-one classification, and a directed acyclic graph SVM. The level of accuracy is approximately 96.6%, and an F1-score of 96.5% is achieved using the one-against-one SVM method with an RFB kernel. The proposed contactless radar in combination with an SVM algorithm can be used to detect and categorize a target in real time without a signal processing toolbox. |
| first_indexed | 2024-03-10T10:07:30Z |
| format | Article |
| id | doaj.art-61f69b2b2ce6440bb0a9b54129b480a2 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T10:07:30Z |
| publishDate | 2021-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-61f69b2b2ce6440bb0a9b54129b480a22023-11-22T01:25:31ZengMDPI AGSensors1424-82202021-06-012113429110.3390/s21134291Machine Learning Based Object Classification and Identification Scheme Using an Embedded Millimeter-Wave Radar SensorHoma Arab0Iman Ghaffari1Lydia Chioukh2Serioja Tatu3Steven Dufour4École Polytechnique de Montréal, Montréal, QC H3T 1J4, CanadaÉcole Polytechnique de Montréal, Montréal, QC H3T 1J4, CanadaÉcole Polytechnique de Montréal, Montréal, QC H3T 1J4, CanadaInstitut National de la Recherche Scientifique (INRS), Montréal, QC H2X 1E3, CanadaÉcole Polytechnique de Montréal, Montréal, QC H3T 1J4, CanadaA target’s movements and radar cross sections are the key parameters to consider when designing a radar sensor for a given application. This paper shows the feasibility and effectiveness of using 24 GHz radar built-in low-noise microwave amplifiers for detecting an object. For this purpose a supervised machine learning model (SVM) is trained using the recorded data to classify the targets based on their cross sections into four categories. The trained classifiers were used to classify the objects with varying distances from the receiver. The SVM classification is also compared with three methods based on binary classification: a one-against-all classification, a one-against-one classification, and a directed acyclic graph SVM. The level of accuracy is approximately 96.6%, and an F1-score of 96.5% is achieved using the one-against-one SVM method with an RFB kernel. The proposed contactless radar in combination with an SVM algorithm can be used to detect and categorize a target in real time without a signal processing toolbox.https://www.mdpi.com/1424-8220/21/13/4291doppler frequencyin-phase/quadrature demodulatormachine learningmillimeter-wavemulti-class SVMsmetronome |
| spellingShingle | Homa Arab Iman Ghaffari Lydia Chioukh Serioja Tatu Steven Dufour Machine Learning Based Object Classification and Identification Scheme Using an Embedded Millimeter-Wave Radar Sensor Sensors doppler frequency in-phase/quadrature demodulator machine learning millimeter-wave multi-class SVMs metronome |
| title | Machine Learning Based Object Classification and Identification Scheme Using an Embedded Millimeter-Wave Radar Sensor |
| title_full | Machine Learning Based Object Classification and Identification Scheme Using an Embedded Millimeter-Wave Radar Sensor |
| title_fullStr | Machine Learning Based Object Classification and Identification Scheme Using an Embedded Millimeter-Wave Radar Sensor |
| title_full_unstemmed | Machine Learning Based Object Classification and Identification Scheme Using an Embedded Millimeter-Wave Radar Sensor |
| title_short | Machine Learning Based Object Classification and Identification Scheme Using an Embedded Millimeter-Wave Radar Sensor |
| title_sort | machine learning based object classification and identification scheme using an embedded millimeter wave radar sensor |
| topic | doppler frequency in-phase/quadrature demodulator machine learning millimeter-wave multi-class SVMs metronome |
| url | https://www.mdpi.com/1424-8220/21/13/4291 |
| work_keys_str_mv | AT homaarab machinelearningbasedobjectclassificationandidentificationschemeusinganembeddedmillimeterwaveradarsensor AT imanghaffari machinelearningbasedobjectclassificationandidentificationschemeusinganembeddedmillimeterwaveradarsensor AT lydiachioukh machinelearningbasedobjectclassificationandidentificationschemeusinganembeddedmillimeterwaveradarsensor AT seriojatatu machinelearningbasedobjectclassificationandidentificationschemeusinganembeddedmillimeterwaveradarsensor AT stevendufour machinelearningbasedobjectclassificationandidentificationschemeusinganembeddedmillimeterwaveradarsensor |