scholarly journals Doppler-Spectrum Feature-Based Human–Vehicle Classification Scheme Using Machine Learning for an FMCW Radar Sensor

Sensors ◽  
2020 ◽  
Vol 20 (7) ◽  
pp. 2001 ◽  
Author(s):  
Eugin Hyun ◽  
YoungSeok Jin
Keyword(s):  
Classification Scheme ◽  
Vehicle Classification ◽  
Doppler Spectrum ◽  
Support Vector ◽  
Radar Sensor ◽  
Moving Vehicle ◽  
Fmcw Radar ◽  
Wave Radar ◽  
Spectrum Feature ◽  
Feature Based

In this paper, we propose a Doppler-spectrum feature-based human–vehicle classification scheme for an FMCW (frequency-modulated continuous wave) radar sensor. We introduce three novel features referred to as the scattering point count, scattering point difference, and magnitude difference rate features based on the characteristics of the Doppler spectrum in two successive frames. We also use an SVM (support vector machine) and BDT (binary decision tree) for training and validation of the three aforementioned features. We measured the signals using a 24-GHz FMCW radar front-end module and a real-time data acquisition module and extracted three features from a walking human and a moving vehicle in the field. We then repeatedly measured the classification decision rate of the proposed algorithm using the SVM and BDT, finding that the average performance exceeded 99% and 96% for the walking human and the moving vehicle, respectively.

scholarly journals YOLO-Based Simultaneous Target Detection and Classification in Automotive FMCW Radar Systems

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2897 ◽  
Author(s):  
Woosuk Kim ◽  
Hyunwoong Cho ◽  
Jongseok Kim ◽  
Byungkwan Kim ◽  
Seongwook Lee
Keyword(s):  
Spatial Clustering ◽  
Radar Data ◽  
Support Vector ◽  
Automotive Radar ◽  
Radar Sensor ◽  
Fmcw Radar ◽  
Radar Systems ◽  
Conventional Methods ◽  
Two Stages ◽  
Deep Learning Model

This paper proposes a method to simultaneously detect and classify objects by using a deep learning model, specifically you only look once (YOLO), with pre-processed automotive radar signals. In conventional methods, the detection and classification in automotive radar systems are conducted in two successive stages; however, in the proposed method, the two stages are combined into one. To verify the effectiveness of the proposed method, we applied it to the actual radar data measured using our automotive radar sensor. According to the results, our proposed method can simultaneously detect targets and classify them with over 90% accuracy. In addition, it shows better performance in terms of detection and classification, compared with conventional methods such as density-based spatial clustering of applications with noise or the support vector machine. Moreover, the proposed method especially exhibits better performance when detecting and classifying a vehicle with a long body.

scholarly journals Machine Learning-Based Human Recognition Scheme Using a Doppler Radar Sensor for In-Vehicle Applications

Sensors ◽  
2020 ◽  
Vol 20 (21) ◽  
pp. 6202
Author(s):  
Eugin Hyun ◽  
Young-Seok Jin ◽  
Jae-Hyun Park ◽  
Jong-Ryul Yang
Keyword(s):  
Machine Learning ◽  
Classification Accuracy ◽  
Continuous Wave ◽  
Rigid Motion ◽  
Doppler Spectrum ◽  
Classification Error ◽  
Test Bed ◽  
Radar Sensor ◽  
Detection Scheme ◽  
Wave Radar

In this paper, we propose a Doppler spectrum-based passenger detection scheme for a CW (Continuous Wave) radar sensor in vehicle applications. First, we design two new features, referred to as an ‘extended degree of scattering points’ and a ‘different degree of scattering points’ to represent the characteristics of the non-rigid motion of a moving human in a vehicle. We also design one newly defined feature referred to as the ‘presence of vital signs’, which is related to extracting the Doppler frequency of chest movements due to breathing. Additionally, we use a BDT (Binary Decision Tree) for machine learning during the training and test steps with these three extracted features. We used a 2.45 GHz CW radar front-end module with a single receive antenna and a real-time data acquisition module. Moreover, we built a test-bed with a structure similar to that of an actual vehicle interior. With the test-bed, we measured radar signals in various scenarios. We then repeatedly assessed the classification accuracy and classification error rate using the proposed algorithm with the BDT. We found an average classification accuracy rate of 98.6% for a human with or without motion.

Human–vehicle classification using feature‐based SVM in 77‐GHz automotive FMCW radar

2017 ◽  
Vol 11 (10) ◽  
pp. 1589-1596 ◽  
Author(s):  
Seongwook Lee ◽  
Young‐Jun Yoon ◽  
Jae‐Eun Lee ◽  
Seong‐Cheol Kim
Keyword(s):  
Vehicle Classification ◽  
Fmcw Radar ◽  
Feature Based ◽  
77 Ghz

Binary Spectrum Feature for Improved Classifier Performance

2020 ◽  
Author(s):  
Nalika Ulapane ◽  
Karthick Thiyagarajan ◽  
sarath kodagoda
Keyword(s):  
Machine Learning ◽  
Classification Performance ◽  
Feature Reduction ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Svm Classifier ◽  
Monitoring Task ◽  
Classifier Performance ◽  
Spectrum Feature

<div>Classification has become a vital task in modern machine learning and Artificial Intelligence applications, including smart sensing. Numerous machine learning techniques are available to perform classification. Similarly, numerous practices, such as feature selection (i.e., selection of a subset of descriptor variables that optimally describe the output), are available to improve classifier performance. In this paper, we consider the case of a given supervised learning classification task that has to be performed making use of continuous-valued features. It is assumed that an optimal subset of features has already been selected. Therefore, no further feature reduction, or feature addition, is to be carried out. Then, we attempt to improve the classification performance by passing the given feature set through a transformation that produces a new feature set which we have named the “Binary Spectrum”. Via a case study example done on some Pulsed Eddy Current sensor data captured from an infrastructure monitoring task, we demonstrate how the classification accuracy of a Support Vector Machine (SVM) classifier increases through the use of this Binary Spectrum feature, indicating the feature transformation’s potential for broader usage.</div><div><br></div>

scholarly journals Millimeter-Wave Radar Sensor for Automated Tomographic Imaging of Composite Materials in a Manufacturing Environment

2021 ◽  
Vol 5 (3) ◽  
pp. 1-4
Author(s):  
Dominik Meier ◽  
Christian Zech ◽  
Benjamin Baumann ◽  
Bersant Gashi ◽  
Matthias Malzacher ◽  
...  
Keyword(s):  
Composite Materials ◽  
Millimeter Wave ◽  
Tomographic Imaging ◽  
Radar Sensor ◽  
Manufacturing Environment ◽  
Millimeter Wave Radar ◽  
Wave Radar

Virtual Radar: Real-Time Millimeter-Wave Radar Sensor Simulation for Perception-driven Robotics

2021 ◽  
pp. 1-1
Author(s):  
Christian Schoffmann ◽  
Barnaba Ubezio ◽  
Christoph Boehm ◽  
Stephan Muhlbacher-Karrer ◽  
Hubert Zangl
Keyword(s):  
Real Time ◽  
Millimeter Wave ◽  
Radar Sensor ◽  
Millimeter Wave Radar ◽  
Wave Radar

scholarly journals Interpretable deep learning for the remote characterisation of ambulation in multiple sclerosis using smartphones

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Andrew P. Creagh ◽  
Florian Lipsmeier ◽  
Michael Lindemann ◽  
Maarten De Vos
Keyword(s):  
Multiple Sclerosis ◽  
Deep Learning ◽  
Inertial Sensor ◽  
Heterogeneous Data ◽  
Fine Tuning ◽  
Sensor Data ◽  
Support Vector ◽  
Deep Convolutional Neural Networks ◽  
Healthcare Applications ◽  
Feature Based

AbstractThe emergence of digital technologies such as smartphones in healthcare applications have demonstrated the possibility of developing rich, continuous, and objective measures of multiple sclerosis (MS) disability that can be administered remotely and out-of-clinic. Deep Convolutional Neural Networks (DCNN) may capture a richer representation of healthy and MS-related ambulatory characteristics from the raw smartphone-based inertial sensor data than standard feature-based methodologies. To overcome the typical limitations associated with remotely generated health data, such as low subject numbers, sparsity, and heterogeneous data, a transfer learning (TL) model from similar large open-source datasets was proposed. Our TL framework leveraged the ambulatory information learned on human activity recognition (HAR) tasks collected from wearable smartphone sensor data. It was demonstrated that fine-tuning TL DCNN HAR models towards MS disease recognition tasks outperformed previous Support Vector Machine (SVM) feature-based methods, as well as DCNN models trained end-to-end, by upwards of 8–15%. A lack of transparency of “black-box” deep networks remains one of the largest stumbling blocks to the wider acceptance of deep learning for clinical applications. Ensuing work therefore aimed to visualise DCNN decisions attributed by relevance heatmaps using Layer-Wise Relevance Propagation (LRP). Through the LRP framework, the patterns captured from smartphone-based inertial sensor data that were reflective of those who are healthy versus people with MS (PwMS) could begin to be established and understood. Interpretations suggested that cadence-based measures, gait speed, and ambulation-related signal perturbations were distinct characteristics that distinguished MS disability from healthy participants. Robust and interpretable outcomes, generated from high-frequency out-of-clinic assessments, could greatly augment the current in-clinic assessment picture for PwMS, to inform better disease management techniques, and enable the development of better therapeutic interventions.

Sign in / Sign up

Export Citation Format

Share Document