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 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.

Risk of Falling in a Timed Up and Go Test Using an UWB Radar and an Instrumented Insole.

Previously, studies reported that falls analysis is possible in the elderly, when using wearable sensors. However, these devices cannot be worn daily, as they need to be removed and recharged from time-to-time due to their energy consumption, data transfer, attachment to the body, etc. This study proposes to introduce a radar sensor, an unobtrusive technology, for risk of falling analysis and combine its performance with an instrumented insole. We evaluated our methods on datasets acquired during a Timed Up and Go (TUG) test where a stride length (SL) was computed by the insole using three approaches. Only the SL from the third approach was not statistically significant (p = 0.2083 > 0.05) compared to the one provided by the radar, revealing the importance of a sensor location on human body. While reducing the number of force sensors (FSR), the risk scores using an insole containing three FSRs and y-axis of acceleration were not significantly different (p > 0.05) compared to the combination of a single radar and two FSRs. We concluded that contactless TUG testing is feasible, and by supplementing the instrumented insole to the radar, more precise information could be available for the professionals to make accurate decision.