In this paper, a method for nonlinear target recognition via machine learning is presented. The nonlinear radar environment used in this study was a frequency-modulated continuous-wave (FMCW) nonlinear radar with a transmit frequency band of 3.0∼3.2 GHz and received a frequency band of 6∼6.4 GHz corresponding to the second harmonics. Nonlinear radar measurements were performed using four types of electronic devices as nonlinear targets. Statistical parameters were extracted from the measured amplitude spectrum of the received harmonic responses for each target to successfully construct a classification algorithm. The extracted characteristic data were then used to construct and verify a support vector machine (SVM) classifier. The accuracy of the target classification by the trained SVM classifier was confirmed through verification data, and an accuracy of 85 % with 10-fold cross-validation was demonstrated.

This paper proposes a compact K-band dual-circularly polarized antenna that can be implemented on a non-linear tag based on third-order intermodulation (IM3) for bio-sensing applications. The proposed antenna has the characteristics of being low-profile and lightweight, with opposite circular polarizations (CP) between ports. The non-linear tag-based bio-sensing scenario utilizes K-band millimeter wave frequencies, which allows for compact non-linear tags for attachment to the body. Also, the proposed antenna features dual-CP, which are for the reception and re-radiation of incident transmit signals and the IM3 responses, respectively. To this end, a two-port traveling-wave series-fed patch array with coplanar proximity coupling is designed. Here, to minimize the size of the antenna, we use only four circular patch elements with a modified diamond-shaped microstrip feedline. Through simulation and measurement, we demonstrate that the proposed antenna has an axial ratio of less than 3 dB from 23.25 GHz to 24.1 GHz, with the reflection coefficients below −10 dB and port-to-port coupling below −15 dB. These results indicate the potential utility of the proposed antenna as a tag antenna for non-linear detection-based bio-sensing applications.