Large-Scale Analysis of the Head Proximity Effects on Antenna Performance Using Machine Learning Based Models

Diao, Yinliang; Rashed, Essam A.; Hirata, Akimasa

doi:10.1109/access.2020.3017773

Cited by 4 publications

(3 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, ML is used to generate models for the experimentation of antenna performance of wireless devices adjacent to the human body, such as radiation patterns, return loss, impedance, etc. [146]. It has been utilized to predict breast cancer by estimating the S-parameter of an ultra-MIMO sensor antenna using PCA [147].…”

Section: Miscellaneous Applicationsmentioning

confidence: 99%

Application of Machine Learning in Electromagnetics: Mini-Review

et al. 2021

View full text Add to dashboard Cite

As an integral part of the electromagnetic system, antennas are becoming more advanced and versatile than ever before, thus making it necessary to adopt new techniques to enhance their performance. Machine Learning (ML), a branch of artificial intelligence, is a method of data analysis that automates analytical model building with minimal human intervention. The potential for ML to solve unpredictable and non-linear complex challenges is attracting researchers in the field of electromagnetics (EM), especially in antenna and antenna-based systems. Numerous antenna simulations, synthesis, and pattern recognition of radiations as well as non-linear inverse scattering-based object identifications are now leveraging ML techniques. Although the accuracy of ML algorithms depends on the availability of sufficient data and expert handling of the model and hyperparameters, it is gradually becoming the desired solution when researchers are aiming for a cost-effective solution without excessive time consumption. In this context, this paper aims to present an overview of machine learning, and its applications in Electromagnetics, including communication, radar, and sensing. It extensively discusses recent research progress in the development and use of intelligent algorithms for antenna design, synthesis and analysis, electromagnetic inverse scattering, synthetic aperture radar target recognition, and fault detection systems. It also provides limitations of this emerging field of study. The unique aspect of this work is that it surveys the state-of the art and recent advances in ML techniques as applied to EM.

show abstract

Section: Miscellaneous Applicationsmentioning

confidence: 99%

Application of Machine Learning in Electromagnetics: Mini-Review

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Patch antennas were backed by a large ground plane. The substrate relative permittivity was 2.2, with a thickness t. To obtain the space EF and MF around the antenna, in-house FDTD [26] code, which had been validated previously [10], [27], was employed. Simulations were performed at 30 GHz using a spatial resolution of 0.25 mm to satisfy the Courant condition.…”

Section: Simulation Modelsmentioning

confidence: 99%

Assessment of mmWave Exposure From Antenna Based on Transformation of Spherical Wave Expansion to Plane Wave Expansion

Diao

Hirata

2021

IEEE Access

Self Cite

View full text Add to dashboard Cite

To protect human beings from overexposure to mmWave electromagnetic fields, international guidelines and standard specified the (exposure) reference level in terms of the peak spatialaverage incident power density (psPD). In this study, we proposed a method to effectively assess the psPD from a mmWave antenna using its spherical near-field measurement data. This method employed the transformation of spherical wave expansion to plane wave expansion to reconstruct the electric and magnetic field components on an evaluation plane in front of the antenna aperture. The psPD was subsequently obtained based on the time-average Poynting vector. The accuracy of the proposed method was validated by comparing it with full-wave simulation results using 12 array antennas at frequencies ranging from 10 to 90 GHz. It was revealed that at 30 GHz, the reconstruction errors for psPD4cm2 were less than 0.8 dB and 0.2 dB on evaluation planes 2 and 5 mm, respectively, in front of the antennas. The robustness of the proposed method against the noise, scan range, and number of spherical modes were evaluated. The proposal may eliminate conventional compliance assessment procedures once antenna performance is evaluated in spherical near-field measurement.

show abstract

“…Machine learning has enormous potential in the realm of antenna design and antenna behavior prediction. With high accuracy it is found to be useful in various electromagnetic applications such as detecting breast cancer by studying radiation patterns, return loss, phase, and impedance [ 14 , 15 , 16 ].…”

Section: Introductionmentioning

confidence: 99%

Compact Wideband Double-Slot Microstrip Feed Engraved TEM Horn Strip Antennas on a Multilayer Substrate Board for in Bed Resting Body Positions Determination Based on Artificial Intelligence

Ghimire

Kim

Choi

2022

Sensors

View full text Add to dashboard Cite

In this paper, a horn-shaped strip antenna exponentially tapered carved on a multilayer dielectric substrate for an indoor body position tracking system is proposed. The performance of the proposed antenna was verified by testing it as a tracking state of an indoor resting body position. Among different feeding techniques, the uniplanar T-junction power divider approach is used. The performance verification of the proposed antenna is explained through its compact size and 3D shape, along with a performance comparison of the return loss radiation pattern and the realized gain. The suggested antenna has an 88.88% fractional bandwidth and a return loss between 6 and 15.6 GHz, with a maximum gain of 9.46 dBi in the 9.5 GHz region. Within the intended band, the radiation pattern had an excellent directivity characteristics. The proposed antenna was connected to an NVA-R661 module of Xethru Inc. for sleeping body position tracking. The performance of the antenna is measured through microwave imagining of the state of the resting body in various sleeping positions on the bed using a Recurrent Neural Network (RNN). The predicted outcomes clearly define the antenna’s performance and could be used for sensing and prediction purposes.

show abstract

Large-Scale Analysis of the Head Proximity Effects on Antenna Performance Using Machine Learning Based Models

Cited by 4 publications

References 46 publications

Application of Machine Learning in Electromagnetics: Mini-Review

Application of Machine Learning in Electromagnetics: Mini-Review

Assessment of mmWave Exposure From Antenna Based on Transformation of Spherical Wave Expansion to Plane Wave Expansion

Compact Wideband Double-Slot Microstrip Feed Engraved TEM Horn Strip Antennas on a Multilayer Substrate Board for in Bed Resting Body Positions Determination Based on Artificial Intelligence

Contact Info

Product

Resources

About