Low-cost microwave biomedical imaging

Bialkowski, Konstanty; Marimuthu, J.; Abbosh, Amin

doi:10.1109/iceaa.2016.7731494

Cited by 2 publications

(2 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mainstream approaches as in [2,3] depend crucially on the backscattered fields of these objects such as their radar cross sectional area (RCS) when illuminated by a field source. However, other approaches proposed target detection mechanisms based on imaging techniques where the whole process depends solely on data extracted from images, e.g., field pattern, rather than working directly with the much more complex 3-dimensional field-theoretic electromagnetic problem [4][5][6][7][8][9][10][11].…”

Section: Introductionmentioning

confidence: 99%

A Spatial Sem-Based Shallow Neural Network for Electromagnetic Inverse Source Modeling

Alzahed¹,

Mikki²,

Antar³

2020

PIER M

View full text Add to dashboard Cite

We derive and verify a new type of low-complexity neural networks using the recently introduced spatial singularity expansion method (S-SEM). The neural network consists of a single layer (shallow learning approach to machine learning) but with its activation function replaced by specialized S-SEM radiation mode functions derived by electromagnetic theory. The proposed neural network can be trained by measured near-or far-field data, e.g., RCS, probe-measured fields, array manifold samples, in order to reproduce the unknown source current on the radiating structure. We apply the method to wire structures and show that the various spatial resonances of the radiating current can be very efficiently predicted by the S-SEM-based neural network. Convergence results are compared with Genetic Algorithms and are found to be considerably superior in speed and accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

A Spatial Sem-Based Shallow Neural Network for Electromagnetic Inverse Source Modeling

Alzahed¹,

Mikki²,

Antar³

2020

PIER M

View full text Add to dashboard Cite

show abstract

“…Two prominent approaches to acquiring the information are either (a) to generate an actual pulse and transmit and receive time-domain data or (b) to acquire frequency domain data over a wide bandwidth and synthesize the recordings into the equivalent time domain pulse. For the former, prototype systems designed by Zeng et al (2014), Porter et al (2013), Kubota et al (2014), Fasoula et al (2018), Marimuthu et al (2016), and Bialkowski et al (2016) have been produced and tested. The Zeng et al system generates a 100 ps pulse (translating to a 3.5 GHz bandwidth centered at 3.0 GHz) through connectorized components and records transmission data.…”

Section: Introductionmentioning

confidence: 99%

A 4-channel, vector network analyzer microwave imaging prototype based on software defined radio technology

Meaney

Hartov

Bulumulla

et al. 2019

Review of Scientific Instruments

View full text Add to dashboard Cite

We have implemented a prototype 4-channel transmission-based, microwave measurement system built on innovative software defined radio (SDR) technology. The system utilizes the B210 USRP SDR developed by Ettus Research that operates over a 70 MHz-6 GHz bandwidth. While B210 units are capable of being synchronized with each other via coherent reference signals, they are somewhat unreliable in this configuration and the manufacturer recommends using N200 or N210 models instead. For our system, N-series SDRs were less suitable because they are not amenable to RF shielding required for the cross-channel isolation necessary for an integrated microwave imaging system. Consequently, we have configured an external reference that overcame these limitations in a compact and robust package. Our design exploits the rapidly evolving technology being developed for the telecommunications environment for test and measurement tasks with the higher performance specifications required in medical microwave imaging applications. In a larger channel configuration, the approach is expected to provide performance comparable to commercial vector network analyzers at a fraction of the cost and in a more compact footprint.

show abstract

Low-cost microwave biomedical imaging

Cited by 2 publications

References 13 publications

A Spatial Sem-Based Shallow Neural Network for Electromagnetic Inverse Source Modeling

A Spatial Sem-Based Shallow Neural Network for Electromagnetic Inverse Source Modeling

A 4-channel, vector network analyzer microwave imaging prototype based on software defined radio technology

Contact Info

Product

Resources

About