Machine-learning-based beam steering in a hybrid plasmonic nano-antenna array

Korany R. Mahmoud; Korany R. Mahmoud; Ahmed M. Montaser

doi:10.1364/JOSAB.458574

Journal of the Optical Society of America B
Vol. 39,
Issue 8,
pp. 2149-2163
(2022)
•https://doi.org/10.1364/JOSAB.458574

Machine-learning-based beam steering in a hybrid plasmonic nano-antenna array

Korany R. Mahmoud and Ahmed M. Montaser

Not Accessible

Your library or personal account may give you access

Get PDF
Email
Share
Get Citation
Copy Citation Text
Korany R. Mahmoud and Ahmed M. Montaser, "Machine-learning-based beam steering in a hybrid plasmonic nano-antenna array," J. Opt. Soc. Am. B 39, 2149-2163 (2022)

Export Citation
- BibTex
- Endnote (RIS)
- HTML
- Plain Text
Citation alert
Save article

Check for updates

Related Topics
Table of Contents Category
- Optics Modes, Structured Light, and Beam Shaping
Optics & Photonics Topics
?

The topics in this list come from the Optics and Photonics Topics applied to this article.

About this Article
History
- Original Manuscript: March 14, 2022
- Revised Manuscript: June 19, 2022
- Manuscript Accepted: June 20, 2022
- Published: July 20, 2022

Abstract

In this paper, different beam-steering techniques are introduced using an ${{8}} \times {{8}}$ hybrid plasmonic nano-antenna array operating at 1550 nm. Two conventional techniques of the switched-beam and phased array are considered for implementing beam steering. For a switched-beam antenna, the beam steering is achieved by switching between the feed antenna elements, whereas the feed antenna array is attached to the back surface of a fishnet achromatic-metalens to collimate the rays. In the phased array antenna, the beam is steered by estimating the appropriate feeding phases of the 64 elements using a deep neural network (DNN) either with or without a lens and comparing the results with those obtained using a traditional method. Finally, a hybrid technique based on activating only a subset of antenna elements in the existence of the lens is proposed to steer the pattern in a certain direction. By predicting the proper feeding phases of the antenna array elements, the neural network with the backpropagation technique and weighted hybrid gravitational search algorithm-particle swarm optimization approach is used to beam-steer the pattern. Furthermore, the DNN is applied to assign the required active subset elements for directing the main beam toward the desired direction. Several sample examples are provided to beam-steer the pattern in numerous directions to assess the correctness of the strategies.

Full Article | PDF Article

More Like This

Photonic-enabled beam steering at 300 GHz using a photodiode-based antenna array and a polymer-based optical phased array

Simon Nellen, Tianwen Qian, Garrit Schwanke, Sebastian Lauck, David de Felipe, Moritz Kleinert, Milan Deumer, Lars Liebermeister, Moritz Baier, Bjoern Globisch, Norbert Keil, Robert B. Kohlhaas, and Martin Schell
Opt. Express 30(25) 44701-44716 (2022)

Beam steered graphene-based Yagi–Uda array antenna with a transverse magnetic to hybrid mode conversion approach

Rajesh Yadav, V. S. Pandey, Sandeep Kumar, and Shailza Gotra
J. Opt. Soc. Am. A 39(10) 1749-1759 (2022)

Metasurface-based Fourier lens fed by compact plasmonic optical antennas for wide-angle beam steering

Guangzhu Zhou, Shi-Wei Qu, Baojie Chen, Yuansong Zeng, and Chi Hou Chan
Opt. Express 30(12) 21918-21930 (2022)

Previous Article Next Article

Data availability

Data underlying the results presented in this paper are not publicly available at this time but may be obtained from the authors upon reasonable request.

Cited By

You do not have subscription access to this journal. Cited by links are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Figures (26)

You do not have subscription access to this journal. Figure files are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Tables (5)

You do not have subscription access to this journal. Article tables are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Equations (4)

You do not have subscription access to this journal. Equations are available to subscribers only. You may subscribe either as an Optica member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access Optica Member Subscription

Parameters	Symbol	Value
Neuron in the input layer	$a$	66
Neuron in the output layer	$v$	64
Neuron in the hidden layer	$h$	45
Coefficient of training	$η$	0.03

Sc.	Test Angle		ML Angle		Max. Gain	HPBW	SLL
No.	$θ$	$φ$	$θ$	$φ$	(dBi)	(°)	(dB)
1	75	75	77.5	71.2	24.1	8.1	−5.2
2	65	155	61.2	159.4	24.7	9.3	−6.7
3	55	−165	58.8	−163.4	23.8	7.5	−7.3
4	45	−5	49.6	−3.7	24.5	8.6	−5.1
5	−35	25	−33.7	29.8	24.6	9.1	−8.4
6	5	−55	6.3	−53.1	23.3	8.7	−6.5
7	−45	65	−43.2	67.4	23.2	8.4	−9.8
8	15	−85	17.8	−82.5	23.9	7.6	−7.0
9	−25	95	−28.6	93.9	24.0	8.2	−5.3
10	65	−105	62.4	−108.2	23.7	8.9	−8.7
11	−55	115	−53.4	119.5	24.9	7.7	−6.4
12	25	−125	27.6	−122.7	23.5	9.2	−10.3
13	−5	135	−3.5	135.1	24.4	8.6	−7.2
14	−45	−145	−44.1	−147.3	23.8	8.3	−9.6
15	−15	155	−16.7	151.2	24.2	7.8	−5.8
16	35	95	38.6	92.3	24.3	8.5	−6.1
17	5	45	3.7	47.9	23.1	7.9	−5.4
18	−15	−115	−18.1	−112.8	24.7	8.0	−8.0
19	−35	−55	−33	−58.2	23.0	9.1	−7.3
20	55	−65	57.8	−63.4	23.6	7.7	−10.2
21	−15	−25	−13.1	−28.2	24.8	8.5	−9.7
22	10	−5	8.3	−7.9	23.9	8.8	−6.8

	Steering
Active	Angle
Element No.	$θ$	$φ$	Max. Gain (dBi)	HPBW [°]	SLL (dB)
1	18	−45	18.92	4.2	−8.1
2	13	−57	18.94	4.3	−8.2
3	8	−68	18.97	3.9	−6.5
4	3	−82	18.99	4.3	−8.2
5	−3	−98	18.99	4.1	−7.6
6	−8	−112	18.97	3.9	−6.4
7	−13	−123	18.94	3.9	−6.8
8	−18	−135	18.92	4.1	−7.4
9	17	−37	19.00	4.3	−8.3
10	12	−48	19.03	4.3	−8.3
11	7	−59	19.15	3.9	−6.5
12	2	−80	19.21	4.3	−8.3
13	−2	−100	19.21	4.3	−8.3
14	−7	−119	19.15	4	−7.3
15	−12	−132	19.03	4.2	−8
16	−17	−143	19.00	3.9	−6.5
17	16	−25	19.33	4	−7.1
18	11	−33	19.39	4.3	−8.2
19	6	−47	19.42	3.7	−7.9
20	1	−73	19.45	4.3	−8.3
21	−1	−107	19.45	4.1	−7.6
22	−6	−133	19.42	3.8	−6.3
23	−11	−147	19.39	4.2	−8.1
24	−16	−155	19.33	4.3	−8.3
25	15	−8	19.44	4.1	−7.7
26	10	−12	19.47	4.2	−7.9
27	5	−33	19.49	4.2	−7.8
28	0	−45	19.51	4	−7.1
29	0	−135	19.51	4.1	−7.6
30	−5	−162	19.49	3.9	−6.6
31	−10	−168	19.47	4.2	−7.8
32	−15	−172	19.44	3.8	−6.3
33	18	8	19.44	3.9	−6.8
34	13	12	19.47	3.8	−6.3
35	8	11	19.49	3.9	−6.4
36	3	45	19.51	4.2	−8
37	−3	135	19.51	4.2	−7.7
38	−8	162	19.49	4	−6.9
39	−13	168	19.47	4.3	−8.3
40	−18	172	19.44	3.8	−6.3
41	17	25	19.33	4	−7.2
42	12	33	19.39	4	−7
43	7	47	19.42	4.2	−7.9
44	2	73	19.45	4.2	−7.9
45	−2	107	19.45	3.9	−6.6
46	−7	133	19.42	4.2	−7.3
47	−12	147	19.39	4	−7.2
48	−17	155	19.33	4.1	−7.6
49	16	37	19.00	4.2	−7.8
50	11	48	19.03	4.2	−7.9
51	6	59	19.15	3.9	−6.8
52	1	80	19.21	4.1	−7.7
53	−1	100	19.21	4.1	−7.6
54	−6	119	19.15	3.9	−6.6

	Test Angle		ML Angle
Sc. No.	$θ$	$φ$	$θ$	$φ$	HPBW [°]	SLL (dB)	Activated Elements
1	75	75	72.8	78.5	12.1	−20.2	35	42	43	51	52
2	65	155	67.4	153.6	11.5	−19.4	47	48	55	56	64
3	55	−165	58.2	−167.1	10	−15.2	22	23	24	31	32
4	45	−5	42.3	−7.9	12.2	−21.5	17	25	26	27	28
5	−35	25	−38.0	22.7	10.7	−18.7	15	22	23	29	30
6	5	−55	3.7	−57.6	11.8	−19.8	2	10	18	19	28
7	−45	65	−47.2	61.9	10.2	−17.1	28	29	30	36	43
8	15	−85	13.6	−88.0	12.4	−16.3	3	11	12	20	28
9	−25	95	−27.4	93.3	11.3	−18.6	45	46	53	54	61
10	65	−105	67.3	−102.5	12	−20.9	13	14	22	23	30
11	−55	115	−52.6	117.8	10.6	−15.3	19	28	37	45	46
12	25	−125	27.1	−122.7	12.7	−19	37	46	47	54	55
13	−5	135	−2.6	138.2	11.9	−17.8	20	28	29	36	37
14	−45	−145	−47.0	−143.4	10.8	−16.4	22	23	24	29	30
15	−15	155	−12.9	157.8	11.5	−21.2	20	28	30	37	38
16	35	95	38.7	94.0	10.1	−18.6	44	45	52	53	61
17	5	45	3.4	47.6	12.3	−15.7	28	29	36	37	43
18	−15	−115	−17.9	−112.2	10.9	−19.3	15	21	22	29	30
19	−35	−55	−32.1	−57.3	11.7	−20.5	38	46	47	48	56
20	55	−65	58.5	−62.6	11.6	−17.1	2	3	11	12	20
21	−15	−25	−17.2	−25	10.5	−19.4	19	27	28	37	46
22	10	−5	12.7	−7.8	12.4	−16.7	20	21	27	28	29

Parameters	Symbol	Value
Neuron in the input layer	$a$	66
Neuron in the output layer	$v$	64
Neuron in the hidden layer	$h$	45
Coefficient of training	$η$	0.03

Abstract

Data availability

Cited By

Figures (26)

Tables (5)

Equations (4)

Journal of the Optical Society of America B