Fast fourier transform based new pooling layer for deep learning

Aqeel Mohsin Hamad

doi:10.2478/ijssis-2022-0003

.blurhash-client-img { display: none !important; }

Fast fourier transform based new pooling layer for deep learning

International Journal on Smart Sensing and Intelligent Systems

Volume 15 (2022): Issue 1 (January 2022)

By: Aqeel Mohsin Hamad

Open Access

|Apr 2022

Figures & Tables

Table 1

Performance of proposed methods.

Images	Metrics	Saeedan et al. (2018)	Lee et al. (2016)	FTM1	FTM2	FTM3
Lena	SNR dB	23.28	24.01	24.1754	24.1603	24.16785
	SSIM	0.7882	0.7893	0.79396	0.77886	0.78641
	Correlation	0.9822	0.9833	0.9846	0.9695	0.97705
Cameraman	SNR	20.14	21.87	20.2935	20.2784	20.28595
	SSIM	0.7854	0.7867	0.7891	0.774	0.78155
	Correlation	0.9814	0.9843	0.9952	0.9801	0.98765
Barbara	SNR	23.69	22.13	27.336	27.3209	27.32845
	SSIM	0.7041	0.7065	0.7092	0.6941	0.70165
	Correlation	0.9622	0.9648	0.9612	0.9461	0.95365
Test image	SNR	28.98	28.78	29.38	29.3649	29.37245
	SSIM	0.7832	0.7841	0.7852	0.7701	0.77765
	Correlation	0.9913	0.9922	0.9965	0.9814	0.98895

Original images, pooled images and reconstructed images by FTM1.

Table 2

Proposed methods results for MNIST dataset.

Method	Saeedan et al. (2018)	Lee et al. (2016)	FTM1	FTM2	FTM3
Accuracy (%)	98.80	98.72	99.95	99.84	99.96

Accuracy of MNIST classification for proposed method.

Sensitivity results for proposed method for MNIST classification.

Specificity results for proposed method for MNIST classification.

Training steps for MNIST classification by (FTM1) method.

Table 3

Confusion matrix for (FTM1) method for MNIST Classification.

	Target class
	Class 0	Class 1	Class 2	Class 3	Class 4	Class 5	Class 6	Class 7	Class 8	Class 9	Sensitivity
Output class
Class 0	250	0	0	0	0	0	0	0	0	0	100
Class 1	0	250	0	0	0	0	0	0	0	0	100
Class 1	0	10%	0	0	0	0	0	0	0	0	%
Class 2	0	0	250	0	0	0	0	0	0	0	100
Class 2	0	0	10%	0	0	0	0	0	0	0	%
Class 3	0	0	0	250	0	0	0	0	0	0	100
Class 3	0	0	0	10%	0	0	0	0	0	0	%
Class 4	0	0	0	0	250	0	0	0	0	0	100
Class 4	0	0	0	0	10%	0	0	0	0	0	%
Class 5	0	0	0	0	0	250	0	0	0	0	100
Class 5	0	0	0	0	0	10%	0	0	0	0	%
Class 6	0	0	0	0	0	0	249	0	0	0	100
Class 6	0	0	0	0	0	0	10%	0	0	0	%
Class 7	0	0	0	0	0	0	0	250	0	0	100
Class 7	0	0	0	0	0	0	0	10%	0	0	%
Class 8	0	0	0	0	0	0	1	0	250	0	99.9
Class 8	0	0	0	0	0	0	1	0	10%	0	6%
Class 9	0	0	0	0	0	0	0	0	0	250	100
Class 9	0	0	0	0	0	0	0	0	0	10%	%
	100	100	100	100	100	100	100	99.9	100	100	100
	%	%	%	%	%	%	%	6%	%	%	%

Table 4

Accuracy results for CIFAR10 dataset classification.

Method	Saeedan et al. (2018)	Lee et al. (2016)	RFT1	RFT2	RFT3
Accuracy (%)	72.59	72.4	73.88	73.82	73.76

Table 5

Confusion matrix for (FTM1) for CIFAR_10 classification.

	Target class
	airplane	*auto mobi*	bird	cat	deer	dog	frog	hour	ship	truc	Sens
Output class
airpla	796	29	68	32	25	13	10	22	57	3	73
autom	10	829	6	6	4	2	3	4	15	7	86
bird	44	10	599	62	69	42	37	32	13	8	66
cat	18	3	61	533	36	16	57	43	10	9	56
deer	24	3	75	60	708	38	26	55	5	1	71
dog	4	4	109	201	55	69	22	97	4	3	58
frog	9	9	46	66	54	13	83	5	7	1	78
hours	7	1	16	12	38	25	3	72	2	4	86
ship	48	36	9	14	9	6	4	6	86	2	82
truck	38	75	8	13	4	6	2	8	18	80	83
specifi	79.8	82.3	59.8	53.3	71.6	69	83	73	86	82	74

Accuracy results for proposed method for CIFAR 10 classification.

Specificity results for proposed method for CIFAR 10 classification.

Precision results for proposed method for CIFAR 10 classification.

References

Authors

Metrics

Articles in this issue

DOI: https://doi.org/10.2478/ijssis-2022-0003 | Journal eISSN: 1178-5608

Journal RSS Feed

Language: English

Submitted on: Jul 1, 2021

Published on: Apr 15, 2022

Published by: International Journal on Smart Sensing and Intelligent Systems

In partnership with: Paradigm Publishing Services

Publication frequency: 1 issue per year

Keywords:

CNN,

DL,

FFT,

FTM and Features

Related subjects:

Engineering,

Introductions and overviews,

Engineering, other

© 2022 Aqeel Mohsin Hamad, published by International Journal on Smart Sensing and Intelligent Systems
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

Volume 15 (2022): Issue 1 (January 2022)

Fast fourier transform based new pooling layer for deep learning

Figures & Tables

Figure 1

Figure 2

Figure 3

Figure 4

Table 1

Figure 5

Table 2

Figure 6

Figure 7

Figure 8

Figure 9

Table 3

Table 4

Table 5

Figure 10

Figure 11

Figure 12

Paradigm

My account