A Brain Computer Interface Based Patient Observation and Indoor Locating System with Capsule Network Algorithm

Janeera, D. A.; Sasipriya, S.

doi:10.1007/978-3-030-51859-2_23

“…However due to the restriction on performing convolution, there is decrease in the need for learning more number of parameters. To solve this problem, researchers begun investigating deep learning networks [7] and the conventional iterative approaches, to provide a correlating link between the two methods. In [8] the authors analyzed the similarity between ISTA algorithm and proposed a neural network which comprised of shared layers resulting in fast approximated sparse coding.…”

Section: Introductionmentioning

confidence: 99%

September 2020

2020

JIIP

1

0

View full text Add to dashboard Cite

The proposed paper addresses the inverse problems using a novel deep convolutional neural network (CNN). Over the years, regularized iterative algorithms have been observed to be the standard approach to address this issue. Though these methodologies give an excellent output, they still impose challenges such as difficulty of hyper parameter selection, increasing computational cost for adjoint operators and forward operators. It has been observed that when the normal operator of the forward model is seen to be a convolution, unrolled iterative methods take up the CNN form. In view of this observation we have proposed a methodology which uses CNN after direct inversion to find the solution for convolutional inverse problem. In the first step the physical model of the system is analyzed using direct inversion. However, this leads to artifacts which are then removed using a combination of residual learning and multi-resolution decomposition in CNN. The results show that the performance of the proposed work outperforms other algorithm and requires a maximum of 1 second to reconstruct an image of high definition.

show abstract

A Deep Net Model for Covid-19 Detection Based on ROC Analysis Using Radiographs

Chauhan

¹

,

Pandey

²

2023

2023 International Conference on Artificial Intelligence and Smart Communication (AISC)

0

View full text Add to dashboard Cite

Posed Inverse Problem Rectification Using Novel Deep Convolutional Neural Network

Vijayakumar¹

2020

JIIP

66

0

View full text Add to dashboard Cite

The proposed paper addresses the inverse problems using a novel deep convolutional neural network (CNN). Over the years, regularized iterative algorithms have been observed to be the standard approach to address this issue. Though these methodologies give an excellent output, they still impose challenges such as difficulty of hyper parameter selection, increasing computational cost for adjoint operators and forward operators. It has been observed that when the normal operator of the forward model is seen to be a convolution, unrolled iterative methods take up the CNN form. In view of this observation we have proposed a methodology which uses CNN after direct inversion to find the solution for convolutional inverse problem. In the first step the physical model of the system is analyzed using direct inversion. However, this leads to artifacts which are then removed using a combination of residual learning and multi-resolution decomposition in CNN. The results show that the performance of the proposed work outperforms other algorithm and requires a maximum of 1 second to reconstruct an image of high definition.

show abstract

A Brain Computer Interface Based Patient Observation and Indoor Locating System with Capsule Network Algorithm

Cited by 8 publications

References 10 publications

September 2020

September 2020

A Deep Net Model for Covid-19 Detection Based on ROC Analysis Using Radiographs

Posed Inverse Problem Rectification Using Novel Deep Convolutional Neural Network

Contact Info

Product

Resources

About