Medical Image Classification and Manifold Disease Identification through Convolutional Neural Networks: A Research Perspective

Kumar, K. Suresh; Radhamani, A. S.; Sundaresan, Sairam; Kumar, T. Ananth

doi:10.1201/9781003144694-8

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wavelet functions, an innovative method, are used to calculate the relative risk (RR) derived from PPG by the authors of the study [ 21 ]. Recent studies have shown that the Hilbert vibration decomposition (HVD) is an effective method for analyzing nonstationary signals [ 22 ]. HVD has been used in a broad number of applications relating to the processing of biological signals, one of which is the processing of cardiovascular signals.…”

Section: Literature Surveymentioning

confidence: 99%

Cryptography-Based Medical Signal Securing Using Improved Variation Mode Decomposition with Machine Learning Techniques

Shukla

Akanbi

Asakipaam

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

There is no question about the value that digital signal processing brings to the area of biomedical research. DSP processors are used to sample and process the analog inputs that are received from a human organ. These inputs come from the organ itself. DSP processors, because of their multidimensional data processing nature, are the electrical components that take up the greatest space and use the most power. In this age of digital technology and electronic gizmos, portable biomedical devices represent an essential step forward in technological advancement. Electrocardiogram (ECG) units are among the most common types of biomedical equipment, and their functions are absolutely necessary to the process of saving human life. In the latter part of the 1990s, portable electrocardiogram (ECG) devices began to appear on the market, and research into their signal processing and electronics design capabilities continues today. System-on-chip (SoC) design refers to the process through which the separate computing components of a DSP unit are combined onto a single chip in order to achieve greater power and space efficiency. In the design of biomedical DSP devices, this body of research presents a number of different solutions for reducing power consumption and space requirements. Using serial or parallel data buses, which are often the region that consumes the most power, it is possible to send data between the system-on-chip (SoC) and other components. To cut down on the number of needless switching operations that take place during data transmission, a hybrid solution that makes use of the shift invert bus encoding scheme has been developed. Using a phase-encoded shift invert bus encoding approach, which embeds the two-bit indication lines into a single-bit encoded line, is one way to solve the issue of having two distinct indicator bits. This method reduces the problem. The PESHINV approach is compared to the SHINV method that already exists, and the comparison reveals that the suggested PESHINV method reduces the total power consumption of the encoding circuit by around 30 percent. The computing unit of the DSP processor is the target of further optimization efforts. Virtually, all signal processing methods need memory and multiplier circuits to function properly.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Cryptography-Based Medical Signal Securing Using Improved Variation Mode Decomposition with Machine Learning Techniques

Shukla

Akanbi

Asakipaam

et al. 2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

Reviewing methods of deep learning for intelligent healthcare systems in genomics and biomedicine

Zafar,

Anwar,

kanwal

et al. 2023

Biomedical Signal Processing and Control

View full text Add to dashboard Cite

A Chaotic Encryption System Based on DNA Coding Using a Deep Neural Network

Sudha

Castro²,

Muthulakshmi

et al. 2022

Int. J. Image Grap.

View full text Add to dashboard Cite

Critical to computer vision applications, deep learning demands a massive volume of training data for great performance. However, encrypting the sensitive information in a photograph is fraught with difficulty, despite rapid technological advancements. The Advanced Encryption System (AES) is the bedrock of classical encryption technologies. The Data Encryption Standard (DES) has low sensitivity, with weak anti-hacking capabilities. In a chaotic encryption system, a chaotic logistic map is employed to generate a key double logistic sequence, and deoxyribonucleic acid (DNA) matrices are created by DNA coding. The XOR operation is carried out between the DNA sequence matrix and the key matrix. Finally, the DNA matrix is decoded to obtain an encrypted image. Given that encrypted images are susceptible to attacks, a rapid and efficient Convolutional Neural Network (CNN) denoiser is used that enhances the robustness of the algorithm by maximizing the resolution of rebuilt images. The use of a key mixing percentage factor gives the proposed system vast key space and great key sensitivity. Its implementation is examined using statistical techniques such as histogram analysis, information entropy, key space analysis and key sensitivity. Experiments have shown that the suggested system is secure and robust to statistical and noise attacks.

show abstract

Medical Image Classification and Manifold Disease Identification through Convolutional Neural Networks: A Research Perspective

Cited by 4 publications

References 0 publications

Cryptography-Based Medical Signal Securing Using Improved Variation Mode Decomposition with Machine Learning Techniques

Cryptography-Based Medical Signal Securing Using Improved Variation Mode Decomposition with Machine Learning Techniques

Reviewing methods of deep learning for intelligent healthcare systems in genomics and biomedicine

A Chaotic Encryption System Based on DNA Coding Using a Deep Neural Network

Contact Info

Product

Resources

About