Multivalued neutrosophic fractals and Hutchinson-Barnsley operator in neutrosophic metric space

Saleem, Naeem; Ahmad, Khaleel; Ishtiaq, Umar; Sen, Manuel De la

doi:10.1016/j.chaos.2023.113607

Cited by 3 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to ensure the symmetry of the number of images in each data category, we collected 990 violent images from the Internet to construct the data set of this paper. In this paper, the image data set was enhanced by changing the brightness, chromaticity, contrast, sharpness, and fuzzy noise [37] and via mirror transformation; the number of images was increased under the premise of ensuring the integrity of the image features. The final data set contains 11,476 pornographic images, 9290 normal images, and 8415 violent images.…”

Section: Experimental Data Setsmentioning

confidence: 99%

RepVGG-SimAM: An Efficient Bad Image Classification Method Based on RepVGG with Simple Parameter-Free Attention Module

Cai,

Qiao,

Zhang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

With the rapid development of Internet technology, the number of global Internet users is rapidly increasing, and the scale of the Internet is also expanding. The huge Internet system has accelerated the spread of bad information, including bad images. Bad images reflect the vulgar culture of the Internet. They will not only pollute the Internet environment and impact the core culture of society but also endanger the physical and mental health of young people. In addition, some criminals use bad images to induce users to download software containing computer viruses, which also greatly endanger the security of cyberspace. Cyberspace governance faces enormous challenges. Most existing methods for classifying bad images face problems such as low classification accuracy and long inference times, and these limitations are not conducive to effectively curbing the spread of bad images and reducing their harm. To address this issue, this paper proposes a classification method (RepVGG-SimAM) based on RepVGG and a simple parameter-free attention mechanism (SimAM). This method uses RepVGG as the backbone network and embeds the SimAM attention mechanism in the network so that the neural network can obtain more effective information and suppress useless information. We used pornographic images publicly disclosed by data scientist Alexander Kim and violent images collected from the internet to construct the dataset for our experiment. The experimental results prove that the classification accuracy of the method proposed in this paper can reach 94.5% for bad images, that the false positive rate of bad images is only 4.3%, and that the inference speed is doubled compared with the ResNet101 network. Our proposed method can effectively identify bad images and provide efficient and powerful support for cyberspace governance.

show abstract

Section: Experimental Data Setsmentioning

confidence: 99%

RepVGG-SimAM: An Efficient Bad Image Classification Method Based on RepVGG with Simple Parameter-Free Attention Module

Cai,

Qiao,

Zhang

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

Strong fixed points for Pata-type coupling with application in fractal generation by construction of iterated function systems

Roy,

Saha,

Choudhury

2024

Asian-European J. Math.

View full text Add to dashboard Cite

In this paper, in the first place, a strong coupled fixed point result is established for couplings satisfying Pata-type contractive conditions along with certain corollaries and a supportive illustration. Couplings are combinations of coupled and cyclic maps which have appeared in recent literature and have several applications. The illustrative example shows that the theorem properly extends some of the existing results. In the second part of the paper we construct a special type of iterated function system and, utilizing the coupled fixed point theorem introduced in this work, we show that such systems lead to strong fractal sets. This part of the paper is a part of the Hutchinson–Barnsley theory.

show abstract

Uncertainty measurement for incomplete lattice-valued information system

Guo

2024

IFS

View full text Add to dashboard Cite

We analyze the properties and characteristics of the information structure in incomplete lattice-valued information system (ILIS), we redefine the information structure and the dependence and information distance between the two information structures. In addition, in order to evaluate the uncertainty of ILIS, the concepts of granular measure and entropy measure are expounded, including information granulation, information quantity, rough entropy and information entropy. Finally, we carry out numerical experiments to verify the feasibility of the method, and carry out effective statistical analysis. These results are conducive to the establishment of granular computing framework in ILIS.

show abstract

Multivalued neutrosophic fractals and Hutchinson-Barnsley operator in neutrosophic metric space

Cited by 3 publications

References 18 publications

RepVGG-SimAM: An Efficient Bad Image Classification Method Based on RepVGG with Simple Parameter-Free Attention Module

RepVGG-SimAM: An Efficient Bad Image Classification Method Based on RepVGG with Simple Parameter-Free Attention Module

Strong fixed points for Pata-type coupling with application in fractal generation by construction of iterated function systems

Uncertainty measurement for incomplete lattice-valued information system

Contact Info

Product

Resources

About