Generative Adversarial Networks : A Survey

kakkar, Tanuj; Singh, Upasna

doi:10.21203/rs.3.rs-300223/v1

Cited by 5 publications

(4 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Methods based on GANs have been applied to generate high-quality COVID-19 CT images [35,36]. However, GANs usually require enormous data with high computational costs, especially when high-quality and high-resolution synthetic images are needed [37,38]. The time required to customise and fine tune the model is ill-advised for rapid response in a fast-spreading pandemic.…”

Section: Synthetic Ct Images 221 Selection Of Synthesis Methodsmentioning

confidence: 99%

A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak

Hou

Navarro‐Cía

2023

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

Coronavirus disease 2019 (COVID-19) has spread globally for over three years, and chest computed tomography (CT) has been used to diagnose COVID-19 and identify lung damage in COVID-19 patients. Given its widespread, CT will remain a common diagnostic tool in future pandemics, but its effectiveness at the beginning of any pandemic will depend strongly on the ability to classify CT scans quickly and correctly when only limited resources are available, as it will happen inevitably again in future pandemics. Here, we resort into the transfer learning procedure and limited hyperparameters to use as few computing resources as possible for COVID-19 CT images classification. Advanced Normalisation Tools (ANTs) are used to synthesise images as augmented/independent data and trained on EfficientNet to investigate the effect of synthetic images. On the COVID-CT dataset, classification accuracy increases from 91.15% to 95.50% and Area Under the Receiver Operating Characteristic (AUC) from 96.40% to 98.54%. We also customise a small dataset to simulate data collected in the early stages of the outbreak and report an improvement in accuracy from 85.95% to 94.32% and AUC from 93.21% to 98.61%. This study provides a feasible Low-Threshold, Easy-To-Deploy and Ready-To-Use solution with a relatively low computational cost for medical image classification at an early stage of an outbreak in which scarce data are available and traditional data augmentation may fail. Hence, it would be most suitable for low-resource settings.

show abstract

Section: Synthetic Ct Images 221 Selection Of Synthesis Methodsmentioning

confidence: 99%

A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak

Hou

Navarro‐Cía

2023

Biomed. Phys. Eng. Express

View full text Add to dashboard Cite

show abstract

“…One of the most prominent techniques in GAI are generative adversarial networks (GANs), which consist of two NNs, a generator and a discriminator, that work together to produce realistic outputs (Creswell et al, 2018). GANs have been widely used in various applications such as image generation, data augmentation, and video synthesis (Kakkar & Singh, 2021). ANNs, on the other hand, which are modeled after the structure of the human brain, are an essential component of artificial intelligence.…”

Section: Generative Artificial Intelligence and Neural Network: Defin...mentioning

confidence: 99%

A Generative AI and Neural Network Approach to Sustainable Digital Transformation: A Focus on Medical and Marketing Sectors

Röser

2024

Fenntarthatósági Átmenet: Kihívások És Innovatív Megoldások : Nemzetközi Tudományos Konferencia a Magyar Tudomány Ünnepe Alkalm

View full text Add to dashboard Cite

Artificial intelligence (AI), in particular generative AI (GAI) and neural networks (NN), is emerging as a transformative force in the evolving landscape of digital transformation in industries such as medicine and marketing. The paper describes the actual and potential impact of AI on the advancement of sustainable practices in these areas through a theoretical study of existing research. Through case studies, from NN in medicine, e.g., skin cancer diagnosis to GAI in marketing strategy, we highlight current applications and challenges. Despite the undeniable capabilities of AI in these domains, there remains a dearth of research that links AI to tangible sustainability outcomes. Our findings on AI in marketing highlight its importance in enhancing branding, optimizing pricing, refining channels and personalizing promotions. Furthermore, the application possibilities of NN in medical are presented. Due to the high model quality in the field of cancer detection, diagnostic processes can be designed more efficiently by NN and thus staff shortages can be compensated cost-efficiently and patient-centered. However, while AI offers promising opportunities, it also requires an ethical, socially responsible approach, as underscored by recent studies. This research underscores the imperative of AI integration for holistic, sustainable outcomes in the medical and marketing sector.

show abstract

Section: Generative Artificial Intelligence and Neural Network: Defin...mentioning

confidence: 99%

Fenntarthatósági átmenet: kihívások és innovatív megoldások : Nemzetközi tudományos konferencia a Magyar Tudomány Ünnepe alkalmából

2024

View full text Add to dashboard Cite

The European project was borne out of the strong desire of Western European politicians to root out wars and create peace and prosperity in Europe in the post-war period. With the Eastern enlargement of the EU, this mission seemed completed. However, a series of crises starting in 2008 with the Global Financial Crisis revealed many pressing problems in the European integration process. The EU needs to adapt to the new geopolitical and geoeconomic realities while it should take new initiatives to make European integration fair and sustainable. In this paper, using a new conceptual framework, we analyse the factors that hinder fairness and sustainability in the EU and suggest broad directions for reforms that can promote the European integration process.

show abstract

Generative Adversarial Networks : A Survey

Cited by 5 publications

References 29 publications

A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak

A computationally-inexpensive strategy in CT image data augmentation for robust deep learning classification in the early stages of an outbreak

A Generative AI and Neural Network Approach to Sustainable Digital Transformation: A Focus on Medical and Marketing Sectors

Fenntarthatósági átmenet: kihívások és innovatív megoldások : Nemzetközi tudományos konferencia a Magyar Tudomány Ünnepe alkalmából

Contact Info

Product

Resources

About