Dr.Puja Padiya
Dr.Puja Padiya has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Dr.Amarsinh Vidhate
Department of Computer Engineering D. Y. Patil Deemed to Ramrao Adik Institute of Technology University Nerul 400706 Navi Mumbai
1 shared publication - Ekta Sarda
Ramrao Adik Institute of Technology, D. Y Patil Deemed to be University
1 shared publication - Himanshu Bhamare
Postgraduate Student Department of Computer Engineering D. Y Ramrao Adik Institute of Technology Patil Deemed to be University Nerul 400706 Navi Mumbai
1 shared publication - Pallavi Sapkale
Ramrao Adik Institute of Technology, D. Y Patil Deemed to be University
1 shared publication - Shamal Salunkhe
Ramrao Adik Institute of Technology, D.Y. Patil Deemed to be University, Navi Mumbai, India
1 shared publication - Smita Bharne
Ramrao Adik Institute of Technology, D Y Patil deemed to be University, Navi Mumbai, India
1 shared publication
Latest Publications
- Open Access
- 16 April 2025
- Published by Springer Nature in Research Square
Towards Sustainable Image Synthesis: A Comprehensive Review of Text-to-Image Generation Models
Text to image generation is a significant area in artificial intelligence, through which descriptive caption can be described and detailed high-context relevant images produced. In the recent years the domain of text-to-image generation has witnessed significant progress, propelled by the development of diverse generative models. This work provides a detailed comprehensive analysis of the prominent image generation models, with a specific emphasis on their capacity to convert textual descriptions into visually consistent and contextually precise images. We systematically evaluate models such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and the more recent Diffusion Models. We also provide an overview of sustainable image synthesis models such as DALLE-2, Stable Diffusion, Imagen and MidJourney. It indicates significant progress made towards the generation of ultra-realistic high-resolution pictures, but still underlies serious issues of semantic coherence, fine-grained control and computational expensive tasks. The findings also emphasize on current challenges and possible future sustainable paths in the field, which contribute to the continuous advancement of more advanced and efficient image generation models.
- 16 April 2025
- Published by Springer Nature in Research Square
Open AccessTowards Sustainable Image Synthesis: A Comprehensive Review of Text-to-Image Generation Models
Text to image generation is a significant area in artificial intelligence, through which descriptive caption can be described and detailed high-context relevant images produced. In the recent years the domain of text-to-image generation has witnessed significant progress, propelled by the development of diverse generative models. This work provides a detailed comprehensive analysis of the prominent image generation models, with a specific emphasis on their capacity to convert textual descriptions into visually consistent and contextually precise images. We systematically evaluate models such as Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and the more recent Diffusion Models. We also provide an overview of sustainable image synthesis models such as DALLE-2, Stable Diffusion, Imagen and MidJourney. It indicates significant progress made towards the generation of ultra-realistic high-resolution pictures, but still underlies serious issues of semantic coherence, fine-grained control and computational expensive tasks. The findings also emphasize on current challenges and possible future sustainable paths in the field, which contribute to the continuous advancement of more advanced and efficient image generation models.
- Open Access
- 4 November 2024
- Published by Dewspublication
- Vol. 20 (S14) , 2351-2364
Enhanced Reliability In Iot With Sdn By Multifactor Authentication Approach
As part of the evolving Internet of Things (IoT), security threats are becoming increasingly rampant as the number of connected devices grows, causing hackers to find their way into devices and steal sensitive data. Given the vulnerabilities of IoT devices, this paper proposes a Multi-factor Authentication (MFA) framework employing Software Defined Networking (SDN). Unlike conventional single-factor techniques, it present a method that integrates token and one-time password (OTP) authentication mechanisms under the centralized management of an SDN controller. The proposed framework minimizes unauthorized access and thus maintains network security by dynamically managing and enacting authentication rules. This paper describes, the architecture, components, and expected performance of the proposed MFA solution, paving the way for secure IoT-SDN environments and looking ahead at scalability and resilience.
- 4 November 2024
- Published by Dewspublication
- Vol. 20 (S14) , 2351-2364
Open AccessEnhanced Reliability In Iot With Sdn By Multifactor Authentication Approach
As part of the evolving Internet of Things (IoT), security threats are becoming increasingly rampant as the number of connected devices grows, causing hackers to find their way into devices and steal sensitive data. Given the vulnerabilities of IoT devices, this paper proposes a Multi-factor Authentication (MFA) framework employing Software Defined Networking (SDN). Unlike conventional single-factor techniques, it present a method that integrates token and one-time password (OTP) authentication mechanisms under the centralized management of an SDN controller. The proposed framework minimizes unauthorized access and thus maintains network security by dynamically managing and enacting authentication rules. This paper describes, the architecture, components, and expected performance of the proposed MFA solution, paving the way for secure IoT-SDN environments and looking ahead at scalability and resilience.