当前位置: X-MOL 学术ACM Trans. Internet Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Blockchain-enabled Tensor-based Conditional Deep Convolutional GAN for Cyber-physical-Social Systems
ACM Transactions on Internet Technology ( IF 5.3 ) Pub Date : 2021-06-21 , DOI: 10.1145/3404890
Jun Feng 1 , Laurence T. Yang 2 , Yuxiang Zhu 1 , Nicholaus J. Gati 1 , Yijun Mo 1
Affiliation  

Deep learning techniques have shown significant success in cyber-physical-social systems (CPSS). As an instance of deep learning models, generative adversarial nets (GAN) model enables powerful and flexible image augmentation, image generation, and classification, thus can be applied to real-world CPSS settings. GAN model training needs a large collection of cyber-physical-social data originating from various CPSS devices. Numerous prevailing GAN models depend on a tacit assumption that several cyber-physical-social data providers present a reliable source to collect training data, which is seldom the case in real CPSS. The existing GAN models also fail to consider multi-dimensional latent structure. In our work, we put forward a novel blockchain-enabled tensor-based conditional deep convolutional GAN (TCDC-GAN) model for cyber-physical-social systems. The blockchain is employed to develop a decentralized and reliable cyber-physical-social data-sharing platform between numerous cyber-physical-social data providers, such that the training data and the model are documented on a ledger that is distributed. Furthermore, a tensor-based generator and a tensor-based discriminator are well designed by employing the tensor model. The results of extensive simulation experiments show the efficacy of the proposed TCDC-GAN model. Compared with the state-of-the-art models, our model gains superior estimation performance.

中文翻译:

基于区块链的基于张量的条件深度卷积 GAN,用于网络-物理-社会系统

深度学习技术在网络-物理-社会系统 (CPSS) 中取得了巨大成功。作为深度学习模型的一个实例,生成对抗网络 (GAN) 模型能够实现强大而灵活的图像增强、图像生成和分类,因此可以应用于现实世界的 CPSS 设置。GAN 模型训练需要大量来自各种 CPSS 设备的网络-物理-社会数据。许多流行的 GAN 模型都依赖于一个默认的假设,即几个网络-物理-社会数据提供者提供了一个可靠的来源来收集训练数据,这在真正的 CPSS 中很少出现。现有的 GAN 模型也未能考虑多维潜在结构。在我们的工作中,我们提出了一种新的基于区块链的基于张量的条件深度卷积 GAN (TCDC-GAN) 模型,用于网络-物理-社会系统。区块链用于在众多网络-物理-社会数据提供者之间开发一个分散且可靠的网络-物理-社会数据共享平台,以便将训练数据和模型记录在分布式账本上。此外,利用张量模型很好地设计了基于张量的生成器和基于张量的鉴别器。大量模拟实验的结果表明了所提出的 TCDC-GAN 模型的有效性。与最先进的模型相比,我们的模型获得了优越的估计性能。区块链用于在众多网络-物理-社会数据提供者之间开发一个分散且可靠的网络-物理-社会数据共享平台,以便将训练数据和模型记录在分布式账本上。此外,利用张量模型很好地设计了基于张量的生成器和基于张量的鉴别器。大量模拟实验的结果表明了所提出的 TCDC-GAN 模型的有效性。与最先进的模型相比,我们的模型获得了优越的估计性能。区块链用于在众多网络-物理-社会数据提供者之间开发一个分散且可靠的网络-物理-社会数据共享平台,以便将训练数据和模型记录在分布式账本上。此外,利用张量模型很好地设计了基于张量的生成器和基于张量的鉴别器。大量模拟实验的结果表明了所提出的 TCDC-GAN 模型的有效性。与最先进的模型相比,我们的模型获得了优越的估计性能。大量模拟实验的结果表明了所提出的 TCDC-GAN 模型的有效性。与最先进的模型相比,我们的模型获得了优越的估计性能。大量模拟实验的结果表明了所提出的 TCDC-GAN 模型的有效性。与最先进的模型相比,我们的模型获得了优越的估计性能。
更新日期:2021-06-21
down
wechat
bug