Search

This paper introduces a cutting-edge data architecture designed for a smart advertising context, prioritizing efficient data flow and performance, robust security, while guaranteeing data privacy and integrity. At the core of this study lies the application of federated learning (FL) as the primary methodology, which emphasizes the authenticity and privacy of data while promptly discarding irrelevant or fraudulent information. Our innovative data model employs a semi-random role assignment strategy based on a variety of criteria to efficiently collect and amalgamate data. The architecture is composed of model nodes, data nodes, and validator nodes, where the role of each node is determined by factors such as computational capability, interconnection quality, and historical performance records. A key feature of our proposed system is the selective engagement of a subset of nodes for modeling and validation, optimizing resource use and minimizing data loss. The AROUND social network platform serves as a real-world case study, illustrating the efficacy of our data architecture in a practical setting. Both simulated and real implementations of our architecture showcase its potential to dramatically curtail network traffic and average CPU usage, while preserving the accuracy of the FL model. Remarkably, the system is capable of achieving over a 50% reduction in both network traffic and average CPU usage even when the user count escalates by twenty-fold. The click rate, user engagement, and other parameters have also been evaluated, proving that the proposed architecture's advantages do not affect the smart advertising accuracy. These findings highlight the proposed architecture's capacity to scale efficiently and maintain high performance in smart advertising environments, making it a valuable contribution to the evolving landscape of digital marketing and FL. [ABSTRACT FROM AUTHOR]

This paper introduces a cutting-edge data architecture designed for a smart advertising context, prioritizing efficient data flow and performance, robust security, while guaranteeing data privacy and integrity. At the core of this study lies the application of federated learning (FL) as the primary methodology, which emphasizes the authenticity and privacy of data while promptly discarding irrelevant or fraudulent information. Our innovative data model employs a semi-random role assignment strategy based on a variety of criteria to efficiently collect and amalgamate data. The architecture is composed of model nodes, data nodes, and validator nodes, where the role of each node is determined by factors such as computational capability, interconnection quality, and historical performance records. A key feature of our proposed system is the selective engagement of a subset of nodes for modeling and validation, optimizing resource use and minimizing data loss. The AROUND social network platform serves as a real-world case study, illustrating the efficacy of our data architecture in a practical setting. Both simulated and real implementations of our architecture showcase its potential to dramatically curtail network traffic and average CPU usage, while preserving the accuracy of the FL model. Remarkably, the system is capable of achieving over a 50% reduction in both network traffic and average CPU usage even when the user count escalates by twenty-fold. The click rate, user engagement, and other parameters have also been evaluated, proving that the proposed architecture’s advantages do not affect the smart advertising accuracy. These findings highlight the proposed architecture’s capacity to scale efficiently and maintain high performance in smart advertising environments, making it a valuable contribution to the evolving landscape of digital marketing and FL.

Smart advertising is an important part of the modern information industry. The main problems of smart advertising in Chinese cities at this stage include cluttered settings, single form, lack of coordination and integration between advertising and cities and urban buildings, and inconspicuous visual effects. In order to deal with these problems, it is necessary to optimize the design of smart advertisements to enhance the visual aesthetic effect. Image aesthetics quality assessment has good application prospects in industries such as image recommendation and image editing aesthetics, and can be used to help smart advertisements improve visual aesthetics. This paper proposes an objective quantitative scoring method for image aesthetics based on a multi-scale feature extraction network, which is a computational intelligence approach. The model is mainly composed of multiple multi-scale feature extraction units cascaded, and each unit contains a feature extraction layer composed of 3 different convolution kernels, fusion layer and mapping layer. The feature extraction layer forms the input end of the network by combining the global view and local view of the image. At the output end, the EMD function is used as the loss function, and the output distribution is a probability density mass function of 1–10 points. In order to verify the effectiveness of the method in this paper, the AVA dataset, which is commonly used in the field of image aesthetic evaluation, is selected for testing experiments. In this paper, two parameters, Spearman Rank Correlation Coefficient and accuracy rate, are selected as indicators to evaluate the method in this paper. The experimental results show that the method proposed in this paper is feasible and effective. Outperforms several mainstream models on the AVA dataset. [ABSTRACT FROM AUTHOR]