AUTHOR=Liu Zhewei , Guo Dayong 

TITLE=Assessing the carbon footprint of soccer events through a lightweight CNN model utilizing transfer learning in the pursuit of carbon neutrality

JOURNAL=Frontiers in Ecology and Evolution

VOLUME=Volume 11 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/ecology-and-evolution/articles/10.3389/fevo.2023.1208643

DOI=10.3389/fevo.2023.1208643

ISSN=2296-701X

ABSTRACT=In soccer competitions, a lot of energy needs to be used, resulting in a lot of carbon emissions. Therefore, reducing the cost of soccer events and reducing energy consumption in the context of carbon neutrality is one of the important ways to accelerate the realization of the goal of carbon neutrality. For this type of problem, most of the current methods often have many parameters, high equipment requirements, and time-consuming reasoning and training. This makes them unsuitable for deployment in real-world industrial scenarios. To address this issue, we propose a lightweight CNN model based on transfer learning to study cost minimization strategies for soccer events in a carbon-neutral context. This lightweight CNN network uses a novel downsampling module based on the human brain for information processing. This module processes input information more efficiently, improving training and inference speed. Furthermore, we introduce a transfer learning based module that speeds up the training progress and shortens the overall training time in the early stages of training. Our experimental results show that our proposed network model has significant advantages over existing models in terms of the number of parameters and computation, while achieving higher recognition accuracy than conventional models. It can effectively predict soccer event data, and then conduct data analysis to propose more reasonable strategies to optimize event costs and accelerate the realization of carbon neutral goals.