A Fairness of Data Combination in Wireless Packet Scheduling

Abstract

With the proliferation of artificial intelligence (AI) technology, the function of AI in a sixth generation (6G) environment is likely to come into play on a large scale. Moreover, in recent years, with the rapid advancement in AI technology, the ethical issues of AI have become a hot topic. In this paper, the ethical concern of AI in wireless networks is studied from the perspective of fairness in data. To make the dataset fairer, novel dataset categorization and dataset combination schemes are proposed. For the dataset categorization scheme, a deep-learning-based dataset categorization (DLDC) model is proposed. Based on the results of the DLDC model, the input dataset is categorized based on the group index. The datasets based on the group index are combined using various combination schemes. Through simulations, the results of each dataset combination method and their performance are compared, and the advantages and disadvantages of fairness and performance according to the dataset configuration are analyzed.

Keywords

• artificial intelligence
• ethical
• fairness
• packet scheduling
• wireless networks
• convolutional neural network