In this article, we present our vision of preamble detection in a physical random access channel for next-generation (Next-G) networks using machine learning techniques. Preamble detection is performed to maintain communication and synchronization between devices of the Internet of Everything and next-generation nodes. Considering the scalability and traffic density, Next-G networks have to deal with preambles corrupted by noise due to channel characteristics or environmental constraints. We show that when injecting 15 percent random noise, the detection performance degrades to 48 percent. We propose an informative instance-based fusion Network (IIFNet) to cope with random noise and to improve detection performance simultaneously. A novel sampling strategy for selecting informa-tive instances from feature spaces has also been explored to improve detection performance. The proposed IIFNet is tested on a real dataset for preamble detection that was collected with the help of a reputable commercial company.

中文翻译：

---

IIFNet：基于融合的 6G 噪声前导检测智能服务

在本文中，我们展示了我们对使用机器学习技术的下一代 (Next-G) 网络的物理随机访问信道中的前导码检测的愿景。执行前导检测以保持万物互联的设备与下一代节点之间的通信和同步。考虑到可扩展性和流量密度，Next-G 网络必须处理由于信道特性或环境限制而被噪声破坏的前导码。我们表明，当注入 15% 的随机噪声时，检测性能会下降到 48%。我们提出了一个信息丰富的基于实例的融合网络（IIFNet）来应对随机噪声并同时提高检测性能。还探索了一种从特征空间中选择信息实例的新采样策略，以提高检测性能。提议的 IIFNet 在一个真实的数据集上进行了测试，该数据集是在一家知名商业公司的帮助下收集的，用于前导检测。