arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.00328eess.SPcs.LG
收藏

用于频谱预测的可微高阶 Markov 模型

Differentiable High-Order Markov Models for Spectrum Prediction

Mitsubishi Electric R&D Centre Europe(三菱电机欧洲研发中心);Mitsubishi Electric Corporation(三菱电机公司)

Vincent Corlay, Tatsuya Nakazato, Kanako Yamaguchi, Akinori Nakajima

AI总结:

本文重新研究高阶 Markov 频谱预测,提出缓解阶数与感知长度不匹配及状态空间复杂性的框架,并通过梯度监督学习微调转移矩阵,在受限含异常值的真实 Wi-Fi 数据上媲美深度学习。

摘要:

深度学习和循环神经网络的出现彻底改变了时间序列处理领域。因此,近期关于频谱预测的研究集中于使用这些工具。然而,频谱预测涉及预测无线频谱的可用性,是一个更古老的领域,在2010年代前后曾考虑过许多“经典”工具,例如 Markov 模型。本工作重新审视用于动态无线环境中频谱预测的高阶 Markov 模型。我们提出一个框架,以解决感知长度与模型阶数之间的不匹配,以及高阶情况下产生的状态空间复杂性。此外,我们扩展了该 Markov 框架,使其能够通过基于梯度的监督学习对概率转移矩阵进行微调,从而提供一种连接概率建模与现代机器学习的混合方法。在真实 Wi-Fi 流量上的仿真表明,与深度学习方法相比,高阶 Markov 模型具有具有竞争力的性能,尤其是在包含异常值且数据集受限的场景中。

英文摘要:

The advent of deep learning and recurrent neural networks revolutionized the field of time-series processing. Therefore, recent research on spectrum prediction has focused on the use of these tools. However, spectrum prediction, which involves forecasting wireless spectrum availability, is an older field where many "classical" tools were considered around the 2010s, such as Markov models. This work revisits high-order Markov models for spectrum prediction in dynamic wireless environments. We introduce a framework to address mismatches between sensing length and model order as well as state-space complexity arising with large order. Furthermore, we extend this Markov framework by enabling fine-tuning of the probability transition matrix through gradient-based supervised learning, offering a hybrid approach that bridges probabilistic modeling and modern machine learning. Simulations on real-world Wi-Fi traffic demonstrate the competitive performance of high-order Markov models compared to deep learning methods, particularly in scenarios with constrained datasets containing outliers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑