当前位置:
X-MOL 学术
›
IEEE Trans. Cognit. Commun. Netw.
›
论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
An Improved Initialization Method for Fast Learning in Long Short-Term Memory-Based Markovian Spectrum Prediction
IEEE Transactions on Cognitive Communications and Networking ( IF 8.6 ) Pub Date : 2020-12-22 , DOI: 10.1109/tccn.2020.3046330 Niranjana Radhakrishnan , Sithamparanathan Kandeepan
IEEE Transactions on Cognitive Communications and Networking ( IF 8.6 ) Pub Date : 2020-12-22 , DOI: 10.1109/tccn.2020.3046330 Niranjana Radhakrishnan , Sithamparanathan Kandeepan
The opportunistic sharing of frequency bands supported in the Dynamic Spectrum Access (DSA) paradigm resolves the spectrum scarcity issue in wireless communications. To this end, deep learning models such as Long Short-Term Memory (LSTM) are becoming a popular choice for predicting the spectrum for cognitive radio type applications. However, the computational complexity to train such models can be very high, and delays in performing spectrum prediction (even in the order of msec) can reduce spectrum utilization efficiency. Here, we propose a novel method to initialize LSTM to reduce the training time to a good extent based on prior (statistical) knowledge of the input data and hence minimize the delay in spectrum prediction. This article proposes the ‘Kandeepan-Niranjana (
K-N
) initialization’, a novel initialization methodology for an LSTM based system model. We consider the well-known Markov model based spectrum utilization data with prior knowledge of the model parameters, such as the transition probabilities, to explain our method. Our results show that initialization with the parameters we propose provides a significant improvement in the training convergence of the LSTM based model for spectrum prediction. We also observe fast training convergence when the proposed method is applied to a real spectrum dataset.
中文翻译:
基于长短期记忆的马尔可夫谱预测中快速学习的改进初始化方法
动态频谱接入 (DSA) 范例中支持的频段机会共享解决了无线通信中的频谱稀缺问题。为此,长短期记忆 (LSTM) 等深度学习模型正成为预测认知无线电类型应用频谱的流行选择。然而,训练此类模型的计算复杂度可能非常高,并且执行频谱预测的延迟(甚至在毫秒级)会降低频谱利用效率。在这里,我们提出了一种基于输入数据的先验(统计)知识来初始化 LSTM 的新方法,以在很大程度上减少训练时间,从而最大限度地减少频谱预测的延迟。这篇文章提出了'Kandeepan-Niranjana (KN ) 初始化',一种用于基于 LSTM 的系统模型的新颖初始化方法。我们考虑众所周知的基于马尔可夫模型的频谱利用数据以及模型参数的先验知识,例如转换概率,来解释我们的方法。我们的结果表明,使用我们提出的参数进行初始化可以显着改善基于 LSTM 的频谱预测模型的训练收敛性。当所提出的方法应用于实际频谱数据集时,我们还观察到快速训练收敛。
更新日期:2020-12-22
中文翻译:
基于长短期记忆的马尔可夫谱预测中快速学习的改进初始化方法
动态频谱接入 (DSA) 范例中支持的频段机会共享解决了无线通信中的频谱稀缺问题。为此,长短期记忆 (LSTM) 等深度学习模型正成为预测认知无线电类型应用频谱的流行选择。然而,训练此类模型的计算复杂度可能非常高,并且执行频谱预测的延迟(甚至在毫秒级)会降低频谱利用效率。在这里,我们提出了一种基于输入数据的先验(统计)知识来初始化 LSTM 的新方法,以在很大程度上减少训练时间,从而最大限度地减少频谱预测的延迟。这篇文章提出了'Kandeepan-Niranjana (