Radio frequency fingerprint identification (RFID) provokes many promising applications of internet of things. Deep learning is considered as one of powerful tools to empower RFID techniques. Recently, several deep learning based RFID methods have been proposed. However, their deep neural networks were trained from the limited length of RF fingerprint samples due to the very high training cost. Hence, existing deep learning based RFID methods are hard to extract full features from the RF fingerprint (RFF) datasets. In order to solve this problem, we propose a joint multislice and cooperative detection aided RFID method based on deep learning. Firstly, acquisition equipment is used to collect RFF signals from seven power amplifiers, which are composed of in-phase and quadrature (IQ) samples with 200,000 sampling points. The IQ samples are sliced and turned into slices with fewer sampling points, which makes them use less training resources, and then they are input into neural network for training. The convolutional neural network (CNN) and convolutional long short-term deep neural networks (CLDNN) are used for training. Secondly, a cooperative detection algorithm is proposed to classify all slices from the same signal to determine the signal category. Finally, experiment results are given to confirm the proposed method in different scenarios. It shows that this method can greatly reduce the training resources, and at the same time maintain a high accuracy.

射频指纹识别（RFID）引发了物联网的许多有希望的应用。深度学习被认为是支持RFID技术的强大工具之一。最近，已经提出了几种基于深度学习的RFID方法。但是，由于训练成本非常高，因此从有限长度的RF指纹样本中训练了他们的深度神经网络。因此，现有的基于深度学习的RFID方法很难从RF指纹（RFF）数据集中提取全部特征。为了解决这个问题，我们提出了一种基于深度学习的联合多层和协同检测辅助RFID方法。首先，使用采集设备从七个功率放大器收集RFF信号，这些功率放大器由具有200,000个采样点的同相和正交（IQ）采样组成。将IQ样本切成薄片，并用更少的采样点切成薄片，这使它们使用的训练资源更少，然后将它们输入到神经网络中进行训练。卷积神经网络（CNN）和卷积长短期深度神经网络（CLDNN）用于训练。其次，提出了一种协同检测算法，对来自同一信号的所有片段进行分类，以确定信号类别。最后，通过实验结果验证了该方法在不同场景下的有效性。结果表明，该方法可以大大减少训练资源，同时保持较高的准确性。卷积神经网络（CNN）和卷积长短期深度神经网络（CLDNN）用于训练。其次，提出了一种协同检测算法，对来自同一信号的所有片段进行分类，以确定信号类别。最后，通过实验结果验证了该方法在不同场景下的有效性。结果表明，该方法可以大大减少训练资源，同时保持较高的准确性。卷积神经网络（CNN）和卷积长短期深度神经网络（CLDNN）用于训练。其次，提出了一种协同检测算法，对来自同一信号的所有片段进行分类，以确定信号类别。最后，通过实验结果验证了该方法在不同场景下的有效性。结果表明，该方法可以大大减少训练资源，同时保持较高的准确性。