Ruisen Luo

Miao Du, Qin Yu, Shaomin Fei et al.

Nowadays, we mainly use various convolution neural network (CNN) structures to extract features from radio data or spectrogram in AMR. Based on expert experience and spectrograms, they not only increase the difficulty of preprocessing, but also consume a lot of memory. In order to directly use in-phase and quadrature (IQ) data obtained by the receiver and enhance the efficiency of network extraction features to improve the recognition rate of modulation mode, this paper proposes a new network structure called Fully Dense Neural Network (FDNN). This network uses residual blocks to extract features, dense connect to reduce model size, and adds attentions mechanism to recalibrate. Experiments on RML2016.10a show that this network has a higher recognition rate and lower model complexity. And it shows that the FDNN model with dense connections can not only extract features effectively but also greatly reduce model parameters, which also provides a significant contribution for the application of deep learning to the intelligent radio system.

Ruisen Luo, Tao Hu, Zuodong Tang et al.

To solve the problem of inaccurate recognition of types of communication signal modulation, a RNN neural network recognition algorithm combining residual block network with attention mechanism is proposed. In this method, 10 kinds of communication signals with Gaussian white noise are generated from standard data sets, such as MASK, MPSK, MFSK, OFDM, 16QAM, AM and FM. Based on the original RNN neural network, residual block network is added to solve the problem of gradient disappearance caused by deep network layers. Attention mechanism is added to the network to accelerate the gradient descent. In the experiment, 16QAM, 2FSK and 4FSK are used as actual samples, IQ data frames of signals are used as input, and the RNN neural network combined with residual block network and attention mechanism is trained. The final recognition results show that the average recognition rate of real-time signals is over 93%. The network has high robustness and good use value.

Chen Wang, Chengyuan Deng, Zhoulu Yu et al.

The dynamic ensemble selection of classifiers is an effective approach for processing label-imbalanced data classifications. However, such a technique is prone to overfitting, owing to the lack of regularization methods and the dependence of the aforementioned technique on local geometry. In this study, focusing on binary imbalanced data classification, a novel dynamic ensemble method, namely adaptive ensemble of classifiers with regularization (AER), is proposed, to overcome the stated limitations. The method solves the overfitting problem through implicit regularization. Specifically, it leverages the properties of stochastic gradient descent to obtain the solution with the minimum norm, thereby achieving regularization; furthermore, it interpolates the ensemble weights by exploiting the global geometry of data to further prevent overfitting. According to our theoretical proofs, the seemingly complicated AER paradigm, in addition to its regularization capabilities, can actually reduce the asymptotic time and memory complexities of several other algorithms. We evaluate the proposed AER method on seven benchmark imbalanced datasets from the UCI machine learning repository and one artificially generated GMM-based dataset with five variations. The results show that the proposed algorithm outperforms the major existing algorithms based on multiple metrics in most cases, and two hypothesis tests (McNemar's and Wilcoxon tests) verify the statistical significance further. In addition, the proposed method has other preferred properties such as special advantages in dealing with highly imbalanced data, and it pioneers the research on the regularization for dynamic ensemble methods.

Ruisen Luo, Tianran Sun, Chen Wang et al.

As an important part of speech recognition technology, automatic speech keyword recognition has been intensively studied in recent years. Such technology becomes especially pivotal under situations with limited infrastructures and computational resources, such as voice command recognition in vehicles and robot interaction. At present, the mainstream methods in automatic speech keyword recognition are based on long short-term memory (LSTM) networks with attention mechanism. However, due to inevitable information losses for the LSTM layer caused during feature extraction, the calculated attention weights are biased. In this paper, a novel approach, namely Multi-layer Attention Mechanism, is proposed to handle the inaccurate attention weights problem. The key idea is that, in addition to the conventional attention mechanism, information of layers prior to feature extraction and LSTM are introduced into attention weights calculations. Therefore, the attention weights are more accurate because the overall model can have more precise and focused areas. We conduct a comprehensive comparison and analysis on the keyword spotting performances on convolution neural network, bi-directional LSTM cyclic neural network, and cyclic neural network with the proposed attention mechanism on Google Speech Command datasets V2 datasets. Experimental results indicate favorable results for the proposed method and demonstrate the validity of the proposed method. The proposed multi-layer attention methods can be useful for other researches related to object spotting.

Chen Wang, Xiaomei Yang, Shaomin Fei et al.

Quantization can be used to form new vectors/matrices with shared values close to the original. In recent years, the popularity of scalar quantization for value-sharing applications has been soaring as it has been found huge utilities in reducing the complexity of neural networks. Existing clustering-based quantization techniques, while being well-developed, have multiple drawbacks including the dependency of the random seed, empty or out-of-the-range clusters, and high time complexity for a large number of clusters. To overcome these problems, in this paper, the problem of scalar quantization is examined from a new perspective, namely sparse least square optimization. Specifically, inspired by the property of sparse least square regression, several quantization algorithms based on $l_1$ least square are proposed. In addition, similar schemes with $l_1 + l_2$ and $l_0$ regularization are proposed. Furthermore, to compute quantization results with a given amount of values/clusters, this paper designed an iterative method and a clustering-based method, and both of them are built on sparse least square. The paper shows that the latter method is mathematically equivalent to an improved version of k-means clustering-based quantization algorithm, although the two algorithms originated from different intuitions. The algorithms proposed were tested with three types of data and their computational performances, including information loss, time consumption, and the distribution of the values of the sparse vectors, were compared and analyzed. The paper offers a new perspective to probe the area of quantization, and the algorithms proposed can outperform existing methods especially under some bit-width reduction scenarios, when the required post-quantization resolution (number of values) is not significantly lower than the original number.