RLRuisen Luo

Ruisen Luo

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Ruisen Luo has a total of 56 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A fully spatio-temporal dense neural network for automatic modulation recognition

    by Ruisen Luo, Yuheng Jiang, Xiaomei Qu, Xianglong Li, Xiaofeng Gong, Hongnan Huang, Ao Xiao, Tao Liu

  • Stacked hourglass network with integration of channel information for automatic modulation recognition

    by Xuanjin Xiong, Honglin Wu, Ruijuan Wu, Guo Xian, Xiaomei Yang, Ruisen Luo


  • A deep learning based algorithm with multi-level feature extraction for automatic modulation recognition

    by Hang Zhang, Ruihua Nie, Minghui Lin, Ruijuan Wu, Guo Xian, Xiaofeng Gong, Qin Yu, Ruisen Luo


  • MMD-encouraging convolutional autoencoder: a novel classification algorithm for imbalanced data

    by Bin Li, Xiaofeng Gong, Chen Wang, Ruijuan Wu, Tong Bian, Yanming Li, Zhiyuan Wang, Ruisen Luo


  • Open Access

    A convolutional recurrent neural network with attention framework for speech separation in monaural recordings

    by Chao Sun, Min Zhang, Ruijuan Wu, Junhong Lu, Guo Xian, Qin Yu, Xiaofeng Gong, Ruisen Luo

    Most speech separation studies in monaural channel use only a single type of network, and the separation effect is typically not satisfactory, posing difficulties for high quality speech separation. In this study, we propose a convolutional recurrent neural network with an attention (CRNN-A) framework for speech separation, fusing advantages of two networks together. The proposed separation framework uses a convolutional neural network (CNN) as the front-end of a recurrent neural network (RNN), alleviating the problem that a sole RNN cannot effectively learn the necessary features. This framework makes use of the translation invariance provided by CNN to extract information without modifying the original signals. Within the supplemented CNN, two different convolution kernels are designed to capture information in both the time and frequency domains of the input spectrogram. After concatenating the time-domain and the frequency-domain feature maps, the feature information of speech is exploited through consecutive convolutional layers. Finally, the feature map learned from the front-end CNN is combined with the original spectrogram and is sent to the back-end RNN. Further, the attention mechanism is further incorporated, focusing on the relationship among different feature maps. The effectiveness of the proposed method is evaluated on the standard dataset MIR-1K and the results prove that the proposed method outperforms the baseline RNN and other popular speech separation methods, in terms of GNSDR (gloabl normalised source-to-distortion ratio), GSIR (global source-to-interferences ratio), and GSAR (gloabl source-to-artifacts ratio). In summary, the proposed CRNN-A framework can effectively combine the advantages of CNN and RNN, and further optimise the separation performance via the attention mechanism. The proposed framework can shed a new light on speech separation, speech enhancement, and other related fields.


  • Open Access

    Adaptive Ensemble of Classifiers with Regularization for Imbalanced Data Classification

    by Chen Wang, Chengyuan Deng, Zhoulu Yu, Dafeng Hui, Xiaofeng Gong, Ruisen Luo

    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.

  • Classification of pure conduct disorder from healthy controls based on indices of brain networks during resting state

    by Jiang Zhang, Yuyan Liu, Ruisen Luo, Zhengcong Du, Fengmei Lu, Zhen Yuan, Jiansong Zhou, Shasha Li

    Conduct disorder (CD) is an important mental health problem in childhood and adolescence. There is presently a trend of revealing neural mechanisms using measures of brain networks. This study goes further by presenting a classification scheme to distinguish subjects with CD from typically developing healthy subjects based on measures of small-world networks. In this study, small-world networks were constructed, and feature data were generated for both the CD and healthy control (HC) groups. Two methods of feature selection, including the F-score and feature projection with singular value decomposition (SVD), were used to extract the feature data. Furthermore, and importantly, the classification performances were compared between the results from the two methods of feature selection. The selected feature data by SVD were employed to train three classifiers—least squares support vector machine (LS-SVM), naive Bayes and K-nearest neighbour (KNN)—for CD classification. Cross-validation results from 36 subjects showed that CD patients can be separated from HC with a sensitivity, specificity and overall accuracy of 88.89%, 100% and 94.44%, respectively, by using the LS-SVM classifier. These findings suggest that the combination of the LS-SVM classifier with SVD can achieve a higher degree of accuracy for CD diagnosis than the naive Bayes and KNN classifiers. Graphical abstract


  • An Improved Non-negative Matrix Factorization Method for Dynamic Industrial Fault Diagnosis

    by XiaoFeng Gong, Dongdong Sun, Zuodong Tang, Kai Zhou, RuiSen Luo

    Most classical fault diagnosis methods such as principal component analysis (PCA), are extracting comprehensive information to represent data features in fault diagnosis. In comparison, Non-Negative Matrix Factorization (NMF) is a method for dimension reduction and feature extraction, and because its characteristic matrix has sparsity, this method is superior in the ability of extracting the local feature and suppressing noises; however, the NMF method is not applicable for dynamic industrial processes. In this paper, we introduce the past information of industrial processes for fault diagnosis, proposing Canonical Variate Analysis - Non-Negative Matrix Factorization (CVA-NMF) methods to improve the dynamic performance of NMF. The experimental results via TE process indicate that the proposed approach could handle a dynamic production process such as Fault 2 and Fault 5 and retain the superior performance of NMF.


  • Open Access

    Fully Dense Neural Network for the Automatic Modulation Recognition

    by Miao Du, Qin Yu, Shaomin Fei, Chen Wang, Xiaofeng Gong, Ruisen Luo

    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.