YZYou Zhang

You Zhang

*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


You Zhang has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Traditional Chinese medicine residues promote the growth and quality of Salvia miltiorrhiza Bunge by improving soil health under continuous monoculture

    by Sha Liu, Guang Yang, Faming Wu, Yang Ge, Fusong Liu, Chunjuan Pu, Zihan Wang, Ye Shen, Xiuteng Zhou, Yuzhi Luo, et al.

    Continuous monoculture of crops has resulted in reduced yields and quality, as well as soil deterioration. Although traditional Chinese medicine residues (TCMRs) are known to promote plant growth and soil health, few studies have investigated their effectiveness in continuous monoculture soils. Here, we studied the impact of chemical fertilizers (CF) and four TCMRs with antibacterial activities on the growth of S. miltiorrhiza (a widely used medicinal plant in China), accumulation of active ingredients in plants, and soil health under continuous monoculture conditions. Compared with no fertilizer (CK) and CF, fermented Sophora flavescens radix residue (SFRf) and fermented and unfermented Moutan cortex residue (MCRf and MCRu, respectively) resulted in a reduction of the disease index of root rot, while CF did not. The CF and four TCMR treatments increased the accumulation of nitrogen (N) (42.8-124.6% and 17.0-101.7%), phosphorous (P) (19.8-74.7% and 8.3-27.4%), and potassium (K) (104.1-212.0% and 9.3-51.8%) in shoots and roots compared to CK. The differences in nutrient accumulation between the CF and TCMR treatments were statistically insignificant, excepted for the N accumulation in the roots. All fertilization treatments increased plant biomass compared to CK, with increases of 25.57-89.86% and 2.62-35.28% in shoots and roots, respectively. The SFRf treatment exhibited the most significant enhancement in both shoot and root biomass. CF significantly reduced the accumulation of seven active ingredients in roots by 23.90-78.95% compared to CK, whereas each TCMR increased accumulation of certain active ingredients. The TCMR treatments effectively improved the health of deteriorated soil by enhancing soil physicochemical properties, restoring the balance of the microbial community, recruiting beneficial bacteria, and reducing the relative abundance of the pathogen Fusarium. The SFRf treatment exhibited superior performance in improving soil health than other treatments. Overall, the TCMRs outperformed CF in restoring soil health and promoting the yield and quality of S. miltiorrhiza. These findings offer guidance for improving the health of continuous cropping soil and recycling TCMRs.


  • Visualizing Deep Learning-Based Radio Modulation Classifier

    by Liang Huang, You Zhang, Weijian Pan, Jinyin Chen, Li Ping Qian, Yuan Wu

    Deep learning has recently been successfully applied in automatic modulation classification by extracting and classifying radio features in an end-to-end way. However, deep learning-based radio modulation classifiers are lacking interpretability, and there is little explanation or visibility into what kinds of radio features are extracted and chosen for classification. In this paper, we visualize different deep learning-based radio modulation classifiers by introducing a class activation vector. Specifically, both convolutional neural networks (CNN) based classifier and long short-term memory (LSTM) based classifier are separately studied, and their extracted radio features are visualized. We explore different hyperparameter settings via extensive numerical evaluations and show both the CNN-based classifier and LSTM-based classifiers extract similar radio features relating to modulation reference points. In particular, for the LSTM-based classifier, its obtained radio features are similar to the knowledge of human experts. Our numerical results indicate the radio features extracted by deep learning-based classifiers greatly depend on the contents carried by radio signals, and a short radio sample may lead to misclassification.


  • Open Access

    Data Augmentation for Deep Learning-Based Radio Modulation Classification

    by Liang Huang, Weijian Pan, You Zhang, Liping Qian, Nan Gao, Yuan Wu

    Deep learning has recently been applied to automatically classify the modulation categories of received radio signals without manual experience. However, training deep learning models requires massive volume of data. An insufficient training data will cause serious overfitting problem and degrade the classification accuracy. To cope with small dataset, data augmentation has been widely used in image processing to expand the dataset and improve the robustness of deep learning models. However, in wireless communication areas, the effect of different data augmentation methods on radio modulation classification has not been studied yet. In this paper, we evaluate different data augmentation methods via a state-of-the-art deep learning-based modulation classifier. Based on the characteristics of modulated signals, three augmentation methods are considered, i.e., rotation, flip, and Gaussian noise, which can be applied in both training phase and inference phase of the deep learning algorithm. Numerical results show that all three augmentation methods can improve the classification accuracy. Among which, the rotation augmentation method outperforms the flip method, both of which achieve higher classification accuracy than the Gaussian noise method. Given only 12.5% of training dataset, a joint rotation and flip augmentation policy can achieve even higher classification accuracy than the baseline with initial 100% training dataset without augmentation. Furthermore, with data augmentation, radio modulation categories can be successfully classified using shorter radio samples, leading to a simplified deep learning model and shorter the classification response time.