HYHui Yu

Hui Yu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hui Yu has a total of 31 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • NegEmotion: Explore the Double-Edged Sword Effect of Negative Emotion on Crowd Evacuation

    by Zena Tian, Guijuan Zhang, Hui Yu, Hong Liu, Dianjie Lu

    In emergencies, negative emotion has a significant impact on decision-making during crowd evacuation. Psychological studies suggest that negative emotion in decision-making has a double-edged sword effect. Excessive negative emotion has adverse impacts, such as causing crowd chaos and congestion. Conversely, moderate negative emotion has a positive effect by speeding up crowd movement. However, current researches mainly focus on one aspect which is how to reduce the negative effects of negative emotion on crowd evacuation, while overlooking the benefits of negative emotion. How to fully explore the double-edged sword effect of negative emotion and regulate negative emotion to improve the efficiency of crowd evacuation is still an open issue. To achieve this, we propose the NegEmotion model which considers the positive impact of negative emotion on crowd evacuation, and regulates crowd emotion by controlling knowledge spreading according to Siminov’s psychological principle. In this model, the knowledge spreading network (KSN) and the stress emotional contagion network (SECN) are constructed. Based on these networks, we study the evolution process of knowledge spreading and stress emotional contagion, respectively. Next, we formulate the emotional regulation as an optimization problem to maximize the efficiency of crowd evacuation. Then, a heuristic algorithm is used to solve for the optimal emotional regulation strategy. Finally, a crowd simulation system is implemented to verify the effectiveness of our NegEmotion model. The experimental results show that our method is effective to improve the efficiency of crowd evacuation.


  • Open Access

    Accelerating Convolutional Neural Network by Exploiting Sparsity on GPUs

    by Weizhi Xu, Yintai Sun, Shengyu Fan, Hui Yu, Xin Fu

    The convolutional neural network (CNN) is an important deep learning method, which is widely used in many fields. However, it is very time consuming to implement the CNN where convolution usually takes most of the time. There are many zero values in feature maps and filters, which leads to redundant calculations and memory accesses if dense methods are used to compute convolution. Many works recently have made use of sparsity to skip the calculations for zero values to reduce the inference time of the CNN. On the graphics processing unit platform, current works cannot fully exploit the sparsity of the feature map and achieve satisfactory performance. Therefore, we design a new parallel strategy to transform the feature map into a new storage format to avoid the redundant computation of zero values on graphics processing units. Also considering the sparsity in the feature map, we propose a fused storage format to combine the convolution operation with the following pooling operation, to further improve the performance. We carry out experiments with mainstream CNN models and achieve better performance compared with cuDNN and cuSPARSE. For VGG-19, ResNet-50, DenseNet-121, and RegNetX-16GF, 1.97×, 2.23×, 2.74×, and 1.58× speedups respectively are obtained over cuDNN. The speedups over cuSPARSE respectively are 2.10×, 1.83×, 2.35×, and 1.35× when only using the first method.


  • Open Access

    Deep Neural Network with Embedding Fusion for Chinese Named Entity Recognition

    by Kaifang Long, Han Zhao, Zengzhen Shao, Yang Cao, Yanfang Geng, Yintai Sun, Weizhi Xu, Hui Yu

    Chinese Named Entity Recognition (NER) is an essential task in natural language processing, and its performance directly impacts the downstream tasks. The main challenges in Chinese NER are the high dependence of named entities on context and the lack of word boundary information. Therefore, how to integrate relevant knowledge into the corresponding entity has become the primary task for Chinese NER. Both the lattice LSTM model and the WC-LSTM model did not make excellent use of contextual information. Additionally, the lattice LSTM model had a complex structure and did not exploit the word information well. To address the preceding problems, we propose a Chinese NER method based on the deep neural network with multiple ways of embedding fusion. First, we use a convolutional neural network to combine the contextual information of the input sequence and apply a self-attention mechanism to integrate lexicon knowledge, compensating for the lack of word boundaries. The word feature, context feature, bigram feature, and bigram context feature are obtained for each character. Second, four different features are used to fuse information at the embedding layer. As a result, four different word embeddings are obtained through cascading. Last, the fused feature information is input to the encoding and decoding layer. Experiments on three datasets show that our model can effectively improve the performance of Chinese NER.


  • Open Access

    CSCC: Convolution Split Compression Calculation Algorithm for Deep Neural Network

    by Shengyu Fan, Hui Yu, Dianjie Lu, Shuai Jiao, Weizhi Xu, Fangai Liu, Zhiyong Liu

    Convolutional Neural Networks (CNNs) have become one of the most successful machine learning techniques for image and video processing. The most computationally intensive part of the CNN is the convolutional layers, which have the multi-channel image and multiple kernels. However, due to the network pruning operation and the application of RELU activation function operation in the training process, numerous zero values are generated in the network. This paper proposes the convolution split compression calculation (CSCC) algorithm, which improves the performance of the convolution layer by utilizing the sparse characteristic of the feature map. In the CSCC algorithm, first, the feature map is directly converted into a sparse matrix of compressed sparse row (CSR) format, which avoids expanding feature map to an intermediate matrix and reduces the memory space consumption. Second, the convolution kernel is converted into a vector. Finally, the convolution result is obtained by the sparse matrix vector multiplication (SpMV). The experimental results show that the CSCC algorithm has a good advantage in computation speed and memory consumption compared with the other convolution algorithms.


  • Open Access

    A Novel Data Reuse Method to Reduce Demand on Memory Bandwidth and Power Consumption For True Motion Estimation

    by Weizhi Xu, Hui Yu, Dianjie Lu, Fangai Liu, Zhiyong Liu

    Motion estimation (ME) is a kernel algorithm in many video applications. Full search integer ME (FSIME) can find the best result but it usually takes plenty of time. Traditionally, only intra-frame data reuse is considered for FSIME. In this paper, a new inter-frame data reuse method is proposed to further utilize inter-frame data reuse for true ME. ME in frame rate up-conversion (FRUC-ME), a kind of true ME, is used as a case study. For FRUC-ME with the new inter-frame data reuse method, a frame is loaded to the on-chip buffer only once instead of twice and used for two interpolated frames. Two levels of the new method are proposed, Inter-D and new Inter-E, which give a good tradeoff between off-chip memory bandwidth and on-chip buffer size. New data access order is used to implement the new data reuse method. The proposed data reuse method (Inter-D) demands less off-chip memory bandwidth than its intra-frame counterpart (Intra-D), and the off-chip memory traffic and power consumption are both reduced by 37.5% for FRUC-ME.