林志坚 高学伟 陈小培 祝志鹏 杜小勇 陈平平
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0026
To tackle the challenge of applying convolutional neural network (CNN) in field-programmable gate array (FPGA) due to its computational complexity, a high-performance CNN hardware accelerator based on Verilog hardware description language was designed, which utilizes a pipeline architecture with three parallel dimensions including input channels, output channels, and convolution kernels. Firstly, two multiply-and-accumulate (MAC) operations were packed into one digital signal processing (DSP) block of FPGA to double the computation rate of the CNN accelerator. Secondly, strategies of feature map block partitioning and special memory arrangement were proposed to optimize the total amount of off-chip access memory and reduce the pressure on FPGA bandwidth. Finally, an efficient computational array combining multiplicative-additive tree and Winograd fast convolution algorithm was designed to balance hardware resource consumption and computational performance. The high parallel CNN accelerator was deployed in ZU3EG of Alinx, using the YOLOv3-tiny algorithm as the test object. The average computing performance of the CNN accelerator is 127.5 giga operations per second (GOPS). The experimental results show that the hardware architecture effectively improves the computational power of CNN and provides better performance compared with other existing schemes in terms of power consumption and the efficiency of DSPs and block random access memory (BRAMs).
张新 娄皓然 蒋励 肖前浩 蔡著文
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0025
李娜 武阳阳 刘颖 李大湘 高嘉乐
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0007
林子涵 郑嘉利 谢孝德 冯敏瑜 何思怡
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0008
谢孝德 郑嘉利 林子涵 何思怡 冯敏瑜
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0010
张承畅 徐余 杨建鹏 李晓梦
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0009
晁浩 连卫芳 刘永利
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0017
The research of emotion recognition based on electroencephalogram (EEG) signals often ignores the related information between the brain electrode channels and the contextual emotional information existing in EEG signals, which may contain important characteristics related to emotional states. Aiming at the above defects, a spatiotemporal emotion recognition method based on a 3-dimensional (3D) time-frequency domain feature matrix was proposed. Specifically, the extracted time-frequency domain EEG features are first expressed as a 3D matrix format according to the actual position of the cerebral cortex. Then, the input 3D matrix is processed successively by multivariate convolutional neural network (MVCNN) and long short-term memory (LSTM) to classify the emotional state. Spatiotemporal emotion recognition method is evaluated on the DEAP data set, and achieved accuracy of 87.58% and 88.50% on arousal and valence dimensions respectively in binary classification tasks, as well as obtained accuracy of 84.58% in four class classification tasks. The experimental results show that 3D matrix representation can represent emotional information more reasonably than two-dimensional (2D). In addition, MVCNN and LSTM can utilize the spatial information of the electrode channels and the temporal context information of the EEG signal respectively.
李玉杰 张晶晶 蒋伟 王春晓
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0006
Emotional space refers to a multi-dimensional emotional model that describes a group of subjective feelings or emotions. Since the existing discrete emotional space is mainly aimed at human’s primary emotions, it cannot describe the complex emotions evoked when watching movies. In order to solve this problem, an emotional fusion space for videos was constructed by selecting movies and TV dramas with rich emotional semantics as the research objects. Firstly, emotional words based on movie and TV drama videos are acquired and analyzed by using subjective evaluation and semantic analysis methods. Then, the emotional word vectors obtained from the above analysis are fused, reduced dimension by t-distributed stochastic neighbor embedding (t-SNE) algorithm, and clustered by bisecting K-means clustering algorithm to get a discrete emotional space for movie and TV drama videos. This emotional fusion space can obtain different categories by changing the value of the emotion classification number without re-labeling and calculation.
李富澄 邓军勇 朱筠 罗佳莹 任含
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0005
张函 井音吉 赵永利
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0018
There are many studies on sales forecasting in e-commerce, most of which focus on how to forecast sales volume with related e-commerce operation data. In this paper, a deep learning method named FS-LSTM was proposed, which combines long short-term memory (LSTM) and feature selection mechanism to forecast the sales volume. The indicators with most contributions by the extreme gradient boosting (XGBoost) model are selected as the input features of LSTM model. FS-LSTM method can get less mean average error (MAE) and mean squared error (MSE) in the forecasting of e-commerce sales volume, comparing with the LSTM model without feature selection. The results show that the FS-LSTM can improve the performance of original LSTM for forecasting the sales volume.
韩宇南 梁珮云 林洋 程春悦 姚雨辰 戴琳 金铭
中国邮电高校学报(英文版), 2022, 29 (5). doi： 10.19682/j.cnki.1005-8885.2022.0016