Most Read

Published in last 1 year |  In last 2 years |  In last 3 years |  All
Please wait a minute...
For Selected: Toggle Thumbnails
Design of high parallel CNN accelerator based on FPGA for AIoT
Lin Zhijian Gao Xuewei Chen Xiaopei Zhu Zhipeng Du Xiaoyong Chen Pingping
The Journal of China Universities of Posts and Telecommunications    2022, 29 (5): 1-9.   DOI: 10.19682/j.cnki.1005-8885.2022.0026
Abstract264)            Save
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).
Reference | Related Articles | Metrics
Artificial intelligence for optical transport networks: architecture, application and challenges
Li Yajie, Zhang Jie
The Journal of China Universities of Posts and Telecommunications    2022, 29 (6): 3-17.   DOI: 10.19682/j.cnki.1005-8885.2022.1024
Abstract185)            Save
Optical network plays an important role in telecommunication networks, which supports high-capacity and long-distance transmission of Internet traffic. However, as the scaling and evolving of optical networks, it faces great challenges in terms of network operation, optimization and maintenance. Artificial intelligence ( AI ) has been proved to have superiority on addressing complex problems, by mimicking cognitive skills similar with human mind. In this paper, we provide a comprehensive investigation of AI applications in optical transport network. First, we give a general AI-based control architecture for optical transport networks. Then, we discuss several typical applications of AI model and algorithms in optical networks. Different use cases are considered, including network planning, quality of transmission ( QoT ) estimation, network reconfiguration, traffic prediction, failure management and so on. In addition, we also present some potential technical challenges for AI application in
optical network for the next years.
Reference | Related Articles | Metrics
Precise and efficient Chinese license plate recognition in the real monitoring scene of intelligent transportation system
Jia Wei, Gong Chao
The Journal of China Universities of Posts and Telecommunications    2022, 29 (3): 1-14.   DOI: 10.19682/j.cnki.1005-8885.2022.1014
Abstract164)            Save
In this paper, the performance of you only look once ( YOLO) series detectors on Chinese license plate  recognition (LPR) in the real intelligent transportation system (ITS) monitoring scene is investigated. Specially, a precise and efficient automatic license plate recognition ( ALPR ) system based on the YOLOv4 detector is proposed. The proposed ALPR system contains three stages including vehicle detection, license plate detection (LPD) and LPR. In vehicle detection stage, YOLOv4 detector is directly applied. In LPD stage, YOLOv4-tiny detector is exploited. In the last stage, the YOLOv4-tiny detector with attention mechanism for LPR is proposed to use. In addition, a large Chinese license plate dataset containing 10 500 images collected from all 31 provinces in the Chinese mainland is created. This Chinese license plate dataset is named Hefei University of Technology license plate version 1 (HFUT-LP v1). Particularly, HFUT-LP v1 dataset is collected in the real ITS monitoring scene. In order to compare the performance of different object detection algorithms for ALPR, a variety of object detection algorithms are used to make a comprehensive performance evaluation. Experimental results show that the proposed ALPR system achieves very high accuracy and has very fast processing speed, which is suitable for real-time LPR.
Reference | Related Articles | Metrics
Thoughts on using scientific system engineering method to  develop quantum computer
Lu Jun, Luan Tian, Tang Pengju, Zhang Yuntao, An Da
The Journal of China Universities of Posts and Telecommunications    2022, 29 (4): 2-8.   DOI: 10.19682/j.cnki.1005-8885.2022.2014
Abstract153)            Save
As the traditional semiconductor complementary metal oxide semiconductor (CMOS) integrated circuit technology  gradually approaches the limit of Moore's Law, quantum computing, as a new system computing technology,with  the potential for higher computing speed and lower power consumption, is getting more and more attention from  governments and research institutions around the world. For instance, the United States (US) government is  adopting a bunch of bills to deploy new quantum information processing technology. The European Union's  “quantum declaration" plans to realize customized quantum computers with more than 100 qubits in the next 10  years. The Chinese government also provides strong support for quantum computer research through the project of  National Science and Technology Major Projects. In the business field, major companies such as International  Business Machines (IBM) Corporation, Intel, Google, Alibaba, Huawei, Baidu, etc. , have joined the “quantum  supremacy" competition in order to seize the initiative in the future information field. Facing the rapid  development trend of quantum computing, we believe that we should refer to the classical computer industry in the  early stage, form an industrial system, and develop the quantum computing industry. We should also use the  scientific system engineering method to carry out the research and development of the quantum computer and  establish the ecological environment of the quantum computer industry with the demand as the traction, so as to  better serve the development of the national economy.
Reference | Related Articles | Metrics
Vehicle-following system based on deep reinforcement learning in marine scene
Zhang Xin, Lou Haoran, Jiang Li, Xiao Qianhao, Cai Zhuwen
The Journal of China Universities of Posts and Telecommunications    2022, 29 (5): 10-20.   DOI: 10.19682/j.cnki.1005-8885.2022.0025
Abstract152)            Save
In order to solve the problems that the feature data type are not rich enough in the data collection process about the vehicle-following task in marine scene which results in a long model convergence time and high training difficulty, a two-stage vehicle-following system was proposed. Firstly, semantic segmentation model predicts the number of pixels of the followed target, then the number of pixels of the followed target is mapped to the position feature. Secondly, deep reinforcement learning algorithm enables the control equipment to make decision action, to ensure that two moving objects remain within the safe distance. The experimental results show that the two-stage vehicle-following system has a 40% faster convergence rate than the model without position feature, and the following stability is significantly improved by adding the position feature.
Reference | Related Articles | Metrics
HQD-RRT*: a high-quality path planner for mobile robot in dynamic environment
Li Qinghua, Wang Jiahui, Li Haiming, Feng Chao
The Journal of China Universities of Posts and Telecommunications    2022, 29 (3): 69-80.   DOI: 10.19682/j.cnki.1005-8885.2022.1007
Abstract142)            Save

Mobile robots have been used for many industrial scenarios which can realize automated manufacturing process instead of human workers. To improve the quality of the optimal rapidly-exploring random tree ( RRT* ) for planning path in dynamic environment, a high-quality dynamic rapidly-exploring random tree ( HQD-RRT* ) algorithm is proposed in this paper, which generates a high-quality solution with optimal path length in dynamic environment. This method proceeds in two stages: initial path generation and path re-planning. Firstly, the initial path is generated by an improved smart rapidly-exploring random tree ( RRT* -SMART) algorithm, and the state tree information is stored as prior knowledge. During the process of path execution, a strategy of obstacle avoidance is proposed to avoid moving obstacles. The cost and smoothness of path are considered to re-plan the initial path to improve the path quality in this strategy. Compared with related work, a higher-quality path in dynamic

environment can be achieved in this paper. HQD-RRT* algorithm can obtain an optimal path with better stability. Simulations on the static and dynamic environment are conducted to clarify the efficiency of HQD-RRT* in avoiding unknown obstacles.

Reference | Related Articles | Metrics
Secrecy Energy Efficiency Maximization for UAV-Enabled Multi-Hop Mobile Relay System
Miao Jiansong, Li Hairui, Zheng Ziyuan, Wang Chu, Zhao Zhenmin
The Journal of China Universities of Posts and Telecommunications    2022, 29 (3): 81-91.   DOI: 10.19682/j.cnki.1005-8885.2022.1002
Abstract132)            Save

To deal with the secrecy issues and energy efficiency issues in the unmanned aerial vehicles ( UAVs) assisted communication systems, an UAV-enabled multi-hop mobile relay system is studied in an urban environment. Multiple rotary-wing UAVs with energy budget considerations are employed as relays to forward confidential information between two ground nodes in the presence of multiple passive eavesdroppers. The system secrecy energy efficiency ( SEE), defined by the ratio of minimum achievable secrecy rate ( SR) to total propulsion energy consumption (PEC), is maximized via jointly optimizing the trajectory and transmit power of each UAV relay. To solve the formulated non-convex fractional optimization problem subject to mobility, transmit power and information-causality constraints, an effective iterative algorithm is proposed by applying the updated-rate-assisted block coordinate decent method, successive convex approximation (SCA) technique and Dinkelbach method. Simulation

results demonstrate the effectiveness of the proposed joint trajectory design and power control scheme.

Reference | Related Articles | Metrics
Methods for solving equations with errors based on  the HHL algorithm
Lv Lihui, Wang Hong, Ma Zhi, Duan Qianheng, Fei Yangyang, Meng Xiangdong
The Journal of China Universities of Posts and Telecommunications    2022, 29 (4): 9-20.   DOI: 10.19682/j.cnki.1005-8885.2022.2015
Abstract129)            Save
To solve polynomial systems, Harrow, Hassidim, and Lloyd (HHL) proposed a quantum algorithm called HHL  algorithm. Based on the HHL algorithm, Chen et al. presented an algorithm, the solving the Boolean solutions of  polynomial systems (PoSSoB) algorithm. Furthermore, Ding et al. introduced the Boolean Macaulay matrix and  analyzed the lower bound on the condition number. Inspired by Ding et al. 's research, several related algorithms  are proposed in this paper. First, the improved PoSSoB algorithm using the Boolean Macaulay matrix is proved to  have lower complexity. Second, for solving equations with errors, a quantum algorithm for the max-polynomial  system solving (Max-PoSSo) problem is proposed based on the improved PoSSoB algorithm. Besides, the Max- PoSSo algorithm is extended to the learning with errors (LWE) problem and its special case, the learning parity  with noise (LPN) problem, providing a quantitative criterion, the condition number, for the security of these basic  problems.
Reference | Related Articles | Metrics
Multi-level fusion with deep neural networks for multimodal sentiment classification
Zhang Guangwei, Zhao Bing, Li Ruifan
The Journal of China Universities of Posts and Telecommunications    2022, 29 (3): 25-33.   DOI: 10.19682/j.cnki.1005-8885.2022.1013
Abstract124)            Save
The task of multimodal sentiment classification aims to associate multimodal information, such as images and texts with appropriate sentiment polarities. There are various levels that can affect human sentiment in visual and textual modalities. However, most existing methods treat various levels of features independently without having effective method for feature fusion. In this paper, we propose a multi-level fusion classification (MFC) model to predict the sentiment polarity based on the fusing features from different levels by exploiting the dependency among them. The proposed architecture leverages convolutional neural networks ( CNNs) with multiple layers to extract levels of features in image and text modalities. Considering the dependencies within the low-level and high-level features, a bi-directional (Bi) recurrent neural network (RNN) is adopted to integrate the learned features from different layers in CNNs. In addition, a conflict detection module is incorporated to address the conflict between modalities. Experiments on the Flickr dataset demonstrate that the MFC method achieves comparable performance compared with strong baseline methods.
Reference | Related Articles | Metrics
Quantum algorithm for soft margin support vector machine with  hinge loss function
Liu Hailing, Zhang Jie, Qin Sujuan, Gao Fei
The Journal of China Universities of Posts and Telecommunications    2022, 29 (4): 32-41.   DOI: 10.19682/j.cnki.1005-8885.2022.2017
Abstract117)            Save
Soft margin support vector machine (SVM) with hinge loss function is an important classification algorithm,  which has been widely used in image recognition, text classification and so on. However, solving soft margin SVM  with hinge loss function generally entails the sub-gradient projection algorithm, which is very time-consuming when  processing big training data set. To achieve it, an efficient quantum algorithm is proposed. Specifically, this  algorithm implements the key task of the sub-gradient projection algorithm to obtain the classical sub-gradients in  each iteration, which is mainly based on quantum amplitude estimation and amplification algorithm and the  controlled rotation operator. Compared with its classical counterpart, this algorithm has a quadratic speedup on the  number of training data points. It is worth emphasizing that the optimal model parameters obtained by this algorithm  are in the classical form rather than in the quantum state form. This enables the algorithm to classify new data at  little cost when the optimal model parameters are determined.
Reference | Related Articles | Metrics
Quantum classifier with parameterized quantum circuit  based on the isolated quantum system
Shi Jinjing, Wang Wenxuan, Xiao Zimeng, Mu Shuai, Li Qin
The Journal of China Universities of Posts and Telecommunications    2022, 29 (4): 21-31.   DOI: 10.19682/j.cnki.1005-8885.2022.2016
Abstract108)            Save
It is a critical challenge for quantum machine learning to classify the datasets accurately. This article develops a  quantum classifier based on the isolated quantum system (QC-IQS) to classify nonlinear and multidimensional  datasets. First, a model of QC-IQS is presented by creating parameterized quantum circuits (PQCs) based on the  decomposing of unitary operators with the Hamiltonian in the isolated quantum system. Then, a parameterized  quantum classification algorithm (QCA) is designed to calculate the classification results by updating the loss  function until it converges. Finally, the experiments on nonlinear random number datasets and Iris datasets are  designed to demonstrate that the QC-IQS model can handle and generate accurate classification results on different  kinds of datasets. The experimental results reveal that the QC-IQS is adaptive and learnable to handle different  types of data. Moreover, QC-IQS compensates the issue that the accuracy of previous quantum classifiers declines  when dealing with diverse datasets. It promotes the process of novel data processing with quantum machine learning  and has the potential for more comprehensive applications in the future.
Reference | Related Articles | Metrics
Reinforced virtual optical network embedding algorithm in EONs for edge computing
Zhu Ruijie, Li Gong, Wang Peisen, Zhang Wenchao
The Journal of China Universities of Posts and Telecommunications    2022, 29 (6): 18-29.   DOI: 10.19682/j.cnki.1005-8885.2022.1020
Abstract108)            Save
As the core technology of optical networks virtualization, virtual optical network embedding ( VONE) enables multiple virtual network requests to share substrate elastic optical network ( EON) resources simultaneously and hence has been applicated in edge computing scenarios. In this paper, we propose a reinforced virtual optical network embedding ( R-VONE ) algorithm based on deep reinforcement learning ( DRL) to optimize network embedding policies automatically. The network resource attributes are extracted as the environment state for model training, based on which DRL agent can deduce the node embedding probability. Experimental results indicate that R-VONE presents a significant advantage with lower blocking probability and higher resource utilization.
Reference | Related Articles | Metrics
Random mating mayfly algorithm for RFID network planning
Xie Xiaode Zheng Jiali Lin Zihan He Siyi Feng Minyu
The Journal of China Universities of Posts and Telecommunications    2022, 29 (5): 40-50.   DOI: 10.19682/j.cnki.1005-8885.2022.0010
Abstract104)            Save

In order to improve robustness and efficiency of the radio frequency identification (RFID) network, a random mating mayfly algorithm (RMMA) was proposed. Firstly, RMMA introduced the mechanism of random mating into the mayfly algorithm (MA), which improved the population diversity and enhanced the exploration ability of the algorithm in the early stage, and find a better solution to the RFID nework planning (RNP) problem. Secondly, in RNP, tags are usually placed near the boundaries of the working space, so the minimum boundary mutation strategy was proposed to make sure the mayflies which beyond the boundary can keep the original search direction, as to enhance the ability of searching near the boundary. Lastly, in order to measure the performance of RMMA, the algorithm is then benchmarked on three well -known classic test functions, and the results are verified by a comparative study with particle swarm optimization (PSO), grey wolf optimization (GWO), and MA. The results show that the RMMA algorithm is able to provide very competitive results compared to these well-known meta-heuristics, RMMA is also applied to solve RNP problems. The performance evaluation shows that RMMA achieves higher coverage than the other three algorithms. When the number of readers is the same, RMMA can obtain lower interference and get a better load balance in each instance compared with other algorithms. RMMA can also solve RNP problem stably and efficiently when the number and position of tags change over time.

Reference | Related Articles | Metrics
Saliency guided self-attention network for pedestrian attribute recognition in surveillance scenarios
Li Na, Wu Yangyang, Liu Ying, Li Daxiang, Gao Jiale
The Journal of China Universities of Posts and Telecommunications    2022, 29 (5): 21-29.   DOI: 10.19682/j.cnki.1005-8885.2022.0007
Abstract103)            Save
Pedestrian attribute recognition is often considered as a multi-label image classification task. In order to make full use of attribute-related location information, a saliency guided sel-attention network ( SGSA-Net) was proposed to weakly supervise attribute localization,without annotations of attribute-related regions. Saliency priors were integrated into the spatial attention module ( SAM ). Meanwhile, channel-wise attention and spatial attention were introduced into the network. Moreover, a weighted binary cross-entropy loss ( WCEL) function was employed to handle the imbalance of training data. Extensive experiments on richly annotated pedestrian ( RAP) and pedestrian attribute ( PETA) datasets demonstrated that SGSA-Net outperformed other state-of-the-art methods.
Reference | Related Articles | Metrics
Adaptive learning path recommendation model for  examination-oriented education
Wang Jian, Qiao Kuoyuan, Yuan Yanlei, Liu Xiaole, Yang Jian
The Journal of China Universities of Posts and Telecommunications    2022, 29 (4): 77-88.   DOI: 10.19682/j.cnki.1005-8885.2022.2021
Abstract103)            Save
Adaptive learning paths provide individual learning objectives that best match a learner's characteristics. This is  especially helpful when learners need to balance limited available learning time and multiple learning objectives.  The automatic generation of personalized learning paths to improve learning efficiency has therefore attracted  significant interest. However, most current research only focuses on providing learners with adaptive objects and  sequences according to their own interests or learning goals given a normal amount of time or ordinary conditions.  There is little research that can help learners to obtain the most important knowledge for a test in the shortest time  possible, which is a typical scenario in exanimation-oriented education systems. This study aims to solve this  problem by introducing a new approach that builds on existing methods. First, the eight properties in Gardner's  multiple intelligence theory are introduced into the present knowledge and learner models to define the relationship  between learning objects (LOs) and learners, thereby improving recommendation accuracy rates. Then, a novel  adaptive learning path recommendation model is presented where viable knowledge topologies, knowledge bases and  the previously-established properties relating to a learner's ability are combined by Dempster-Shafer (D-S) evidence  theory. A series of practical experiments were performed to assess the approach's adaptability, the appropriateness  of the selected evidence and the effectiveness of the recommendations. In the results, it was found that the proposed  learning path recommendation model helped learners learn the most important elements and obtain superior test  grades when confronted with limited time for learning.
Reference | Related Articles | Metrics
Ensemble relation network with multi-level measure
Li Xiaoxu, Qu Xue, Cao Jie
The Journal of China Universities of Posts and Telecommunications    2022, 29 (3): 15-24.   DOI: 10.19682/j.cnki.1005-8885.2022.1015
Abstract103)            Save
Fine-grained few-shot learning is a difficult task in image classification. The reason is that the discriminative
features of fine-grained images are often located in local areas of the image, while most of the existing few-shot learning image classification methods only use top-level features and adopt a single measure. In that way, the local features of the sample cannot be learned well. In response to this problem, ensemble relation network with multi-level measure (ERN-MM) is proposed in this paper. It adds the relation modules in the shallow feature space to compare the similarity between the samples in the local features, and finally integrates the similarity scores from the feature spaces to assign the label of the query samples. So the proposed method ERN-MM can use local details and global information of different grains. Experimental results on different fine-grained datasets show that the proposed method achieves good classification performance and also proves its rationality.
Reference | Related Articles | Metrics
Intelligent Service Function Chain Mapping Framework for Cloud-and-Edge-Collaborative IoT
Yang Chao, Li Yimin, Li Tong, Xu Siya, Qi Jun, Zhang Yu
The Journal of China Universities of Posts and Telecommunications    2022, 29 (3): 54-68.   DOI: 10.19682/j.cnki.1005-8885.2021.1018
Abstract100)            Save
With the rapid development of Internet of thing (IoT) technology, it has become a challenge to deal with the increasing number and diverse requirements of IoT services. By combining burgeoning network function virtualization ( NFV) technology with cloud computing and mobile edge computing ( MEC), an NFV-enabled cloud-and-edge-collaborative IoT (CECIoT) architecture can efficiently provide flexible service for IoT traffic in the form of a service function chain (SFC) by jointly utilizing edge and cloud resources. In this promising architecture, a difficult issue is how to balance the consumption of resource and energy in SFC mapping. To overcome this challenge, an intelligent energy-and-resource-balanced SFC mapping scheme is designed in this paper. It takes the comprehensive deployment consumption as the optimization goal, and applies a deep Q-learning(DQL)-based SFC mapping (DQLBM) algorithm as well as an energy-based topology adjustment (EBTA) strategy to make efficient use of the limited network resources, while satisfying the delay requirement of users. Simulation results show that the proposed scheme can decrease service delay, as well as energy and resource consumption.
Reference | Related Articles | Metrics
Summary of research on recommendation system  based on serendipity
Meng Wei, Wang Liting, Lu Meng
The Journal of China Universities of Posts and Telecommunications    2022, 29 (4): 89-105.   DOI: 10.19682/j.cnki.1005-8885.2022.2022
Abstract96)            Save
Personalized recommender systems provide various personalized recommendations for different users through the  analysis of their respective historical data. Currently, the problem of the “filter bubble" which has to do with over- specialization persists. Serendipity (SRDP), one of the evaluation indicators, can provide users with unexpected  and useful recommendations, and help to successfully mitigate the filter bubble problem, and enhance users'  satisfaction levels and provide them with diverse recommendations. Since SRDP is highly subjective and challenging  to study, only a few studies have focused on it in recent years. In this study, the research results on SRDP were  summarized, the various definitions of SRDP and its applications were discussed, the specific SRDP calculation  process from qualitative to quantitative perspectives was presented, the challenges and the development directions  were outlined to provide a framework for further research.
Reference | Related Articles | Metrics
Face anti-spoofing based on multi-modal and multi-scale features fusion
Kong Chao, Ou Weihua, Gong Xiaofeng, Li Weian, Han Jie, Yao Yi, Xiong Jiahao
The Journal of China Universities of Posts and Telecommunications    2022, 29 (6): 73-82.   DOI: 10.19682/j.cnki.1005-8885.2022.1004
Abstract91)            Save
Face anti-spoofing is used to assist face recognition system to judge whether the detected face is real face or fake face. In the traditional face anti-spoofing methods, features extracted by hand are used to describe the difference between living face and fraudulent face. But these handmade features do not apply to different variations in an unconstrained environment. The convolutional neural network (CNN) for face deceptions achieves considerable results. However, most existing neural network-based methods simply use neural networks to extract single-scale features from single-modal data, while ignoring multi-scale and multi-modal information. To address this problem, a novel face anti-spoofing method based on multi-modal and multi-scale features fusion ( MMFF) is proposed. Specifically, first residual network ( Resnet )-34 is adopted to extract features of different scales from each modality, then these features of different scales are fused by feature pyramid network (FPN), finally squeeze-and-excitation fusion ( SEF) module and self-attention network ( SAN) are combined to fuse features from different modalities for classification. Experiments on the CASIA-SURF dataset show that the new method based on MMFF  achieves better performance compared with most existing methods.
Reference | Related Articles | Metrics
Spatiotemporal emotion recognition based on 3D time-frequency domain feature matrix
Chao Hao Lian Weifang Liu Yongli
The Journal of China Universities of Posts and Telecommunications    2022, 29 (5): 62-72.   DOI: 10.19682/j.cnki.1005-8885.2022.0017
Abstract90)            Save
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.

Reference | Related Articles | Metrics