2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI)最新文献

Cross-Session EEG-Based Emotion Recognition Via Maximizing Domain Discrepancy 基于跨会话脑电图的最大域差异情感识别

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00116

Xinyue Zhu, Yalan Ye, Li Lu, Yunxia Li, Haohui Wu

{"title":"Cross-Session EEG-Based Emotion Recognition Via Maximizing Domain Discrepancy","authors":"Xinyue Zhu, Yalan Ye, Li Lu, Yunxia Li, Haohui Wu","doi":"10.1109/iwecai55315.2022.00116","DOIUrl":"https://doi.org/10.1109/iwecai55315.2022.00116","url":null,"abstract":"Cross-session pose a challenge to the application of EEG-based emotion recognition (ER), which is due to the non-stationary nature of EEG that causes the EEG to reveal distribution discrepancies over time, thereby leading to degradation of performance. The traditional way is by collecting labelled data over multiple sessions and then retraining a new model, but this is time-consuming and labor-intensive. In this paper, we propose the Maximizing Domain Discrepancy for EEG-based ER (MDD-ER) to improve cross-session performance. MDD-ER applies distinct domain adaptation strategies to alleviate feature distribution discrepancies between source session and target session at different levels: for shallow features, we use maximum mean discrepancy (MMD) to align the source and target domains based on statistical criterion, and for deep features, we adversarially train two classifiers, which effectively improves the alignment precision of the source and target domains due to the consideration of the class of features. Consequently, the proposed MDD-ER method can improve model generalization across sessions. We conduct comprehensive experiments on SEED dataset, and the experimental results demonstrate the effectiveness of the proposed MDD-ER method in cross-session ER.","PeriodicalId":115872,"journal":{"name":"2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI)","volume":"83 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115168289","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Bayesian Network Structure Learning Algorithm Based on Node Order Constraint 基于节点顺序约束的贝叶斯网络结构学习算法

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00049

Xiaoqing Li, Haizheng Yu

引用次数: 0

GLMFD: An Attention-Based CNN-LSTM Model for Transmembrane Domains Localization GLMFD:一种基于注意力的CNN-LSTM跨膜域定位模型

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00098

Quanchao Ma, F. Yang, Kai Zou, Zhihai Zhang

{"title":"GLMFD: An Attention-Based CNN-LSTM Model for Transmembrane Domains Localization","authors":"Quanchao Ma, F. Yang, Kai Zou, Zhihai Zhang","doi":"10.1109/iwecai55315.2022.00098","DOIUrl":"https://doi.org/10.1109/iwecai55315.2022.00098","url":null,"abstract":"The transmembrane domains (TMDs) are involved in many significant protein-protein interactions. Structural information of TMDs is necessary for increasing our understanding of such biological processes. However, experimental determination of TMDs position was laborious and inefficient for mass integral membrane proteins. In the past two decades, many statistical algorithms were proposed to predict TMDs and achieved excellent results. These algorithms were both limited in large amounts of detailed protein topology data. In this paper, we proposed an attention-based global-local model to locate TMDs called GLMFD. TMD as a functional domain has its particular hydrophobicity patterns that the right-sized local window can capture. Different from these traditional TMD prediction models, the position information of TMDs was an extra ‘byproduct’ of our localization model. Moreover, our model combined with proposed penalization terms successful located TMDs by learning the quantity distribution of TMDs. Experimental results show that our model and strategy perform well in TMD localization.","PeriodicalId":115872,"journal":{"name":"2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI)","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121017686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Satisfaction Analysis of Smart Teaching System Based on Structural Equation Model 基于结构方程模型的智能教学系统满意度分析

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00119

Zhiguo Wang, Qi-ping Yang, Yu-Chia Chen, Shuheng Zhang

{"title":"Satisfaction Analysis of Smart Teaching System Based on Structural Equation Model","authors":"Zhiguo Wang, Qi-ping Yang, Yu-Chia Chen, Shuheng Zhang","doi":"10.1109/iwecai55315.2022.00119","DOIUrl":"https://doi.org/10.1109/iwecai55315.2022.00119","url":null,"abstract":"The application of smart teaching system is an effective way to promote the reform and innovation of higher education and improve the quality, and it is the innovation frontier of the development of education informatization. Learning satisfaction and improvement of learning effect are important indicators for testing the application of smart teaching system. The article introduces the structural equation model and improves the technology acceptance model (TAM) to construct a smart teaching system satisfaction that includes 6 latent variables of teaching function, interactive function, learning interest, learning satisfaction, learning effect, and 21 observation variables Analytical model (ITSAM), take the wisdom teaching system of Jinan University as an example to conduct empirical research. The results show that improving the satisfaction and learning effect of the smart teaching system can be achieved by increasing students' interest in learning. Appropriate tools should be selected when applying information systems, and interaction and social functions should be used appropriately. Excessive interaction will affect the learning effect and Satisfaction.","PeriodicalId":115872,"journal":{"name":"2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI)","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125931268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on the Performance of Commercial Artificial Intelligence Model for Internet Audio Streaming Media's Lyrics Recognition 商业人工智能模型在网络音频流媒体歌词识别中的性能研究

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00069

Kaizhen Tang

引用次数: 0

Meta-Modeling for Autoencoder-Based End-to-End Communications Systems 基于自编码器的端到端通信系统元建模

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00097

Hongxia Tang

引用次数: 0

Method analysis of avoiding bus interference in high frequency system 高频系统中避免母线干扰的方法分析

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00034

Lei Zhang

引用次数: 0

A Study of Unsupervised Networks Based on the Network Prior for the Image Inpainting 基于网络先验的无监督网络图像补漆研究

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00029

Haoxuan Li, Zhiyuan Zhang

引用次数: 0

Speed up QC-LDPC decoder through memory subsystem optimization 通过内存子系统优化提高QC-LDPC解码器的解码器速度

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00027

Yajie Li, Dake Liu, Xinbing Zhou, Wei Chen

{"title":"Speed up QC-LDPC decoder through memory subsystem optimization","authors":"Yajie Li, Dake Liu, Xinbing Zhou, Wei Chen","doi":"10.1109/iwecai55315.2022.00027","DOIUrl":"https://doi.org/10.1109/iwecai55315.2022.00027","url":null,"abstract":"In this paper, we proposed a QC-LDPC decoder for 5G NR, WiMAX, and WLAN applications. The decoder can flexibly support arbitrary code length and rate under 5G NR standard. This design follows programmable ASIP (Application Specific Instruction-set Processor) design method and uses data parallel SIMD (Single Instruction Multiple Data) architecture. We doubled the logic computing speed to improve the throughout instead of using double speed memory architecture. Compared with the design mentioned in [1], the original design could achieve the highest QC-LDPC decoding throughput of 533Mbps (12 SISO in parallel) when the clock frequency is 200MHz (memory clock frequency is 400MHz). The existing design saved 47% of the decoding clock cycle without lossing decoding circuit quality. We achieved a maximum QC-LDPC decoding throughput of 1984 Mbps (with 48 SISO in parallel) when the system frequency is 400MHz (memory clock frequency is also 400MHz). Further, through circuit optimization, the upper limit of the system clock is promoted from 344MHz to 1.1GHz. The throughput can possibly be upto 5456Mbps. Finally, through the logic synthesis using 28nm SMIC CMOS cell library, the design is physically verified, and the logic gate count is reported 1716K. It is similar to that of the original design per SISO.","PeriodicalId":115872,"journal":{"name":"2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI)","volume":"27 18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133995717","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-stage classification of diabetic retinopathy based on mixed attention network 基于混合注意网络的糖尿病视网膜病变多阶段分类

2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI) Pub Date : 2022-01-01 DOI: 10.1109/iwecai55315.2022.00102

Zhijing Xu, Jian-nan Dong

{"title":"Multi-stage classification of diabetic retinopathy based on mixed attention network","authors":"Zhijing Xu, Jian-nan Dong","doi":"10.1109/iwecai55315.2022.00102","DOIUrl":"https://doi.org/10.1109/iwecai55315.2022.00102","url":null,"abstract":"Diabetic retinopathy (DR) has small differences among the multi-stage types, it is difficult to classify accurately in early stage. For this reason, we proposed a high-efficiency model of diabetic retinopathy based on hybrid attention and multi-stage, which is named Coordinate Attention and Squeeze- and-Excitation Networks EfficientNet-V2 (CS-ENetV2). Firstly, we used coordinate attention mechanism and hybrid attention mechanism of compression and excitation network module to localize the feature target precisely. Secondly, we designed a hybrid attention efficient network based on diabetic retinopathy feature extraction to further optimize the quality of feature extraction. Finally, to enhance the accuracy of the classification, the feature information obtained from each layer is fused by using multi-feature fusion. Moreover, we used a migration learning strategy to pre-train the CS-ENetV2 model. After pre-processing the publicly available dataset from Kaggle, relevant classification experiments were done by us, the experimental results showed that the specificity, sensitivity, classification accuracy and Quadratic Weighted Kappa score of the model reached 97. 8%, 93.8%,94.9%and 0.86, which are better than the current typical classification methods and have better classification and robustness. Our method provides a good solution for accurate automatic staging of diabetic retinopathy.","PeriodicalId":115872,"journal":{"name":"2022 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130985279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0