2021 7th International Conference on Systems and Informatics (ICSAI)最新文献_第5页

Supervised Classification of Plant Image Based on Attention Mechanism 基于注意机制的植物图像监督分类

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/icsai53574.2021.9664220

Jie Li, Jie Yang

引用次数: 2

Vehicles Connectivity on Highways Adopting Erlang-distribution for Time Headway 采用erlang时距分布的高速公路车辆连通性研究

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/ICSAI53574.2021.9664069

Liu Yang, Ya-guang Sun, Yi Wang, Tongkuai Zhang

引用次数: 0

Birds Fine-grained Feature Extraction Based on Transfer Learning 基于迁移学习的鸟类细粒度特征提取

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/ICSAI53574.2021.9664058

Peng Wu, Gang Wu

引用次数: 0

A Method for Steel Surface Defect Recognition Based on Deep Learning and Receptive Field Block 基于深度学习和接受场块的钢表面缺陷识别方法

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/icsai53574.2021.9664135

Jinyuan Gan, Chaobing Huang

{"title":"A Method for Steel Surface Defect Recognition Based on Deep Learning and Receptive Field Block","authors":"Jinyuan Gan, Chaobing Huang","doi":"10.1109/icsai53574.2021.9664135","DOIUrl":"https://doi.org/10.1109/icsai53574.2021.9664135","url":null,"abstract":"Surface defects are an important factor affecting the steel quality, and their classification is crucial for detecting the steel surface defects and analyzing the causes of the damage. Recently, computer image technology has achieved remarkable recognition rates in image classification tasks. And the traditional steel defect image detection algorithm due to the low contrast between background and characteristics, can not meet the detection requirements. Although the accuracy has improved, there is still a great potential for optimization. This paper deeply investigates the image classification algorithm and proposes a residual network based on the optimization initial module and Receptive Field Block(RFB). The entire network is optimized based on a residual network model and establishes a fast connection between the network modules. Residual structure is suitable for deep network, and RFB module is helpful for extracting detailed features, enhancing feature discrimination and improving network quality. Experimental results show that compared with some classical methods, this method can effectively improve the accuracy of steel surface defect classification.","PeriodicalId":131284,"journal":{"name":"2021 7th International Conference on Systems and Informatics (ICSAI)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131178391","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

An Improved Half-bridge Type Active Power Filter for Aircraft Power Grids 一种改进的飞机电网半桥型有源滤波器

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/icsai53574.2021.9664099

Chaowen Zhu, Yongming Zhou, Xin Su, Shi-yu Chen, L. Guan, Zhichao Li

{"title":"An Improved Half-bridge Type Active Power Filter for Aircraft Power Grids","authors":"Chaowen Zhu, Yongming Zhou, Xin Su, Shi-yu Chen, L. Guan, Zhichao Li","doi":"10.1109/icsai53574.2021.9664099","DOIUrl":"https://doi.org/10.1109/icsai53574.2021.9664099","url":null,"abstract":"Great harmonics and reactive current has been brought to aircraft power grids because of much more nonlinear avionics' application with the proposal of concept of “more electric aircraft” and “all electric aircraft”. To fulfill the high power quality and reliability of aircraft power grids, an improved power converter topology of active power filter (APF) is proposed. It is configured by 6 independent split half-bridges consist of one diode and one power switch, in place of the traditional 3 bridge-arms within two power switches. The salient feature of the aeronautic APF using the improved half-bridge power converter is that the inevitable “shoot-through” path during each upper and lower power switch is absolutely eliminated. Furthermore, the original bipolar compensation current is decomposed into two parts of unipolar ones with the novel configuration. The operation principle and mathematical model of the novel APF is analyzed, meanwhile, the correlative key techniques including current control strategy and dc-link voltage control are described as well. Finally, both simulation and experimental results have demonstrated that the improved half-bridge type APF is good in harmonic reduction and reactive power compensation.","PeriodicalId":131284,"journal":{"name":"2021 7th International Conference on Systems and Informatics (ICSAI)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132424401","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

Comment Text Grading for Chinese Graduate Academic Dissertation Using Attention Convolutional Neural Networks 基于注意卷积神经网络的中文研究生论文评语文本评分

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/icsai53574.2021.9664159

Yupei Zhang, Yaya Zhou, Min Xiao, Xuequn Shang

{"title":"Comment Text Grading for Chinese Graduate Academic Dissertation Using Attention Convolutional Neural Networks","authors":"Yupei Zhang, Yaya Zhou, Min Xiao, Xuequn Shang","doi":"10.1109/icsai53574.2021.9664159","DOIUrl":"https://doi.org/10.1109/icsai53574.2021.9664159","url":null,"abstract":"Educational big data connects learning science with data science, where various educational problems are formulating into data mining tasks towards new solutions and new discoveries. This paper provides a path of automatically grading graduate academic dissertations according to the expert-given comment texts. The proposed method fed comment texts to an attention convolutional neural network consisted of an embedding layer, an attention mechanism layer, a convolutional layer, and a fully connected neural network, where the data imbalance issue was handled by data augmentations. The used comment texts were collected from 943 students spreading at 145 universities in China, where these review comments were yielded by experts to grade the academic dissertations. The results from the proposed method achieve a classification accuracy of 77% that gains 12% and 15% implementations compared to the classical convolutional neural network and the linear support vector machine. However, the result analyses show that there are many conflicts between expert-given comments and their given grades in the collected data. This study provides an automatic tool that could remove these conflicts in the dissertation review, leading to more objective dissertation grades.","PeriodicalId":131284,"journal":{"name":"2021 7th International Conference on Systems and Informatics (ICSAI)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116393968","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

A Chinese Text Classification Method Based on BERT and Convolutional Neural Network 基于BERT和卷积神经网络的中文文本分类方法

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/ICSAI53574.2021.9664066

Yiran Cui, Chaobing Huang

引用次数: 4

Entity-Aware Graph Convolution Networks for Event Detection 事件检测的实体感知图卷积网络

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/ICSAI53574.2021.9664062

Congcong Zhang, Gaofei Xie, Ning Liu, Xiaojin Hu, Yatian Shen, Xiajiong Shen

引用次数: 0

A Grey Wolf Optimization Algorithm with Triangular Community and Crossover Operator for Community Discovery 基于三角社区和交叉算子的社区发现灰狼优化算法

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/icsai53574.2021.9664202

Yan Kang, Xin Huang, Zhongming Xu, Xuekun Yang, Xinyan Li

引用次数: 1

Research on Key Technologies of Digital Multimedia Passive Forensics 数字多媒体被动取证关键技术研究

2021 7th International Conference on Systems and Informatics (ICSAI) Pub Date : 2021-11-13 DOI: 10.1109/icsai53574.2021.9664045

X. Lv, Yuli Xia, Junsuo Zhao, Peng Qiao, Bo Zhu

{"title":"Research on Key Technologies of Digital Multimedia Passive Forensics","authors":"X. Lv, Yuli Xia, Junsuo Zhao, Peng Qiao, Bo Zhu","doi":"10.1109/icsai53574.2021.9664045","DOIUrl":"https://doi.org/10.1109/icsai53574.2021.9664045","url":null,"abstract":"In recent years, the median filtering operation is increasingly used as a commonly used image post-processing method to hide the traces of other tampering operations. The detection of image tampering with median filtering has gradually become an important branch in the field of digital image forensics. However, the existing median filter detector field lacks a high-precision method to detect whether the image has undergone a median filter operation in terms of low-resolution images compressed with low quality factors. This paper combines the characteristics of median filter and proposes a median filter detection method based on convolutional neural network (CNN), which can automatically extract features directly from the image and build a high-precision detector. The first layer of the CNN Network in this paper adopts median filtered residuals (MFRs) of original and median filtered images. Then, the hierarchical representation is learned by alternating convolutional layers and pooling layers, and multiple features are extracted for further classification. At the same time, based on the detection of the median filter algorithm by the convolutional neural network, in order to further increase the accuracy of the algorithm detection, this paper supplements the method of wavelet high-frequency coefficients of the median filtered residual to extract the feature vector. Finally, extensive experiments show that algorithm can obtain a better performance by CNN and wavelet high-frequency coefficients algorithm, which is of importance in practical applications.","PeriodicalId":131284,"journal":{"name":"2021 7th International Conference on Systems and Informatics (ICSAI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133223792","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