2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)最新文献_第8页

Handwritten String Recognition Based on YOLOv4 and CRNN on Different Deep Learning Frameworks 基于YOLOv4和CRNN在不同深度学习框架下的手写字符串识别

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731149

X.-W. Yin, Zhongli Ma, Xu Chen, Qiaoling Zhou

{"title":"Handwritten String Recognition Based on YOLOv4 and CRNN on Different Deep Learning Frameworks","authors":"X.-W. Yin, Zhongli Ma, Xu Chen, Qiaoling Zhou","doi":"10.1109/acait53529.2021.9731149","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731149","url":null,"abstract":"Character recognition is one of the most important contents of pattern recognition research. Among them, due to the instability and continuity of individual differences in handwritten strings, it is difficult to extract features in recognition. At present, the recognition of handwritten strings is based on single character segmentation. However, due to the difficulty of character segmentation of handwritten string, the accuracy of recognition based on segmentation method is relatively low. In this paper, we use the non segmentation method based on RNN for character recognition, combined with the time sequence characteristics to improve the recognition accuracy of continuous strings. Firstly, handwritten string detection methods are studied respectively, based on YOLOv4, YOLOv4-Tiny model and OpenCV, the detection methods are tested; then the handwritten string recognition methods are studied, the ‘CNN+RNN+CTC’ pattern is used to calculate loss function model, thus can identify undivided strings, and then through CTC decoding, string results with higher accuracy can be obtained; finally, after testing was carried out, the experimental result shows that the method proposed in this paper can solve the problem of stylus and variable length of handwritten strings, therefore improve the efficiency of converting handwritten manuscripts into electronic manuscripts.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130960679","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

Multiple Latent Spaces Learning for Cross-Domain Text Classification 跨领域文本分类的多重潜在空间学习

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9730891

Jianhan Pan, Teng Cui, Mingjing Du, Qingyang Zhang, Bingbing Song, Qiaoli Qu

{"title":"Multiple Latent Spaces Learning for Cross-Domain Text Classification","authors":"Jianhan Pan, Teng Cui, Mingjing Du, Qingyang Zhang, Bingbing Song, Qiaoli Qu","doi":"10.1109/acait53529.2021.9730891","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9730891","url":null,"abstract":"When the training data and test data are drawn from similar but different data distributions, transfer learning (TL) can be exploited to learn a consistent distribution for knowledge transfer. To reduce distribution differences, some recent transfer learning approaches typically build potential feature spaces to exploit the potential information and learn multiple high-level concepts to model a latent potential shared structure. However, only utilizing the potential information in one latent space will neglect some other potential information existing in different latent feature spaces. And this neglected potential information may also help model potential structures shared as bridges. In this paper, we propose Multiple Latent Spaces Learning (MLSL), a novel approach which mines a massive amount of potential information on multiple latent spaces to construct a shared bridge (or multiple bridges) across domains by learning different high-level concepts. Our strategy can dig out the latent information that exists in the latent space ignored by the previous methods to build a knowledge transfer bridge. Compared with the TL method that only learns a latent space, our strategy is more suitable for actual scenarios, and the use of data is also fuller. In addition, an iterative algorithm is developed to solve the optimization problem. Finally, the system test on benchmark data sets shows the superiority of the MLSL method.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"5 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130905188","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

Automatic Cardiomyopathy Diagnosis with a Cost-sensitive Ensemble Classifier 成本敏感集成分类器的心肌病自动诊断

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731304

Qiwei Ye, Linbo Qiao, Hongyi Chen, Q. Tao, Jingjing Xiao

引用次数: 0

Types and Evolutionary Boundaries of Agents 智能体的类型和进化边界

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731137

Feng Liu, Ying Liu

引用次数: 0

Alignment Analysis of English Chinese Bilingual Corpora based on CRFS Model 基于CRFS模型的英汉双语语料库对齐分析

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731293

Miao Wu

引用次数: 0

Automatic Classification of User Requirements Information Based on Convolutional Neural Network 基于卷积神经网络的用户需求信息自动分类

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731258

Xiang Chen, Mengxing Huang, Siling Feng, Yuan-hsin Chen, Wenquan Li

{"title":"Automatic Classification of User Requirements Information Based on Convolutional Neural Network","authors":"Xiang Chen, Mengxing Huang, Siling Feng, Yuan-hsin Chen, Wenquan Li","doi":"10.1109/acait53529.2021.9731258","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731258","url":null,"abstract":"User requirements information is semi-structured or unstructured data with sparse features and short lengths. Since manual labeling methods nowadays are time-consuming, which cannot meet increasing requirements for classifying massive user requirements information, an automatic classification method of user requirements information based on Convolutional Neural Networks (CNN) is proposed. Firstly, NLPIR word segmentation tool is used to preprocess word segmentation and remove stop words in user requirements information. Secondly the word vector is trained by word vector model (word2vec). Thirdly convolutional neural network is used to extract abstract features of text information. And finally these features are used as input,and the softmax classifier is used to achieve automatic classification of user requirements information. Compared with the traditional classification method based on probability and statistics, the classification accuracy of the automatic classification model of user requirements information based on CNN has been improved by 13.54%. The experimental results show that the CNN classification algorithm is more suitable for the automatic classification of the user requirements information.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123160092","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 Extraction and Translation of English Public Signs in Tourist Attractions Based on Machine Vision 基于机器视觉的旅游景点英语公示语提取与翻译研究

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731335

Rongjing Meng

引用次数: 0

Cross-Dataset Pose Estimation of Faces In The Wild 野外人脸的跨数据集姿势估计

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731187

Mo Zhao, Ya Ma, Zhendong Li, Hao Liu

引用次数: 0

Intelligent CNN-based Fault Diagnosis of Rotating Machinery with Small Fault Samples 基于cnn的旋转机械小故障样本智能诊断

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731233

Guoqiang Li, Chong Chen, Zhenguo Song, Jun Wu, C. Deng, Zuoyi Chen

{"title":"Intelligent CNN-based Fault Diagnosis of Rotating Machinery with Small Fault Samples","authors":"Guoqiang Li, Chong Chen, Zhenguo Song, Jun Wu, C. Deng, Zuoyi Chen","doi":"10.1109/acait53529.2021.9731233","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731233","url":null,"abstract":"Up to now, convolution neural network (CNN) has been widely applied in fault diagnosis of rotating machinery. The CNN-based diagnostic methods often with the help of the fault data to implement the optimization. However, in real industrial applications, it is difficult and costly to obtain the fault data. In this paper, a ResNet-based diagnostic method combined a designed data transformation combination is proposed to achieve the fault diagnosis under small fault samples. Specifically, several data transformation of image are selected to deal with the small samples, where the parameter of the transformation is determined by the mutual information between the inputted sample and the corresponding transformed sample. Meanwhile, these obtained transformations are used as the input layer of the ResNet. Then, a fault diagnosis model is established by the constructed ResNet, and which is trained only by using small samples. Noting that the introduced data transformation is randomly used for the training samples to increase the complexity of the inputted samples in the training process for alleviating the overfitting risk. The bearing fault dataset is used to evaluated the effectiveness of the proposed method. From the experimental result, it is found the proposed has the capability to implement the effective fault diagnosis under small samples, and achieve a higher diagnostic performance than other existing methods.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115844684","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 Transmission Line Fault Detection Method based on M-Apriori Algorithm 基于M-Apriori算法的输电线路故障检测方法研究

2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT) Pub Date : 2021-10-29 DOI: 10.1109/acait53529.2021.9731306

Qian Liu, Zhiming Jiao, Fangbo Gong, Hong-chao Ji, Jie Chen

{"title":"Research on Transmission Line Fault Detection Method based on M-Apriori Algorithm","authors":"Qian Liu, Zhiming Jiao, Fangbo Gong, Hong-chao Ji, Jie Chen","doi":"10.1109/acait53529.2021.9731306","DOIUrl":"https://doi.org/10.1109/acait53529.2021.9731306","url":null,"abstract":"Ensuring the stability of transmission line is the key to ensure the normal operation of the whole power grid system. In order to realize intelligent detection of transmission line fault and big data analysis, a transmission line fault detection method based on improved M-Apriori optimization algorithm is proposed. Firstly, the transmission line fault detection index system is constructed, and the M-Apriori algorithm is optimized and improved based on the traditional Apriori algorithm. In order to verify the comprehensive performance of the algorithm, five common transmission line fault types are selected for simulation this time, and the execution time of Apriori and M-Apriori algorithms are compared and analyzed respectively when the number of things with the same support is different, the system degree is different, and the number of things is the same. The simulation results show that the improved M-apriori has better algorithm efficiency, better recognition rate than BP neural network algorithm, and can realize the automatic monitoring of transmission line fault.","PeriodicalId":173633,"journal":{"name":"2021 5th Asian Conference on Artificial Intelligence Technology (ACAIT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125458314","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