{"title":"Unsupervised Sentiment and Style Transfer from Massive Texts","authors":"Xianjie Shen, Wei Chen, Shuren Xu","doi":"10.1145/3573428.3573464","DOIUrl":"https://doi.org/10.1145/3573428.3573464","url":null,"abstract":"Unsupervised style transfer aims to transfer the intrinsic style of text while preserving its content without parallel datasets. Many sophisticated methods using reinforcement learning and neural networks have been developed to address this problem, however, their performance is not very ideal yet. We observe that given massive unpaired texts, there would exist high-quality sentence pairs that have similar style-independent content but different style words. Inspiring by this observation, in this paper, we propose a simple yet effective method without any neural network. Specifically, we consider both embedding similarity and BLEU score to locate similar sentences of different styles for a pseudo-parallel dataset construction. From this pseudo-parallel dataset, we distill the style words and align them into pairs based on statistical signals. We further refine our pseudo-parallel dataset by ignoring the identified style words during similarity calculation. After the style word pairs converged, we put them together as a lookup table to recognize and replace style words for style transfer. Extensive experiments demonstrate that our method is effective in different style transferring settings, such as sentiment and formality, outperforming state-of-the-art methods.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122555931","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}
{"title":"Design of a Radar and Laser Compound Altimeter for Ground Detection","authors":"Hui Yang, Yifei Zhang, Kaibo Bi","doi":"10.1145/3573428.3573459","DOIUrl":"https://doi.org/10.1145/3573428.3573459","url":null,"abstract":"Radar altimeters and laser altimeters are two kinds of altitude detection devices with different performances. The laser altimeter has the advantages of high detection accuracy and strong anti-electromagnetic interference ability, while the radar altimeter is not affected by weather and environment, so it can be used in all weather. Therefore, the compound detection combined the radar altimeter and the laser altimeter is beneficial to improve the detection accuracy and enhance the anti-jamming capability of the system. According to the advantages and disadvantages of the two kinds of altimeters, a radar and laser compound altimeter is designed, the overall composition of the compound altimeter is studied, and the filtering and fusion algorithm of the two kinds of altimeters is proposed. The digital simulation result shows that the accuracy of the altitude detection based on multi-sensors fusion is higher than that of a single sensor, and the stability and reliability of the compound system are stronger. It shows that the compound altitude detection system combined radar and laser altimeter is feasible.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121226096","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}
{"title":"A Method of Mask-Wearing Detection Based on Improved YOLOv4","authors":"Xuan Liu, Changgeng Yu, Dewang Yang","doi":"10.1145/3573428.3573662","DOIUrl":"https://doi.org/10.1145/3573428.3573662","url":null,"abstract":"In this paper, a lightweight network based on improved YOLOv4 is proposed to solve the problems of complex model structure and unsatisfactory performance of detection speed in fast-moving situations. Firstly, the inverted residual blocks (IRB) based on Mobilenetv2 are adopted into the backbone feature extraction network to reduce the complexity of the model structure. Then, the feature fusion network based on the depth-wise separable convolution is applied to minimize model calculations and parameters. Experimental results show that the proposed model has the advantages of high accuracy, fast detection speed, and lightweight, which has satisfied the requirements of real-time detection of mask-wearing in fast-moving situations.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122299425","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}
Liwen Shen, Yimin Tian, Hai Wang, Saisai Zhang, Yunfei Du, Hongmei Chen
{"title":"Simulation of basic digital signal processing operations","authors":"Liwen Shen, Yimin Tian, Hai Wang, Saisai Zhang, Yunfei Du, Hongmei Chen","doi":"10.1145/3573428.3573669","DOIUrl":"https://doi.org/10.1145/3573428.3573669","url":null,"abstract":"With the continuous development of information technology, digital signal processing is also getting more and more attention. Meanwhile, MATLAB, as an excellent and efficient scientific computing application software for science and engineering, has been widely used in many fields. In this paper, we design and develop a digital signal processing simulation platform for visualizing the basic operations of digital signal processing with the help of MATLAB GUI and demonstrate the course contents in an interactive real-time dynamic manner. The system implements simple operations and provides corresponding display functions. The simulation platform is simple to operate, intuitive to display, comprehensive in function, with good interactivity and strong intuitive, can make abstract and difficult to understand algorithms become visualized, students will be able to learn the course content more intuitive and comprehensive, easy to understand and master, improve the quality of student learning while enriching the teacher's teaching tools.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127127007","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}
{"title":"Site selection of the rural tourism logistics network based on the evolution game under the heuristic algorithm","authors":"Jiang Zhou, Lan Feng, Zhiyong Bu","doi":"10.1145/3573428.3573558","DOIUrl":"https://doi.org/10.1145/3573428.3573558","url":null,"abstract":"In order to actively respond to the spirit of the 20th National People's Congress of the Communist Party of China and revitalize rural development, China has set off a upsurge of rural tourism, which is conducive to alleviating the large difference between urban and rural development, and also plays a positive role in the development of traditional villages. However, rural logistics is closely related to rural tourism, which can not only improve the convenience of rural tourism, but also further promote the development of rural tourism. However, at present, the development of rural logistics under the background of rural tourism still has problems to be solved. Taking some traditional villages such as Yongxing County, Chenzhou City, Hunan Province as an example, the construction of its logistics service network is not perfect. Based on this paper according to the Chenzhou yongxing county, the location of the passenger population distribution, using unconstrained optimization, heuristic algorithm, established the mathematical model of logistics service network site selection, using Matlab software to solve the preliminary site conclusion, then use the evolution game to the conclusion, so as to achieve the purpose of more accurate. The significance of this paper is to choose the construction of appropriate tourism logistics outlets to promote the development of rural tourism and maximize the economic benefits, but also to let more tourists and villagers to get faster services.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125717216","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}
{"title":"Automatic generation of SysML requirement models based on Chinese natural language requirements","authors":"Jialu Chen, Baokun Hu, W. Diao, Yuqian Huang","doi":"10.1145/3573428.3573470","DOIUrl":"https://doi.org/10.1145/3573428.3573470","url":null,"abstract":"In the face of increasingly complex systems engineering R&D, Model-Based Systems Engineering (MBSE) is gradually replacing Traditional Systems Engineering, producing a significant shift in modelling language, modelling thinking and modelling tools. And SysML, as a common modelling language for MBSE practitioners, has many irreplaceable advantages. Requirements diagrams are the primary medium of SysML for conveying traceability between requirements and from requirements to structure and behaviour in a system model. Today, how to automate the construction of SysML requirements models is a significant challenge. This paper proposes an automatic SysML model generation method based on Chinese free-text requirements using natural language processing. Firstly, perform word segmentation and POS Tagging on the requirement text to construct a domain lexicon, extract effective requirements by combining the domain lexicon and regular expressions, and then mark the effective requirements with semantic roles, and determine the requirements elements through established rules, which are ultimately converted into SysML requirements diagrams.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126355410","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}
{"title":"Detection of Marine Chemical Pollution Based on Image Processing and Machine Learning","authors":"Lingyun Chen, Min Gao, Langyue Wang, Chuhan Xue","doi":"10.1145/3573428.3573785","DOIUrl":"https://doi.org/10.1145/3573428.3573785","url":null,"abstract":"The problem of oil spills is lethal to the ocean ecosystem. To solve the problem, one of the most important key steps is to detect the ocean surface and judge whether there are or not oil spills. Remote sensing provides the advantage of controlling and observing events remotely, and it can cover the areas that people cannot access, so we use it to build a database. Next, we choose to use Matlab for the pre-image processing and then use the neural network by Python to realize and there are five pre-processing methods: expanding the dynamic histogram range in the ‘Y’ channel (method 1), expanding the dynamic histogram range in three channels (method 2), contrast enhancement (method 3), expanding the dynamic histogram range and then contrast enhancement (method 4), and contrast enhancement, and then expanding the dynamic histogram range (method 5). Finally, we use a neural network to test accuracy, in comparison, method 1 is the best and we improve the accuracy from 72% to 82%.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127823739","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}
{"title":"Fast Pedestrian Detection Algorithm Based on Improved YOLOv3","authors":"Jiahao Li, Yin Tian, Yanxuan Jiang, Jie Yang, Zhichao Chen, Zhicheng Feng","doi":"10.1145/3573428.3573740","DOIUrl":"https://doi.org/10.1145/3573428.3573740","url":null,"abstract":"Aiming at the problems of fast-moving speed, easy occlusion, and complex background of pedestrians in traffic scenes, a fast pedestrian detection algorithm based on improved YOLOv3 is proposed. First, choose the efficient lightweight network ShuffleNetv2 to replace the original backbone network Darknet-53 to reduce the model complexity and improve the detection speed. Second, a reverse residual structure is introduced in the detection network layer to enhance the expressiveness of features. Third, a coordinate attention mechanism is introduced to suppress useless information and enhance the network's ability to focus on key features. Fourth, the spatial pyramid pooling structure is introduced to realize multi-scale feature fusion of the network and improve the detection accuracy of small objects. The experimental results show that compared with YOLOv3, the improved YOLOv3 proposed in this paper can improve the detection accuracy and detection speed by 0.7% and 53.8% respectively, which is more conducive to the rapid detection of pedestrians.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128781095","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}
{"title":"Super-Resolution Reconstruction Algorithm Based on Improved Generative Adversarial Network","authors":"Xiangyu Deng, Yao Ma, Yangyang Bian","doi":"10.1145/3573428.3573748","DOIUrl":"https://doi.org/10.1145/3573428.3573748","url":null,"abstract":"The current super-resolution algorithm for generative adversarial networks (SRGAN) has problems such as an unstable model training process and excessive smoothing of reconstructed images, which can affect the quality of generated images to a large extent. In this paper, based on SRGAN, all BN layers in the generative network are removed, and WGAN is used instead of JS scatter to optimize the discriminate network, This efficiently prevents the phenomenon of gradient disappearance and resolves the issue of unstable training of generative adversarial networks. The SA module is added to the vgg19 feature extraction network to obtain better feature information and improve the quality of the generated images. The experiments show that the proposed method has better stability in the training process compared with the traditional SRGAN on the DIV2K datasets, improvements are made to the reconstructed images' peak signal-to-noise ratio (PSNR), structural similarity (SSIM), and visual effect performance.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122368758","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}
Qiankuo Ma, Xiaokuan Zhang, Yang Wang, Binfeng Zong, Jiahua Xv, Shuyu Zheng, Yongquan Su
{"title":"Dynamic RCS Statistical Modeling of Stealth Aircraft","authors":"Qiankuo Ma, Xiaokuan Zhang, Yang Wang, Binfeng Zong, Jiahua Xv, Shuyu Zheng, Yongquan Su","doi":"10.1145/3573428.3573496","DOIUrl":"https://doi.org/10.1145/3573428.3573496","url":null,"abstract":"With the development of stealth technology, the threat of stealth aircraft with high speed and high maneuverability is increasing. Statistical distribution model can reveal dynamic RCS characteristics, which is an important part of anti-stealth technology. In this paper, the static RCS database is established initially. Combining with the level flight and the circling track models, two dynamic RCS sequences are obtained based on the static RCS database. Then, these dynamic RCS sequences are described by chi-square distribution model, log-normal distribution model and Weibull distribution model. The K-S test results reveal that the log-normal distribution has high accuracy. So, the log-normal distribution has good potential in anti-stealth.","PeriodicalId":314698,"journal":{"name":"Proceedings of the 2022 6th International Conference on Electronic Information Technology and Computer Engineering","volume":"316 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132763348","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}