Pub Date : 2022-08-01DOI: 10.1109/cost57098.2022.00011
Yang Yang, Hui Wu, Dingguo Yu, Chengpeng Yang
Image classification is the key research in the field of computer vision. Based on real data, this paper adopts the method of image ontology modeling and image transfer learning. In this paper, the image knowledge is transferred to the experimental data, and the neural network is trained by knowledge verification. This paper proposes a ceramic type recognition algorithm based on ontology modeling and transfer learning(ICOT) for image classification. Experimental results show that the proposed algorithm is better than the traditional algorithm. This paper provides a general idea for similar problems.
{"title":"Ceramic Type Recognition Algorithm Based on Ontology Modeling and Transfer Learning","authors":"Yang Yang, Hui Wu, Dingguo Yu, Chengpeng Yang","doi":"10.1109/cost57098.2022.00011","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00011","url":null,"abstract":"Image classification is the key research in the field of computer vision. Based on real data, this paper adopts the method of image ontology modeling and image transfer learning. In this paper, the image knowledge is transferred to the experimental data, and the neural network is trained by knowledge verification. This paper proposes a ceramic type recognition algorithm based on ontology modeling and transfer learning(ICOT) for image classification. Experimental results show that the proposed algorithm is better than the traditional algorithm. This paper provides a general idea for similar problems.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126483912","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}
Pub Date : 2022-08-01DOI: 10.1109/cost57098.2022.00022
Yubo Deng, Yu Zhang, Haoyin Lv, Yezhou Yang, Yongchen Wang
This paper uses the Bi-directional Gated Recurrent Unit(BI-GRU) recurrent neural network, combined with the historical data of the high-speed toll station entrances and exits at different time nodes on weekdays, weekends and holidays, to predict the traffic flow of vehicles entering the province and reaching key tourist cities, and realize the expressway in Gansu Province. It can be seen from the experimental results that in a larger time and space range, BI-GRU has improved prediction accuracy compared with standard Gated Recurrent Unit (GRU) and Long short-term memory (LSTM), and its prediction ability for data with large fluctuations and peak data is more prominent.
{"title":"Prediction of freeway self-driving traffic flow based on bidirectional GRU recurrent neural network","authors":"Yubo Deng, Yu Zhang, Haoyin Lv, Yezhou Yang, Yongchen Wang","doi":"10.1109/cost57098.2022.00022","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00022","url":null,"abstract":"This paper uses the Bi-directional Gated Recurrent Unit(BI-GRU) recurrent neural network, combined with the historical data of the high-speed toll station entrances and exits at different time nodes on weekdays, weekends and holidays, to predict the traffic flow of vehicles entering the province and reaching key tourist cities, and realize the expressway in Gansu Province. It can be seen from the experimental results that in a larger time and space range, BI-GRU has improved prediction accuracy compared with standard Gated Recurrent Unit (GRU) and Long short-term memory (LSTM), and its prediction ability for data with large fluctuations and peak data is more prominent.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126682954","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}
Pub Date : 2022-08-01DOI: 10.1109/cost57098.2022.00036
Minghong Wang, Ying Yu
In response to the call to consolidate and expand the success of poverty alleviation and promote the overall revitalization of the countryside, rural tourism is taken as the research direction in this paper. In the existing research work on rural areas of tourism to poverty alleviation, it is mainly to put forward feasible suggestions for the overall level or to carry out one-way developing analysis for individual areas. A personalized analysis of rural areas of tourism to poverty alleviation from the perspective of users with real travel experience is conducted innovatively in this paper, which can enrich the research content of travel behavior. Through the research, training, and application of the Bidirectional Encoder Representation from Transformer (BERT) model, a deep sentiment analysis of the feelings expressed by tourists in demonstrative areas of tourism to poverty alleviation in China via Trip.com is conducted in this paper. The experiment shows that the accuracy of the BERT model on the test set is 86.9%. Based on completing the sentiment classification, this experiment completed the drawing of the word cloud by counting the frequency of sentiment words in the comments of different tendencies and completed the related results display on the WeChat Mini Program. Tourists can access the platform to learn about the scenic features, geographical location, cultural background, advantages, disadvantages, and characteristics of the scenic spot in advance.
{"title":"Deep Sentiment Analysis of the Feelings Expressed by Tourists Based on BERT Model","authors":"Minghong Wang, Ying Yu","doi":"10.1109/cost57098.2022.00036","DOIUrl":"https://doi.org/10.1109/cost57098.2022.00036","url":null,"abstract":"In response to the call to consolidate and expand the success of poverty alleviation and promote the overall revitalization of the countryside, rural tourism is taken as the research direction in this paper. In the existing research work on rural areas of tourism to poverty alleviation, it is mainly to put forward feasible suggestions for the overall level or to carry out one-way developing analysis for individual areas. A personalized analysis of rural areas of tourism to poverty alleviation from the perspective of users with real travel experience is conducted innovatively in this paper, which can enrich the research content of travel behavior. Through the research, training, and application of the Bidirectional Encoder Representation from Transformer (BERT) model, a deep sentiment analysis of the feelings expressed by tourists in demonstrative areas of tourism to poverty alleviation in China via Trip.com is conducted in this paper. The experiment shows that the accuracy of the BERT model on the test set is 86.9%. Based on completing the sentiment classification, this experiment completed the drawing of the word cloud by counting the frequency of sentiment words in the comments of different tendencies and completed the related results display on the WeChat Mini Program. Tourists can access the platform to learn about the scenic features, geographical location, cultural background, advantages, disadvantages, and characteristics of the scenic spot in advance.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"292 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133111538","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}
Videos can be easily tampered, copied and redistributed by attackers for illegal and monetary usage. Such behaviors severely jeopardize the interest of content owners. Despite huge efforts made in digital video watermarking for copyright protection, typical distortions in video transmission can still easily erase the embedded signal. Among them, temporal synchronization attacks is one of the most prevalent attacks. To address this issue, we present a new video watermarking based on joint Dual-Tree Cosine Wavelet Transform (DTCWT) and Singular Value Decomposition (SVD), which is resistant to frame rate conversion. We simulate the watermark embedding by adjusting the shape of candidate coefficient and perform group-level watermarking that includes moderate temporal redundancy to resist temporal synchronization attacks. Extensive experimental results show that the proposed scheme is more resilient to temporal synchronization attacks and performs better than the existing blind video watermarking schemes.
{"title":"A DTCWT-SVD Based Video Watermarking Resistant to Frame Rate Conversion","authors":"Yifei Wang, Qichao Ying, Zhenxing Qian, Sheng Li, Xinpeng Zhang","doi":"10.1109/CoST57098.2022.00017","DOIUrl":"https://doi.org/10.1109/CoST57098.2022.00017","url":null,"abstract":"Videos can be easily tampered, copied and redistributed by attackers for illegal and monetary usage. Such behaviors severely jeopardize the interest of content owners. Despite huge efforts made in digital video watermarking for copyright protection, typical distortions in video transmission can still easily erase the embedded signal. Among them, temporal synchronization attacks is one of the most prevalent attacks. To address this issue, we present a new video watermarking based on joint Dual-Tree Cosine Wavelet Transform (DTCWT) and Singular Value Decomposition (SVD), which is resistant to frame rate conversion. We simulate the watermark embedding by adjusting the shape of candidate coefficient and perform group-level watermarking that includes moderate temporal redundancy to resist temporal synchronization attacks. Extensive experimental results show that the proposed scheme is more resilient to temporal synchronization attacks and performs better than the existing blind video watermarking schemes.","PeriodicalId":135595,"journal":{"name":"2022 International Conference on Culture-Oriented Science and Technology (CoST)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129142864","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}