发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications最新文献

筛选
英文 中文
MacBERT classification model of memory attention mechanism and its application to the power system of EAST neutral beam injection facility 记忆注意机制的MacBERT分类模型及其在EAST中性束注入装置电力系统中的应用
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications Pub Date : 2023-06-15 DOI: 10.1145/3606843.3606857
Xin Han, J. Pan, Zhimin Liu, Yuanzhe Zhao, Caichao Jiang, Shiyong Chen, Sheng Liu, Yahong Xie
{"title":"MacBERT classification model of memory attention mechanism and its application to the power system of EAST neutral beam injection facility","authors":"Xin Han, J. Pan, Zhimin Liu, Yuanzhe Zhao, Caichao Jiang, Shiyong Chen, Sheng Liu, Yahong Xie","doi":"10.1145/3606843.3606857","DOIUrl":"https://doi.org/10.1145/3606843.3606857","url":null,"abstract":"To provide researcher and operation personnel with recommendations on the condition of equipment so as to ensure the safe, reliable, and smooth operation of the EAST-NBI (Experimental Advanced Superconducting Tokamak Neutral Beam Injection) power system, we propose a memory attention mechanism MacBERT (MLM as correction Bidirectional Encoder Representation from Transformers) text classification model. Firstly, we use MacBERT to generate word vectors containing context, which alleviates the masking differences in pre-training and fine-tuning phases. Secondly, the deep features are further extracted and important parts are highlighted through the memory attention module. Finally, the Linear layer and Softmax layer are used to find the label with the highest predicted probability. Experimental results show that the proposed model performs well in the classification of maintenance records for the EAST-NBI power system, which shows certain research significance.","PeriodicalId":134294,"journal":{"name":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","volume":"13 7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131938262","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
XGBoost-Based Multi-Factor Stock Selection Model for Rotational Trading 基于xgboost的旋转交易多因素选股模型
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications Pub Date : 2023-06-15 DOI: 10.1145/3606843.3606862
Thanadon Praphutikul, Y. Limpiyakorn
{"title":"XGBoost-Based Multi-Factor Stock Selection Model for Rotational Trading","authors":"Thanadon Praphutikul, Y. Limpiyakorn","doi":"10.1145/3606843.3606862","DOIUrl":"https://doi.org/10.1145/3606843.3606862","url":null,"abstract":"Unlike traditional buy and sell signals, Rotational trading is a popular method of switching positions between various symbols based on their relative score. Today machine learning techniques are used in various real-world applications, including investments in stock markets. Quantitative investment powered by machine learning would enhance the performance of portfolio formation in financial markets. In this research, we propose an approach of applying a highly efficient gradient boosting tree-based ensemble, XGBoost, for multi-factor stock selection. The two models, monthly and quarterly stock selection were trained on Thailand large-mid capitalization data containing twenty-seven factors which belong to several categories such as value, growth, momentum, liquidity, quality, dividend, and size. It is discovered that the technical factor mainly affects the price movement in monthly XGBoost, whereas the fundamental factor majorly influences the stock changing trends in quarterly XGBoost. The monthly and quarterly rotational portfolio simulation were then performed to evaluate the investing performance measured by portfolio and trade statistics. The three scenarios of monthly and quarterly rotational trading were analyzed. The common findings of the three scenarios reported that the monthly portfolios outperformed in terms of portfolio statistics, due to more opportunities to select new stocks into the portfolio, while in terms of trade statistics, the quarterly portfolios achieved the better results since the longer holding period would reduce noise or whipsaw in trading.","PeriodicalId":134294,"journal":{"name":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122482587","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
Learning with Balanced Criss-Cross Attention for Cross-Modality Crowd Counting 基于平衡交叉注意的跨模态人群计数学习
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications Pub Date : 2023-06-15 DOI: 10.1145/3606843.3606852
Xin Zeng, Wanjun Zhang, Huake Wang, Xiao-Xiao Bian
{"title":"Learning with Balanced Criss-Cross Attention for Cross-Modality Crowd Counting","authors":"Xin Zeng, Wanjun Zhang, Huake Wang, Xiao-Xiao Bian","doi":"10.1145/3606843.3606852","DOIUrl":"https://doi.org/10.1145/3606843.3606852","url":null,"abstract":"Cross-modality crowd counting is one of the most essential tasks in multimedia and image processing, which usually uses multi-sensor information as input in neural networks. Various approaches have been proposed to extract the alignment and relationships between the different modalities in the task of crowd counting. In this work, we explore how to further remedy the cross-modal discrepancies and learn latent relevance across different modalities. We present a novel RGBT crowd counting framework, namely Balanced Criss-Cross Attention Network (BCANet), to overcome the above limitations. To bridge the two modalities, we introduce a Balanced Criss-Cross Attention (BCA) module to encode complementary information across modalities. Lastly, we evaluate our BCANet via extensive experiments and demonstrate that it consistently achieves state-of-the-art results on RGBT-CC and DroneRGBT datasets.","PeriodicalId":134294,"journal":{"name":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125077152","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
Structural Deep Graph Network with Adjacency Matrix Alignment 具有邻接矩阵对齐的结构深度图网络
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications Pub Date : 2023-06-15 DOI: 10.1145/3606843.3606856
Chang Liu, S. Wang
{"title":"Structural Deep Graph Network with Adjacency Matrix Alignment","authors":"Chang Liu, S. Wang","doi":"10.1145/3606843.3606856","DOIUrl":"https://doi.org/10.1145/3606843.3606856","url":null,"abstract":"Recently, deep clustering methods have become a hot research topic, as they fuse deep learning and clustering by utilizing deep neural networks like autoencoders to learn effective feature representations from data. SDCN (Structured Deep Clustering Network) is a GCN-based deep clustering method that combines the data features learned by autoencoders with graph neural network to achieve better performance of the node clustering task. However, we find that SDCN only utilize the feature information, but not consider the adjacency matrix information. Thus we propose the SDAA method, which further enhances clustering performance by aligning the similarity matrix learned by the autoencoder with the adjacency matrix in the graph structure. We conduct node clustering experiments on two real-world datasets to demonstrate the performance of our method.","PeriodicalId":134294,"journal":{"name":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130207158","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
Simplified time synchronization method for 5G NR system in high-frequency offset environment 高频偏移环境下5G NR系统的简化时间同步方法
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications Pub Date : 2023-06-15 DOI: 10.1145/3606843.3606847
Xin Wang, Zhenghao Li, Xu Zhao, Jie Gan, Baozhi Zhang, Han Liu
{"title":"Simplified time synchronization method for 5G NR system in high-frequency offset environment","authors":"Xin Wang, Zhenghao Li, Xu Zhao, Jie Gan, Baozhi Zhang, Han Liu","doi":"10.1145/3606843.3606847","DOIUrl":"https://doi.org/10.1145/3606843.3606847","url":null,"abstract":"A simplified time synchronization method for 5G in high-frequency offset environments is proposed, which includes two steps: coarse synchronization and fine synchronization. In the first stage, a method based on FFT window is proposed to find the approximate position of the PSS. Then, in the frequency domain, auto-correlation is used to eliminate the phase rotation on the PSS sub-carriers caused by timing synchronization offset, and then cross correlation is performed with the local pre-stored sequence to determine the PSS sequence. In the second stage, due the known PSS sequence, a sliding cross correlation method based on frequency offset pre-compensation is used to achieve precise synchronization in a limited area adjacent to the coarse synchronization position.Simulation results show that the proposed method has good robustness in high-frequency offset environment and significantly reduces complexity compared to existing popular methods. This method is not only applicable to 5G system, but also serves as a reference for improving the synchronization performance of other wireless systems with high linear frequency offset caused by crystal oscillators deviation or high mobility.","PeriodicalId":134294,"journal":{"name":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128212214","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 Multi-path Quantum Key Distribution Scheme without Public Nodes Based on Trust Relaying 基于信任中继的无公共节点多路径量子密钥分发方案研究
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications Pub Date : 2023-06-15 DOI: 10.1145/3606843.3606845
Jingran Wang, Weijia Xue, Congli Wang, Jinhua Wang
{"title":"Research on Multi-path Quantum Key Distribution Scheme without Public Nodes Based on Trust Relaying","authors":"Jingran Wang, Weijia Xue, Congli Wang, Jinhua Wang","doi":"10.1145/3606843.3606845","DOIUrl":"https://doi.org/10.1145/3606843.3606845","url":null,"abstract":"ABSTRACT. Quantum key distribution (QKD) network develops rapidly in recent years. In order to improve the efficiency and security of quantum key distribution, this paper analyzes the advantages and disadvantages of single-path and multi-path quantum key distribution and proposes a multi-path quantum key distribution scheme. This scheme includes two aspects which are path equalization priority strategy and the No-public nodes strategy. The priority of the chosen path is based on the path bandwidth utilization, the number of routing hops and quantum keys stored in the trusted nodes. The no-public nodes strategy selects multiple key distribution paths without public nodes. The scheme can reduce the risk of path blocking and the consumption of quantum keys, improve the efficiency and security of QKD. Finally, this scheme is analyzed and verified.","PeriodicalId":134294,"journal":{"name":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131144885","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 Application of SPOC Blended Learning Mode in “College English Viewing, Listening & Speaking” SPOC混合学习模式在“大学英语看、听、说”中的应用研究
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications Pub Date : 2023-06-15 DOI: 10.1145/3606843.3606855
Ming-der Wu
{"title":"Research on the Application of SPOC Blended Learning Mode in “College English Viewing, Listening & Speaking”","authors":"Ming-der Wu","doi":"10.1145/3606843.3606855","DOIUrl":"https://doi.org/10.1145/3606843.3606855","url":null,"abstract":"Faced with the gradual reduction of College English course in university, this study takes the course of “College English Viewing, Listening & Speaking” as an example and probes into the online and offline blended learning mode based on SPOC for part of the top freshen, which lasts 16 weeks among two semesters and makes up for the reduced lesson time by extending the teaching content. The integration of high-quality MOOC and offline classes has changed the traditional single teaching mode, updated the teaching content and stimulated students' interest in learning. The results show that this learning mode can make students have more time to study independently and meet their individual learning needs, which is more helpful to the realization of college English training.","PeriodicalId":134294,"journal":{"name":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114419607","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
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications 2023第五届信息技术与计算机通信国际会议论文集
Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications Pub Date : 1900-01-01 DOI: 10.1145/3606843
{"title":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","authors":"","doi":"10.1145/3606843","DOIUrl":"https://doi.org/10.1145/3606843","url":null,"abstract":"","PeriodicalId":134294,"journal":{"name":"Proceedings of the 2023 5th International Conference on Information Technology and Computer Communications","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126673280","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
首页 上一页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信