发布求助
文献互助 智能选刊 最新文献

Proceedings of the 5th International Conference on Computer Science and Software Engineering最新文献

筛选
英文 中文
A practical hybrid BCI speller for Chinese Character Input: Integrating an Eye Tracker into a P300-Based Spelling approach 一种实用的混合脑机接口拼字器:将眼动仪集成到基于p300的拼字方法中
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3570046
Hao Li, Xun Fang, Zeqi Ye, Xingxing Chu, Gai Lu, Yang Yu
{"title":"A practical hybrid BCI speller for Chinese Character Input: Integrating an Eye Tracker into a P300-Based Spelling approach","authors":"Hao Li, Xun Fang, Zeqi Ye, Xingxing Chu, Gai Lu, Yang Yu","doi":"10.1145/3569966.3570046","DOIUrl":"https://doi.org/10.1145/3569966.3570046","url":null,"abstract":"In this study, we proposed a practical hybrid brain-computer interface (BCI) speller to enhance the performance for Chinese character input by incorporating eye tracker into the traditional P300 event-related potential spelling paradigm. The spelling process is activated asynchronously when subjects gazes at the Start-button. Then, the interface turns to the classic row-column P300 paradigm. A Chinese character can be inputted in three steps, i) input the initial consonant, ii) input the vowel component, and iii) selecting the target character. With the combination of an eye-tracker, the proposed paradigm achieves asynchronous operation, and achieves accurate and fast-reading Chinese character input without adding additional cognitive load compared to the traditional P300 method. The improved system showed an average speed of about 1.14 sinograms per minute. The experimental results revealed that the proposed paradigm can achieve character input asynchronously with a high accuracy and speed, improving the traditional P300-based spelling paradigm.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software 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":"124054065","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
Algae Image Classification Algorithm Based on the Improved MobileNetV2 基于改进MobileNetV2的藻类图像分类算法
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3569988
Ke Lin, Rusha Hao, S. Zhang, Jianheng Tang, Zhisong Qin
{"title":"Algae Image Classification Algorithm Based on the Improved MobileNetV2","authors":"Ke Lin, Rusha Hao, S. Zhang, Jianheng Tang, Zhisong Qin","doi":"10.1145/3569966.3569988","DOIUrl":"https://doi.org/10.1145/3569966.3569988","url":null,"abstract":"To address the problems of large number of parameters, poor real-time performance and low classification accuracy of existing algae image classification models, this paper proposes a lightweight model based on MobileNetV2. By using the GELU activation function instead of the RELU activation function, the generalization ability of the model and classification accuracy are improved; In order to establish the dependency between channel information and location information, a lightweight coordinate attention mechanism is embedded in the model. The experimental results show that the model can efficiently identify algae categories, and the overall recognition accuracy of the model reaches 97.0% on the algae image dataset after convergence. Moreover, the number of model parameters is only 10.68M, which has certain practical application value.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"20 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":"117070649","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
A Few-Shot Relation Extraction Method for Enhancing Entity Attention 一种增强实体注意力的少镜头关系提取方法
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3570014
Fengying Li, Ye He, Rongsheng Dong
{"title":"A Few-Shot Relation Extraction Method for Enhancing Entity Attention","authors":"Fengying Li, Ye He, Rongsheng Dong","doi":"10.1145/3569966.3570014","DOIUrl":"https://doi.org/10.1145/3569966.3570014","url":null,"abstract":"The aim of the few-shot relation extraction (FSRE) method is to study the relation classification problem with fewer samples. An effective few-shot relation extraction model EnAttConceptFERE is proposed to effectively classify relationships through externally introduced entity concept information and the greater use of internal information. First, we introduce an entity-level vector representation, which uses selects appropriate entity concepts by comparing the similarity between the semantics of entity pairs in a sentence and the semantics of the concepts corresponding to the entities. In addition, the access to external resources is often limited and the introduction of noise cannot be avoided. Therefore, this paper is based on fully mining the effective information of the sample itself, and by introducing the entity self-attention module, the model can pay greater attention to the information of entity pairs that have an impact on relationship extraction. In order to verify the performance of EnAttConceptFERE, experiments are conducted on the FSRE benchmark dataset FewRel. Under the few-shot task setting of 5 way1shot (N=5,K=1) and 10way1shot (N=10,K=1), the accuracy rate is improved by 2.53% and 1.06%, and under the task setting of 5way5shot(N=5,K=5), the accuracy was improved by 1.31% compared with the TD-Proto model, demonstrating the effectiveness and superiority of the EnAttConceptFERE model.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"2 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":"114610587","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
Garbage image classification method based on improved convolution neural network and long short-term memory network 基于改进卷积神经网络和长短期记忆网络的垃圾图像分类方法
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3571180
Xiufang Xie
{"title":"Garbage image classification method based on improved convolution neural network and long short-term memory network","authors":"Xiufang Xie","doi":"10.1145/3569966.3571180","DOIUrl":"https://doi.org/10.1145/3569966.3571180","url":null,"abstract":"When dealing with garbage image classification task, with the deepening of network layer, convolutional neural network will lead to gradient disappearance / explosion and large time consumption. Therefore, a garbage image classification method combining improved convolutional neural network and long short-term memory network is proposed. Taking ResNet-50 as the network backbone, it is optimized by using deep separable convolution and attention mechanism. At the same time, supplemented by LSTM, the features extracted by convolution network and cyclic network are fused to complete classification output. Ablation experiments are carried out on this model and compared with other typical convolutional neural networks. The results show that the accuracy of this model increases by an average of 4.5%. The introduction of deep separable convolution can reduce the training time by about 35.4% compared with the baseline method.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"51 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":"125951506","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
Web Images Relevance and Quality: User Evaluation 网络图像的相关性和质量:用户评价
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3569984
Ehsan Elahi, Ana Iglesias, Jorge Luis Morato Lara
{"title":"Web Images Relevance and Quality: User Evaluation","authors":"Ehsan Elahi, Ana Iglesias, Jorge Luis Morato Lara","doi":"10.1145/3569966.3569984","DOIUrl":"https://doi.org/10.1145/3569966.3569984","url":null,"abstract":"The growth of the Web has been exponential in the last two decades. Currently, the WWW offers a large volume of information and services. Although the user has access to this profusion of information, there are different levels of quality in the information and its publication, which highly influences the understanding. In this paper, we have attempted to establish a relationship between the relevance of web images and their quality. First, a comparative analysis of previous research works in the literature has been carried out. Two methods of web page evaluation have been compared, on the one hand, the evaluation of the end-users of the page, and on the other hand, the heuristic evaluation, carried out by accessibility experts. A user study has been carried out with objective and perception questions. The results obtained with both evaluation methods were similar, agreeing on the characteristics which influence the relevance and quality of the web images. This will help web designers to improve the quality by considering only the relevant content of a web page, without relying on expert judgment.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software 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":"126057515","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
General Discrete Scheme of Finite Difference Method Based on Node Set Vector for Two Dimensional Poisson Equation 基于节点集向量的二维泊松方程有限差分法的一般离散格式
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3570027
Zhizhong Luo
{"title":"General Discrete Scheme of Finite Difference Method Based on Node Set Vector for Two Dimensional Poisson Equation","authors":"Zhizhong Luo","doi":"10.1145/3569966.3570027","DOIUrl":"https://doi.org/10.1145/3569966.3570027","url":null,"abstract":"This paper presents a general discrete scheme of finite difference method based on node set vector for numerical computation of two dimensional Poisson equation, it firstly achieved the relationships between various derivatives by Poisson equation, then deduced simplification of truncated Taylor series by the relationships, based on the simplified expression, the paper analyzed the basic discrete scheme of any high order, investigated general scheme of interior node and boundary node, at last the paper conducted the comparisons of discrete scheme with other forms put forth in other paper, the results testified that the general discrete scheme of any order proposed by this paper is true.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"11 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":"126507461","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
Application of Big Data Technology in the Field of Public Service: Precise Demand Management 大数据技术在公共服务领域的应用:精准需求管理
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3571183
Lingchun Meng, Wenyue Li
{"title":"Application of Big Data Technology in the Field of Public Service: Precise Demand Management","authors":"Lingchun Meng, Wenyue Li","doi":"10.1145/3569966.3571183","DOIUrl":"https://doi.org/10.1145/3569966.3571183","url":null,"abstract":"This paper expounds the construction of precise demand management for the public service field, and introduces the application of related technologies such as data acquisition, preprocessing and analysis. The implementation and application of big data technology in the context of the public service field will contribute to the scientific and precise decision-making in various stages of management in the public service field, and further promote the improvement of the quality of public services.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"13 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":"131760832","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
A systematic literature review of clone evolution 克隆进化的系统文献综述
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3570091
Yan Zhong, Xunhui Zhang, Wang Tao, Yanzhi Zhang
{"title":"A systematic literature review of clone evolution","authors":"Yan Zhong, Xunhui Zhang, Wang Tao, Yanzhi Zhang","doi":"10.1145/3569966.3570091","DOIUrl":"https://doi.org/10.1145/3569966.3570091","url":null,"abstract":"Code clones are identical or nearly similar code fragments often introduced into software systems by programmers with software modification and maintenance. During the evolution of the software system, code clones may experience multiple changes, such as the increase in number, disappearance, location change, etc. These changes increase the difficulty of clone management and possibly introduce bugs into the software, leading to the high price of clone management and maintenance. Therefore, it is necessary to study the clone evolution. In this paper, we summarize the research works in code clone evolution in recent decades. Based on the previous review and survey, we found a total of 47 relevant papers and divided them into five categories with the help of the LDA model. We present our analysis of the current research and discussion about the possible future progress in this paper. The final result of the debate is that we believe the future work will divide into two aspects. On the one hand, developing clone management tools based on the current results become a possible direction; on the other hand, development and improvement may appear in existing tools with more theoretical support due to more knowledge of the evolutionary characteristics of clones.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"1 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":"130612212","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 Efficient Visual Place Recognition System by Predicting Unique Features 基于独特特征预测的高效视觉位置识别系统
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3570105
Reem Aljuaidi, M. Manzke
{"title":"An Efficient Visual Place Recognition System by Predicting Unique Features","authors":"Reem Aljuaidi, M. Manzke","doi":"10.1145/3569966.3570105","DOIUrl":"https://doi.org/10.1145/3569966.3570105","url":null,"abstract":"Visual place recognition (VPR) is the challenge of determining whether a sensor is visiting a previously recorded location or exploring new locations using visual inputs. VPR approaches typically presume that the appearance remains the same as the moment the map (reference) was produced. This presents a significant challenge, since the premise of static appearance is invalid. Instead, the environment is constantly changing because of weather, time of day, building sites, the upgrading of facades and billboards, and so on. A prominent way to deal with the resilience of environmental change is to demand the selection of features from unique and non-unique objects. By doing this, a method can properly discriminate the image, but it is computationally expensive. In this paper, we seek to recognize a place efficiently by reducing the number of its features. In particular, we predict unique features and avoid using features from non-unique objects by taking advantage of geo-tags. Our method provides increased accuracy with lower computational costs compared with other state-of-the-art methods.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"44 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":"130483310","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
Knowledge Map Analysis of Mother Tongue Studies Based on CSSCI Database 基于CSSCI数据库的母语研究知识图谱分析
Proceedings of the 5th International Conference on Computer Science and Software Engineering Pub Date : 2022-10-21 DOI: 10.1145/3569966.3570069
Bing-zhang Wu
{"title":"Knowledge Map Analysis of Mother Tongue Studies Based on CSSCI Database","authors":"Bing-zhang Wu","doi":"10.1145/3569966.3570069","DOIUrl":"https://doi.org/10.1145/3569966.3570069","url":null,"abstract":"In order to intuitively understand the current research situation of mother tongue studies in China, this paper uses the bibliometric method, with the help of Microsoft Excel and Vosviewer (1.6.18) software, to analyze the 618 literature data on mother tongue studies in CSSCI database from 1998 to 2021. By drawing visual maps of annual publication trends, author cooperation networks, keywords, etc., this paper conducts research on the development context, author cooperation, and research hotspots of mother tongue studies. It is found that the development of mother tongue research in China has gradually slowed down in the past three years. There are four main types of author cooperation, but the degree of cooperation still needs to be strengthened. And the research focuses mainly on linguistics and pedagogy. It is hoped that the research results can not only provide reference for the in-depth study on mother tongue and related fields, but also effectively expand the scope of bibliometrics research.","PeriodicalId":145580,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Software Engineering","volume":"90 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":"124613945","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 下一页 尾页
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：481959085
Book学术官方微信