发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence最新文献

筛选
英文 中文
A Deep Learning Assisted Intelligent Monitoring System for Smart Grid 一种基于深度学习的智能电网智能监测系统
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508627
Bin Luo, Wen Chen, Xinxiu Xiao, Weibing Weng
{"title":"A Deep Learning Assisted Intelligent Monitoring System for Smart Grid","authors":"Bin Luo, Wen Chen, Xinxiu Xiao, Weibing Weng","doi":"10.1145/3508546.3508627","DOIUrl":"https://doi.org/10.1145/3508546.3508627","url":null,"abstract":"The smart grid provides effective power supply by integrating the traditional grid system with the latest information technologies. Video surveillance is widely used in smart grid to monitor the system behavior as well as detect illegal intrusions. Currently, this video data is normally processed and analyzed manually in real-world applications, which is not only cost inefficient but also error-prone. To enhance the utilization of this video data, we investigate how to design a deep learning assisted intelligent monitoring system for smart grid. First, we classify the characteristics of various target detection algorithms and discuss their potential applications in smart grids. Second, we analyze the challenges of employing target detection algorithms in smart grids. Finally, we propose a framework for constructing intelligent processing systems for smart grids. Our work contributes novel research ideas for the construction of a strong smart grid.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129119009","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: 2
Tessellation-based Kernel Density Estimation 基于镶嵌的核密度估计
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508582
V. Belov, R. Marik
{"title":"Tessellation-based Kernel Density Estimation","authors":"V. Belov, R. Marik","doi":"10.1145/3508546.3508582","DOIUrl":"https://doi.org/10.1145/3508546.3508582","url":null,"abstract":"Kernel density estimation is a complex task that plays an essential role in a variety of applications. In this paper, we introduce an approach to the task that converts the problem of bandwidth evaluation in the Parzen-window-like framework into the non-parametric evaluation of a fine-grained density estimate which can then be scaled by means of the Scale-Space theory to achieve the desired level of smoothness. The detailed estimate is realized through the Delaunay space tessellation method and properties of its output simplices. Additionally, in the experimental part of the paper, we showcase the new method and demonstrate its outputs at various scales, reaching results that perceivably outperform its counterparts.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122255948","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
Urban Traffic Congestion Identification Based on Adaptive Graph Convolutional Network 基于自适应图卷积网络的城市交通拥堵识别
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508617
Huifang Feng, Ruonan Wu, Youji Xu
{"title":"Urban Traffic Congestion Identification Based on Adaptive Graph Convolutional Network","authors":"Huifang Feng, Ruonan Wu, Youji Xu","doi":"10.1145/3508546.3508617","DOIUrl":"https://doi.org/10.1145/3508546.3508617","url":null,"abstract":"Accurately identifying the status of urban traffic is helpful to improve the level of refined management and emergency response capability of urban traffic. Based on trajectory big data, a traffic status recognition model based on an adaptive graph convolutional network is proposed. Firstly, the transportation complex network is constructed using the dual approach and the global characteristics of the traffic network are extracted using high-order graph convolution. Then, according to the global characteristics, the traffic status classification model based on affinity propagation clustering algorithm is established. Finally, according to the clustering results, a traffic status recognition model is proposed based on a fuzzy comprehensive evaluation. A case study of Lanzhou is used to evaluate the performance of the model. Experimental results show that our proposed model is consistent with the actual traffic status and has high recognition accuracy.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127434496","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
Pixel-level segmentation method of concrete cracks based on MU-Net 基于MU-Net的混凝土裂缝像素级分割方法
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508611
Zhili Chen, S. Zhang, Adamu Abubakar Abba, Bing Wang, Yupeng Li
{"title":"Pixel-level segmentation method of concrete cracks based on MU-Net","authors":"Zhili Chen, S. Zhang, Adamu Abubakar Abba, Bing Wang, Yupeng Li","doi":"10.1145/3508546.3508611","DOIUrl":"https://doi.org/10.1145/3508546.3508611","url":null,"abstract":"In order to improve the segmentation accuracy of complex crack and lightweight network, this paper proposes a concrete crack segmentation network named MU-Net (Modified U-Net). In the encoder part, depthwise separable convolution is used to reduce network parameters, and inverted residual structure and attention mechanism are combined to fully extract features while highlighting target features. The decoder part also introduces the depthwise separable convolution and attention mechanism, and improves the segmentation accuracy by integrating the deep and light layers of information. In order to strictly evaluate the effectiveness of the network, this paper constructs a dataset of concrete cracks, which contains complex backgrounds and a variety of cracks, which is more in line with the engineering practice. Experimental results of 5-fold cross validation show that the proposed semantic segmentation network has superior performance compared with other advanced semantic segmentation networks.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"201 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127110027","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 Hybrid Sampling Method in the Prediction of Telecom Customer Churn 混合抽样法在电信客户流失预测中的应用
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508597
Shuai Ye, Guo-en Xia, Xianquan Zhang, Xiangqin Li
{"title":"Application of Hybrid Sampling Method in the Prediction of Telecom Customer Churn","authors":"Shuai Ye, Guo-en Xia, Xianquan Zhang, Xiangqin Li","doi":"10.1145/3508546.3508597","DOIUrl":"https://doi.org/10.1145/3508546.3508597","url":null,"abstract":"In the telecommunications industry, there is a widespread problem of data imbalance. This problem seriously affects the prediction results, making it impossible for telecommunications operators to accurately find potential lost customers, causing a lot of losses. Aiming at the problem of economic loss caused by the imbalance of telecommunications customer data that affects model prediction performance, this paper proposes two hybrid algorithms DB-QCS (DBSCAN Quadrilateral centroid SMOTE) and KM-QCS (K-Means Quadrilateral centroid SMOTE) to solve the above problems, The hybrid algorithm mainly solves the problem of further increasing the marginalization of the sample distribution and introducing noise when the SMOTE algorithm synthesizes new samples. The main idea is to first use the under-sampling method to delete outliers or edge samples in most classes of samples, thereby reducing the number of synthesized new samples to solve the problem of introducing excessive noise. Then, the problem of marginalization of the sample distribution is solved by limiting the synthesis area of the new sample during oversampling, and finally the sampled data set is used for classification training. A large number of experiments on 5 unbalanced telecom customer data sets show that the hybrid algorithm achieves higher F-measure, G-mean and AUC values compared with the SMOTE algorithm.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"80 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126219551","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
Residual Networks with Channel Attention for Single Image Super-Resolution 单幅图像超分辨率的信道关注残差网络
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508651
Yadong Wang, Junmin Wu, Hui Wang
{"title":"Residual Networks with Channel Attention for Single Image Super-Resolution","authors":"Yadong Wang, Junmin Wu, Hui Wang","doi":"10.1145/3508546.3508651","DOIUrl":"https://doi.org/10.1145/3508546.3508651","url":null,"abstract":"With the development of convolution neural network (CNN), CNN-based methods also achieve a great success for image super-resolution tasks. Further, ResNet makes it possible that the network of super-resolution can be trained deeply. However, simply increasing the depth or width of the network has a scant improvement on the reconstruction quality. Therefore, we need to exploit some new mechanisms to boost the quality of the reconstructed SR images. In this paper, we utilize channel attention mechanism to rescale channel-wise features and extract the desired high-frequency information. Additionally, we add feature fusion structure into the network in order to make full use of all the extracted middle high-frequency information instead of that extracted only by the final layer. Experiments we have conducted show that the network we proposed could reconstruct high quality images with only a few parameters.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133681107","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 Capsule Network to Tablet Identification 胶囊网络在片剂鉴定中的应用
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508569
Wenliang He, Minling Zhu
{"title":"Application of Capsule Network to Tablet Identification","authors":"Wenliang He, Minling Zhu","doi":"10.1145/3508546.3508569","DOIUrl":"https://doi.org/10.1145/3508546.3508569","url":null,"abstract":"To address the problem of pill defect recognition, we propose to apply capsule neural network for pill defect recognition. The effects of dynamic routing iteration rounds and different compression function constant term schemes on the performance of the capsule neural network are investigated in the context of small data sets, and the model effects are verified experimentally. The experimental results show that both the number of dynamic routing iteration rounds and different compression function constant term schemes can affect the performance of the capsule neural network, and it is essential to choose an appropriate scheme in the process of training the model. The capsule neural network is found to be suitable for the field of pill defect recognition through experiments. CCS CONCEPTS • Computing methodologies∼Visual content-based indexing","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134142747","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
3D Hand Pose Estimation for Guqin Performance 古琴演奏的三维手部姿态估计
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508655
Lanlan Lyu, Yi Chen, Li Chen, H. Yuan
{"title":"3D Hand Pose Estimation for Guqin Performance","authors":"Lanlan Lyu, Yi Chen, Li Chen, H. Yuan","doi":"10.1145/3508546.3508655","DOIUrl":"https://doi.org/10.1145/3508546.3508655","url":null,"abstract":"3D Hand Pose Estimations an important research content in the field of human-computer interaction, virtual reality, augmented reality and other gesture interaction. In this paper, 3D hand pose surface estimation based on personalized hand features is proposed and applied to guqin performance. We constructed the database of basic finger-pointing for guqin performance,and based on the Mask R-CNN and FPN network structure, a new MMFPN structure is proposed, which can not only realize the three-dimensional surface estimation of basic finger-pointing, but also effectively solve the problem of self-occlusion.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129886414","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 Contour Detection Model Based on Primary Visual Path Response Mechanism 基于主视觉路径响应机制的轮廓检测模型研究
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508563
Xiu Liu, Junbao Zheng, Lixian Wang
{"title":"Research on Contour Detection Model Based on Primary Visual Path Response Mechanism","authors":"Xiu Liu, Junbao Zheng, Lixian Wang","doi":"10.1145/3508546.3508563","DOIUrl":"https://doi.org/10.1145/3508546.3508563","url":null,"abstract":"Considering the subjectivity of the contour detection task and the characteristics of the visual nerve, the traditional contour detection models simulate the surrounding suppression effect of the non-classical receptive field in the V1 area, and affect the primary contour map. This paper proposes a new model that involved the frequency domain separation characteristics and feedforward compensation in the visual pathway based on the traditional contour detection model. This paper takes the sub-high frequency part of the input images as the suppression template and combines the OTSU classification algorithm to initially determine the texture area to be suppressed. The primary contour map is fed forward to the response after multiple suppression to ensure the rapidity and completeness of the final response. Experimental results show that this model has higher performance indicators than the traditional models. While suppressing the background texture, it retains more right contours.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125128079","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
Retrieval and Evaluation of Target Component Based on Ontology Knowledge 基于本体知识的目标构件检索与评价
Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence Pub Date : 2021-12-22 DOI: 10.1145/3508546.3508644
Lijuan Liu, Cheng-Hao Guo
{"title":"Retrieval and Evaluation of Target Component Based on Ontology Knowledge","authors":"Lijuan Liu, Cheng-Hao Guo","doi":"10.1145/3508546.3508644","DOIUrl":"https://doi.org/10.1145/3508546.3508644","url":null,"abstract":"Software reuse most focuses on component based software development (CBSD). However, it's not so accurate and efficient in the process, to solve this problem, this paper proposes an intelligent knowledge-driven method of target component retrieval and evaluation. This method is based on Ontology component description. With the help of the knowledge graph, a semantic mapping is formed between the component to be queried and the component description library, so the entity component is located. In order to measure the component matching performance, it gives multi-angle evaluation of queried candidate components by an evaluation index system. Based on component query information, it makes the searching target clearer, extends the semantic scope of components to be queried. In order to assembly components, a multi agent system (MAS) is also established. The result shows that this method not only makes the component retrieval process higher recall and precision, but also makes the component retrieval process more intelligent by meeting the assembly requirement.","PeriodicalId":300032,"journal":{"name":"Proceedings of the 2021 4th International Conference on Algorithms, Computing and Artificial Intelligence","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130660778","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
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
小红书