发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence最新文献

筛选
英文 中文
Multi-Tenant Machine Learning Platform Based on Kubernetes 基于Kubernetes的多租户机器学习平台
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404565
Chun-Hsiang Lee, Zhaofeng Li, Xu Lu, Tiyun Chen, Saisai Yang, Chao Wu
{"title":"Multi-Tenant Machine Learning Platform Based on Kubernetes","authors":"Chun-Hsiang Lee, Zhaofeng Li, Xu Lu, Tiyun Chen, Saisai Yang, Chao Wu","doi":"10.1145/3404555.3404565","DOIUrl":"https://doi.org/10.1145/3404555.3404565","url":null,"abstract":"In this paper, we propose a flexible and scalable machine learning architecture based on Kubernetes that can support simultaneous use by huge numbers of users. Its utilization of computing resources is superior to virtual-machine-based architectures because of its container-level resource isolation and highperformance orchestration mechanism. We also describe the implementation of several important features that are designed to simplify the entire modeling lifecycle for machine learning developers. Real case studies for machine learning model development are presented that demonstrates the effectiveness of the platform in reducing the barriers to machine learning.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114768402","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: 5
Cutting Pattern Positioning Method Based on Improved ROI Pooling of R2CNN 基于改进R2CNN ROI池的切割模式定位方法
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404620
Lei Geng, Yang Liu, Zhitao Xiao, Jun Tong, Fang Zhang, Jun Wu
{"title":"Cutting Pattern Positioning Method Based on Improved ROI Pooling of R2CNN","authors":"Lei Geng, Yang Liu, Zhitao Xiao, Jun Tong, Fang Zhang, Jun Wu","doi":"10.1145/3404555.3404620","DOIUrl":"https://doi.org/10.1145/3404555.3404620","url":null,"abstract":"It is of great significance for textile industry to realize automatic pattern detection and positioning. In this paper, combining with image processing technology and deep learning theory, an improved pattern location method based on R2CNN is proposed. Firstly, the multi-scale ROI pooling structure was designed on the basis of R2CNN network, the proportion of the suggestion window generated by RPN network was adjusted, and the pattern Angle prediction function was introduced. The experimental results show that the training on the self-made and labeled data sets achieves an average accuracy of 85%, which greatly improves the positioning accuracy of cut patterns.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133744044","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
Objective Function Optimization Based Time-competition Forwarding Strategy in Internet of Marine Things 基于目标函数优化的海洋物联网时间竞争转发策略
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404631
Jiabao Cao, Lijuan Wang, Jinfeng Dou, Lei Chu, Changrui Qu
{"title":"Objective Function Optimization Based Time-competition Forwarding Strategy in Internet of Marine Things","authors":"Jiabao Cao, Lijuan Wang, Jinfeng Dou, Lei Chu, Changrui Qu","doi":"10.1145/3404555.3404631","DOIUrl":"https://doi.org/10.1145/3404555.3404631","url":null,"abstract":"The rapidly growing data amount brings a great challenge to the various marine communications conditions with the limited resources such as energy, band width and channel capabilities in the Internet of Marine things (IoMaT). A large number of redundant data increases the network load, wastes the energy, and enlarges the probability of data conflict and network congestion. The paper proposes the time-competition forwarding strategy based on objective function optimization (OFO) to prevent redundant forwarding data copies from communication as much as possible, aiming at comprehensive optimization of network performance. The layer-based set of effective relay nodes and complete object function lessen the number of potential forwarding-nodes and avoids the multiple duplicate forwarding. Meantime, the acoustic velocity of ocean is considered into the objective function to optimize the transmission time. The simulation results demonstrate that the proposed strategy can effectively reduce the network traffic and perform well in term of the balance of energy consumption, the network lifetime, the packet delivery ratio, the data conflict and the network congestion.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"158 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134174138","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
Missing Frame Detection of Surveillance Videos Based on Deep Learning in Forensic Science 基于法医学深度学习的监控视频缺失帧检测
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404576
Zefeng Zhang, H. Feng, Shaoyou Pan, Muyang Yi, Hongtao Lu
{"title":"Missing Frame Detection of Surveillance Videos Based on Deep Learning in Forensic Science","authors":"Zefeng Zhang, H. Feng, Shaoyou Pan, Muyang Yi, Hongtao Lu","doi":"10.1145/3404555.3404576","DOIUrl":"https://doi.org/10.1145/3404555.3404576","url":null,"abstract":"The identification of road traffic accidents plays an essential role in the litigation process of complicated traffic cases. Speed appraisement is the main part among all kinds of judicial identification in the area of road traffic accident. When evaluating the speed of vehicles, video frame time is an important parameter. The situation of missing frames may cause an imprecision of speed inspection. In this paper, we propose a method to detect missing frames by the movement of objects in video based on deep learning techniques. The method is based on object detection neural network. A derived distance of target object is calculated and applied to detect missing frames. We then confirm the performance of proposed method on dataset consisted of collected surveillance videos. It can find missing frames accurately and rapidly, which effectively reduces calculation errors of vehicle speed and promotes the authenticity of forensic investigation.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133023788","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
Study on Prediction of Legal Judgments Based on the CNN-BiGRU Model 基于CNN-BiGRU模型的法律判决预测研究
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404573
Chenlu Wang, Xiaoning Jin
{"title":"Study on Prediction of Legal Judgments Based on the CNN-BiGRU Model","authors":"Chenlu Wang, Xiaoning Jin","doi":"10.1145/3404555.3404573","DOIUrl":"https://doi.org/10.1145/3404555.3404573","url":null,"abstract":"As the cases exploded, leading legal judgment prediction becomes a promising application of artificial intelligence techniques in the legal field. The goal of legal judgment prediction is to predict the judgment results based on the facts information of a case. However, the classifier of the traditional method has poor accuracy performance and cost large computational time. The commonly used deep learning models are CNN and RNN. In this paper, CNN-BiGRU was established and analyzed, which combined the good extraction ability of CNN for local feature information and RNN for long-term dependencies information of the text. Compared with the CAIL 2018 dataset, the prediction accuracy of the charges, law articles and the terms of penalty are 94.8%, 93.6%, and 73.4%, respectively. Results showed that CNN-BiGRU has a higher prediction accuracy than CNN or RNN alone and a good training efficiency over baselines. The effectiveness and practicability of this model are validated.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127987060","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
Detection of Eupatorium Adenophorum Based on Migration Learning 基于迁移学习的紫茎泽兰检测
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404562
Yi Jiang, Junhua Zhang, Jiaqing Wang
{"title":"Detection of Eupatorium Adenophorum Based on Migration Learning","authors":"Yi Jiang, Junhua Zhang, Jiaqing Wang","doi":"10.1145/3404555.3404562","DOIUrl":"https://doi.org/10.1145/3404555.3404562","url":null,"abstract":"Eupatorium adenophorum is one of the most typical examples of invasive alien species in China. Invasion of Eupatorium adenophorum causes serious damage to ecological environment and affects economic development of agroforestry. As the key step in the entire prevention and treatment process, the detection of Eupatorium adenophorum is beneficial to the effective implementation of control measures. Therefore, this paper uses the improved YOLOv3 network to detect Eupatorium adenophorum. Data augmentation and migration learning methods are used to avoid overfitting problems in the model and improve robustness and generalization capabilities. Experimental results show that the average precision value of Eupatorium adenophorum test reached 54.22%. The speed and precision of test are slightly improved compared with the original network. The way of this paper can realize effective detection of Eupatorium adenophorum.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129953792","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
Optical Flow Estimation Using a Non-Local Convolutional Network 基于非局部卷积网络的光流估计
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404616
Liping Zhang, Zongqing Lu
{"title":"Optical Flow Estimation Using a Non-Local Convolutional Network","authors":"Liping Zhang, Zongqing Lu","doi":"10.1145/3404555.3404616","DOIUrl":"https://doi.org/10.1145/3404555.3404616","url":null,"abstract":"Convolutional neural network(CNN) models for optical flow estimation based on coarse-to-fine method are usually difficult to obtain accurate estimates of large displacement motions in the rough layer, so that the estimation error will be passed to the final estimation result. This article proposes an effective convolutional neural network model for optical flow estimation called NTFlow. NTFlow uses a non-local convolutional layer to obtain the correlation of the full feature map, and constrains the estimate of the larger error in the loss function. Experiment results show that our network can get accurate estimation results on public data sets, and the proposed loss function is very robust.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123052366","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
The Performance of Improved Infotaxis in 3D Turbulence 三维湍流中改进信息趋向性的性能
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404572
Dongxia Hao, Shurui Fan, Xu-Dong Sun
{"title":"The Performance of Improved Infotaxis in 3D Turbulence","authors":"Dongxia Hao, Shurui Fan, Xu-Dong Sun","doi":"10.1145/3404555.3404572","DOIUrl":"https://doi.org/10.1145/3404555.3404572","url":null,"abstract":"Emergency response to harmful gases in the environment is an important research field in environmental monitoring. In recent years, more autonomous search algorithms for harmful gas emission sources in uncertain environments have been proposed, which can avoid close contact with harmful gas by emergency personnel. In this paper, Infotaxis is extended to three-dimensional scene for application, and the source guidance in the reward function of the traditional Infotaxis algorithm is too small and the seven alternative direction movement methods in three-dimensional scenes tend to search by layers is optimized. At the same time, two multi-directional movement strategies based on the source guidance algorithm are proposed. The performance of the improved Infotaixs algorithm is analyzed under three internal release source conditions and two external environmental conditions, and the relative optimal mobile strategy is obtained. Many simulation experiments show that compared with the traditional Infotaxis algorithm, the Infotaxis algorithm based on source guidance with 14 alternative directions reduces the mean search path by 25.97% and improves the success rate by 0.2% in three-dimensional scene.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115535962","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 Review on Software Project Scheduling and Task Assignment Approaches 软件项目进度和任务分配方法的系统回顾
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404588
Taskeen Fatima, F. Azam, Muhammad Waseem Anwar, Yawar Rasheed
{"title":"A Systematic Review on Software Project Scheduling and Task Assignment Approaches","authors":"Taskeen Fatima, F. Azam, Muhammad Waseem Anwar, Yawar Rasheed","doi":"10.1145/3404555.3404588","DOIUrl":"https://doi.org/10.1145/3404555.3404588","url":null,"abstract":"Software Project Scheduling and Task Assignment are important integral aspects of software project management and contributes to the overall success of software projects. Key objective of Task scheduling/ assignment is to minimize the cost and time of the project. This article i.e. a systematic literature review, is in-fact the first of its kind, conducted in the context of task scheduling and assignment in software industry. This study specifically elaborates the models used in task assignment and summarizes the techniques/ machine learning algorithms to solve the software project scheduling problem (SPSP). Our Initial search brought out 1100 research articles. However, after applying the inclusion and exclusion criteria, 23 most relevant researches were segregated and thereafter thoroughly reviewed. The review revealed that there are 2 types of basic models of Task Scheduling i.e. static and dynamic, however, static models are most widely used. For Task Scheduling, evolutionary algorithms, whereas, for Task Assignment, Support Vector Machine (SVM) algorithms are most widely used. Due to lack of real-world data in software projects, most of the researches utilized synthetic data sets for Task Assignment. Exploring the Task Assignment tools during the course of review process, 7 tools were identified, however, TAMRI has been graded as most efficient.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131274572","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: 5
mRNA Big Data Analysis of Hepatoma Carcinoma Between Different Genders 不同性别肝癌mRNA大数据分析
Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence Pub Date : 2020-04-23 DOI: 10.1145/3404555.3404601
Jianzhi Deng, Yuehan Zhou, Xiaohui Cheng, Tianyu Li, C. Qin
{"title":"mRNA Big Data Analysis of Hepatoma Carcinoma Between Different Genders","authors":"Jianzhi Deng, Yuehan Zhou, Xiaohui Cheng, Tianyu Li, C. Qin","doi":"10.1145/3404555.3404601","DOIUrl":"https://doi.org/10.1145/3404555.3404601","url":null,"abstract":"In this paper, we did the researches of the directly related differentially expression mRNAs (DEmRNAs) and their gene ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG) signal pathway, COX model and survival analysis. For the purpose, the 87 directly related DEmRNAs (DRmRNAs) to the hepatoma carcinoma illness were selected from the intersectional DEmRNAs of normal-tumor sample matrix and male-female tumor's sample matrix. By the analysis of online databases, DAVID, KOBAS and KEGG, DRmRNAs were enriched in 18 biological process (BP), 5 cellular component (CC), 9 molecular function (MF) and 3 signal pathways (hsa04974, hsa04972 and hsa04080). The co-expression DRmRNAs were analyzed by using the COX model. CHGA was regard as a potential biomarker of hepatoma carcinoma by the proof of survival kmplot analysis and ROC curve analysis.","PeriodicalId":220526,"journal":{"name":"Proceedings of the 2020 6th International Conference on Computing and Artificial Intelligence","volume":"167 S355","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"113973006","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：604180095
Book学术官方微信