发布求助
文献互助 智能选刊 最新文献

2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)最新文献

筛选
英文 中文
PCIe P2P Communication for the High Performance Heterogeneous Computing System 面向高性能异构计算系统的PCIe P2P通信
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498081
Zhen-qi Xu, Hongwei Liu, Yu Liu
{"title":"PCIe P2P Communication for the High Performance Heterogeneous Computing System","authors":"Zhen-qi Xu, Hongwei Liu, Yu Liu","doi":"10.1109/ICAICA52286.2021.9498081","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498081","url":null,"abstract":"PCIe’s point-to-point transmissions provides a low data latency in a computer host. To eliminate the TCP/IP stack bottleneck and improve the service performance in data center, a PCIe P2P transmission for the high-performance heterogeneous computing system is addressed. Based on basic elements including the specific PCIe adapter and PCIe switch, a PCIe P2P data transfers mechanism among the heterogeneous service nodes had been proposed. To implement the point-to-point data transfers mechanism, the related functions and interfaces in the portable software stack had been designed based on the fast-remote memory access network. It does not introduce extra processing overheads to the data transmission process among multiple service hosts, and simplifies the function calling of the related P2P data transfer mechanism. The performance analysis shows that the proposed data transfers mechanism is able to achieve a low latency, high-throughput distributed computing solutions, and can provide a kind of peer-to-peer transmission solution with low-latency and high-bandwidth to improve the processing for the computing cluster and high-performance data center.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122632739","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
Research on Transient Numerical Simulation of Quantitative Identification Pattern of Pipeline Single Defect 管道单一缺陷定量识别模式的瞬态数值模拟研究
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9497979
Xinyuan Wang, Feng Zhou, Xiaoke Liu
{"title":"Research on Transient Numerical Simulation of Quantitative Identification Pattern of Pipeline Single Defect","authors":"Xinyuan Wang, Feng Zhou, Xiaoke Liu","doi":"10.1109/ICAICA52286.2021.9497979","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9497979","url":null,"abstract":"It has been difficult to accurately identify and quantify the type and degree of pipeline defects from the results of pipeline magnetic flux leakage detection. Aiming at this problem, the numerical simulation method is used to study the pattern of quantitative identification of pipeline compound defects. According to the internal and external walls of the pipelines, the pipeline defects are decomposed into basic single damages. ,and the transient finite element simulation is used to analyze and summarize their characteristics and patterns. The results show that there is a direct correspondence between the peak and time span extracted from the results of magnetic flux leakage detection, which are used as the transient response characteristic signals, and the type and extent of defects.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127842147","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 Consumer Purchasing Prediction Based on XGBoost Algorithm 基于XGBoost算法的消费者购买预测研究
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9497944
Shengyin Luo, Sibo Zhang, Hang Cong
{"title":"Research on Consumer Purchasing Prediction Based on XGBoost Algorithm","authors":"Shengyin Luo, Sibo Zhang, Hang Cong","doi":"10.1109/ICAICA52286.2021.9497944","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9497944","url":null,"abstract":"To predict how many consumers will buy goods in the next month helps the e-commerce platform discover potential buyers and carry out the corresponding strategic activities. After analyzing and cleaning the data, we select user purchase features to use eXtreme Gradient Boosting (XGBoost) algorithm to train the divided data sets. Meanwhile, we choose Light Gradient Boosting Machine (LightGBM), Long Short-Term Memory (LSTM) and Fully Connected Neural Network (FCNN) as comparison algorithms. Expectedly, the experiments indicate that using the XGBoost algorithm to predict purchasing can improve performance. Specifically, LightGBM and LSTM increase significantly before remaining stable, whereas FCNN begins in the highest number falling dramatically to approximately the accuracy of 0.32 and keeps steady. Throughout the iteration process, the accuracy of XGBoost surpassed FCNN, and experienced a moderate increase from 0.55 to 0.67, increasing the accuracy by 12%.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133069338","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
A dummy location generation algorithm based on the semantic quantification of location 一种基于位置语义量化的虚拟位置生成算法
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9497903
Xiujin Shi, Junrui Zhang, Yuan Gong
{"title":"A dummy location generation algorithm based on the semantic quantification of location","authors":"Xiujin Shi, Junrui Zhang, Yuan Gong","doi":"10.1109/ICAICA52286.2021.9497903","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9497903","url":null,"abstract":"With the widespread use of location-based services, the risk of location privacy leakage increases. Aiming at the problem that the traditional privacy protection scheme does not fully consider the location privacy leakage caused by the attacker's ability to infer the attack through location semantics, this paper proposes a dummy location generation algorithm based on semantic quantification of location (Virtual Location -based on Semantics, VLBS). The location semantics were quantified by the number of users visiting in different time periods, and a multi-objective optimized dummy location set was constructed from three aspects: historical query probability, semantics of location and physical dispersion uniformity. Experiments show that, compared with other algorithms, the proposed scheme improves the anonymity success rate by 45.6%, the anonymity time by 20.5%, and the physical dispersion uniformity by 12.7%.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123029058","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: 6
Research on Sentiment Analysis Model of Online Shopping Product Evaluation Based on Machine Learning 基于机器学习的网络购物产品评价情感分析模型研究
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498066
Yifan Xu, Yong Ren
{"title":"Research on Sentiment Analysis Model of Online Shopping Product Evaluation Based on Machine Learning","authors":"Yifan Xu, Yong Ren","doi":"10.1109/ICAICA52286.2021.9498066","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498066","url":null,"abstract":"Based on the sentiment analysis of commodity evaluation text, a self-updating iterative algorithm is proposed to solve the problem of the mismatch between commodity evaluation and scoring, and the experiment proves that the algorithm is simple and efficient, and the accuracy of commodity evaluation can reach more than 99.17%.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124413923","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
An Improved Random Forest Classifier for Imbalanced Learning 一种改进的不平衡学习随机森林分类器
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9497933
Weiping Lin, Jie Gao, Beizhan Wang, Qingqi Hong
{"title":"An Improved Random Forest Classifier for Imbalanced Learning","authors":"Weiping Lin, Jie Gao, Beizhan Wang, Qingqi Hong","doi":"10.1109/ICAICA52286.2021.9497933","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9497933","url":null,"abstract":"There are many application scenarios involving imbalanced datasets, whereas many traditional machine learning methods have limited ability to adapt to this kind of data. These methods usually have a bias to identify the majority classes while the minority classes are more important in many cases. In this study, we propose a variant of the completely random forest called HCRF. To improve the classification performance of imbalanced data, we introduced 2 mechanisms: random hybrid-resampling and a cost function that focuses on the minority classes. Verified on several imbalanced datasets, HCRF outperforms all comparison methods, demonstrating excellent performance on imbalanced learning.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121267715","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: 3
A Novel Scatter-enhanced Correlation Feature Learning Method 一种新的散射增强相关特征学习方法
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9497991
Shuzhi Su, Jun Xie, Yanmin Zhu, Xingzhu Liang
{"title":"A Novel Scatter-enhanced Correlation Feature Learning Method","authors":"Shuzhi Su, Jun Xie, Yanmin Zhu, Xingzhu Liang","doi":"10.1109/ICAICA52286.2021.9497991","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9497991","url":null,"abstract":"Canonical Correlation Analysis (CCA) is an essential algorithm in the feature learning field. However, it does not utilize supervised information, and it failed to solve nonlinear problems. Therefore, this paper proposes a novel feature learning algorithm called Scatter-enhanced Canonical Correlation Analysis (SeCCA). This paper integrates the internal structure information and supervised information of the data and embeds them into the canonical correlation framework. The excellent image recognition performance of this algorithm can be demonstrated by extensive experimental results.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116422289","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 Path Planning Model and Algorithm of Driverless Logistics Distribution under Intelligent Network 智能网络下无人驾驶物流配送路径规划模型与算法研究
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498150
Jiang Yuzhe, Yu Hanqing, Qiao Yuan
{"title":"Study on Path Planning Model and Algorithm of Driverless Logistics Distribution under Intelligent Network","authors":"Jiang Yuzhe, Yu Hanqing, Qiao Yuan","doi":"10.1109/ICAICA52286.2021.9498150","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498150","url":null,"abstract":"With the rapid improvement of unmanned driving technology, unmanned driving technology in physical distribution can make full use of logistics resources and improve the quality of logistics services. It aimed to solve the optimization problem of driverless logistics distribution under an intelligent network, a vehicle route planning model with optimization goals of minimizing total cost and maximizing customer satisfaction under the single distribution center’s constraint, multiple vehicle types, closed routes, soft time windows, etc. According to the multi-objective optimization model’s characteristics, an augmented epsilon-constrained algorithm is designed to solve the problem and applied to a multi-customer distribution example to verify its effectiveness and efficiency. In this case, customer satisfaction is as high as 91.67%, and the algorithm only takes 0.94 seconds. The study can provide a reference in the field of driverless physical distribution in the future.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116682047","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
Research on SOC Estimation and Energy Cooperative Control for Electric Vehicles 电动汽车荷电状态估计与能量协同控制研究
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9498217
Fang Bin, Peng Fuming, Lin Qingchao
{"title":"Research on SOC Estimation and Energy Cooperative Control for Electric Vehicles","authors":"Fang Bin, Peng Fuming, Lin Qingchao","doi":"10.1109/ICAICA52286.2021.9498217","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9498217","url":null,"abstract":"The lithium-ion battery model is divided into three subsystems, and then the model parameters are identified online by FFRLS algorithm. The SFEKF algorithm is used to improve the filtering accuracy of traditional EKF algorithm. The SOC estimation algorithm is presented, which is based on FFRLS and SFEKF algorithm. It can accurately estimate the SOC of lithium-ion batteries with an error of around 3%. In addition, lithium-ion batteries and super-capacitors form a hybrid power supply system. An energy co-control strategy is presented, which is based on fuzzy logic control that is optimized by genetic algorithms. The designed algorithm is simulated by Simulink / advisor co-simulation platform. The simulation results showed that the service life of the power battery of electric vehicles was prolonged and the energy utilization of electric vehicles was improved.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115399287","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
Fair Observation of Multiple Moving Targets in Cooperative Multi-UAV Systems 协同多无人机系统中多运动目标的公平观测
2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA) Pub Date : 2021-06-28 DOI: 10.1109/ICAICA52286.2021.9497893
Junbo Zou, Dian-xi Shi
{"title":"Fair Observation of Multiple Moving Targets in Cooperative Multi-UAV Systems","authors":"Junbo Zou, Dian-xi Shi","doi":"10.1109/ICAICA52286.2021.9497893","DOIUrl":"https://doi.org/10.1109/ICAICA52286.2021.9497893","url":null,"abstract":"Cooperative Multi-robot observation of moving the targets (CMOMMT) represents the problem in which a group of autonomous mobile robots equipped with a limited range of sensors that can be used to keep moving targets in observation. The robots plan the movement of the target in coordination to maximize the observation time during which each target appears within the sensing range of at least one robot. We present a novel multi-objective optimization model based on UAVs for CMOMMT schemes which features fairness of observation among different targets as an additional objective. The proposed model uses a quad-tree data structure to model the movement decisions of UAVs in order to maximize duration and the variable qualities (resolutions) of observations. For any given future time, a probabilistic occupancy map for each target is estimated in a Bayesian framework. The experiment results display the effectiveness of the proposed method.","PeriodicalId":121979,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114346593","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