2022 2nd International Conference on Networking Systems of AI (INSAI)最新文献

筛选
英文 中文
Analysis of Tunable F-P filter and Peak-Detection Algorithm in FBG Demodulation System FBG解调系统中可调F-P滤波器及峰值检测算法分析
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00023
Zengbiao Chen, C. Zhang
{"title":"Analysis of Tunable F-P filter and Peak-Detection Algorithm in FBG Demodulation System","authors":"Zengbiao Chen, C. Zhang","doi":"10.1109/INSAI56792.2022.00023","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00023","url":null,"abstract":"The FBG demodulation system is introduced. The tunable ring cavity laser is used as the light source. The output wavelength of the tunable F-P filter is calibrated by the F-P etalon, and the F-P etalon is calibrated by the temperature compensation reference grating. By interpolation between two comb-shaped teeth of etalon, the center wavelength of the sensing grating between the two comb-shaped teeth is obtained, and the demodulation accuracy is improved. The Gaussian mathematical model of the spectrum is established, and the relationship between the fiber grating sensor with a bandwidth of 0.2nm and the tunable F-P filter with bandwidths of 0.01, 0.17 and 0.25nm is given. Through the comparison of Gaussian fitting, centroid method and orthogonal least square method, it is found that the measurement accuracy based on orthogonal polynomial least square method is second only to Gaussian fitting, but its operation speed and stability are greatly improved, and it is more suitable for FBG sensor network with large data volume.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131601896","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 Machine Learning in Risk Assessment of Big Data IOT Credit Financial Management of Operator 机器学习在运营商大数据物联网信用财务风险评估中的应用
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00050
Liyuan Wang
{"title":"Application of Machine Learning in Risk Assessment of Big Data IOT Credit Financial Management of Operator","authors":"Liyuan Wang","doi":"10.1109/INSAI56792.2022.00050","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00050","url":null,"abstract":"With the advent of the era of big data, Internet technology has been developed in various industries. As a communications equipment supplier, telecom operators are coming to recognize that the Internet of Things plays a crucial role in improving enterprise asset management capabilities and reducing costs. Therefore, on the basis of machine learning, it is very necessary to study the risk assessment of big data IOT credit and the financial management of operators. This paper first introduces the concept of credit risk assessment, and then studies the Internet of Things credit assessment system, and then discusses the application of machine learning algorithm deeply. Based on this, this paper designs and studies the credit financial management risk assessment model of big data Internet of Things from different dimensions. At the same time, through a series of performance simulations, the model has good security, stability and compatibility, and it can basically meet the needs of users.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131285966","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 Innovative Multilevel Line Graph Attention Network for Predicting Molecular Properties 一种用于预测分子性质的创新多层线形注意网络
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00044
Yeling Zhang, Huancong Shi, Zhihui Chen, Dongfang Wu, Linhua Jiang
{"title":"An Innovative Multilevel Line Graph Attention Network for Predicting Molecular Properties","authors":"Yeling Zhang, Huancong Shi, Zhihui Chen, Dongfang Wu, Linhua Jiang","doi":"10.1109/INSAI56792.2022.00044","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00044","url":null,"abstract":"Predicting molecular properties is a fundamental task of quantum chemistry and a prerequisite for subsequent research, such as compound discovery and drug design. Recent studies show that, graph neural networks are more effective for this task. By analyzing the composition of molecular energy, we designed a multilevel line graph method for graph data generation, which was experimentally verified to be more capable of representing molecules. Furthermore, we designed an innovative multi-task graph neural network based on graph attention network to predict molecular properties by learning the features embedded in multilevel line graph. Experiments show that our method has higher accuracy in predicting energy properties. Specifically, our method improves performance when trained with fewer samples, which has a great significance for practical applications with sparse samples.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"283 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130969577","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 of Gesture Recognition Algorithm Based on Acceleration Trajectory Image 基于加速度轨迹图像的手势识别算法研究
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00015
Yaling Zhu, Gang Zheng, Xiangwei Li
{"title":"Research of Gesture Recognition Algorithm Based on Acceleration Trajectory Image","authors":"Yaling Zhu, Gang Zheng, Xiangwei Li","doi":"10.1109/INSAI56792.2022.00015","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00015","url":null,"abstract":"According to the characteristics of neural network computing, this paper designs a neural network based on acceleration for gesture detection. First, the acceleration information is collected by using the acceleration sensor to extract the key point information, and convert the effective data into the acceleration track image data. Two neural networks with depth distribution of 50 and 101 are built and trained by ResNet algorithm. Matching image data features to obtain models with accuracy rates of 85% and 91% respectively, so as to achieve higher gesture recognition accuracy with less computational time and storage space complexity.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132650435","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 Unsupervised Domain Adaptation System for Machine Translation 面向机器翻译的无监督域自适应系统研究
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00043
Menghua Jiang, Shiyu Zhao
{"title":"Research on Unsupervised Domain Adaptation System for Machine Translation","authors":"Menghua Jiang, Shiyu Zhao","doi":"10.1109/INSAI56792.2022.00043","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00043","url":null,"abstract":"With the intensive research on neural networks and deep learning, neural machine translation proposed in recent years has greatly improved translation quality and gradually replaced traditional statistical-based machine translation. Although neural machine translation can achieve very high translation accuracy with translation models trained on resource-rich outer domains, it tends to perform poorly in other inner domains where resources are scarce. Domain adaptation is one approach to enhance its performance, which uses resource-rich domains to help improve the translation quality of machine translation in resource-scarce domains. In this paper, we try to build a parallel corpus in the inner domain by using the parallel corpus in the outer domain to better train the translation model, which is eventually invoked by the system to realize the translation. The experimental results show that the accuracy of the machine translation system is significantly improved when translating data from the inner domain after applying this method.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"101 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133356282","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 Time Delay of Controller Area Network for Vehicle 车载控制器区域网络时延研究
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00028
Hongrong Wang, Xincheng Liang, Guojun Huang, Chenguang Lai
{"title":"Research on the Time Delay of Controller Area Network for Vehicle","authors":"Hongrong Wang, Xincheng Liang, Guojun Huang, Chenguang Lai","doi":"10.1109/INSAI56792.2022.00028","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00028","url":null,"abstract":"Controller Area Network (CAN) play a vital role in the trend of network connectivity and intellectualization for vehicle, while some performances including reliability and real-time are facing the challenge due to the higher load rate of network. Time delay of CAN bus has become the urgent focus because the vehicle safety is decided by the instantaneity of bus during high-speed driving, especially for the driverless vehicle. In this study the mechanism of CAN bus can be reviewed, and different types time delay will be analyzed. In addition, the model of on-bus delay of message is established under the EMI environment, and simulations will be gained and researched. Considering the tremendous difficulty to eliminate time delay of CAN bus, more means should be adopted to cope with the rigorous challenges.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115673812","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 Particle Swarm Algorithm Based on Adaptive Acceleration Mechanism 基于自适应加速机制的粒子群算法研究
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00034
Peng Liu, Pengjuan Liu
{"title":"Research on Particle Swarm Algorithm Based on Adaptive Acceleration Mechanism","authors":"Peng Liu, Pengjuan Liu","doi":"10.1109/INSAI56792.2022.00034","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00034","url":null,"abstract":"Aiming at the problems of the particle swarm optimization algorithm, such as poor parameter adjustment ability, low convergence accuracy and easy to fall into local minimum, this paper proposes a particle swarm optimization algorithm based on adaptive acceleration mechanism. According to the current particle position priority, the algorithm adjusts the particle flight acceleration in real time, so that the particles jump out of the local optimal position trap and avoid premature phenomenon. Take some tests about the adaptive acceleration mechanism, convergence accuracy, anti-interference ability and particle diversity of the proposed algorithm. The experimental results show that the particle swarm optimization algorithm with adaptive acceleration mechanism not only enhances the local and global search ability, but also improves the convergence accuracy, convergence speed and avoids the premature problem.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115680343","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 and Implementation of Autonomous Learning Platform for Image Classification 图像分类自主学习平台的研究与实现
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00039
Shiyu Zhao, Menghua Jiang, Zengwen Li, Changxue Chen, Liang Song
{"title":"Research and Implementation of Autonomous Learning Platform for Image Classification","authors":"Shiyu Zhao, Menghua Jiang, Zengwen Li, Changxue Chen, Liang Song","doi":"10.1109/INSAI56792.2022.00039","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00039","url":null,"abstract":"The image classification task aims to automatically classify image content based on machine learning methods. This task is a basic task in the field of computer vision, which has broad application prospects and great research value. At present, in the case of large-scale corpus annotation, mainstream image classification algorithms based on deep learning have been able to obtain better classification results. In order to achieve the above goals, this paper has carried out the following work. This paper studies two mainstream pre-training models in the field of image classification: one is the CNN network based on residual learning; the other is the Vision Transformer model based on Transformer. And according to the performance comparison of each model in four data sets: MNIST, CIFAR-10, CIFAR-100 and ImageNet under different parameters, the optimal model is selected as the background training model of the system. The experimental results show that the Transformer-based model Vision Transformer has better performance and can be used as the back-end training model of the autonomous learning platform.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124568087","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
Design and Test of Intelligent Diffuse Reflector False Target Jamming System 智能漫反射假目标干扰系统的设计与测试
2022 2nd International Conference on Networking Systems of AI (INSAI) Pub Date : 2022-10-01 DOI: 10.1109/INSAI56792.2022.00053
Y. Yang, Tao Shen, Boxiong Fan
{"title":"Design and Test of Intelligent Diffuse Reflector False Target Jamming System","authors":"Y. Yang, Tao Shen, Boxiong Fan","doi":"10.1109/INSAI56792.2022.00053","DOIUrl":"https://doi.org/10.1109/INSAI56792.2022.00053","url":null,"abstract":"Diffuse reflector is a kind of false target which is widely used in laser angle deception system. Because of its protective ability, it has become an important part of laser angle deception system aiming at laser guided weapons. At present, there are some problems in the application of decoy target, such as complex deployment process and low jamming efficiency, which restrict the performance of equipment. Based on the requirements of equipment development, this paper proposes a design of jamming system based on Intelligent diffuse reflector false target, builds a complete hardware test platform and establishes the model. The angle and attitude error of the diffuse reflector, the response time of the system and the energy density of the reflected laser are measured in the direction of 0°,30° and 45° commonly used in the equipment deployment. The test results show that the real-time control angle error of the intelligent diffuse reflector false target jamming system is within 1° and the average response time of the system is less than 10s, and the average value of the reflected energy density is 4.72 respectively×10-15J/mm2, 4.30×10-15J/mm2 and 4.15×2 J/mm2 interference distance is 2046m, 2007m and 1976m. It can be seen that the diffuse reflection board can improve the real-time jamming effect of the false target by adjusting the diffuse reflection board and the false target. It provides a new idea for the development of laser countermeasure equipment.","PeriodicalId":318264,"journal":{"name":"2022 2nd International Conference on Networking Systems of AI (INSAI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125550908","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
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
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