2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)最新文献_第2页

Classification Coding and Image Recognition Based on Pulse Neural Network 基于脉冲神经网络的分类编码与图像识别

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456528

Dong Li, Yiwen Jiao, Pengcheng Ge, Kuanfei Sun, Zefu Gao, Feilong Mao

引用次数: 0

3D scene geometry estimation method of substation inspection robot based on lightweight neural network 基于轻量级神经网络的变电站巡检机器人三维场景几何估计方法

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456574

Hong Yu, F. Shen

引用次数: 1

A Streaming Transmission Scheme for DVC over Wireless Mobile Ad hoc Networks 一种基于无线移动自组织网络的DVC流传输方案

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456493

Tian Bo, Jing Chunmei

引用次数: 0

Research on the application of big data in modern financial reform based on genetic algorithm 基于遗传算法的大数据在现代金融改革中的应用研究

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456455

Jingui Wu

{"title":"Research on the application of big data in modern financial reform based on genetic algorithm","authors":"Jingui Wu","doi":"10.1109/AIID51893.2021.9456455","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456455","url":null,"abstract":"Under the background of the prevailing development of big data technology at this stage, the contribution of its technology to modern economic and financial reforms is also increasing. This paper takes big data technology as the main research theory, combines genetic algorithm with support vector machine, and makes overall planning to study its application analysis in modern economic and financial reform. This article takes the basic concepts of related research as the starting point, from a more comprehensive and effective analysis of my country's current corporate financial reform and innovation, and then introduces the specific methods of modern economic and financial innovation and reform, and how to improve the effectiveness of innovation Sex made some related suggestions. The research results show that support vector machine technology is a new general-purpose machine learning method in recent years, and this article combines it with genetic algorithm, which has certain significance in solving modern economic and financial reforms. In this paper, parameter optimization is carried out to improve the support vector machine in many aspects, and the support vector machine hybrid genetic algorithm is applied to the modern economic and financial reform, and the economic and financial reform model is constructed.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132537982","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 Transfer for Semantic Segmentation Based on Feature Aggregation 基于特征聚合的语义分割知识转移

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456500

Guo Fan, Wang Ziyuan

{"title":"Knowledge Transfer for Semantic Segmentation Based on Feature Aggregation","authors":"Guo Fan, Wang Ziyuan","doi":"10.1109/AIID51893.2021.9456500","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456500","url":null,"abstract":"In recent years, deep neural network has achieved high accuracy in the field of image recognition, but the consumption of resource is high. Inspired by collaborative learning approaches and the knowledge distillation technique, this study proposes a knowledge transfer method for semantic segmentation based on feature aggregation. In this research, the original student network is applied to generate the auxiliary teacher network, and share the information learned from the network by establishing dense feature connections between the two networks, which are trained simultaneously. Any one of these networks has access to information that is not available to the individual networks. In addition, in order to increase the degree of collaboration, this paper proposes two methods for establishing connections between the teacher network and the student network. The first method is a dense feature connection between networks of the same layer, and the second method is a dense feature connections between multi-layer networks. The approaches proposed above are validated on the train of Unet, and the experimental results show that the knowledge transfer approach of shared feature aggregation has better performance than the traditional single network.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"344 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115578250","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 Stability of SAAS Application Software Based on Dynamic Fault Prediction of Internet of Things 基于物联网动态故障预测的SAAS应用软件稳定性研究

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456553

Guoshan Liu, Fu Liu

{"title":"Research on Stability of SAAS Application Software Based on Dynamic Fault Prediction of Internet of Things","authors":"Guoshan Liu, Fu Liu","doi":"10.1109/AIID51893.2021.9456553","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456553","url":null,"abstract":"With the maturity of the deployment mode of Internet of things services, the application fields are more and more extensive. People have higher requirements on the availability of network platform services, hoping to obtain uninterrupted network platform services. SAAS service mode can upload all kinds of data needed by customers to SAAS platform for storage. Many of these data are business sensitive data. Once a data security accident occurs, the impact will be very bad. This paper proposes a network data security optimization algorithm based on compactness. Firstly, in order to consider the uneven distribution of training samples and the influence of noise samples on classification accuracy, a method based on the closeness degree between samples is proposed to calculate membership degree. Then, the fuzzy entropy value of the feature is used to determine the weight of each sample feature, and the weighted Euclidean distance based on the feature weight is used to determine the nearest neighbor of the sample to be classified, so as to better reflect the difference of each sample feature. Finally, the classification of the samples to be classified is determined according to the membership degree of each category. Through experimental comparison test, the prediction accuracy of the research method in this paper is significantly higher than that of other comparison methods, with higher practical effect, which can provide a stable operation guarantee for the SAAS platform.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121957241","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

Analysis of process design of aircraft pneumatic accessory maintenance workshop 飞机气动附件维修车间工艺设计分析

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456484

Chen Wenjie, Feng Mengqiao, Shi Zhan

引用次数: 0

Study on the External Quenching Circuit of Halogen GM Tube 卤素GM管外淬火电路的研究

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456550

T. Wei, Zheng Yongchun, Zhu Xuezheng

引用次数: 0

A new deep model based on part pooling for medical image classification 基于局部池化的医学图像深度分类新模型

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456464

Xiaohong Li, Zhendong Guo, Shan Zhang, Xiaoyong Guo

引用次数: 1

Application of barcode recognition technology in baggage verification at airports 条码识别技术在机场行李查验中的应用

2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID) Pub Date : 2021-05-28 DOI: 10.1109/AIID51893.2021.9456592

Xue Zhao, Yingrui Hu

{"title":"Application of barcode recognition technology in baggage verification at airports","authors":"Xue Zhao, Yingrui Hu","doi":"10.1109/AIID51893.2021.9456592","DOIUrl":"https://doi.org/10.1109/AIID51893.2021.9456592","url":null,"abstract":"Barcodes were first proposed by N.T. Woodland in 1949. In recent years, with the popularization of computer applications, bar codes have been widely used. For example, in the airport baggage check-in process, bar codes are used to mark luggage. In this paper, the airport baggage monitoring robot based on bar code recognition is studied and proposed. The overall concept of building the robot is to use the OpenMV camera to obtain the RGB image of the baggage claim certificate and the barcode on the luggage, convert the RGB image to the grayscale image, and then dualize the grayscale image, and finally get the black and white result map, because the black and white bar reflects the light signal is different, so get different electrical signals, digitalize the electrical signal through the shaping circuit, and then get the digital character information corresponding to the bar code through the decoding interface. Extract the recognized bar code information, and add the frame head and end of the frame to the information packaging, the packaged data transmission to the STM32 microcontroller, through analysis of the obtained bar code data information to obtain the baggage is not taken by mistake, if the baggage collection vouchers and baggage verification and carry luggage audit is inconsistent, then give an alert, effectively prevent the phenomenon of luggage being mistakenly taken. The robot has many advantages, such as saving manpower, low contact rate and reducing contact with people.","PeriodicalId":412698,"journal":{"name":"2021 IEEE International Conference on Artificial Intelligence and Industrial Design (AIID)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129070707","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