发布求助
文献互助 智能选刊 最新文献

2021 International Conference on Digital Society and Intelligent Systems (DSInS)最新文献

筛选
英文 中文
Gender face Recognition Using Advanced Convolutional Neural Network Model 基于高级卷积神经网络模型的人脸性别识别
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670602
Hafsa Yousif, Isselmou Abd El Kader
{"title":"Gender face Recognition Using Advanced Convolutional Neural Network Model","authors":"Hafsa Yousif, Isselmou Abd El Kader","doi":"10.1109/dsins54396.2021.9670602","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670602","url":null,"abstract":"Gender face recognition has several useful applications in human Android reactions, in which the overall user experience can improved. The convolutional neural network model has made excellent achievements in this field. This paper proposed an advanced convolutional neural network model named \"A-CNN\" to recognize gender. The advantage of the model is training big data without technical challenges and achieved excellent overall performance. The model train used 5000 images, which consisted of gender face male and female. The results have shown that the proposed model gives excellent achievement during the training stage with an accuracy of 97% and loss validation 0.1. The result has demonstrated that the proposed model can facilitate the automatic classification of human gender.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121798766","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
LBPNet: Inserting Local Binary Patterns into Neural Networks to Enhance Manipulation Invariance of Fake Face Detection LBPNet:在神经网络中插入局部二值模式以增强假人脸检测的操作不变性
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670608
Sida Chen
{"title":"LBPNet: Inserting Local Binary Patterns into Neural Networks to Enhance Manipulation Invariance of Fake Face Detection","authors":"Sida Chen","doi":"10.1109/dsins54396.2021.9670608","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670608","url":null,"abstract":"Fake face detection is an essential yet under-explored area, because faces generated by modern Generative Adversarial Networks (GANs) are virtually indiscernible by human observers. A recent work, GramNet[1], proposed using global texture information as heuristic because the features that previous approaches rely on are largely lost after image corruption and are not generalizable to different GANs. However, our theoretical reasoning and empirical studies both lead to the realization that their GLCM descriptor, as a global texture descriptor, is still not robust enough in all cases of image manipulation, because it doesn't take enough pixels into account, making it distortion-prone. Statistical analyses show that LBP is more generalizable to different GANs, and also reaches high consistency in outputs after image manipulation. Motivated by this finding, we implemented a Convolutional Neural Network with a ResNet backbone that uses LBP to enhance its global texture perception, effectively describing the texture at various semantic levels in an image with improved robustness. We conducted experiments with our model on images generated from StyleGAN and StyleGAN2, as well as images manipulated by different filters, and showed that our model reaches better and more consistent performance during image manipulation or in cross-domain settings, especially when images are subjected to Gaussian noise, in which we reached a performance increase from 82% to 90%. We open-sourced our code at https://github.com/Josh-Cena/lbpnet.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124722004","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
Multi-layer Graph Neural Network-Based Random Anomalous Behavior Detection 基于多层图神经网络的随机异常行为检测
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670589
Haoran Shi, Lixin Ji, Shuxin Liu, Kai Wang
{"title":"Multi-layer Graph Neural Network-Based Random Anomalous Behavior Detection","authors":"Haoran Shi, Lixin Ji, Shuxin Liu, Kai Wang","doi":"10.1109/dsins54396.2021.9670589","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670589","url":null,"abstract":"Random anomalous behavior is a false or redundant behavior that randomly appears in the network structure, affecting the analysis result of the network. Current methods mainly capture the relationship between entities in a complex network, using structure features to distinguish this behavior, which is known as graph-based anomaly detection. As a representation learning method that abstracts network entities into feature vectors, the graph embedding method is widely used in abnormal node detection and has been proven to have a relatively accurate detection effect. But it is difficult to apply in anomaly detection of numerous edges. Therefore, we combine the GCN and GAT based on node characteristics, proposing an anomaly detection model for random anomalous edges. It compares with other methods in 6 real networks and proves its effectiveness.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134633190","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 Wearable Vision-To-Audio Sensory Substitution System Based on Deep Learning for the Visually Impaired 基于深度学习的视障可穿戴视觉-听觉感官替代系统
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670599
Zifeng Wang, Heng Li, Jianping Chen, X. Chai, Zhenzhen Zhai
{"title":"A Wearable Vision-To-Audio Sensory Substitution System Based on Deep Learning for the Visually Impaired","authors":"Zifeng Wang, Heng Li, Jianping Chen, X. Chai, Zhenzhen Zhai","doi":"10.1109/dsins54396.2021.9670599","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670599","url":null,"abstract":"Visual impairment has caused serious influence on the human being and society. Due to more sensitive hearing and touch, for visually impaired people, it is an available solution to improve their quality of live, work and study by Sensory Substitution Devices (SSDs) which transfer visual information to audio or touch. In this paper, we proposed a wearable, vision-to-audio sensory substitution system with scene-perception-based deep learning to help the visually impaired users recognize and locate normal objects in the environment. The system consists of a wireless camera module, a Bluetooth speech feedback module with a microphone, and an Android mobile phone with a customized application. The camera module captures images from the scene and sends them to the application of Android mobile phone. The Bluetooth speech feedback module sends speech commands to application and broadcasts speech guidance to visually impaired users. The application based on Android platform loads speech recognition and object detection models. The system has been proved to provide an effective way to help the visually impaired people recognize and locate objects.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128554142","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 Pedestrian Detection Technology Based on SSD Algorithm 基于SSD算法的行人检测技术研究
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670618
Shan Xiong, Zhang Fan
{"title":"Research on Pedestrian Detection Technology Based on SSD Algorithm","authors":"Shan Xiong, Zhang Fan","doi":"10.1109/dsins54396.2021.9670618","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670618","url":null,"abstract":"Artificial intelligence has experienced two cold winters. As algorithms based on deep learning have entered people's sight, target detection technology has also ushered in a leaping development. Compared with other algorithms, the SSD algorithm has very obvious advantages in detection speed and accuracy. This algorithm only runs detection at the top level, which has very high feasibility. Background interference often occurs in pedestrian detection, and there is also the problem of missed detection of small targets. The main research content of the thesis has three parts: the improvement of the original SSD algorithm and the discussion of the basic composition and characteristics of the neural network; changing the basic vgg16 of the original SSD algorithm to resnet50 can improve the detection speed and accuracy.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126094482","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
Image Recognition Technology in Pest Control Based on Convolution Neural Network and An Improved VGG-16 Algorithm : A Case Stduy of Asian Gaint Hornet 基于卷积神经网络和改进VGG-16算法的害虫防治图像识别技术——以亚洲大黄蜂为例
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670624
Guangzhe Wang, Qiaoying Bo
{"title":"Image Recognition Technology in Pest Control Based on Convolution Neural Network and An Improved VGG-16 Algorithm : A Case Stduy of Asian Gaint Hornet","authors":"Guangzhe Wang, Qiaoying Bo","doi":"10.1109/dsins54396.2021.9670624","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670624","url":null,"abstract":"Since the first witness of a cluster of Asian giant hornet in Canada, the Asian giant hornet, which is also called Vespa mandarinia, has caused serious ecological problems. Therefore, in order to detect Asian giant hornet and collect sighting reports from witnesses, the state of Washington has created a website for people to submit their reports. However, most reported sightings mistake other hornets for the Vespa mandarinia. In order to Identify the image of Vespa mandarinia efficiently, based on convolution neural network, we introduced an improved VGG-16 algorithm to solve the problem. By comparing the results of two experiments, the accuracy of treatment group is better than control group.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"16 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122365208","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
Construction Method of Knowledge Graph in Textile Field Facing Industrial Internet 面向工业互联网的纺织领域知识图谱构建方法
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670627
Guodong Wang, Guohua Liu
{"title":"Construction Method of Knowledge Graph in Textile Field Facing Industrial Internet","authors":"Guodong Wang, Guohua Liu","doi":"10.1109/dsins54396.2021.9670627","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670627","url":null,"abstract":"In the industrial Internet environment in the textile field, the structure and standardization of data is the basis for the configuration optimization of network manufacturing resources. In combination with the characteristics of the textile industry data, we propose a method for knowledge map construction method for the textile field facing industrial Internet. This method is guided by Ontology theory, and the natural language processing technology is integrated with artificial, which is fully integrated with a wide range of knowledge, complex structure and poor demultiplexing. Compared with the construction method of traditional knowledge map, the accuracy and coverage of knowledge are improved. Finally, its future application scenarios and support for industrial Internet manufacturing are analyzed.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"307 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127565618","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
Short-term wind power prediction based on extreme learning machine 基于极限学习机的短期风电预测
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670587
Yaming Ren
{"title":"Short-term wind power prediction based on extreme learning machine","authors":"Yaming Ren","doi":"10.1109/dsins54396.2021.9670587","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670587","url":null,"abstract":"Large-scale grid connection of green and clean energy has become a development trend in the energy field. Accurate prediction of wind power output power can reduce the negative impact of wind power on the power system. In this paper, we use extreme learning machine method to achieve short-term prediction of wind power, and determine the optimal number of hidden layer neurons by lattice method. In order to verify the effectiveness of extreme learning machine neural network, we compare the simulation results of extreme learning neural network method and BP neural network method. Simulation results show that the prediction accuracy of extreme learning machine method is similar to that of BP neural network. At the same, considering that extreme learning machine only need to calculate the weight matrix from the hidden layer to the output layer, so extreme learning machine has certain computing advantage compared with BP neural networks.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115705689","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
A Design Based on SysML for High Lift System of Civil Aircraft 基于SysML的民用飞机大升力系统设计
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670570
Xiaoyi Wang, Weida Wang, X. Cai
{"title":"A Design Based on SysML for High Lift System of Civil Aircraft","authors":"Xiaoyi Wang, Weida Wang, X. Cai","doi":"10.1109/dsins54396.2021.9670570","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670570","url":null,"abstract":"With evolution of advanced technologies and new design concepts, new functions and complex interactions are introduced into High Lift System (HLS), which cause requirements to be captured difficultly and system architecture unable to be determined through traditional documents/text to capture requirements and present system architecture, especially iterative revise on requirements and scheme will lead to system design confusion. An effective method of MBSE based on SysML has been required and applied in design of engineering field, such as an aircraft of China. This paper provides a design method based on MBSE using SysML to build up system/product architecture of High Lift System installed on aircraft from capturing demands of stakeholders to final system/products, which also considers effects on establishment of system/product taken safety as an example. This step-by-step design method can make system design and design process clear and reliable, and provide favorable support for the future validation and verification of High Lift System installed on aircraft.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121701519","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 of bank service products based on AI digital human technology 基于AI数字人技术的银行服务产品设计
2021 International Conference on Digital Society and Intelligent Systems (DSInS) Pub Date : 2021-12-03 DOI: 10.1109/dsins54396.2021.9670620
J. Fang, Xinxin Guo
{"title":"Design of bank service products based on AI digital human technology","authors":"J. Fang, Xinxin Guo","doi":"10.1109/dsins54396.2021.9670620","DOIUrl":"https://doi.org/10.1109/dsins54396.2021.9670620","url":null,"abstract":"In recent years, big data, 5g, artificial intelligence and other technologies have penetrated and applied in various fields. Major bank outlets are also looking for the combination of advanced technology and banking services, trying to carry out digital transformation of banks and provide customers with more intelligent and fast interactive experience. At the same time, in the current special period of epidemic prevention and control, the requirement of \"no contact\" makes the digital transformation of banks more urgent. Therefore, in this context, a scattered bank network layout is established to provide customers with services that can replace manual work through \"Ai digital man technology\", so that users do not need to conduct business handling face-to-face with manual work, effectively resolve the risk of face-to-face contact infection, and let users have a great sense of security in business handling. Based on the \"Ai digital human service\" technology, this paper focuses on the design of the bank network of \"Ai digital human service\", and tries to carry out the design practice from the aspects of man-machine, interaction mode and use mode.","PeriodicalId":243724,"journal":{"name":"2021 International Conference on Digital Society and Intelligent Systems (DSInS)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124154061","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 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：481959085
Book学术官方微信