发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering最新文献

筛选
英文 中文
Industrial Parts Detection Based on Deep Learning 基于深度学习的工业零件检测
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501556
Haochen Jiang, Wei Wei, Deng Chen, Chenguang Feng
{"title":"Industrial Parts Detection Based on Deep Learning","authors":"Haochen Jiang, Wei Wei, Deng Chen, Chenguang Feng","doi":"10.1145/3501409.3501556","DOIUrl":"https://doi.org/10.1145/3501409.3501556","url":null,"abstract":"Object detection is the core technique of industrial sorting based on machine vision. However, traditional object detection algorithm is difficult to solve sorting tasks in complex industrial scenarios. To this end, this paper proposes an industrial parts detection network based on deep learning. This method is to use the object detection network to detect the parts on the conveyor belts and obtain the category and location information of the parts. In order to improve the network's detection accuracy of multi-scale parts, this paper use the K-Means algorithm to redesign the size of the anchor. In addition, we construct a private dataset for model training and use dataset augmentation to expand our dataset, then using the pre-trained weights based on the VOC dataset for transfer learning. Experiments based on self-constructed dataset show that the mAP of our method achieves 97.03%, which can satisfy the requirements of practical applications.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133717715","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
Edge-enhanced Generative Adversarial Network for Reconstruction of Compressed Image 边缘增强生成对抗网络在压缩图像重建中的应用
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501520
Nan Lin, Yinglin Zhu, Yanqing Zhang, Jianhong Ma, Yangjie Cao, Jie Li
{"title":"Edge-enhanced Generative Adversarial Network for Reconstruction of Compressed Image","authors":"Nan Lin, Yinglin Zhu, Yanqing Zhang, Jianhong Ma, Yangjie Cao, Jie Li","doi":"10.1145/3501409.3501520","DOIUrl":"https://doi.org/10.1145/3501409.3501520","url":null,"abstract":"The images are often compressed to reduce storage usage or accelerate image transmission. However, the compression process always results in the loss of image details, such as edge details, which degrades the visual experience. Plenty of reconstruction methods have been proposed, but it is yet challenging to enhance edge details more precisely. In this paper, we propose a GAN-based image reconstruction architecture mainly for edge enhancement. Our model improves by cycleGAN; the model's input adds the extracted edge of the compressed image to promote generating more precise edge information. To further optimize the image edge details, we define a new edge loss function to improve the quality of the generated image. Lastly, we train and test the images from the CelebA dataset and the ACDC medical dataset. The experimental results show that the reconstructed images are clear under the high compression ratio and have more precise image edge details.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130508977","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 Genetic Algorithm in Truss Optimization with Interval Variables 遗传算法在区间变量桁架优化中的应用
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501644
C. Pei, Yingshuang Zhang
{"title":"Application of Genetic Algorithm in Truss Optimization with Interval Variables","authors":"C. Pei, Yingshuang Zhang","doi":"10.1145/3501409.3501644","DOIUrl":"https://doi.org/10.1145/3501409.3501644","url":null,"abstract":"The optimal design of the structure is often based on the determined parameters. However, due to the limitation of standardization or process, the parameters of the final product may not be based on the calculated optimal design value. A new method for solving the optimal solution interval of truss structure is proposed, and the range and boundary of the optimal solution are given. Assuming that the structure is uncertain, the uncertain design variables are expressed as interval parameters. Using interval method, a mathematical model of interval optimization design is given. The interval optimization problem is equivalently transformed into a deterministic one. Genetic algorithm is applied to solve this optimization problem, and finally the optimal solutions and the corresponding interval values are obtained. The interval optimization method is applied to a truss structure, which proves the effectiveness of the method.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130698268","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
Research of Artificial Intelligence Computer Vision Application 人工智能计算机视觉应用研究
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501700
G. Xu
{"title":"Research of Artificial Intelligence Computer Vision Application","authors":"G. Xu","doi":"10.1145/3501409.3501700","DOIUrl":"https://doi.org/10.1145/3501409.3501700","url":null,"abstract":"With the continuous development of Internet technology, Internet users are no longer satisfied with obtaining information only through text. More and more users like to take photos or screenshots through smart phones to save and share their life information. Subsequently, using computer to recognize and process image information becomes more and more important. Image recognition technology is an important research field of artificial intelligence. This technology can enable computers to process a large amount of information instead of human beings, so as to free human beings from cumbersome workload. Image recognition technology [3-5] meets the relevant needs of actual users through the steps of relevant information acquisition, preprocessing and model training. Image recognition technology first defines the characteristics of related objects, then memory image matching, and finally image recognition. For the definition of the features of related objects, we can not only use the predefined features, but also train the related features through convolutional neural network.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116984745","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 design of water environment' parameter detection system based on SPR sensor 基于SPR传感器的水环境参数检测系统设计
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501410
Lihui Fu, J. Dai
{"title":"The design of water environment' parameter detection system based on SPR sensor","authors":"Lihui Fu, J. Dai","doi":"10.1145/3501409.3501410","DOIUrl":"https://doi.org/10.1145/3501409.3501410","url":null,"abstract":"The detection system of water environment' parameters based on SPR sensor is studied, it can realize the detection of temperature, PH value and refractive index. Optical fiber surface plasmon resonance sensor was fabricated by magnetron sputtering, the detection accuracy of the optical fiber PH sensor is improved with the increase of the PH value of the solution, meanwhile, the refractive index sensitivity and temperature characteristics of the sensor are studied, it has the characteristics of short response time, strong stability and high sensitivity. The research of the detection method provides a new solution for the detection of temperature, pH value and refractive index, it has certain practicability.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131872627","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
Smart Monitoring and Checking Technology of Substation Information based on Virtual Intelligent Electronic Device 基于虚拟智能电子设备的变电站信息智能监控与检测技术
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501702
Yu Wang, Changbao Xu, Jipu Gao, Chenghui Lin, Mingyong Xin
{"title":"Smart Monitoring and Checking Technology of Substation Information based on Virtual Intelligent Electronic Device","authors":"Yu Wang, Changbao Xu, Jipu Gao, Chenghui Lin, Mingyong Xin","doi":"10.1145/3501409.3501702","DOIUrl":"https://doi.org/10.1145/3501409.3501702","url":null,"abstract":"Substation is the core node of power grid energy conversion and operation control. At present, digital and standardized smart substations have been extensively constructed. Data communication gateway machine information point table is the basis and key of information interaction between substation and master station. When building a new substation, it is necessary to manually compare the correctness of the information one by one between the station terminal and the dispatching master station. Thousands of information points make work efficiency very low, so A new method for automatic verification of substation monitoring information is proposed, which based on the total station configuration file and remote control information configuration file of smart substations. Besides, virtual IED(Intelligent Electronic Device, IED) are used instead of physical IED to build a system to realize the automatic verification system of new substation monitoring information. It provides a new effective means for checking the information point table of newly-built substations.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125621134","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
Registration of Lithium Battery x-ray Images Based on an Improved RANSAC Algorithm 基于改进RANSAC算法的锂电池x射线图像配准
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501498
Chang Ding, Deng Chen
{"title":"Registration of Lithium Battery x-ray Images Based on an Improved RANSAC Algorithm","authors":"Chang Ding, Deng Chen","doi":"10.1145/3501409.3501498","DOIUrl":"https://doi.org/10.1145/3501409.3501498","url":null,"abstract":"Image registration and stitching are required in the defect detection of lithium batteries. However, existing image registration methods will suffer from a large number of mismatches caused by similar textures and structures in lithium battery x-ray images. In order to address the problem, we propose an improved RANSAC (random sample consensus, RANSAC) algorithm, which is optimized based on the structure characteristics of lithium battery. When solving the relationship model, this method calculates the matching quality of the matching pair based on the longitudinal pixel distance of the matching pair, and then eliminates the wrong matching point pairs according to the matching quality of the matching pair, thereby reducing the number of mismatched pairs. Experiments show that the algorithm proposed in this paper can eliminate obvious mismatched pairs, and the registration accuracy of lithium battery X-ray digital images is improved by 20.5% on average.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122361004","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
Novel Closed-Form Expressions for Ergodic Capacity of MIMO Ad-Hoc Networks MIMO Ad-Hoc网络遍历容量的新封闭表达式
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501690
Md. Foysal Ahmed, J. Yin, Yin Long
{"title":"Novel Closed-Form Expressions for Ergodic Capacity of MIMO Ad-Hoc Networks","authors":"Md. Foysal Ahmed, J. Yin, Yin Long","doi":"10.1145/3501409.3501690","DOIUrl":"https://doi.org/10.1145/3501409.3501690","url":null,"abstract":"In this letter, we study the ergodic capacity of MIMO Ad-Hoc networks under imperfect channel state information (CSI). Evaluating MIMO capacity under imperfect CSI is still an open problem, and only approximate results for it can be obtained in asymptotic regions so far. In this letter, different from the previous method, we apply the exact probability density function (PDF) of the ratio of two Wishart matrices to evaluate the ergodic capacity of MIMO Ad-Hoc networks. For utilizing the most cutting-edge PDF to solve our problem, we first derive an equivalent Wishart matrix for the sum of interference covariance matrices. And then, based on the equivalent matrix, we obtain an expression for the ergodic capacity by directly applying the PDF of the ratio of two Wishart matrices, which requires M-fold (M is the number of receive antennas) multiple integrals. To avoid the time-consuming M-fold multiple integral, based on Laplace transform, we provide an alternative method which only involves several single integrals.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123012069","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
Gesture Recognition with Complex Background Based on Improved Convolutional Neural Network 基于改进卷积神经网络的复杂背景手势识别
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501647
Lei Li, Wei Wei, Deng Chen, Ou-Yang Wei, Haochen Jiang
{"title":"Gesture Recognition with Complex Background Based on Improved Convolutional Neural Network","authors":"Lei Li, Wei Wei, Deng Chen, Ou-Yang Wei, Haochen Jiang","doi":"10.1145/3501409.3501647","DOIUrl":"https://doi.org/10.1145/3501409.3501647","url":null,"abstract":"Vision based gesture recognition is a research hotspot in the field of human-computer interaction. Existing techniques are inefficient to deal with situations of drastic illumination changes and complex background. This paper is based on the basis of edge detection, individual difference is fused for threshold segmentation to improve the accuracy of hand cutting. In the stage of feature extraction and classification, constructing basic convolutional neural network and support vector machine is used for gesture recognition of geographic information in complex environment. Experiments were carried out on 14 gestures in complex background and skin color like scenes, and the average recognition rate was 98.73%. Our method can effectively segment and recognize gestures in various complex backgrounds and skin color backgrounds, meet the needs of engineering projects, with low hardware requirements.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128005547","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
Conv-Attention Model Based on Multivariate Time Series Prediction: The Cyanobacteria Bloom Case 基于多元时间序列预测的逆向注意模型:蓝藻水华案例
Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering Pub Date : 2021-10-22 DOI: 10.1145/3501409.3501591
Xiaoqian Chen, Yonggang Fu, Honghua Zhou
{"title":"Conv-Attention Model Based on Multivariate Time Series Prediction: The Cyanobacteria Bloom Case","authors":"Xiaoqian Chen, Yonggang Fu, Honghua Zhou","doi":"10.1145/3501409.3501591","DOIUrl":"https://doi.org/10.1145/3501409.3501591","url":null,"abstract":"Multivariate time series forecasting problems are an important part of research in various fields at all times, such as financial and stock markets, natural disasters, disease prevention. However, forecasting has always been difficult due to its own reasons or external factors. In this paper, we propose a brand-new Conv-Attention network (CANet) for harmful algal blooms prediction. To capture more spatial dimension feature information, the network extracts the context dependency from each time series, and at the same time obtains the impact score between the interacting time series. In the previous stage of training, the feature factors are acquired through different convolution kernels. Then attention mechanism is adopted to model the processes that depend on mutual influence. To further enhance the robustness of the network, the CANet incorporates simple MLP layer-assisted training. The experimental results show that our proposed network performs well under the evaluation of the performance index.","PeriodicalId":191106,"journal":{"name":"Proceedings of the 2021 5th International Conference on Electronic Information Technology and Computer Engineering","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129171156","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