2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)最新文献_第4页

Communication Security Design of Distribution Automation System with Multiple Protection 多重保护配电自动化系统的通信安全设计

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342482

Siliang Suo, Kaitian Huang, Xiaoyun Kuang, Yang Cao, Liming Chen, Wenwei Tao

引用次数: 2

Safety Belt Wearing Detection Algorithm Based on Human Joint Points 基于人体关节点的安全带磨损检测算法

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342340

Q. Yi, Qu Yi

引用次数: 2

Differential Privacy Stochastic Gradient Descent with Adaptive Privacy Budget Allocation 差分隐私随机梯度下降与自适应隐私预算分配

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342525

Yun Xie, Peng Li, Chao Wu, Qiuling Wu

{"title":"Differential Privacy Stochastic Gradient Descent with Adaptive Privacy Budget Allocation","authors":"Yun Xie, Peng Li, Chao Wu, Qiuling Wu","doi":"10.1109/ICCECE51280.2021.9342525","DOIUrl":"https://doi.org/10.1109/ICCECE51280.2021.9342525","url":null,"abstract":"The Stochastic gradient descent algorithm (SGD) is a classical algorithm for model optimization in machine learning. Introducing a differential privacy model to avoid privacy leakages in the optimization iteration process can achieve the balance of training accuracy and data availability. In addition, a fixed number of iterations are chosen in a conventional implementation scheme. At each iteration, parameters are updated with a noisy gradient. However, the privacy budget is mostly split evenly to each iteration without taking into account the difference in the privacy leakage risk under optimal processing. In this paper, we improve the SGD-based algorithms by appropriately allocating the privacy budget for each iteration. Intuitively, the gradient value is inversely proportional to the number of iterations. The closer the parameter is to its optimal objective value, the smaller the gradient is, and hence the gradients need to be measured more accurately. We propose an adaptive “noise reduction” algorithm that can be applied to private SGD-based empirical risk minimization (ERM) algorithms, meets the accuracy constraint simultaneously. We apply our approach to the backpropagation (BP) neural network. In the experiment, we show and validate that the proposed noise parameter configuration method provides sufficient privacy protection and improves the accuracy of data utility.","PeriodicalId":229425,"journal":{"name":"2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126825297","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: 4

Study of Dynamic Geometrical Parameter Detection System for Tramcar Track Irregularity 有轨电车轨道不平顺动态几何参数检测系统研究

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342227

Hongru Fan, Zhichao He, Jiabin Huang, Chen Li, Yi Yin, Yong-Jun Xie

{"title":"Study of Dynamic Geometrical Parameter Detection System for Tramcar Track Irregularity","authors":"Hongru Fan, Zhichao He, Jiabin Huang, Chen Li, Yi Yin, Yong-Jun Xie","doi":"10.1109/ICCECE51280.2021.9342227","DOIUrl":"https://doi.org/10.1109/ICCECE51280.2021.9342227","url":null,"abstract":"Despite the rapid development of the tramcar market, the study concerning security detection has been a later starter and mostly remains the human detection stage currently, resulting in low detection efficiency and precision. In this case, the paper suggests a detection system for the track irregularity of tramcars, realizing non-contact dynamic measurement over the geometric parameters for groove track longitudinal level and alignment irregularity. In light of this, it further proposes an irregularity detection algorithm for the geometric parameters of groove tracks based on the principle of laser distance measuring and the mid-chord offset (MCO) method, which overcomes the traditional asymmetrical chord offset method’s defect of being only capable of checking the irregularity of short wavelengths within lm and avoids the damage of tracks due to contact track measuring instruments. Importantly, the high detection accuracy, favorable stability, and other favorable characteristics of the detection system proposed have been proven by experimental verification, thereby providing the detection of geometric parameters for modern tramcars with a new method and a new tool.","PeriodicalId":229425,"journal":{"name":"2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124954389","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

RAU-Net: U-Net Model Based on Residual and Attention for Kidney and Kidney Tumor Segmentation RAU-Net:基于残差和关注的U-Net模型用于肾脏和肾肿瘤分割

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342530

Jingna Guo, Weizhen Zeng, Sengoku Yu, Junqiu Xiao

{"title":"RAU-Net: U-Net Model Based on Residual and Attention for Kidney and Kidney Tumor Segmentation","authors":"Jingna Guo, Weizhen Zeng, Sengoku Yu, Junqiu Xiao","doi":"10.1109/ICCECE51280.2021.9342530","DOIUrl":"https://doi.org/10.1109/ICCECE51280.2021.9342530","url":null,"abstract":"Various variants based on U-Net model have made great achievements in various medical image segmentation competitions, however their ability to generalize is less than satisfactory. Therefore, RAU-Net, our proposed model is used for renal tumors segmentation. To improve the performance of the model, the work can be summarized as the following four points: Above all, we have proposed an end-to-end automatic segmentation model, which combined with residual and attention, and allowed us to obtain the kidney and kidney tumor just by preconditioning. Second, the weighted dice loss function and the cross entropy loss function enable the model to fully identify the positive samples and improve the tumor sensitivity. Third, the pretreatment and post-treatment combined with traditional methods and machine learning methods provide us with the possibility to accurately segment kidney and kidney tumor, and improve the segmentation results. Finally, in the KiTS19 dataset (a total of 210 patients), we divided the training set and test set by 8:2, and then obtained the average dice of 0.96 and 0.77 for the kidney and tumor segmentation, also gained the global dice of 0.96 and 0.92 for kidney and tumor segmentation respectively.","PeriodicalId":229425,"journal":{"name":"2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123051929","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: 18

The Study on the Improvement of Humanistic Tour Experience Based on VR Technology 基于VR技术的人文旅游体验提升研究

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342519

Lei Zhao, Jingnan Huang

引用次数: 1

ICCECE 2021 Preface

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/iccece51280.2021.9342438

引用次数: 0

3D Segment and Pickup Framework for Pancreas Segmentation 胰腺三维分割与拾取框架

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342350

Kaiyi Peng, Bin Fang

引用次数: 0

Design and Module Simulation of a Smart Parking System Based On QR Code and Drone Monitoring for Open-Space Temporary Parking Lots 基于二维码和无人机监控的露天临时停车场智能停车系统设计与模块仿真

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342550

F. Hu, B. Wang, Hong Xin Zhang

{"title":"Design and Module Simulation of a Smart Parking System Based On QR Code and Drone Monitoring for Open-Space Temporary Parking Lots","authors":"F. Hu, B. Wang, Hong Xin Zhang","doi":"10.1109/ICCECE51280.2021.9342550","DOIUrl":"https://doi.org/10.1109/ICCECE51280.2021.9342550","url":null,"abstract":"To solve the problem of low parking efficiency and poor management in open temporary parking lots, a smart parking system was designed based on QR code and drone monitoring technologies. The system consists of four modules: parking spot QR code module, drone photography module, data processing module, and user interface module. Functional simulation of each module in the system was carried out by experiments with software programming. The capture of QR codes was achieved by fixed-point drone photography. Programmed with Python, the main system could successfully decipher QR codes, gather the occupancy status of parking spots and update the status as well. Then the user interface module could help users to make decisions on parking spots by presenting the parking status in different colors via a program written with Autoit3. The results show that this system is userfriendly, capable to be deployed at a low cost in a short time, and remains stable when running over a certain period. In the meantime, the occupancy status of the parking spots can be detected and recorded smoothly and readily, suggesting that this technology will have a wide range of applications in future.","PeriodicalId":229425,"journal":{"name":"2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"212 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133389630","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

Image defogging method combining light field depth estimation and dark channel 结合光场深度估计和暗通道的图像去雾方法

2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE) Pub Date : 2021-01-15 DOI: 10.1109/ICCECE51280.2021.9342382

B. Xie, Junxia Yang, Jianhao Shen, Zhiming Lv

引用次数: 3