Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135420
Qingliu Li, D. Ren, Yuan Luo
The tail- ℓ1 minimization model greatly improves the sparse signal recovery ability compared with ℓ1 minimization model. However, solving the tail- ℓ1 minimization problem requires high computational cost and a lot of time. The hard thresholding pursuit (HTP) technology is attractive due to its computational efficiency in practice. Inspired by the HTP technology, the HTP technology is considered to be an efficient technique to solve the tail- ℓ1 minimization problem. This paper introduces an improved HTP technology, namely tail-HTP. The tail-HTP technology retains the computational simplicity of the HTP technology and greatly improves the efficiency of solving the tail- ℓ1 minimization problem. In addition, the tail-HTP technology also improves the sparse signal recovery ability of the HTP technology. The experimental results verify the high efficiency and superior sparse signal recovery ability of the tail-HTP technology.
{"title":"An Improved Hard Thresholding Pursuit Algorithm for Compressive Sensing","authors":"Qingliu Li, D. Ren, Yuan Luo","doi":"10.1109/ICCECE58074.2023.10135420","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135420","url":null,"abstract":"The tail- ℓ1 minimization model greatly improves the sparse signal recovery ability compared with ℓ1 minimization model. However, solving the tail- ℓ1 minimization problem requires high computational cost and a lot of time. The hard thresholding pursuit (HTP) technology is attractive due to its computational efficiency in practice. Inspired by the HTP technology, the HTP technology is considered to be an efficient technique to solve the tail- ℓ1 minimization problem. This paper introduces an improved HTP technology, namely tail-HTP. The tail-HTP technology retains the computational simplicity of the HTP technology and greatly improves the efficiency of solving the tail- ℓ1 minimization problem. In addition, the tail-HTP technology also improves the sparse signal recovery ability of the HTP technology. The experimental results verify the high efficiency and superior sparse signal recovery ability of the tail-HTP technology.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125134716","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135500
Yilong Liu
Accurate pose estimation is crucial for understanding human behavior in images or videos. Given an RGB image, we want to be able to accurately locate some important keypoints on the body. Understanding human pose and body structure is important for high-level tasks such as human-computer interaction. Human pose estimation usually has problems such as low discrimination between human body and background, and human pose estimation based on HRnet network does not make full use of important feature information. To solve these problems, a human pose estimation method MCSA-hrnet (Multi-scale Channel and Spatial Attention) based on multi-scale channel and spatial attention is improved by using channel attention mechanism and spatial attention mechanism. Starting from the channel domain and spatial domain, MCSA-HRnet integrates the multi-level attention mechanism into the high-resolution network structure, and designs the channel attention block and spatial attention block. This enables the network to focus on the regions of the image that are highly associated with the human body and not on other regions. MCSA-HRnet uses 1×1 convolutions for information extraction in the core part of the ca block (channel attention block) and parallel $boldsymbol{3mathrm{x}3}$ and $boldsymbol{5mathrm{x}5}$ convolutions in the sa block (spatial attention block). Different sizes of parallel convolutions can derive spatial attention maps of different scales, which makes the ability of the network to distinguish human features from background features more significant. Thus, the human body region and its key points can be accurately located. The improved method is verified on COCO keypoint dataset, and the results show that MCSA-HRnet can effectively improve the accuracy of human pose estimation joint point localization.
准确的姿态估计对于理解图像或视频中的人类行为至关重要。给定一个RGB图像，我们希望能够准确地定位身体上的一些重要关键点。了解人体姿势和身体结构对于人机交互等高级任务非常重要。人体姿态估计通常存在人体与背景识别率低、基于HRnet网络的人体姿态估计没有充分利用重要特征信息等问题。针对这些问题，利用通道注意机制和空间注意机制对基于多尺度通道和空间注意的人体姿态估计方法MCSA-hrnet (Multi-scale Channel and Spatial Attention)进行了改进。MCSA-HRnet从通道域和空间域出发，将多层次注意机制集成到高分辨率网络结构中，设计了通道注意块和空间注意块。这使得网络能够专注于图像中与人体高度相关的区域，而不是其他区域。MCSA-HRnet在ca块(通道注意力块)的核心部分使用1×1卷积进行信息提取，并在sa块(空间注意力块)中并行使用$boldsymbol{3mathrm{x}3}$和$boldsymbol{5mathrm{x}5}$卷积。不同大小的并行卷积可以得到不同尺度的空间注意图，这使得网络区分人类特征和背景特征的能力更加显著。从而准确定位人体区域及其关键点。在COCO关键点数据集上对改进方法进行了验证，结果表明MCSA-HRnet可以有效提高人体姿态估计关节点定位的精度。
{"title":"Study on human pose estimation based on channel and spatial attention","authors":"Yilong Liu","doi":"10.1109/ICCECE58074.2023.10135500","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135500","url":null,"abstract":"Accurate pose estimation is crucial for understanding human behavior in images or videos. Given an RGB image, we want to be able to accurately locate some important keypoints on the body. Understanding human pose and body structure is important for high-level tasks such as human-computer interaction. Human pose estimation usually has problems such as low discrimination between human body and background, and human pose estimation based on HRnet network does not make full use of important feature information. To solve these problems, a human pose estimation method MCSA-hrnet (Multi-scale Channel and Spatial Attention) based on multi-scale channel and spatial attention is improved by using channel attention mechanism and spatial attention mechanism. Starting from the channel domain and spatial domain, MCSA-HRnet integrates the multi-level attention mechanism into the high-resolution network structure, and designs the channel attention block and spatial attention block. This enables the network to focus on the regions of the image that are highly associated with the human body and not on other regions. MCSA-HRnet uses 1×1 convolutions for information extraction in the core part of the ca block (channel attention block) and parallel $boldsymbol{3mathrm{x}3}$ and $boldsymbol{5mathrm{x}5}$ convolutions in the sa block (spatial attention block). Different sizes of parallel convolutions can derive spatial attention maps of different scales, which makes the ability of the network to distinguish human features from background features more significant. Thus, the human body region and its key points can be accurately located. The improved method is verified on COCO keypoint dataset, and the results show that MCSA-HRnet can effectively improve the accuracy of human pose estimation joint point localization.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121920262","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135334
Xinyi Lin, Xiaoyun Chen, Yanming Lin
The purpose of graph embedding is to encode the known node features and topological information of graph into low-dimensional embeddings for further downstream learning tasks. Graph autoencoders can aggregate graph topology and node features, but it is highly dependent on the gradient descent optimizer with a large iterative learning time, and susceptible to local optimal solutions. Thus, we propose Graph Convolutional Extreme Learning Machine Autoencoder. To address the limitation that the extreme learning machine autoencoder cannot use topological information, the graph convolution operation is introduced between the input layer and the hidden layer to improve the representation ability of the graph embedding obtained. Experiments of link prediction and node classification on 5 real datasets show that our method is effective.
{"title":"Graph Convolutional Extreme Learning Machine Autoencoder for Graph Embedding","authors":"Xinyi Lin, Xiaoyun Chen, Yanming Lin","doi":"10.1109/ICCECE58074.2023.10135334","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135334","url":null,"abstract":"The purpose of graph embedding is to encode the known node features and topological information of graph into low-dimensional embeddings for further downstream learning tasks. Graph autoencoders can aggregate graph topology and node features, but it is highly dependent on the gradient descent optimizer with a large iterative learning time, and susceptible to local optimal solutions. Thus, we propose Graph Convolutional Extreme Learning Machine Autoencoder. To address the limitation that the extreme learning machine autoencoder cannot use topological information, the graph convolution operation is introduced between the input layer and the hidden layer to improve the representation ability of the graph embedding obtained. Experiments of link prediction and node classification on 5 real datasets show that our method is effective.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122473482","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135253
Y. Huang
In recent years, the tremendous potential of GAN in image generation has been demonstrated. Transformer derived from the NLP field is also gradually applied in computer vision, and Vision Transformer performs well in image classification problems. In this paper, we design a ViT-based GAN architecture for image generation. We found that the Transformer-based generator did not perform well due to using the same attention matrix for each channel. To overcome this problem, we increased the number of heads to generate more attention matrices. And this part is named enhanced multi-head attention, replacing multi-head attention in Transformer. Secondly, our discriminator uses a hybrid model of ResNet50 and ViT, where ResNet50 works on feature extraction making the discriminator perform better. Experiments show that our architecture performs well on image generation tasks.
{"title":"ViT-R50 GAN: Vision Transformers Hybrid Model based Generative Adversarial Networks for Image Generation","authors":"Y. Huang","doi":"10.1109/ICCECE58074.2023.10135253","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135253","url":null,"abstract":"In recent years, the tremendous potential of GAN in image generation has been demonstrated. Transformer derived from the NLP field is also gradually applied in computer vision, and Vision Transformer performs well in image classification problems. In this paper, we design a ViT-based GAN architecture for image generation. We found that the Transformer-based generator did not perform well due to using the same attention matrix for each channel. To overcome this problem, we increased the number of heads to generate more attention matrices. And this part is named enhanced multi-head attention, replacing multi-head attention in Transformer. Secondly, our discriminator uses a hybrid model of ResNet50 and ViT, where ResNet50 works on feature extraction making the discriminator perform better. Experiments show that our architecture performs well on image generation tasks.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"235 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122951082","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135312
Meijiao Wang, Chen Xu, Xiaoqiang Ji, Xiaoting Kan, Sun Qi
About 70% of Parkinson's disease patients have the initial symptoms of tremors at the end of upper limbs in the clinic, which seriously affects the normal work and life of patients. The severity of Parkinson's disease patients is evaluated clinically by doctors based on their experience, lacking objective evaluation criteria. It is particularly important to study an objective and fast tremor assessment method to assist doctors in the diagnosis and treatment of Parkinson's disease. In this paper, a recognition system of Parkinson's patients' hand function tremor based on machine learning is designed. Firstly, the acceleration sensor is used to collect the hand tremor signal, and then the median and band-pass filters are used to remove the noise. Next, the time-domain and frequency-domain characteristics of the tremors signal are extracted. Finally, BP neural network algorithm is used to classify the tremor degree into three categories. 12 volunteers were selected to carry out the system function experiment, and the results show that the system can achieve the classification of hand tremors, with an accuracy rate of 84.5%. The Parkinson's patient's hand tremor evaluation system designed in this paper has the advantages of low cost, small size, comfortable wearing, and high accuracy. It can assist clinical rehabilitation training and help doctors formulate scientific and reasonable rehabilitation training programs.
{"title":"Design of system for parkinson's hand tremor evaluating based on machine learning","authors":"Meijiao Wang, Chen Xu, Xiaoqiang Ji, Xiaoting Kan, Sun Qi","doi":"10.1109/ICCECE58074.2023.10135312","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135312","url":null,"abstract":"About 70% of Parkinson's disease patients have the initial symptoms of tremors at the end of upper limbs in the clinic, which seriously affects the normal work and life of patients. The severity of Parkinson's disease patients is evaluated clinically by doctors based on their experience, lacking objective evaluation criteria. It is particularly important to study an objective and fast tremor assessment method to assist doctors in the diagnosis and treatment of Parkinson's disease. In this paper, a recognition system of Parkinson's patients' hand function tremor based on machine learning is designed. Firstly, the acceleration sensor is used to collect the hand tremor signal, and then the median and band-pass filters are used to remove the noise. Next, the time-domain and frequency-domain characteristics of the tremors signal are extracted. Finally, BP neural network algorithm is used to classify the tremor degree into three categories. 12 volunteers were selected to carry out the system function experiment, and the results show that the system can achieve the classification of hand tremors, with an accuracy rate of 84.5%. The Parkinson's patient's hand tremor evaluation system designed in this paper has the advantages of low cost, small size, comfortable wearing, and high accuracy. It can assist clinical rehabilitation training and help doctors formulate scientific and reasonable rehabilitation training programs.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129580981","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135298
Dadong Zhu, Maoping Li, Hongping Zhou, Gang Zhao
The Yangtze River embankment project is a critical barrier to ensuring the safety of the Yangtze River channel, and it is necessary to strengthen the safety monitoring of the embankment project. Embankment safety is influenced by various factors, while the influence weight of each factor is difficult to determine, and the expert scoring method and other methods are highly subjective and mainly rely on empirical judgment. Based on machine learning theory, this paper constructs an embankment safety evaluation method based on T-S model neural network. The model primarily consists of four layers of structure. (1) the input layer, this paper selects six types of evaluation factors as input parameters; (2) the fuzzification layer; (3) the fuzzy inference layer, matching the fuzzy rules and calculating the connection weights using the concatenation algorithm; (4) output layer, outputting the embankment safety coefficient value by inverse normalization and defuzzification. This paper selected three specific experimental areas in the river core of the Nanjing section of the Yangtze River as the research objects, used the data to conduct safety evaluation tests, and compared them with the actual operation of the embankment. The experimental results show that the safety level of the embankment calculated by the design method is consistent with the existing safety state of the embankment.
{"title":"Research on Safety Evaluation of Yangtze River Embankment Based on Fuzzy Neural Network","authors":"Dadong Zhu, Maoping Li, Hongping Zhou, Gang Zhao","doi":"10.1109/ICCECE58074.2023.10135298","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135298","url":null,"abstract":"The Yangtze River embankment project is a critical barrier to ensuring the safety of the Yangtze River channel, and it is necessary to strengthen the safety monitoring of the embankment project. Embankment safety is influenced by various factors, while the influence weight of each factor is difficult to determine, and the expert scoring method and other methods are highly subjective and mainly rely on empirical judgment. Based on machine learning theory, this paper constructs an embankment safety evaluation method based on T-S model neural network. The model primarily consists of four layers of structure. (1) the input layer, this paper selects six types of evaluation factors as input parameters; (2) the fuzzification layer; (3) the fuzzy inference layer, matching the fuzzy rules and calculating the connection weights using the concatenation algorithm; (4) output layer, outputting the embankment safety coefficient value by inverse normalization and defuzzification. This paper selected three specific experimental areas in the river core of the Nanjing section of the Yangtze River as the research objects, used the data to conduct safety evaluation tests, and compared them with the actual operation of the embankment. The experimental results show that the safety level of the embankment calculated by the design method is consistent with the existing safety state of the embankment.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133914596","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135300
Shuiping Zhang, Guanxing Yuan, Bi Wang
Addressing the issue of insufficient realism and real-time property of the existing volume cloud simulation, a multi-noise rendering method for simulation optimization is proposed. First of all, in terms of cloud modeling, the Perlin/Worley noise modeling is used to increase cloud diversity; then, Curl noise is also introduced to achieve cloud irregularity. Secondly, with respect to illumination of volume cloud, the dual Henyey-Greenstein phase function is selected for the approximate simulation of Mie scattering, thus overcoming such a shortcoming of the single Henyey-Greenstein phase function as later phase scattering while enhancing the realism and real-time efficiency of illumination. In the end, the improved Raymarching is adopted for rendering, with variable step size and early jump-out to enhance rendering efficiency. According to analysis of the experimental results, the method proposed herein can effectively simulate the effect of volume clouds and guarantee the real-time performance of the system.
{"title":"Optimization Methods for Real-time Volumetric Cloud Simulation","authors":"Shuiping Zhang, Guanxing Yuan, Bi Wang","doi":"10.1109/ICCECE58074.2023.10135300","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135300","url":null,"abstract":"Addressing the issue of insufficient realism and real-time property of the existing volume cloud simulation, a multi-noise rendering method for simulation optimization is proposed. First of all, in terms of cloud modeling, the Perlin/Worley noise modeling is used to increase cloud diversity; then, Curl noise is also introduced to achieve cloud irregularity. Secondly, with respect to illumination of volume cloud, the dual Henyey-Greenstein phase function is selected for the approximate simulation of Mie scattering, thus overcoming such a shortcoming of the single Henyey-Greenstein phase function as later phase scattering while enhancing the realism and real-time efficiency of illumination. In the end, the improved Raymarching is adopted for rendering, with variable step size and early jump-out to enhance rendering efficiency. According to analysis of the experimental results, the method proposed herein can effectively simulate the effect of volume clouds and guarantee the real-time performance of the system.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116692365","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135531
Gang Zhou, Zhenghui Hu, Xiaolei Chen, Qingjie Liu
Given a set of 2D scattering points from an edge detection operator, the aim of ellipse fitting is to construct an elliptic equation that best fit the observations. For the data collected often contain noisy, uncertainty, and incompleteness which constitutes a considerable challenge for all algorithms. To address this issue, a method of direct ellipse fitting by minimizing the L0 algebraic distance is presented. Unlike its L2 counterparts that assumed the fitting error follows a Gaussian distribution, our method tried to model the outliers using the L0 norm of the algebraic distance between the ideal elliptic equation and its fitting data. In addition, an efficient numerical algorithm based on alternating optimization strategy with half-quadratic splitting is developed to solve the resulting L0 minimization problem and a detailed research of the selection of algorithm parameters is carried out benefit from which it does not suffer from the convergence issues due to poor initialization, which is an open question encountered in all iterative based approaches. Numerical experiments suggest that the proposed method achieves a very high precision and reliability to various bias especially for Non-Gaussian artifacts as well as easy to implement.
{"title":"Direct ellipse fitting by minimizing the L0 algebraic distance","authors":"Gang Zhou, Zhenghui Hu, Xiaolei Chen, Qingjie Liu","doi":"10.1109/ICCECE58074.2023.10135531","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135531","url":null,"abstract":"Given a set of 2D scattering points from an edge detection operator, the aim of ellipse fitting is to construct an elliptic equation that best fit the observations. For the data collected often contain noisy, uncertainty, and incompleteness which constitutes a considerable challenge for all algorithms. To address this issue, a method of direct ellipse fitting by minimizing the L0 algebraic distance is presented. Unlike its L2 counterparts that assumed the fitting error follows a Gaussian distribution, our method tried to model the outliers using the L0 norm of the algebraic distance between the ideal elliptic equation and its fitting data. In addition, an efficient numerical algorithm based on alternating optimization strategy with half-quadratic splitting is developed to solve the resulting L0 minimization problem and a detailed research of the selection of algorithm parameters is carried out benefit from which it does not suffer from the convergence issues due to poor initialization, which is an open question encountered in all iterative based approaches. Numerical experiments suggest that the proposed method achieves a very high precision and reliability to various bias especially for Non-Gaussian artifacts as well as easy to implement.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132292682","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135259
Jingyi Liu, Jiawei Qi, Kun Wang, Zheng Liu
With the abolition of the sales price of China's industrial and commercial catalog, the competition in the power purchase market of industrial and commercial users is becoming increasingly stimulated. In order to solve the problem of difficult and low accuracy of power marketing operation risk assessment for industrial and commercial users, a power marketing operation risk assessment method based on convolutional neural network is proposed. Firstly, the neighbor propagation clustering method is used to analyze the clustering of industrial and commercial users, and the evaluation characteristics of industrial and commercial users are obtained. On this basis, the set of electric power marketing operation evaluation indicators is constructed. Secondly, the convolutional neural network is used to adjust the weight of the evaluation index, and the power marketing operation risk of industrial and commercial users is evaluated. Finally, the accuracy of the method was 96.37% when applied in a city. The application results show that the proposed method can effectively evaluate the risks of industrial and commercial power marketing.
{"title":"Risk assessment method of power marketing operation based on convolutional neural network","authors":"Jingyi Liu, Jiawei Qi, Kun Wang, Zheng Liu","doi":"10.1109/ICCECE58074.2023.10135259","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135259","url":null,"abstract":"With the abolition of the sales price of China's industrial and commercial catalog, the competition in the power purchase market of industrial and commercial users is becoming increasingly stimulated. In order to solve the problem of difficult and low accuracy of power marketing operation risk assessment for industrial and commercial users, a power marketing operation risk assessment method based on convolutional neural network is proposed. Firstly, the neighbor propagation clustering method is used to analyze the clustering of industrial and commercial users, and the evaluation characteristics of industrial and commercial users are obtained. On this basis, the set of electric power marketing operation evaluation indicators is constructed. Secondly, the convolutional neural network is used to adjust the weight of the evaluation index, and the power marketing operation risk of industrial and commercial users is evaluated. Finally, the accuracy of the method was 96.37% when applied in a city. The application results show that the proposed method can effectively evaluate the risks of industrial and commercial power marketing.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133179535","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}
Pub Date : 2023-01-06DOI: 10.1109/ICCECE58074.2023.10135291
Jiale Li, Jingbing Wu, Hanxi Wang
This paper first briefly introduces digital culture museums and the three modules of digital culture museums; then proposes that due to the rapid development of image processing technology, many image-processing-related software can easily modify digital information such as images and videos, and there are also some unscrupulous media that maliciously tamper with images in order to gain attention and clicks; then Finally, a set of anti-tampering research of digital culture museums based on hash algorithm for checking digital culture museum resource files and using difference value hashing method for querying and tracing digital culture museum images is constructed to facilitate people's verification of digital culture museums that claim to originate from digital culture museums, supplemented by micro-copyright authorization and tracking system of digital culture museum websites. resources for verification.
{"title":"Tamper-proof Research Based on Digital Culture Museums","authors":"Jiale Li, Jingbing Wu, Hanxi Wang","doi":"10.1109/ICCECE58074.2023.10135291","DOIUrl":"https://doi.org/10.1109/ICCECE58074.2023.10135291","url":null,"abstract":"This paper first briefly introduces digital culture museums and the three modules of digital culture museums; then proposes that due to the rapid development of image processing technology, many image-processing-related software can easily modify digital information such as images and videos, and there are also some unscrupulous media that maliciously tamper with images in order to gain attention and clicks; then Finally, a set of anti-tampering research of digital culture museums based on hash algorithm for checking digital culture museum resource files and using difference value hashing method for querying and tracing digital culture museum images is constructed to facilitate people's verification of digital culture museums that claim to originate from digital culture museums, supplemented by micro-copyright authorization and tracking system of digital culture museum websites. resources for verification.","PeriodicalId":120030,"journal":{"name":"2023 3rd International Conference on Consumer Electronics and Computer Engineering (ICCECE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133339291","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：